CN118708112B

CN118708112B - Data dynamic analysis optimization method for irrigation area and related equipment

Info

Publication number: CN118708112B
Application number: CN202410736005.4A
Authority: CN
Inventors: 李思维; 干先龙; 李梦妮; 卢林; 张凡; 郭佚芳
Original assignee: Wuhan Shengkeda Technology Co ltd
Current assignee: Wuhan Shengkeda Technology Co ltd
Priority date: 2024-06-07
Filing date: 2024-06-07
Publication date: 2024-12-10
Anticipated expiration: 2044-06-07
Also published as: CN118708112A

Abstract

The present application discloses a data dynamic analysis and optimization method for irrigation areas and related equipment, which relates to the field of data analysis. The method comprises: obtaining an irrigation area data group in real time through a sensor group, slicing the irrigation area data group to obtain a plurality of data blocks, and storing each data block in a corresponding node of a distributed database of a cloud computing platform; retrieving a corresponding data block from at least one target node of the distributed database; inputting each data block into a first cloud computing node to obtain a multi-source feature set; determining the execution requirements of the multi-source feature set; obtaining the state of a second cloud computing node, and determining an optimal cloud computing node; inputting the multi-source feature set into the optimal cloud computing node to generate an irrigation strategy; simulating the irrigation strategy according to the current weather conditions obtained, obtaining the irrigation effect corresponding to the irrigation strategy under the current weather conditions, and dynamically adjusting the irrigation time and irrigation amount according to the irrigation effect, so that the irrigation effect corresponding to the irrigation strategy is optimal.

Description

Data dynamic analysis optimization method for irrigation area and related equipment

Technical Field

The embodiment of the application relates to the field of data analysis, in particular to a data dynamic analysis optimization method for a irrigated area and related equipment.

Background

Irrigation areas refer to particular areas that provide irrigation water for agricultural production, and typically include one or more sources of water (e.g., rivers, reservoirs, wells, etc.), as well as various facilities (e.g., channels, pipes, pump stations, etc.) for delivering and distributing water resources. In order to optimize the water resource utilization of the irrigation area, an irrigation plan can be formulated by analyzing data such as soil humidity, meteorological conditions, crop water demand and the like, so that accurate irrigation is realized.

At present, data of the irrigation area, such as soil humidity, climate temperature and the like, are mainly obtained through various sensors arranged in the irrigation area, and the obtained data of the irrigation area are displayed in the form of a line graph or a column graph and other charts, so that a decision maker can know the change trend of the data in the irrigation area according to the intuitively displayed charts, and an irrigation plan is formulated. However, since the line graph or the bar graph only shows the basic trend of the data, and the irrigation strategy is determined by the experience of the decision maker, the method has strong subjectivity, and the accuracy of the irrigation strategy is low, so that the irrigation effect is poor.

Based on the above problems, there is currently no better solution.

Disclosure of Invention

The embodiment of the application provides a data dynamic analysis optimization method for an irrigation area and related equipment, which are used for effectively improving the accuracy of an irrigation strategy and improving the irrigation effect.

In order to achieve the above purpose, the embodiment of the present application adopts the following technical scheme:

In a first aspect, a method for dynamically analyzing and optimizing data in a irrigation area is provided, and the method is applied to electronic equipment, wherein the electronic equipment is deployed with a cloud computing platform, the cloud computing platform comprises at least one first cloud computing node and at least one second cloud computing node, and a sensor group is arranged in the irrigation area, and the method comprises the following steps:

acquiring a pouring area data set in real time through the sensor group, performing data slicing on the pouring area data set acquired in real time to obtain a plurality of data blocks, and respectively storing each data block in a corresponding node in a distributed database of the cloud computing platform, wherein the nodes of the distributed database comprise m master nodes and n slave nodes, and m and n are positive integers;

In response to a user request, invoking a corresponding data block from at least one target node of the distributed database, wherein the user request is used for requesting to invoke at least one target node of the distributed database, each data block corresponds to one first cloud computing node, and the first cloud computing node is used for performing feature extraction;

inputting each data block into a corresponding first cloud computing node to obtain a multi-source feature set, wherein the multi-source feature set is a set of feature sets output by each first cloud computing node;

Determining an execution requirement of the multi-source feature set;

Acquiring the state of the second cloud computing node, and determining an optimal cloud computing node according to the state of the second cloud computing node and the execution requirement of the multi-source feature set;

Inputting the multisource feature set into the optimal cloud computing node to generate an irrigation strategy, wherein the irrigation strategy comprises irrigation time and irrigation quantity;

According to the obtained current weather conditions, simulating the irrigation strategy to obtain an irrigation effect corresponding to the irrigation strategy under the current weather conditions, and dynamically adjusting the irrigation time and the irrigation amount according to the irrigation effect to enable the irrigation effect corresponding to the irrigation strategy to be optimal.

In a possible implementation manner of the first aspect, the master node of the distributed database includes a first master node and a second master node, the performing data slicing on the irrigation area data set acquired in real time to obtain a plurality of data blocks, and storing each data block in a corresponding node in the distributed database of the cloud computing platform, where the method includes:

Dividing the irrigation area data set acquired in each unit time period into a plurality of data blocks according to the geographical position of the irrigation area;

Determining a first data block and a last data block in each irrigation area data group according to time sequence, storing the first data blocks in all the irrigation area data groups in a first main node, and storing the last data blocks in all the irrigation area data groups in a second main node;

Constructing a hash ring, and calculating a first hash value of each slave node in the distributed database by adopting a hash function according to the identification of each slave node in the distributed database;

for each data block to be stored except the first data block and the last data block in each irrigation area data group, calculating an average time stamp of each data block to be stored, and calculating a second hash value of each data block to be stored by adopting the hash function according to each average time stamp;

Mapping the data blocks to be stored and the slave nodes of the distributed database onto the hash ring according to the first hash value and the second hash value;

And regarding the second hash value of each data block to be stored, taking the slave node corresponding to the first hash value which is larger than or equal to the first hash value of the second hash value as a target slave node, and storing the data block to be stored in the target slave node.

In a possible implementation manner of the first aspect, a feature extraction algorithm is preset on a first cloud computing node, the execution requirement of the multi-source feature set includes a computing resource requirement, a data transmission requirement and a storage requirement, and the determining the execution requirement of the multi-source feature set includes:

Obtaining the time complexity of the feature extraction algorithm and the computing capacity of each first cloud computing node, wherein the computing capacity is used for representing the number of instructions processed by the first cloud computing node per second;

Calculating the computing resource requirement of each data block on the corresponding first cloud computing node according to the computing capacity and the time complexity;

Summarizing the computing resource requirements of all the data blocks on the corresponding first cloud computing nodes to obtain the computing resource requirements of the multi-source feature set;

acquiring the size of each data block and acquiring network bandwidth among the first cloud computing nodes;

calculating the transmission time of each data block to the corresponding first cloud computing node according to the size of each data block and the network bandwidth, and summarizing the transmission time of all data blocks to the corresponding first cloud computing node to obtain the data transmission requirement of the multi-source feature set;

And acquiring the feature set size obtained after each data block passes through the first cloud computing node, and summarizing the feature set size obtained after all the data blocks pass through the corresponding first cloud computing node to obtain the storage requirement of the multi-source feature set.

