CN110852387B - Energy internet super real-time state studying and judging algorithm - Google Patents
Energy internet super real-time state studying and judging algorithm Download PDFInfo
- Publication number
- CN110852387B CN110852387B CN201911104262.1A CN201911104262A CN110852387B CN 110852387 B CN110852387 B CN 110852387B CN 201911104262 A CN201911104262 A CN 201911104262A CN 110852387 B CN110852387 B CN 110852387B
- Authority
- CN
- China
- Prior art keywords
- data
- state
- cloud platform
- strategy
- edge computing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Signal Processing (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Networks & Wireless Communication (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses an energy internet super-real-time state studying and judging algorithm, which is characterized in that based on the occurrence frequency (support degree and confidence degree) of energy internet system state data, state studying and judging tasks are distributed to a local edge computing platform or a system center cloud platform to be respectively carried out, and a state-based system operation strategy is formed; the strategy of the local edge computing platform is only executed locally, so that the accuracy and the effectiveness of the strategy can be ensured; the cloud platform is used for studying and judging the state of the whole system, and the generated strategy is used for controlling and coordinating the operation state of the whole energy Internet, so that the cloud platform has robustness and reliability; the state study and judgment and the strategy generation mainly adopt an artificial intelligence technology. Through the cooperation of the local strategy and the global strategy, the stability, the high efficiency and the timeliness of the operation of the energy Internet are ensured.
Description
Technical Field
The invention relates to the technical field of gateways, in particular to an energy internet super real-time state studying and judging algorithm.
Background
Based on ubiquitous and efficient information communication infrastructure and open and shared internet concepts, the energy internet is combined with an internet networking technology and an information physical fusion system, can realize source-network-load-storage overall coordination, maximizes the energy utilization efficiency through energy cascade utilization and multi-energy complementation, greatly reduces the energy production and consumption cost, promotes environmental protection and reduces exhaust emission, and provides a solid energy guarantee for social harmonious development and human happy life.
With the development of society and economy, the energy consumption demand is larger and larger, and the types and the load capacity of load equipment are rapidly increased; meanwhile, the production proportion of various distributed energy resources is gradually increased; the dynamic random fluctuation of the power network, particularly the energy internet, is greatly increased when the power network runs, and adverse effects are brought to the stable running of the network, even breakdown is caused; in order to ensure the stable operation of the system, the requirements for the super real-time state study and judgment of the energy internet system are more and more strict.
At present, the state of the energy internet is researched and judged mainly based on a cloud platform technology, along with the wide access of monitoring equipment and the mass increase of monitoring data, the computing task processed by the cloud platform becomes heavier, the limit of processing capacity and communication bandwidth is difficult to ensure the real-time performance and effectiveness of the state research and judgment, and great threat is brought to the normal operation of the energy internet.
The technology corresponding to the cloud platform is edge computing, and the edge computing is distributed real-time computing technology. The technology integrates a distributed open platform with core capabilities of network, calculation, storage and application at the edge side of a network close to an object or a data source, provides edge intelligent service nearby, and can meet the key requirements of industry digitization on aspects of agile connection, real-time service, data optimization, application intelligence, safety, privacy protection and the like.
The idea of combining centralized and decentralized cooperative control is provided with cloud-edge cooperation. By accessing the edge computing to the cloud platform processing architecture, the edge computing platform can realize the localization processing of the computing task, and can ensure the real-time performance and effectiveness of local state study and judgment while reducing the communication bandwidth and energy consumption. And the global task related information is transmitted to the cloud platform for processing, so that global optimization can be performed, the overall stable and efficient operation of the energy Internet system is ensured, and possible conflicts and low efficiency of local distributed control are avoided. The combination of the two can significantly improve the system processing performance.
And (3) the association algorithm of the big data mines the association and effectiveness among the examples through the support degree and confidence degree calculation of the related data items. The data items with high support degree and confidence degree show that the relevance frequently appears, have certain reliability and can be locally judged and analyzed; and the data items with extremely low support degree often represent the occurrence of abnormal phenomena, such as faults, equipment failure and the like, and need to be transmitted to the cloud platform in time. Based on the support degree and the confidence degree, the normal operation state and the abnormal operation state can be effectively distinguished, the two types of data are respectively transmitted to the edge computing platform and the cloud platform to be processed, the real-time performance and the reliability of the system state study and judgment can be greatly improved, and the robustness and the stability of strategy execution are improved.