In a possible implementation manner of the first aspect, the state of the second cloud computing node includes a CPU usage rate, a memory usage rate, a disk I/O, a network bandwidth, and a current task queue length, and the determining, according to the state of the second cloud computing node and the execution requirement of the multi-source feature set, the optimal cloud computing node includes:

for each second cloud computing node, calculating to obtain available CPU resources according to the CPU utilization rate, calculating to obtain available memory resources according to the memory utilization rate, calculating to obtain available disk I/O resources according to the disk I/O, and calculating to obtain available network bandwidth according to the network bandwidth;

Dividing the available CPU resource by the computing resource requirement to obtain computing resource fitness, dividing the available memory resource by the storage requirement to obtain memory fitness, dividing the available disk I/O resource by the storage requirement to obtain disk I/O fitness, dividing the available network bandwidth by the data transmission requirement to obtain network bandwidth fitness, and calculating according to the current task queue length to obtain task queue length fitness;

the computing resource fitness, the memory fitness, the disk I/O fitness, the network bandwidth fitness and the task queue length fitness are weighted and summed to obtain comprehensive fitness;

and taking the second cloud computing node with the greatest comprehensive fitness as the optimal cloud computing node.

In a possible implementation manner of the first aspect, the optimal cloud computing node is pre-configured with a neural network model for generating the irrigation policy according to the input multisource feature set.

In a possible implementation manner of the first aspect, the simulating the irrigation strategy according to the obtained current weather condition to obtain an irrigation effect corresponding to the irrigation strategy in the current weather condition includes:

acquiring rainfall, current soil humidity, runoff, crop coefficients, net radiation, soil heat flux density, dry-wet ratio, average air temperature, wind speed, saturated vapor pressure and actual vapor pressure under current weather conditions;

Calculating the reference crop evapotranspiration according to the net radiation, the soil heat flux density, the dry-wet ratio, the average air temperature, the air speed, the saturated vapor pressure and the actual vapor pressure by adopting a reference crop evapotranspiration calculation formula;

calculating the evapotranspiration according to the reference crop evapotranspiration and the crop coefficients by adopting an evapotranspiration calculation formula;

calculating to obtain deep seepage according to the irrigation quantity and the irrigation time by adopting a deep seepage calculation formula;

calculating to obtain soil moisture variation according to the evapotranspiration, the irrigation quantity, the deep leakage quantity and the runoff quantity by adopting a water balance calculation formula;

According to the current soil humidity and the soil moisture variation, calculating to obtain the soil humidity irrigated by adopting an irrigation strategy;

Determining whether the soil humidity is within a preset crop proper humidity range under the current weather condition;

under the condition that the soil humidity is within a preset proper humidity range of crops, determining that the irrigation effect corresponding to the irrigation strategy under the current weather condition is good;

and under the condition that the soil humidity is not in the proper humidity range of the preset crops, determining that the irrigation effect corresponding to the irrigation strategy is poor under the current weather condition.

In a possible implementation manner of the first aspect, the dynamically adjusting the irrigation time and the irrigation amount according to the irrigation effect to optimize the irrigation effect corresponding to the irrigation strategy includes:

Under the condition that the irrigation effect corresponding to the irrigation strategy is poor in the current weather condition, determining the irrigation quantity to be adjusted according to the preset proper humidity range of crops, the current soil humidity, the evapotranspiration quantity and the rainfall;

updating the irrigation strategy according to the irrigation quantity to be adjusted until the humidity of soil irrigated by adopting the updated irrigation strategy is within the proper humidity range of the preset crops.

In a possible implementation manner of the first aspect, the updating the irrigation strategy according to the irrigation amount to be adjusted until the soil humidity after irrigation using the updated irrigation strategy is within the preset crop proper humidity range includes:

obtaining irrigation flow of the irrigation area;

determining the updated target soil moisture variation of the irrigation strategy;

circularly executing the first step until the humidity of soil irrigated by adopting the updated irrigation strategy is within the proper humidity range of the preset crops;

The first step includes:

taking the product of the target soil moisture variation and the obtained soil effective root zone depth as a target irrigation amount;

dividing the target irrigation quantity by the irrigation flow to obtain target irrigation time;

Determining the soil moisture variation according to the target irrigation amount and the target irrigation time;

according to the current soil humidity and the soil moisture variation, calculating to obtain the soil humidity irrigated by the updated irrigation strategy;

and under the condition that the soil humidity is not in a proper humidity range of the preset crops, determining the irrigation quantity to be adjusted, and updating the irrigation strategy according to the irrigation quantity to be adjusted.

In a second aspect, the present application provides a data dynamic analysis optimization apparatus for an irrigation area, comprising:

a memory configured to store instructions, and

And the processor is configured to call the instructions from the memory and can realize the data dynamic analysis optimization method for the irrigation area when executing the instructions.

In a third aspect, the present application provides an electronic device comprising:

the data dynamic analysis optimizing device for the irrigation area.

According to the technical scheme, the data set of the irrigation area is acquired in real time through the sensor group and is segmented and stored, timeliness and completeness of data can be effectively ensured, besides, the data blocks are stored in a plurality of nodes of the distributed database, the first cloud computing node is utilized for feature extraction, the second cloud computing node is utilized for outputting an irrigation strategy, data processing efficiency and computing capacity can be effectively improved, meanwhile, the first cloud computing node is utilized for feature extraction of the data blocks, a multi-source feature set is generated, dependence on artificial experience is reduced, decision scientificity and accuracy are improved, in addition, the optimal cloud computing node is determined according to execution requirements of the multi-source feature set and states of the second cloud computing node, an irrigation strategy is generated, simulation is carried out in combination with current weather conditions, irrigation time and irrigation quantity are dynamically adjusted, optimal irrigation effect is ensured, accurate irrigation can be realized, water resource utilization is optimized, and meanwhile, optimal irrigation effect can be achieved under different weather conditions, and the accuracy of irrigation effect is improved.

Additional features and advantages of embodiments of the application will be set forth in the detailed description which follows.

Drawings

FIG. 1 is a flow chart of a method for optimizing dynamic analysis of data in a irrigated area according to an embodiment of the present application;

FIG. 2 is a schematic diagram of data slicing and storing according to an embodiment of the present application;

Fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more apparent, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the detailed description described herein is merely for illustrating and explaining the embodiments of the present application, and is not intended to limit the embodiments of the present application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

It should be noted that, if directional indications (such as up, down, left, right, front, and rear are referred to in the embodiments of the present application), the directional indications are merely used to explain the relative positional relationship, movement conditions, and the like between the components in a specific posture (as shown in the drawings), and if the specific posture is changed, the directional indications are correspondingly changed.

In addition, if there is a description of "first", "second", etc. in the embodiments of the present application, the description of "first", "second", etc. is for descriptive purposes only and is not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In addition, the technical solutions of the embodiments may be combined with each other, but it is necessary to base that the technical solutions can be realized by those skilled in the art, and when the technical solutions are contradictory or cannot be realized, the combination of the technical solutions should be considered to be absent and not within the scope of protection claimed in the present application.

Fig. 1 schematically shows a flow chart of a method for optimizing dynamic analysis of data for irrigation areas according to an embodiment of the application. As shown in fig. 1, an embodiment of the present application provides a method for dynamically analyzing and optimizing data in a irrigation area, which is applied to an electronic device, where the electronic device is deployed with a cloud computing platform, and the cloud computing platform includes at least one first cloud computing node and at least one second cloud computing node, and a sensor group is disposed in the irrigation area.