Based on the requirements, the invention provides an energy internet system super-real-time state studying and judging method based on equal interval data classification, cloud-edge cooperation, and state confidence and support degree.
Disclosure of Invention
The invention aims to provide an energy internet super real-time state studying and judging algorithm to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
an energy internet super real-time state studying and judging algorithm comprises the following steps:
A. the data center counts the maximum value vmax, the minimum value vmin and the classification number n of each item of data according to historical data and transmits the maximum value vmax, the minimum value vmin and the classification number n to the edge computing equipment;
B. the edge computing equipment and the cloud platform realize equal interval classification on the data according to the data values, the adopted association algorithm can be Apriori or FP-growth, each data item of each piece of data is divided into a certain interval, and one piece of data can be regarded as the combined representation of various classified data by classifying the data items of each interval into one class;
C. when new data are acquired, the data are firstly transmitted to the edge computing equipment, all data items contained in the new data are classified based on the classification interval in the step B, the classified data and the historical classification data are subjected to correlation analysis, the support degree and the confidence degree of the classified data are counted, and task allocation is carried out between the cloud platform and the edge computing equipment in a self-adaptive mode according to actual needs;
D. applying various algorithms to respectively carry out state study and judgment on the corresponding area systems in the edge computing equipment and the cloud platform, and sending study and judgment results to the cloud platform by the edge computing equipment;
E. and generating a strategy based on the state studying and judging result, wherein the strategy generated by the edge computing equipment is used for local control operation, and the strategy generated by the cloud platform is used for system global control operation.
As a further scheme of the invention: the association algorithm used in the association analysis in step C may be Apriori or FP-growth.
As a further scheme of the invention: in the step C: if the support degree and the confidence degree are larger than a certain threshold, state study and judgment of a local system are carried out on the edge side, study and judgment results and relevant statistical data are sent to the cloud platform within a certain time interval, if the support degree is smaller than the certain threshold, the data are marked as abnormal data and sent to the cloud platform in real time, global state study and judgment are carried out on the cloud platform, and state study and judgment tasks can be adaptively distributed between the cloud platform and the edge computing equipment according to actual needs of the data of the rest part.
As a further scheme of the invention: in the task allocation in step C, if there is a free computing device in the adjacent edge computing device, the relevant computing task may be transmitted to the device for execution, so as to further reduce the computing overhead of the cloud platform.
As a further scheme of the invention: in the step C, if the data sent to the cloud platform is a study result, the results generated by all edge nodes and the number of support items belonging to the state are stored in a relevant database to assist in the subsequent study of the global state of the system, and if the data is abnormal data, the data is directly applied to the study of the global state, and the number of times of occurrence of the abnormal data on the cloud platform is counted and stored.
As a further scheme of the invention: in the step D, if the data sent to the cloud platform is a study result, the results generated by all edge nodes and the number of support items belonging to the state are stored in a relevant database to assist in the subsequent study of the global state of the system, and if the data is abnormal data, the data is directly applied to the study of the global state, and the number of times of occurrence of the abnormal data on the cloud platform is counted and stored.
As a further scheme of the invention: in the step D, for state study and judgment, based on the advancement and high efficiency of the deep learning neural network, the state study and judgment technology can be used as the state study and judgment technology of the algorithm, and the neural network is used to realize real-time prediction of main parameters and states through model training based on historical data, specifically, for judgment of the system state, deep learning can set a series of output threshold values, and if a certain output of the neural network is greater than a corresponding threshold value, occurrence of a corresponding state can be judged; otherwise, the state is normal.
As a further scheme of the invention: in the step D, for state judgment, if the judgment result is an abnormal state confirmed by abnormal data, the data is marked and stored, and if the judgment result is an abnormal state confirmed by non-abnormal data, the data needs to be stored and simultaneously notified to the edge computing device generating related data, and the edge computing device can realize effective identification and differentiation of the data by changing state classification intervals or optimization manners such as support degree and confidence threshold.