S110, acquiring a pouring area data set in real time through a sensor group, performing data slicing on the pouring area data set acquired in real time to obtain a plurality of data blocks, and respectively storing each data block in a corresponding node in a distributed database of a cloud computing platform, wherein the nodes of the distributed database comprise m master nodes and n slave nodes, and m and n are positive integers;

S120, responding to a user request, and calling corresponding data blocks from at least one target node of the distributed database, wherein the user request is used for requesting to call the at least one target node of the distributed database, each data block corresponds to a first cloud computing node, and the first cloud computing node is used for extracting characteristics;

s130, inputting each data block into a corresponding first cloud computing node to obtain a multi-source feature set, wherein the multi-source feature set is a set of feature sets output by each first cloud computing node;

s140, determining the execution requirement of the multi-source feature set;

S150, acquiring the state of a second cloud computing node, and determining an optimal cloud computing node according to the state of the second cloud computing node and the execution requirements of the multi-source feature set;

S160, inputting the multisource feature set into an optimal cloud computing node to generate an irrigation strategy, wherein the irrigation strategy comprises irrigation time and irrigation quantity;

s170, simulating the irrigation strategy according to the obtained current weather condition to obtain an irrigation effect corresponding to the irrigation strategy under the current weather condition, and dynamically adjusting the irrigation time and the irrigation amount according to the irrigation effect to ensure that the irrigation effect corresponding to the irrigation strategy is optimal.

Through the sensor group arranged in the irrigation area, various data of the irrigation area, such as soil humidity, temperature, illumination intensity, rainfall and the like, can be obtained in real time. The sensor group comprises a plurality of sensors, and the sensors are distributed over the whole irrigation area so as to ensure the comprehensiveness and accuracy of the data. After the data of the irrigation area is acquired, the acquired data of the irrigation area is subjected to data slicing and split into a plurality of data blocks so as to be convenient to manage and store.

Wherein each data block contains sensor data over a range of times. Specifically, each data block is stored in a distributed database of the cloud computing platform. The distributed database is composed of a plurality of nodes, and is divided into a master node and a slave node, so that the reliability and the high efficiency of data storage are ensured. The master node is responsible for writing and managing data, and the slave node is responsible for reading and backing up the data, so that the data can be ensured to be accessed and restored when any node fails.

When a user makes a request, the electronic device invokes a corresponding data block from the distributed database in response to the user request. The user request contains specific query conditions, such as specific sensor data, and the user request is distributed to the target nodes, each data block corresponding to one of the first cloud computing nodes. The first cloud computing node is used for extracting features of the fetched data blocks to obtain feature sets of the data blocks, namely multi-source feature sets, wherein the multi-source feature sets refer to feature sets extracted from a plurality of data sources. Specifically, each first cloud computing node is configured to process one or more data blocks, and extract key information or features. After feature extraction is completed by all the first cloud computing nodes, the extracted features are summarized together to form a comprehensive feature set. This feature set contains data from all sensors in the irrigation area, providing a comprehensive view, facilitating subsequent analysis and decision-making. The comprehensiveness and comprehensiveness of the multisource feature set can reflect the overall situation of the irrigation area, so that a foundation is provided for generating a more accurate irrigation strategy.

The first cloud computing nodes are preset with feature extraction algorithms, and after the data blocks are called from at least one target node in the distributed database, the data blocks are input to the corresponding first cloud computing nodes. Each first cloud computing node may perform feature extraction on the received data blocks to extract useful information or features.

The execution requirements of the multi-source feature set include computing resource requirements, data transmission requirements, and the like. By analyzing the complexity and data volume of the multi-source feature set, the execution requirements of the multi-source feature set can be determined. For example, if the feature set contains a large amount of time series data, more computing resources may be required to perform complex time series analysis. After the execution requirement is determined, the computing resources can be better distributed, and the high efficiency and accuracy of data processing are ensured.

The state of the second cloud computing node is obtained for determining an optimal computing node to process the multi-source feature set. The state of the second cloud computing node includes CPU utilization, memory utilization, disk I/O, network bandwidth, and the like. By monitoring the states of the second cloud computing nodes, the real-time condition of each second cloud computing node can be known. According to the state of the second cloud computing node and the execution requirement of the multi-source feature set, an optimal cloud computing node can be determined, and the optimal cloud computing node has enough computing resources and meets the data transmission requirement of the multi-source feature set so as to ensure the high efficiency and accuracy of data processing.

After inputting the multi-source feature set to the optimal cloud computing node, the optimal cloud computing node may generate an irrigation policy from the multi-source feature set. Irrigation strategies include specific irrigation times and irrigation amounts. Specifically, each second cloud computing node is preset with an irrigation strategy algorithm, such as a machine learning algorithm, an optimization algorithm and the like, so that optimal irrigation time and irrigation quantity can be calculated according to information in the multisource feature set, the water resource utilization efficiency of an irrigation area is ensured to be maximized, and meanwhile, the growth requirements of crops are ensured.

In particular, the second cloud computing node is primarily used to perform complex computing tasks and generate irrigation policies. After feature extraction is completed by all the first cloud computing nodes, the generated multi-source feature set is input to the second cloud computing nodes. The second cloud computing node may calculate, according to the multisource feature set, an irrigation policy using an optimization algorithm, a machine learning model, a neural network model, and the like. In addition, the second cloud computing node is also responsible for simulating and dynamically adjusting the irrigation strategy, and optimizing the irrigation effect according to the actual weather conditions.

The generated irrigation strategy can be simulated according to the acquired current weather conditions. Weather conditions include temperature, humidity, rainfall, etc., all of which affect the irrigation effect. Through simulation, the actual effect of the irrigation strategy under the current weather condition can be predicted. The simulation results show the soil humidity change, crop growth and the like under different irrigation time and irrigation quantity. According to the simulation result, the irrigation strategy can be dynamically adjusted, so that the optimal combination of the irrigation time and the irrigation quantity is achieved, and the optimal irrigation effect is ensured. This dynamic adjustment can cope with weather changes, ensuring the flexibility and effectiveness of the irrigation strategy.

In addition, the data blocks are stored in a plurality of nodes of a distributed database, the first cloud computing node is utilized for carrying out feature extraction, the second cloud computing node is utilized for outputting an irrigation strategy, the data processing efficiency and the computing capacity can be effectively improved, meanwhile, the first cloud computing node is utilized for carrying out feature extraction on the data blocks, a multi-source feature set is generated, dependence on artificial experience is reduced, the scientificity and the accuracy of decision making are improved, in addition, the optimal cloud computing node is determined according to the execution requirement of the multi-source feature set and the state of the second cloud computing node, the irrigation strategy is generated, the current weather condition is combined for simulation, the irrigation time and the irrigation quantity are dynamically adjusted, the optimal irrigation effect is ensured, accurate irrigation can be realized, the water resource utilization is optimized, the optimal irrigation effect can be effectively ensured under different weather conditions, and the accuracy of the irrigation effect is improved.

In one implementation manner of the embodiment, the master node of the distributed database includes a first master node and a second master node, performs data slicing on the irrigation area data set acquired in real time to obtain a plurality of data blocks, and stores each data block in a corresponding node in the distributed database of the cloud computing platform, where the method includes the following steps:

S210, dividing the irrigation area data set acquired in each unit time period into a plurality of data blocks according to the geographical position of the irrigation area;

S220, determining a first data block and a last data block in each irrigation area data group according to time sequence, storing the first data blocks in all the irrigation area data groups in a first main node, and storing the last data blocks in all the irrigation area data groups in a second main node;

s230, constructing a hash ring, and calculating a first hash value of each slave node in the distributed database by adopting a hash function according to the identification of each slave node in the distributed database;

S240, calculating an average time stamp of each data block to be stored for each data block to be stored except the first data block and the last data block in each irrigation area data group, and calculating a second hash value of each data block to be stored by adopting a hash function according to each average time stamp;

S250, mapping the data blocks to be stored and the slave nodes of the distributed database onto a hash ring according to the first hash value and the second hash value;

S260, regarding the second hash value of each data block to be stored, taking the slave node corresponding to the first hash value which is larger than or equal to the second hash value as a target slave node, and storing the data block to be stored in the target slave node.

Fig. 2 shows a data slicing and storage schematic diagram provided in this embodiment, in which a data set of an irrigation area acquired in real time is subjected to data slicing, and first, the data set of the irrigation area acquired in each unit time period is divided into a plurality of data blocks according to geographical positions of the irrigation area. In specific implementation, the irrigation area can be divided into a plurality of geographic areas, and each area corresponds to one data block. For example, one irrigation area can be divided into a north area, a south area, an east area and a west area, and sensor data in each area are respectively stored in corresponding data blocks, so that geographic consistency of the data can be effectively ensured, and subsequent processing and analysis are facilitated. Meanwhile, the division mode can effectively reduce the size of a single data block and improve the efficiency of data processing.

In this embodiment, according to the time sequence, a first data block and a last data block are determined in each irrigation area data set, the first data blocks in all the irrigation area data sets are stored in the first master node, and the last data blocks in all the irrigation area data sets are stored in the second master node. In particular, the first data block (i.e., the first data block) of each time period may be stored to the first master node to ensure centralized management and fast access of the first data block. Also, the last data block (i.e., last data block) of each period is stored to the second master node to ensure centralized management and fast access of the last data block. This approach may ensure high availability and fast response of the first and last data blocks.

By intensively storing the first and last data blocks, the starting and ending positions of the data can be quickly positioned, thereby improving the data access efficiency. And during the data recovery process, the data index and the metadata can be quickly reconstructed through the head and the tail data blocks on the main node.

To further optimize data storage, a hash ring is constructed and a hash function is used to calculate a first hash value for each slave node based on the identity of each slave node in the distributed database. A hash ring is a distributed data storage structure that enables even distribution and load balancing of data by mapping all slave nodes onto one ring. In specific implementation, a consistent hash algorithm may be adopted, an identifier (such as a node ID) of each slave node is input into a hash function, and a corresponding hash value (i.e., a first hash value) is calculated. These hash values will be used for subsequent data block memory mapping, ensuring even distribution and efficient storage of data. In particular, the identification of the nodes is used to uniquely identify each node, typically a unique string or number.

For each data block to be stored except the first data block and the last data block in each irrigated area data group, calculating an average time stamp of each data block to be stored, and calculating a second hash value of each data block to be stored by adopting a hash function according to each average time stamp. In practice, the time stamps of all the data points in each data block may be averaged to obtain an average time stamp. The average timestamp is then input into a hash function, and a corresponding hash value (i.e., a second hash value) is calculated. The method can uniformly distribute the data blocks to the whole hash ring, and improves the uniformity of data storage and the access efficiency.

And mapping the data blocks to be stored and the slave nodes of the distributed database onto a hash ring according to the first hash value and the second hash value by adopting a consistent hash algorithm. In the implementation, the first hash values of all the slave nodes and the second hash values of all the data blocks to be stored can be mapped to the hash ring respectively, so that the distribution condition of the data blocks and the slave nodes can be intuitively known, and the subsequent data block storage operation is convenient. By the method, the data blocks can be uniformly distributed, overload of certain nodes is avoided, and meanwhile, the reliability and the high efficiency of data storage are improved.

And finally, regarding the second hash value of each data block to be stored, taking the slave node corresponding to the first hash value which is larger than or equal to the second hash value as a target slave node, and storing the data block to be stored in the target slave node. In specific implementation, the second hash value of each data block to be stored can be found on the hash ring, then a first hash value which is greater than or equal to the hash value is found, and the corresponding slave node is determined as the target slave node. By the method, the data blocks can be stored in the target slave nodes, so that the uniform distribution and efficient storage of the data can be ensured, meanwhile, the reliability and the access efficiency of the data are improved, the efficient management and the rapid access of the data can be realized, and the real-time property and the accuracy of the data in the irrigation area are ensured.

In the embodiment, the distributed database has two master nodes, which can be mutually backed up, when one master node fails, the other master node can continue to provide service, so that the high availability of the cloud computing platform is ensured, the plurality of slave nodes can share the load of the read operation, the pressure of the master nodes is reduced, the response speed of the cloud computing platform is effectively improved, in addition, the consistency hash algorithm can ensure that only a small amount of data migration is required for the increase or decrease of the cloud computing nodes, the cloud computing platform can be easily expanded and contracted, in addition, the hash function uniformly distributes data blocks to the plurality of slave nodes, the data inclination can be effectively prevented, and the storage and the computing load of each node are balanced.

In one implementation manner of the present embodiment, a feature extraction algorithm is preset on a first cloud computing node, execution requirements of a multi-source feature set include a computing resource requirement, a data transmission requirement and a storage requirement, and the determining of the execution requirements of the multi-source feature set includes the following steps:

s310, acquiring time complexity of a feature extraction algorithm and computing capacity of each first cloud computing node, wherein the computing capacity is used for representing the number of instructions processed by the first cloud computing nodes per second;

S320, calculating the calculation resource requirement of each data block on the corresponding first cloud calculation node according to the calculation capability and the time complexity;

S330, summarizing the computing resource requirements of all the data blocks on the corresponding first cloud computing nodes to obtain the computing resource requirements of the multi-source feature set;

s340, acquiring the size of each data block and acquiring network bandwidth among the first cloud computing nodes;

s350, calculating the transmission time of each data block to the corresponding first cloud computing node according to the size of each data block and the network bandwidth, and summarizing the transmission time of all the data blocks to the corresponding first cloud computing node to obtain the data transmission requirement of the multi-source feature set;

And S360, acquiring the feature set size obtained after each data block passes through the first cloud computing node, and summarizing the feature set size obtained after all data blocks pass through the corresponding first cloud computing node to obtain the storage requirement of the multi-source feature set.

In this embodiment, it is first necessary to acquire the time complexity of the feature extraction algorithm, and acquire the computing power of each first cloud computing node. The time complexity represents the worst-case computational resources required by the feature extraction algorithm, for example, if the time complexity of the feature extraction algorithm is O (n ²), then the computation time will increase in square steps as the amount of input data n increases. The computing power represents the number of instructions that each first cloud computing node can process per second, for example, one node has a computing power of 10 billion instructions per second (10 GFLOPS).

Next, computing a computing resource requirement of each data block on the corresponding first cloud computing node according to the computing power and the time complexity. In specific implementation, the size of the data block can be substituted into a time complexity formula, and the calculation time required by each data block can be calculated. For example, if one data block contains 1000 data points and the algorithm time complexity is O (n ²), the calculation time is 1000 ² =1000000 calculation steps. Assuming that the computational power of the node is 10 hundred million instructions per second, the time to process the data block is 1000000/1000000000 = 0.001 seconds. In this way, the computational resource requirements of each data block can be accurately assessed.