As a further scheme of the invention: in the step E, the strategy generation adopts a technology of combining an expert system and a decision tree, generating a relevant decision tree by using knowledge in the expert system in a training stage, and forming a relevant strategy by step-by-step matching of the decision tree in a strategy generation stage, wherein if the strategy generated by the edge computing device and the cloud platform is in conflict, the strategy generated by the cloud platform can be adopted only, or more relevant data can be transmitted to the cloud platform for further strategy judgment.
As a further scheme of the invention: in the step E, the strategy generation is based on the feedback result of the strategy operation, and the thresholds of the related classification modes can be further optimized by using the feedback technology, so as to achieve the joint performance optimization of distributed cooperation and centralized control.
Compared with the prior art, the invention has the beneficial effects that: 1. the energy internet adopts distributed renewable energy and power electronic devices on a large scale, so that the network state is likely to fluctuate on a short time and on a large scale, the stable operation of the energy internet is seriously affected, the network state needs to be researched and judged, timely and effective control is carried out, the stable operation of the system is ensured, the fault processing overhead and the energy consumption cost are reduced, and the energy consumption efficiency of the system is improved.
2. Because the state of the energy Internet system is changed dramatically in some time or under some circumstances, the network research and judgment has higher real-time requirements. If only the cloud platform technology is adopted, the judgment result may exceed the time limit, and great potential risks and hazards are brought to network operation. Meanwhile, the cloud platform has huge computing, transmitting and storing capabilities, the defect of insufficient computing power of edge computing can be effectively overcome, and the problem of high complexity of energy internet state research and judgment can be effectively solved by combining the cloud platform and the edge computing power.
3. On the basis of correlating the acquired data with the historical state data, the real-time monitoring and control of the states of all parts of the system can be ensured through cloud-edge cooperation, the communication and processing time delay is reduced, and the guarantee is provided for network robustness and stable operation.
Drawings
Fig. 1 is a schematic block diagram of the present invention.
FIG. 2 is a diagram of the hardware relationship of the present invention.
FIG. 3 is a diagram illustrating data state determination according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-3, example 1: in the embodiment of the invention, an energy internet super real-time state studying and judging algorithm comprises the following steps:
A. the data center counts the maximum value vmax, the minimum value vmin and the classification number n of each item of data according to historical data and transmits the maximum value vmax, the minimum value vmin and the classification number n to the edge computing equipment;
B. the edge computing equipment and the cloud platform realize equal interval classification on the data according to the data values, the adopted association algorithm can be Apriori or FP-growth, each data item of each piece of data is divided into a certain interval, and one piece of data can be regarded as the combined representation of various classified data by classifying the data items of each interval into one class;
C. when new data are acquired, the data are firstly transmitted to the edge computing equipment, all data items contained in the new data are classified based on the classification interval in the step B, the classified data and the historical classification data are subjected to correlation analysis, the support degree and the confidence degree of the classified data are counted, and task allocation is carried out between the cloud platform and the edge computing equipment in a self-adaptive mode according to actual needs;
D. applying various algorithms to respectively carry out state study and judgment on the corresponding area systems in the edge computing equipment and the cloud platform, and sending study and judgment results to the cloud platform by the edge computing equipment;
E. and generating a strategy based on the state studying and judging result, wherein the strategy generated by the edge computing equipment is used for local control operation, and the strategy generated by the cloud platform is used for system global control operation.
The association algorithm used in the association analysis in step C may be Apriori or FP-growth.
In the step C: if the support degree and the confidence degree are larger than certain thresholds (such as 0.1 and 0.5), the state of the local system is judged at the edge side, and the judgment result and relevant statistical data (such as the number of support items) are sent to the cloud platform within a certain time interval. If the support degree is smaller than a certain threshold (such as 0.005), the data is marked as abnormal data and is sent to the cloud platform in real time, and the cloud platform carries out overall state study and judgment. The rest part of data can be adaptively distributed between the cloud platform and the edge computing equipment according to actual needs (such as cost, processing delay, bandwidth requirement, energy consumption condition and the residual computing capacity of the current edge computing equipment).