And then, summarizing the computing resource requirements of all the data blocks on the corresponding first cloud computing nodes to obtain the computing resource requirements of the multi-source feature set. In particular, the computing time of all the data blocks may be added to obtain the total computing resource requirement. For example, assuming that there are 10 data blocks, each with a computation time of 0.001 seconds, the total computation resource requirement is 10×0.001=0.01 seconds. By summarizing, the computing resource requirements of the multi-source feature set can be comprehensively known, and reasonable distribution and use of computing resources are ensured.

In this embodiment, the calculation data transmission requirement first obtains the size of each data block, and obtains the network bandwidth between the first cloud computing nodes. The size of a data block is typically in bytes, for example, one data block is 1MB in size. The network bandwidth then represents the transmission rate between the nodes, for example, the network bandwidth is 100MB per second.

The storage requirement of the multi-source feature set is obtained, firstly, the transmission time of each data block to the corresponding first cloud computing node is calculated according to the size of each data block and the network bandwidth, and the transmission time of all the data blocks to the corresponding first cloud computing node is summarized, so that the data transmission requirement of the multi-source feature set is obtained. In practice, the data block size may be divided by the network bandwidth to obtain the transmission time. For example, a 1MB block of data is transmitted over a bandwidth of 100MB per second, with a required time of 1/100=0.01 seconds. Assuming that there are 10 data blocks, each of which has a transmission time of 0.01 seconds, the total transmission time is 10 x 0.01=0.1 seconds. By the method, the data transmission requirement can be accurately evaluated, and the high efficiency of the transmission process is ensured.

The method comprises the steps of obtaining the feature set size obtained after each data block passes through a first cloud computing node, summarizing the feature set size obtained after all data blocks pass through the corresponding first cloud computing node, and obtaining the storage requirement of the multi-source feature set. In specific implementation, the feature set size of each data block can be calculated through a feature extraction algorithm. For example, a 1MB block of data may be processed to generate a 100KB feature set. Assuming that there are 10 data blocks, each data block has a feature set size of 100KB, the total feature set size is 10×100=1000 KB. Through the summary, the storage requirement can be accurately evaluated, and reasonable distribution and use of storage resources are ensured.

According to the method and the system, the high efficiency and reliability of the feature extraction process can be ensured by analyzing the computing resource requirement, the data transmission requirement and the storage requirement in detail, the execution requirement of the multi-source feature set in the distributed cloud computing environment can be comprehensively evaluated and optimized, for example, the computing resource requirement of each data block is accurately calculated, the reasonable distribution of computing resources is ensured, the resource waste and node overload are avoided, in addition, the high efficiency transmission of data among nodes is ensured, the transmission delay is reduced, the overall processing efficiency is improved by analyzing the data transmission requirement in detail, in addition, the reasonable use of the storage resource is ensured by evaluating the storage requirement of the feature set, the storage bottleneck is avoided, and finally, the high efficiency and reliability of the feature extraction process are ensured by comprehensively evaluating and optimizing various requirements, and the processing efficiency and the processing performance of the whole cloud computing platform are improved.

In one implementation manner of this embodiment, the state of the second cloud computing node includes a CPU usage rate, a memory usage rate, a disk I/O, a network bandwidth, and a current task queue length, and the determining, according to the state of the second cloud computing node and an execution requirement of the multi-source feature set, an optimal cloud computing node includes the following steps:

s410, for each second cloud computing node, calculating to obtain available CPU resources according to CPU utilization rate, calculating to obtain available memory resources according to memory utilization rate, calculating to obtain available disk I/O resources according to disk I/O, and calculating to obtain available network bandwidth according to network bandwidth;

S420, dividing available CPU resources by computing resource requirements to obtain computing resource fitness, dividing available memory resources by storage requirements to obtain memory fitness, dividing available disk I/O resources by storage requirements to obtain disk I/O fitness, dividing available network bandwidth by data transmission requirements to obtain network bandwidth fitness, and calculating according to the current task queue length to obtain task queue length fitness;

S430, carrying out weighted summation on the computing resource fitness, the memory fitness, the disk I/O fitness, the network bandwidth fitness and the task queue length fitness to obtain the comprehensive fitness;

s440, taking the second cloud computing node with the largest comprehensive adaptability as an optimal cloud computing node.

In this embodiment, first, for each second cloud computing node, available resources are computed according to the current state thereof. Specifically, CPU utilization reflects the current processing load condition of the node. Assuming that the CPU utilization of a node is 70%, the available CPU resources are 30%. Similarly, the memory usage represents the memory occupancy of the node, and the available memory resources are 40% assuming the memory usage is 60%. The use condition of the disk I/O indicates the read-write operation load of the node, and the available disk I/O resource is 50% assuming that the disk I/O use ratio is 50%. The calculation of the network bandwidth is based on the current bandwidth utilization, and the available network bandwidth is 20% assuming that the network bandwidth utilization is 80%. The calculation steps ensure the accuracy and the instantaneity of resource use by monitoring the node state in real time.

After the available resources (namely, available CPU resources, available memory resources, available disk I/O resources and available network bandwidth) are obtained, the available resources are compared with the execution requirements of the multi-source feature set, and the fitness of each available resource is calculated. In specific implementation, the available CPU resource is divided by the computing resource requirement to obtain the computing resource fitness. For example, if the available CPU resource is 30% and the computing resource requirement is 10%, the computing resource fitness is 30%/10% =3. Similarly, the available memory resource is divided by the storage requirement to obtain the memory fitness, for example, the available memory resource is 40%, the storage requirement is 20%, and the memory fitness is 40%/20% =2. Dividing the available disk I/O resources by the storage requirement to obtain the disk I/O fitness, for example, the available disk I/O resources are 50%, and the storage requirement is 20%, and the disk I/O fitness is 50%/20% =2.5. Dividing the available network bandwidth by the data transmission requirement to obtain the network bandwidth fitness, for example, the available network bandwidth is 20%, the data transmission requirement is 10%, and the network bandwidth fitness is 20%/10% = 2. According to the length of the current task queue, assuming that the length of the task queue is 5 tasks, the fitness of the length of the task queue is calculated to be 1/5=0.2. The calculation of the fitness can effectively ensure the matching degree of each node resource and the task requirement.

And carrying out weighted summation on the fitness to obtain the comprehensive fitness. In the specific implementation, different weights can be given according to the importance of different resources, and the sum of the weights corresponding to the fitness is 1. For example, assume that the weight of the computing resource fitness is 0.4, the weight of the memory fitness is 0.2, the weight of the disk I/O fitness is 0.2, the weight of the network bandwidth fitness is 0.1, and the weight of the task queue length fitness is 0.1. The calculation formula of the overall fitness is:

Overall fitness = 0.4 x computing resource fitness +0.2 x memory fitness +0.2 x disk I/O fitness +0.1 x network bandwidth fitness +0.1 x task queue length fitness;

for example, if the computing resource fitness is 3, the memory fitness is 2, the disk I/O fitness is 2.5, the network bandwidth fitness is 2, and the task queue length fitness is 0.2, the overall fitness is that the overall fitness=0.4x3+0.2x2+0.2x2.5+0.1x2+0.1 x 0.2=1.2+0.4+0.5+0.2+0.02=2.32.