And C, task allocation in the step C, if an idle computing device exists in the adjacent edge computing device, the related computing task can be transmitted to the device for execution, so that the computing overhead of the cloud platform is further reduced.
And C, for the data sent to the cloud platform, if the data are judged results, storing results generated by all edge nodes and the number of the support items belonging to the state into a related database to assist the subsequent system global state judgment, if the data are abnormal data, directly applying the data to the global state judgment, and counting and storing the occurrence times of the abnormal data on the cloud platform.
As a further scheme of the invention: in the step D, if the data sent to the cloud platform is a study result, the results generated by all edge nodes and the number of support items belonging to the state are stored in a relevant database to assist in the subsequent study of the global state of the system, and if the data is abnormal data, the data is directly applied to the study of the global state, and the number of times of occurrence of the abnormal data on the cloud platform is counted and stored.
In step D, for state study and judgment, based on the advancement and the high efficiency of a deep learning neural network, the state study and judgment technology can be used as the state study and judgment technology of the algorithm, the neural network is used for realizing the real-time prediction of main parameters and states through model training based on historical data, specifically, for the judgment of the system state, the deep learning can set a series of output threshold values, and if a certain output of the neural network is greater than a corresponding threshold value, the occurrence of the corresponding state can be judged; otherwise, the state is normal.
In step D, the state is evaluated, if the evaluation result is an abnormal state confirmed by abnormal data, the data is marked and stored, if the evaluation result is an abnormal state confirmed by non-abnormal data, the data needs to be stored and simultaneously the edge computing device generating related data is notified, and the edge computing device can effectively identify and distinguish the data by changing the state classification interval or the optimization modes such as support degree and confidence threshold.
In the step E, the strategy generation adopts the technology that an expert system and a decision tree are combined, in the training stage, a relevant decision tree is generated by utilizing knowledge in the expert system, in the strategy generation stage, a relevant strategy is formed through step-by-step matching of the decision tree, and if the strategy generated by the edge computing equipment and the cloud platform conflicts, the strategy generated by the cloud platform can be only adopted, or more relevant data are transmitted to the cloud platform for further strategy judgment.
In step E, the strategy generation is based on the feedback result of the strategy operation, and the thresholds of the relevant classification modes can be further optimized by using the feedback technology, so as to achieve the combined performance optimization of distributed cooperation and centralized control.
Example 2: on the basis of the embodiment 1, before the algorithm runs, historical data related to the running of the energy internet state system needs to be obtained, and the data classification interval is determined based on the statistical characteristics of the historical data.
According to the system state related data acquired in real time, after classifying the related data items by the edge computing equipment, performing correlation analysis on the related data items and the locally stored historical data to acquire related support degree and confidence degree and the number of similar data item combinations.
Based on the support degree and the confidence degree, in combination with other performance considerations, the edge device determines data that needs to be processed locally and data that needs to be transmitted to the cloud platform or an adjacent edge computing device for processing, and notifies the relevant party to perform transmission and processing in time.
The related computing equipment trains (models) the state of the energy Internet system according to historical data by using a neural network algorithm, judges the state of the system according to the obtained data, formulates a reasonable strategy according to a state judgment result, modifies and optimizes the state judgment neural network model according to feedback strategy execution performance, and can further optimize the interval of data classification and the threshold of support degree by using an error minimization algorithm if necessary.