The weighted summation method can effectively ensure comprehensive consideration of each resource fitness, so that the comprehensive fitness can comprehensively reflect the node adaptation condition.

And finally, taking the second cloud computing node with the greatest comprehensive fitness as an optimal cloud computing node. In the implementation, the comprehensive fitness of all the nodes can be compared, and the node with the highest fitness can be selected. For example, if there are three nodes with comprehensive fitness of 2.32, 1.85 and 2.10, respectively, a node with comprehensive fitness of 2.32 is selected as the best cloud computing node. This step ensures that the selected node optimally meets the execution requirements of the multi-source feature set on each resource, thereby optimizing overall computing efficiency and resource utilization.

According to the method and the device for processing the task, the resource utilization condition of each cloud computing node can be accurately evaluated, and the optimal cloud computing node is selected to process the task according to the execution requirements of the multi-source feature set, so that the resource utilization efficiency is improved, and the high efficiency and the reliability of task execution are effectively ensured.

In one implementation manner of this embodiment, the optimal cloud computing node is preset with a neural network model, and is used for generating an irrigation strategy according to the input multisource feature set.

In this embodiment, the optimal cloud computing node is preset with a neural network model for generating an irrigation policy according to the input multisource feature set.

Specifically, the neural network model is obtained by training a large amount of historical data. The historical data may include a set of primary characteristics of the irrigated area data. By repeating the training, the neural network can capture complex relationships between features and generate efficient irrigation strategies. The construction steps of the neural network model comprise the steps of data collection, data preprocessing, model training, model verification and the like. The data preprocessing stage comprises data cleaning, normalization and other processes on historical data, the model training stage comprises training a neural network by using a training set and continuously adjusting network parameters through a back propagation algorithm, and the model verification stage comprises the step of using a verification data set to evaluate the performance of the neural network model and ensure the accuracy and reliability of the model.

After training the neural network model, the input multisource feature set is input into the neural network model. The multi-source feature set is a set of main features of the irrigated area data. When the multi-source feature set is input into the neural network model, the conversion and normalization processing of the data format are needed to ensure that the multi-source feature set meets the input requirement of the neural network model. For example, soil moisture may be expressed in percent, while air temperature is expressed in degrees celsius and precipitation is expressed in millimeters. Through normalization processing, the data with different dimensions are converted into the same range, so that the neural network processing is facilitated.

Then, the neural network model calculates according to the input multisource feature set to generate an irrigation strategy. The neural network processes the input characteristics through the weighted summation and activation functions of the neurons of each layer through a forward propagation process, transmits the characteristics layer by layer, and finally generates an irrigation strategy at an output layer. Specifically, the input layer of the neural network receives the multi-source feature set, the hidden layer captures complex relationships between features through nonlinear transformation, and the output layer generates a specific irrigation strategy. The output layer may include a plurality of nodes, each corresponding to a different irrigation parameter, such as irrigation time, irrigation volume, etc. It should be noted that the generated irrigation strategy may be applied in an actual irrigation system. The irrigation system can automatically adjust the operation of the irrigation equipment according to the irrigation strategy output by the neural network. For example, the irrigation strategy may include irrigation time and amount per day, and the irrigation system will automatically control the irrigation pumps and valves based on these parameters, ensuring that the crop is getting the proper amount of moisture.

According to the method, the irrigation quantity can be accurately controlled through the neural network model, water resources can be effectively saved, the crop yield and quality are improved, and meanwhile the problems of soil salinization and the like caused by excessive irrigation are reduced. In general, intelligent and fine management of agricultural irrigation is realized by presetting a neural network model and generating an irrigation strategy according to a multisource feature set, and the efficiency and the sustainability of agricultural production are greatly improved.

In one implementation manner of the embodiment, according to the obtained current weather condition, an irrigation strategy is simulated to obtain an irrigation effect corresponding to the irrigation strategy under the current weather condition, including the following steps:

S610, obtaining rainfall under the current weather condition, current soil humidity, runoff, crop coefficients, net radiation, soil heat flux density, dry-wet ratio, average air temperature, air speed, saturated vapor pressure and actual vapor pressure;

S620, calculating to obtain the reference crop evapotranspiration according to the net radiation, the soil heat flux density, the dry-wet ratio, the average air temperature, the air speed, the saturated vapor pressure and the actual vapor pressure by adopting a reference crop evapotranspiration calculation formula;

s630, calculating to obtain the evapotranspiration according to the reference crop evapotranspiration and crop coefficients by adopting an evapotranspiration calculation formula;

s640, calculating to obtain deep seepage according to the irrigation quantity and the irrigation time by adopting a deep seepage quantity calculation formula;

s650, calculating to obtain the soil moisture variation according to the evapotranspiration, irrigation, deep leakage and runoff by adopting a water balance calculation formula;

S660, calculating to obtain the soil humidity after irrigation by adopting an irrigation strategy according to the current soil humidity and the soil moisture variation;

S670, determining whether the soil humidity is in a preset proper humidity range of crops under the current weather condition;

S680, determining that the irrigation effect corresponding to the irrigation strategy under the current weather condition is good under the condition that the soil humidity is within the proper humidity range of the preset crops;

S690, determining that the irrigation effect corresponding to the irrigation strategy under the current weather condition is poor under the condition that the soil humidity is not in the proper humidity range of the preset crops.

The calculation formula of the reference crop evapotranspiration is as follows:

Wherein ET ₀ is the reference crop evapotranspiration (mm/day), delta is the slope of saturated vapor pressure curve (kPa/°C), rn is the net radiation, G is the soil heat flux density, Y is the dry-wet ratio, T is the average air temperature, u ₂ is the wind speed, e _s is the saturated vapor pressure, and e _a is the actual vapor pressure.

The calculation formula of the evapotranspiration is as follows:

ET=Kc×ET₀;

Wherein Kc is the crop coefficient, the crops in different growth stages have different coefficients, and ET0 is the reference crop evapotranspiration.

The calculation formula of the deep leakage amount is as follows:

D=k×I×T;

Wherein D is deep leakage amount, k is leakage coefficient under current weather condition, I is irrigation amount, and T is irrigation time.

The water balance calculation formula is:

ΔW=I-ET-D-R;

wherein DeltaW is the soil moisture variation, I is irrigation quantity, ET is evapotranspiration quantity, D is deep seepage quantity, and R is runoff quantity.

In summary, according to the embodiment, the irrigation strategy can be simulated according to the obtained current weather condition, so as to obtain the irrigation effect corresponding to the irrigation strategy under the current weather condition. Firstly, rainfall under the current weather condition, current soil humidity, runoff, crop coefficient, net radiation, soil heat flux density, dry-wet ratio, average air temperature, air speed, saturated vapor pressure and actual vapor pressure are obtained. These data can be collected in real time by various sensors and weather stations. For example, rainfall can be measured by a rain gauge, soil humidity can be measured by a soil humidity sensor, wind speed can be measured by an anemometer, air temperature can be measured by a thermometer, net radiation and soil heat flux density can be measured by a radiometer, saturated vapor pressure and actual vapor pressure can be calculated by the humidity sensor, current weather and soil conditions can be comprehensively known, and basic data can be provided for subsequent calculation.