The above control process needs to be performed in real time, that is, the judgment of the state is completed within a specified sampling time interval to ensure the timeliness and effectiveness of the control, but the timeliness of the relevant control strategy can be effectively prolonged, that is, the system running state is controlled for a longer time under the condition that the system is stable.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (9)
1. An energy internet super real-time state studying and judging algorithm is characterized by comprising the following steps:
A. the data center counts the maximum value vmax, the minimum value vmin and the classification number n of each item of data according to historical data and transmits the maximum value vmax, the minimum value vmin and the classification number n to the edge computing equipment;
B. the edge computing device and the cloud platform realize equal interval classification of the data according to the data values, the adopted association algorithm can be Apriori or FP-growth, each data item of each piece of data is divided into a certain interval,
by classifying the data items of each interval into one class, one piece of data can be regarded as a combined representation of various kinds of classified data;
C. when new data is collected, the data is first transmitted to the edge computing device, and all data items contained in the new data are classified based on the classification interval of step B, and performing correlation analysis on the classified data and the historical classification data, and counting the support degree, the confidence degree, and adaptively allocating tasks between the cloud platform and the edge computing device according to actual needs, if the support degree and the confidence degree are greater than a certain threshold, the state of the local system is researched and judged at the edge side, the research and judgment result and the related statistical data are sent to the cloud platform within a certain time interval, if the support degree is less than a certain threshold, the data is marked as abnormal data and is sent to the cloud platform in real time, the cloud platform carries out overall state study and judgment, the rest part of data can be subjected to state studying and judging task distribution between the cloud platform and the edge computing equipment in a self-adaptive manner according to actual needs;
D. applying various algorithms to respectively carry out state study and judgment on the corresponding area systems in the edge computing equipment and the cloud platform, and sending study and judgment results to the cloud platform by the edge computing equipment;
E. and generating a strategy based on the state studying and judging result, wherein the strategy generated by the edge computing equipment is used for local control operation, and the strategy generated by the cloud platform is used for system global control operation.
2. The algorithm of claim 1, wherein the correlation algorithm used in the correlation analysis in step C is Apriori or FP-growth.
3. The algorithm for studying and judging the ultra real-time state of the energy internet as claimed in claim 1, wherein the task allocation in the step C can transmit the related computing task to the adjacent edge computing device for execution if the adjacent edge computing device has an idle computing device, so as to further reduce the computing overhead of the cloud platform.
4. The algorithm for studying and judging the super real-time state of the energy internet as claimed in claim 1, wherein in the step C, for the data sent to the cloud platform, if the data is a studying and judging result, the results generated by all edge nodes and the number of the support items belonging to the state are stored in the related database to assist the subsequent study and judgment of the global state of the system, and if the data is abnormal data, the data is directly applied to the study and judgment of the global state, and the occurrence frequency of the abnormal data on the cloud platform is counted and stored.
5. The algorithm for studying and judging the super real-time state of the energy internet as claimed in claim 1, wherein in the step D, for the data sent to the cloud platform, if the data is a studying and judging result, the results generated by all edge nodes and the number of the support items belonging to the state are stored in the related database to assist the subsequent study and judgment of the global state of the system, and if the data is abnormal data, the data is directly applied to the study and judgment of the global state, and the number of times of the abnormal data appearing on the cloud platform is counted and stored.
6. The energy internet super real-time state studying and judging algorithm as claimed in claim 1, wherein in the step D, for the state studying and judging, based on the advancement and high efficiency of the deep learning neural network, it can be used as the state studying and judging technology of the algorithm, through model training based on historical data, the neural network is used to realize real-time prediction of main parameters and states, specifically, for the judgment of the system state, the deep learning can set a series of output threshold values, if a certain output of the neural network is greater than the corresponding threshold value, the occurrence of the corresponding state can be judged; otherwise, the state is normal.
7. The algorithm as claimed in claim 1, wherein in the step D, for the state learning, if the determination result is an abnormal state confirmed by abnormal data, the data is marked and stored, and if the data is an abnormal state confirmed by non-abnormal data, the data needs to be stored and simultaneously the edge computing device generating related data is notified, and the edge computing device can effectively identify and distinguish the data by changing the state classification interval or the optimization modes such as support and confidence threshold.
8. The algorithm as claimed in claim 1, wherein in the step E, the strategy generation adopts a technique of combining an expert system and a decision tree, in a training phase, a relevant decision tree is generated by using knowledge in the expert system, in a strategy generation phase, a relevant strategy is formed by matching the decision tree stage by stage, and if there is a conflict between the strategy generated by the edge computing device and the cloud platform, the strategy generated by the cloud platform can be adopted only, or more relevant data can be transmitted to the cloud platform for further strategy judgment.
9. The algorithm as claimed in claim 1, wherein in step E, the strategy generation is based on the feedback result of the strategy operation, and the thresholds of the relevant classification modes can be further optimized by using a feedback technique, so as to achieve the combined performance optimization of distributed coordination and centralized control.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911104262.1A CN110852387B (en) | 2019-11-13 | 2019-11-13 | Energy internet super real-time state studying and judging algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911104262.1A CN110852387B (en) | 2019-11-13 | 2019-11-13 | Energy internet super real-time state studying and judging algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110852387A CN110852387A (en) | 2020-02-28 |
| CN110852387B true CN110852387B (en) | 2022-04-22 |
Family
ID=69601065
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911104262.1A Active CN110852387B (en) | 2019-11-13 | 2019-11-13 | Energy internet super real-time state studying and judging algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110852387B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111026556A (en) * | 2020-03-09 | 2020-04-17 | 蘑菇物联技术（深圳）有限公司 | Method and system for helping RTU (remote terminal Unit) to realize edge calculation through cloud algorithm |
| CN111355619B (en) * | 2020-05-26 | 2020-08-14 | 成都信息工程大学 | Cross-chain cooperation method of multi-core mesh cooperation relationship |
| CN111626792A (en) * | 2020-06-01 | 2020-09-04 | 长沙理工大学 | Technology for accurately portraying load storage of comprehensive energy source in distribution network |
| CN111783968B (en) * | 2020-06-30 | 2024-05-31 | 山东信通电子股份有限公司 | Power transmission line monitoring method and system based on cloud edge cooperation |
| CN111928334A (en) * | 2020-07-30 | 2020-11-13 | 瑞纳智能设备股份有限公司 | Heat supply control method and system based on edge cloud cooperative framework and computer equipment |
| CN112162849A (en) * | 2020-08-28 | 2021-01-01 | 中冶华天工程技术有限公司 | Cloud and edge computing cooperative equipment intelligent control system and method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102724059A (en) * | 2012-03-31 | 2012-10-10 | 常熟市支塘镇新盛技术咨询服务有限公司 | Website operation state monitoring and abnormal detection based on MapReduce |
| CN104794499A (en) * | 2015-05-08 | 2015-07-22 | 上海电机学院 | Method for designing interval gray correlation classifier based on self-adaptive entropy coefficient |
| CN104993988A (en) * | 2015-07-03 | 2015-10-21 | 清华大学 | Method for scheduling and controlling energy Internet |
| CN107835098A (en) * | 2017-11-28 | 2018-03-23 | 车智互联（北京）科技有限公司 | A kind of network fault detecting method and system |
| CN108591104A (en) * | 2018-04-18 | 2018-09-28 | 广东寰球智能科技有限公司 | A kind of Research on Fan Fault Forecasting based on cloud platform and health management system arranged, method |
| CN108919120A (en) * | 2018-07-20 | 2018-11-30 | 南京怡咖电气科技有限公司 | A kind of energy internet fault diagnosis method for power converter |
| CN109819030A (en) * | 2019-01-22 | 2019-05-28 | 西北大学 | A kind of preparatory dispatching method of data resource based on edge calculations |
| CN109946967A (en) * | 2019-03-25 | 2019-06-28 | 北京快电科技有限公司 | A kind of building energy internet information interchanger of combination of edge intelligence |
| CN110401262A (en) * | 2019-06-17 | 2019-11-01 | 北京许继电气有限公司 | GIS device state intelligent monitoring system and method based on edge calculations technology |
-
2019
- 2019-11-13 CN CN201911104262.1A patent/CN110852387B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102724059A (en) * | 2012-03-31 | 2012-10-10 | 常熟市支塘镇新盛技术咨询服务有限公司 | Website operation state monitoring and abnormal detection based on MapReduce |
| CN104794499A (en) * | 2015-05-08 | 2015-07-22 | 上海电机学院 | Method for designing interval gray correlation classifier based on self-adaptive entropy coefficient |
| CN104993988A (en) * | 2015-07-03 | 2015-10-21 | 清华大学 | Method for scheduling and controlling energy Internet |
| CN107835098A (en) * | 2017-11-28 | 2018-03-23 | 车智互联（北京）科技有限公司 | A kind of network fault detecting method and system |