Then, a reference crop evapotranspiration calculation formula is adopted, and the reference crop evapotranspiration is calculated according to net radiation, soil heat flux density, dry-wet ratio, average air temperature, air speed, saturated vapor pressure and actual vapor pressure. The reference crop evapotranspiration (ET ₀) is used to represent the total amount of evaporation and transpiration of the crop under standard conditions. Then, the evapotranspiration is calculated according to the reference crop evapotranspiration and the crop coefficient by adopting an evapotranspiration calculation formula. The crop coefficient (Kc) is a correction coefficient for adjusting the reference crop evapotranspiration to accommodate the actual evapotranspiration requirements of a particular crop. The reference crop evapotranspiration is multiplied by the crop coefficient, so that the evapotranspiration of the specific crop under the current condition can be obtained, the actual moisture demand of the crop can be accurately reflected by the evapotranspiration, and a basis is provided for subsequent irrigation strategy adjustment.

And then, calculating the deep seepage amount according to the irrigation amount and the irrigation time by adopting a deep seepage amount calculation formula. The deep leakage (D) refers to the amount of irrigation water that permeates down into the soil below the root layer. Then, a water balance calculation formula is adopted, and the soil moisture variation is calculated according to the evapotranspiration, the irrigation quantity, the deep leakage quantity and the runoff quantity. The water balance formula represents the relationship between the input and output of soil moisture. And then, according to the current soil humidity and the change amount of the soil moisture, calculating to obtain the soil humidity irrigated by adopting an irrigation strategy. The calculation formula of the soil humidity is as follows:

new soil humidity = current soil humidity + aw;

The current soil humidity and the soil moisture variation are added to obtain the soil humidity after irrigation. The method can accurately predict the water condition of the irrigated soil and provide basis for evaluating the effect of an irrigation strategy.

And finally, determining whether the soil humidity is within a preset proper humidity range of crops under the current weather condition. The suitable humidity range for a crop refers to the optimum soil humidity range required for a particular crop during growth. And comparing the calculated soil humidity with a proper humidity range to judge whether the irrigation strategy is effective. If the soil humidity is in a proper range, the irrigation strategy is reasonable, and the water demand of crops can be met.

Under the condition that the soil humidity is in a preset proper humidity range of crops, the irrigation effect corresponding to the irrigation strategy under the current weather condition is determined to be good. This means that current irrigation strategies can effectively meet the moisture demand of crops under existing weather conditions, improving the growth and yield of crops.

And under the condition that the soil humidity is not in the range of the proper humidity of the preset crops, determining that the irrigation effect corresponding to the irrigation strategy under the current weather condition is poor. This indicates that current irrigation strategies are not effective in meeting the moisture demand of the crop and that it may be necessary to adjust the amount of irrigation or the time of irrigation to optimize the irrigation effect.

The simulation method provided by the embodiment can evaluate the effect of the irrigation strategy before implementing the irrigation strategy, so that necessary adjustment is performed, the effectiveness and scientificity of the irrigation strategy are ensured, and the accuracy of the irrigation strategy is further effectively improved.

In one implementation manner of this embodiment, the method dynamically adjusts the irrigation time and the irrigation amount according to the irrigation effect, so as to optimize the irrigation effect corresponding to the irrigation strategy, and includes the following steps:

s710, under the condition that the irrigation effect corresponding to the irrigation strategy is poor in the current weather condition, determining the irrigation quantity to be adjusted according to a preset proper humidity range of crops, the current soil humidity, the evapotranspiration quantity and the rainfall;

and S720, updating an irrigation strategy according to the irrigation quantity to be adjusted until the humidity of soil irrigated by adopting the updated irrigation strategy is within a proper humidity range of the preset crops.

In one implementation manner of this embodiment, the irrigation time and the irrigation amount may be dynamically adjusted according to the irrigation effect, so as to optimize the irrigation effect corresponding to the irrigation strategy. Firstly, under the condition that the irrigation effect corresponding to the irrigation strategy under the current weather condition is poor, determining the irrigation quantity to be adjusted according to the preset proper humidity range of crops, the current soil humidity, the evapotranspiration quantity and the rainfall. When the irrigation effect is evaluated as poor, it means that the current irrigation strategy fails to effectively meet the moisture demand of the crop. At this time, the irrigation amount needs to be re-evaluated and adjusted. The preset proper humidity range of the crops is an ideal soil humidity range preset according to the growth requirements of the crops. The current soil humidity is an actual soil humidity value measured in real time by a soil humidity sensor. The Evapotranspiration (ET) represents the water consumption of the crop under the current meteorological conditions, and the rainfall is the actual rainfall measured by a rain gauge. By combining these factors, the amount of irrigation to be adjusted can be calculated. The specific calculation method can be expressed as:

Irrigation quantity to be adjusted= (median value of preset crop proper humidity range-current soil humidity) +et-rainfall;

Through the irrigation quantity to be adjusted, the soil humidity can be effectively ensured to be improved to a proper range, and meanwhile, moisture gaps caused by insufficient evaporation and rainfall are supplemented.

And then updating the irrigation strategy according to the irrigation quantity to be adjusted until the humidity of soil irrigated by adopting the updated irrigation strategy is within a preset proper humidity range of crops. After the adjusted irrigation volume is determined, the irrigation strategy needs to be updated to ensure that the new irrigation volume can be effectively applied to the actual irrigation process. Updating the irrigation strategy includes adjusting the irrigation time and the irrigation volume to achieve optimal irrigation. For example, if the amount of irrigation to be adjusted is large, it may be selected to increase the irrigation time or increase the amount of water per irrigation, or a combination of both. In specific implementation, the operation parameters of the irrigation equipment can be automatically adjusted through the irrigation control system, so that the new irrigation quantity can be accurately conveyed to the field. And verifying whether the updated irrigation strategy is effective or not by monitoring the soil humidity in real time. If the humidity of the irrigated soil does not reach the proper range, the irrigation amount and time can be further adjusted until the humidity of the soil is stabilized within the proper humidity range of the preset crops.

According to the method, the irrigation strategy is dynamically adjusted, so that the change of different weather conditions and crop demands can be effectively dealt with, the irrigation effect is ensured to be kept in an optimal state all the time, and healthy growth and high yield of crops are promoted.

In one implementation manner of this embodiment, the irrigation strategy is updated according to the irrigation amount to be adjusted until the humidity of soil irrigated by the updated irrigation strategy is within a preset proper humidity range of crops, and the method includes the following steps:

s810, acquiring irrigation flow of an irrigation area;

S820, determining the target soil moisture variation of the updated irrigation strategy;

s830, circularly executing the first step until the humidity of soil irrigated by adopting the updated irrigation strategy is within a proper humidity range of the preset crops;

The first step comprises:

S840, taking the product of the target soil moisture variation and the obtained soil effective root zone depth as a target irrigation quantity;

S850, dividing the target irrigation quantity by the irrigation flow to obtain target irrigation time;

s860, determining the soil moisture variation according to the target irrigation amount and the target irrigation time;

S870, calculating to obtain the soil humidity after irrigation by adopting the updated irrigation strategy according to the current soil humidity and the soil moisture variation;

S880, determining whether the soil humidity is within a proper humidity range of a preset crop under the current weather condition;

And S890, determining the irrigation quantity to be adjusted under the condition that the soil humidity is not in the proper humidity range of the preset crops, and updating the irrigation strategy according to the irrigation quantity to be adjusted.

In one implementation of this embodiment, the irrigation strategy may be updated according to the amount of irrigation to be adjusted, so as to ensure that the humidity of soil irrigated by using the updated irrigation strategy is within a preset suitable humidity range for crops. First, the irrigation flow of the irrigation area is obtained. The irrigation flow is the water quantity delivered by the irrigation system in unit time, and is measured in real time by a flowmeter and other devices. Next, a target soil moisture variance for the updated irrigation strategy is determined. The target soil moisture variation refers to the expected increase in soil moisture content after irrigation. And according to the water demand of crops and the current soil humidity, calculating to obtain the target soil moisture change. For example, if the current soil humidity is 15% and the preset crop suitable humidity range is 20% to 30%, the target soil moisture variation may be set to 5%, i.e., the soil humidity is increased from 15% to 20% by irrigation.

And circularly executing the first step until the humidity of soil irrigated by the updated irrigation strategy is within the proper humidity range of the preset crops. The specific implementation process of the first step is as follows:

First, the product of the target soil moisture amount and the obtained soil effective root zone depth is taken as the target irrigation amount. The depth of the effective root zone of the soil refers to the depth of the soil layer in which the root system of the crop is mainly distributed, and is usually determined by field investigation or literature data. For example, if the depth of the effective root zone of a crop is 30 cm, the target irrigation amount can be calculated by the following formula:

Target irrigation amount = target soil moisture change amount × soil effective root zone depth;

Assuming that the target soil moisture variation is 5% and the depth of the effective root zone of the soil is 30 cm, the target irrigation amount is 0.05×30=1.5 cm.

Next, the target irrigation amount is divided by the irrigation flow amount to obtain a target irrigation time. The target irrigation time refers to the irrigation time period required to reach the target irrigation amount. Assuming an irrigation flow rate of 500 liters per hour, an irrigation volume of 1 cm corresponds to 10 liters of water per square meter, and an irrigation volume of 1.5 cm is 15 liters of water per square meter. The target irrigation time can be calculated by the following formula:

target irrigation time = target irrigation volume/irrigation flow;

Assuming an irrigation area of 100 square meters, the target irrigation time is (15×100)/500=3 hours.

And determining the soil moisture variation according to the target irrigation quantity and the target irrigation time. Through actual irrigation operation, it is verified whether the target irrigation amount and time can reach the expected soil moisture variation amount. For example, by measuring the soil moisture again after irrigation, it is confirmed whether irrigation increases the soil moisture by 5%.

And then, calculating to obtain the soil humidity after irrigation by adopting the updated irrigation strategy according to the current soil humidity and the soil moisture variation. For example, the current soil humidity is 15%, the soil moisture variation is 5%, and the soil humidity after irrigation should be 15% +5% = 20%.

Next, it is determined whether the soil moisture is within a predetermined crop suitable moisture range for the current weather conditions. If the soil humidity after irrigation is between 20% and 30%, the irrigation strategy is effective, and the soil humidity reaches a preset range.

And finally, determining the irrigation quantity to be adjusted under the condition that the soil humidity is not in the proper humidity range of the preset crops, and updating the irrigation strategy according to the irrigation quantity to be adjusted. If the humidity of the irrigated soil does not reach the expected range, the amount of irrigation to be adjusted needs to be recalculated, and the irrigation strategy needs to be adjusted. For example, if the soil humidity increases by only 3% after irrigation, it is necessary to increase the irrigation amount by 2% again, and recalculate the target irrigation time and irrigation amount until the soil humidity reaches a preset range. Therefore, by continuously adjusting and optimizing the irrigation strategy, the soil humidity can be ensured to be always in a proper range of crops, and healthy growth and high yield of the crops are promoted.

According to the method, the calculation and verification steps are circularly carried out, so that the humidity of the irrigated soil is ensured to reach or be close to a preset proper range. If the expected effect is not achieved, the irrigation amount and time are automatically adjusted until the target is achieved. The dynamic adjustment mechanism can flexibly cope with the changes of different weather conditions and crop demands, and by accurately controlling irrigation quantity and time, the waste of water resources is avoided, meanwhile, the crops are ensured to obtain enough water, the irrigation efficiency is improved, the water resources are saved, and the dynamic adjustment mechanism has important economic and environmental benefits.

The embodiment of the application also discloses a data dynamic analysis optimizing device for the irrigation area, which comprises the following steps:

A memory 10 configured to store instructions, and

The processor 20 is configured to call instructions from the memory 10 and when executing the instructions is capable of implementing the data dynamic analysis optimization method for the irrigation areas described above.

The embodiment of the application also discloses an electronic device, which comprises:

the data dynamic analysis optimizing device for the irrigation area.

Embodiments of the present application also provide a machine-readable storage medium having stored thereon instructions for causing a machine to perform the above-described method for dynamic analysis optimization of data for a irrigated area.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.

Claims

1. The utility model provides a data dynamic analysis optimization method for irrigated area, characterized by is applied to electronic equipment, the electronic equipment is deployed with cloud computing platform, the cloud computing platform includes at least one first cloud computing node and at least one second cloud computing node, the sensor group has been laid in the irrigated area, the method includes:

Determining an execution requirement of the multi-source feature set;

simulating the irrigation strategy according to the obtained current weather condition to obtain an irrigation effect corresponding to the irrigation strategy under the current weather condition, and dynamically adjusting the irrigation time and the irrigation amount according to the irrigation effect to ensure that the irrigation effect corresponding to the irrigation strategy is optimal;

the first cloud computing node is preset with a feature extraction algorithm, the execution requirements of the multi-source feature set comprise computing resource requirements, data transmission requirements and storage requirements, the determining the execution requirements of the multi-source feature set includes:

2. The method according to claim 1, wherein the master nodes of the distributed database include a first master node and a second master node, the performing data slicing on the irrigation area data set acquired in real time to obtain a plurality of data blocks, and storing each data block in a corresponding node in the distributed database of the cloud computing platform, respectively, includes:

3. The method of claim 1, wherein the state of the second cloud computing node comprises CPU utilization, memory utilization, disk I/O, network bandwidth, and current task queue length, wherein the determining an optimal cloud computing node based on the state of the second cloud computing node and the execution requirements of the multi-source feature set comprises:

4. The method of claim 1, wherein the optimal cloud computing node is pre-configured with a neural network model for generating the irrigation strategy from the input set of multi-source features.

5. The method according to claim 1, wherein the simulating the irrigation strategy according to the obtained current weather condition to obtain the irrigation effect corresponding to the irrigation strategy under the current weather condition includes:

6. The method of claim 5, wherein dynamically adjusting the irrigation time and the irrigation volume based on the irrigation effect to optimize the irrigation effect corresponding to the irrigation strategy comprises:

7. The method of claim 6, wherein updating the irrigation strategy according to the amount of irrigation to be adjusted until the humidity of soil irrigated with the updated irrigation strategy is within the predetermined crop proper humidity range, comprises:

obtaining irrigation flow of the irrigation area;

The first step includes:

8. A dynamic analysis optimizing apparatus for data of an irrigation area, comprising:

a memory configured to store instructions, and

A processor configured to invoke the instructions from the memory and when executing the instructions is capable of implementing a data dynamic analysis optimization method for a irrigated area according to any one of claims 1 to 7.

9. An electronic device, comprising:

the apparatus of claim 8.