| CN108591104A (en) * | 2018-04-18 | 2018-09-28 | 广东寰球智能科技有限公司 | A kind of Research on Fan Fault Forecasting based on cloud platform and health management system arranged, method |
| CN108919120A (en) * | 2018-07-20 | 2018-11-30 | 南京怡咖电气科技有限公司 | A kind of energy internet fault diagnosis method for power converter |
| CN109819030A (en) * | 2019-01-22 | 2019-05-28 | 西北大学 | A kind of preparatory dispatching method of data resource based on edge calculations |
| CN109946967A (en) * | 2019-03-25 | 2019-06-28 | 北京快电科技有限公司 | A kind of building energy internet information interchanger of combination of edge intelligence |
| CN110401262A (en) * | 2019-06-17 | 2019-11-01 | 北京许继电气有限公司 | GIS device state intelligent monitoring system and method based on edge calculations technology |
Non-Patent Citations (2)
| Title |
|---|
| Anomaly detection of online monitoring data of power equipment based on association rules and clustering algorithm;Yu-Xiang Cai等;《Advances in Engineering Research》;20161231;全文 * |
| 基于边缘计算的物联网监测系统中利用自编码神经网络实现的异常检测;于天琪等;《物联网学报》;20181231;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110852387A (en) | 2020-02-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110852387B (en) | Energy internet super real-time state studying and judging algorithm | |
| CN117472587B (en) | Resource scheduling system of AI intelligent computation center | |
| CN107274105B (en) | Linear discriminant analysis-based multi-attribute decision tree power grid stability margin evaluation method | |
| CN106603293A (en) | Network fault diagnosis method based on deep learning in virtual network environment | |
| CN109657003A (en) | A method of hardware data is directly accessed big data platform | |
| CN113723773A (en) | Electric energy decision system based on big data analysis | |
| CN113722303A (en) | Electric energy equipment and information operation and maintenance system based on visualization | |
| Kashyap et al. | DECENT: Deep learning enabled green computation for edge centric 6G networks | |
| CN113743246A (en) | Key electric energy equipment fault diagnosis method based on deep learning | |
| Yuan et al. | FedTSE: Low-cost federated learning for privacy-preserved traffic state estimation in IoV | |
| CN117336137B (en) | Internet of things data processing method and system based on intelligent edge gateway | |
| He et al. | Research on equipment health diagnosis system of railway passenger station based on cloud-edge collaboration | |
| Wu et al. | A Novel Joint Optimization Method of Multi-Agent Task Offloading and Resource Scheduling for Mobile Inspection Service in Smart Factory | |
| CN116109058A (en) | Substation inspection management method and device based on deep reinforcement learning | |
| Saxena et al. | Latency Analysis and Reduction Methods for Edge Computing | |
| Xu et al. | Enhancing power marketing audit through IoT and multi-sensor information fusion: A substation scenario analysis | |
| Lin et al. | Hypergraph-based autonomous networks: adaptive resource management and dynamic resource scheduling | |
| Zhang et al. | Design of the Information Management System of the Public Logistics in the Port of the Collection and Transportation Environment | |
| Wang et al. | Research on Fault Identification Method of Power System Communication Network Based on Deep Learning | |
| Yan et al. | Autonomous coordinated control strategy for complex process of traffic information physical fusion system based on big data | |
| Joo et al. | Ensemble fog computing architecture for unstable state detection of hydraulic system | |
| Wang et al. | Intelligent Network operation and maintenance based on deep learning technology | |
| Gao et al. | Network Operation and Maintenance Technology Based on Machine Learning Algorithms in Cloud Computing Environment | |
| Runsewe et al. | Digital Twin Based Learning Framework for Adaptive Fault Diagnosis In Microgrids with Autonomous Reconfiguration Capabilities | |
| Lv | Cognitive Analytics of Social Media for Industrial Manufacturing under Internet of Things Technology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |