CN116755866B - A resource scheduling method, device, electronic equipment and readable storage medium - Google Patents

Abstract

The invention discloses a resource scheduling method, a device, electronic equipment and a readable storage medium, which relate to the technical field of computers and are used for acquiring the type of a target task and the running state information of a resource node; under the condition that the type of the target task is a preset type, determining a first function according to the target task and the running state information, wherein the preset type represents any one of the 2 nd to the N th to-be-completed tasks of the N to-be-completed tasks, the N to-be-completed tasks are sequentially arranged, and N is an integer larger than 1; calculating the first function according to a target algorithm to obtain a target solution; and scheduling the resource node to process the target task according to a target resource scheduling scheme determined based on the target solution. When the task which is not completed exists on the resource nodes, the tasks can be distributed to other resource nodes which have completed the tasks, so that the total task execution time is shortened.

Description

A resource scheduling method, device, electronic equipment and readable storage medium

Technical field

The present invention relates to the field of artificial intelligence technology, and in particular, to a resource scheduling method, device, electronic equipment and readable storage medium.

Background technique

As the number of user tasks continues to increase, the time it takes for cloud computing resource nodes to complete corresponding tasks also increases significantly, seriously affecting user service quality.

When the cloud computing resource node has not completed the old task and the user has submitted a new task, the existing resource node scheduling scheme usually waits for all cloud computing resource nodes to complete all old tasks before executing the new task. In the node scheduling scheme, because the completion time of old tasks on cloud computing resource nodes is different, there may be situations where some cloud computing resource nodes complete old tasks in advance, but no new tasks are assigned to the cloud computing resource nodes.

Since a reasonable resource node scheduling scheme is not adopted to fully utilize the resource nodes, there is a problem in the existing technology that the total time required for the resource nodes to complete tasks is long.

Contents of the invention

Embodiments of the present invention provide a resource scheduling method, device, electronic device and readable storage medium to solve the problem in the prior art that the total time required for resource nodes to complete tasks is long.

In a first aspect, embodiments of the present invention provide a resource node scheduling method, including:

Obtain the type of target task and the running status information of the resource node;

When the type of the target task is a preset type, a first function is determined based on the target task and the running status information, wherein the preset type indicates that the target task is N tasks to be completed. Any to-be-completed task from the 2nd to N-th to-be-completed task in , the N to-be-completed tasks are arranged in sequence, and N is an integer greater than 1;

Calculate the first function according to the target algorithm to obtain the target solution;

According to the target resource scheduling plan determined based on the target solution, the resource node is scheduled to process the target task.

Optionally, the target algorithm includes at least one of a genetic algorithm and a greedy algorithm.

Optionally, when the target algorithm includes a genetic algorithm and a greedy algorithm, calculating the first function according to the target algorithm to obtain the target solution includes:

According to the greedy algorithm and the required resource type of the first individual, the target resource node of the first individual is determined in the resource list. The first individual is an individual that does not meet the preset constraints. The individual Determined based on the genetic algorithm;

Determine a first population according to the target resource node of the first individual, and the first population includes the target resource node of the first individual;

According to the genetic algorithm, iteratively calculate the first population and record the number of iterations;

When the number of iterations of the first population reaches the preset number of iterations, the individual with the highest fitness in the current population is determined as the target solution of the first function, and the current population is the preset number of iterations for the first population. Let the number of iterations be the iteratively calculated population.

Optionally, the iterative calculation of the first population according to the genetic algorithm includes:

Calculate the fitness of individuals within the first population according to a genetic algorithm;

According to the genetic algorithm, the fitness of individuals in the first population and the preset fitness threshold, the second population is determined and iteratively calculated.

Optionally, the iterative calculation of the first population according to the genetic algorithm, the crossover probability and the mutation probability includes:

Calculate the fitness of the M individuals of the first population and the sum of the fitnesses of the M individuals, where M is a positive integer;

According to the fitness of the target individual and the sum of the fitnesses of the M individuals, the first probability of the target individual is determined, the target individual is any of the M individuals, and the first probability is the target The probability that an individual is selected into the second population;

The second population is determined according to the first probability of the target individual, and the second population is the population after one iteration of the first population.

Optionally, when the first duration is less than the preset duration, the first function is:

;

in, Indicates the time required to complete the N to-be-completed tasks when the first duration is less than the preset duration, Indicates the cost required to complete the N to-be-completed tasks when the first duration is less than the preset duration, The value range of is 0 to 1, The value range of is 0 to 1, and , the running status information includes the first time of each resource node, the first time is the time when the resource node completes the processing of the to-be-completed task before the target task, and the first duration is the The difference between the second time and the current time. The second time is the latest time among the first time.

Optionally, when the first duration is greater than the preset duration, the first function is:

;

in, Indicates the time required to complete the N to-be-completed tasks when the first duration is greater than the preset duration, Indicates the cost required to complete the N to-be-completed tasks when the first duration is longer than the preset duration, The value range of is 0 to 1, The value range of is 0 to 1, and , the running status information includes the first time of each resource node, the first time is the time when the resource node completes the processing of the to-be-completed task before the target task, and the first duration is the The difference between the second time and the current time. The second time is the latest time among the first time.

In a second aspect, an embodiment of the present invention also provides a resource scheduling device, where the resource scheduling device includes:

Monitoring module, used to obtain the type of target tasks and the running status information of resource nodes;

Determining module, configured to determine a first function according to the target task and the running status information when the type of the target task is a preset type, wherein the preset type indicates that the target task is Any to-be-completed task from the 2nd to N-th to-be-completed tasks among the N to-be-completed tasks, the N to-be-completed tasks are arranged in sequence, and N is an integer greater than 1;

Get a module, used to calculate the first function according to the target algorithm and obtain the target solution;

A scheduling module, configured to schedule the resource node to process the target task according to the target resource scheduling plan determined based on the target solution.

In a third aspect, embodiments of the present invention further provide an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the above is implemented. The steps in the resource scheduling method described above.

In a fourth aspect, embodiments of the present invention also provide a computer-readable storage medium. A computer program is stored on the computer-readable storage medium. When the computer program is executed by a processor, the steps in the resource scheduling method as described above are implemented. .

In the embodiment of the present invention, the type of the target task and the running status information of the resource node are obtained; in the case that the type of the target task is a preset type, the first task is determined based on the target task and the running status information. A function, wherein the preset type indicates that the target task is any to-be-completed task from the 2nd to N-th to-be-completed tasks among the N to-be-completed tasks, and the N to-be-completed tasks are The tasks are arranged in order, and N is an integer greater than 1; the first function is calculated according to the target algorithm to obtain the target solution; the resource nodes are scheduled to process the target task according to the target resource scheduling plan determined based on the target solution . When there are unfinished tasks on a resource node, tasks can be assigned to other resource nodes that have completed tasks, thereby shortening the total task execution time.

Description of the drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without exerting any creative effort.

Figure 1 is a flow chart of a resource scheduling method provided by an embodiment of the present invention;

Figure 2 is a schematic structural diagram of a resource scheduling device provided by an embodiment of the present invention;

Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the present invention.

The flow chart of the resource scheduling method provided by the embodiment of the present invention, as shown in Figure 1, includes the following steps:

Step 101: Obtain the type of target task and the running status information of the resource node;

It should be understood that the type of the above target task may be the first type or the second type. The type of the target task is the first type, which means that there is no unfinished task on the resource node before the target task is submitted. At this time, the type of the target task is determined to be the first type; the target task The type is the second type, which means that there are still unfinished tasks on the resource node before the target task is submitted. At this time, the type of the target task is determined to be the second type.

It should be understood that the running status information of the resource node includes: whether there are tasks being executed and the completion time of executing the remaining tasks.

In step 101, the type of the target task and the running status information of the resource node can be obtained every certain period after the user submits the target task to the resource node; it can also be obtained in real time after the user submits the target task to the resource node. The type of task and the running status information of the resource node.

Step 102: When the type of the target task is a preset type, determine a first function according to the target task and the running status information, wherein the preset type indicates that there are N target tasks. Any of the 2nd to Nth to-be-completed tasks among the to-be-completed tasks, the N to-be-completed tasks are arranged in sequence, and N is an integer greater than 1;

It should be understood that the above-mentioned preset type is the second type; the target task has a task length.

In step 102, when the type of the target task is a preset type, that is, when the type of the target task is the second type, a first value is determined based on the target task and the running status information. function.

It should be noted that the first function can be , and satisfy the following constraints: represents a task resource node Medium resource type consumption, For resource nodes China resources available amount, Indicates the available resources of the CPU, Represents the available amount of memory resources and Indicates the amount of resource available for bandwidth, is a weight parameter with a value ranging from 0 to 1, is a weight parameter with a value ranging from 0 to 1, and , n represents the number of tasks, m represents the number of resource nodes, , Indicates the time required to complete the N tasks to be completed when the first duration is less than the preset duration, m indicates the number of resource nodes, , represents a task Whether it is in the resource node implement, The value is 1 or 0, represents a task at the resource node executed on represents a task Not in the resource node executed on for task length, For resource nodes CPU execution speed,; , f _cost represents the cost of executing the task, represents a task Whether it is in the resource node implement, The value is 1 or 0, represents a task at the resource node executed on represents a task Not in the resource node executed on For resource nodes Resource usage cost per unit time, n represents the number of tasks, m represents the number of resource nodes, For resource nodes China Resources available amount, Represents the available resources of CPU, memory and bandwidth respectively, for task length, For resource nodes CPU execution speed.

The first function can also be , and satisfy the following constraints: , represents a task resource node Medium resource type consumption, For resource nodes China resources available amount, Indicates the available resources of the CPU, Represents the available amount of memory resources and Indicates the amount of resource available for bandwidth, is a weight parameter with a value ranging from 0 to 1, is a weight parameter with a value ranging from 0 to 1, and , , Indicates that all resource nodes have completed the submitted tasks to the resource nodes before submitting the target task. The time interval between completing the target tasks in Indicates resource nodes The time to complete the target task, n represents the number of tasks, m represents the number of resource nodes, for task length, For resource nodes CPU execution speed, Indicates the time required to complete the N to-be-completed tasks when the first duration is greater than the preset duration, represents a task Whether it is in the resource node implement, The value is 1 or 0, represents a task at the resource node executed on represents a task Not in the resource node executed on , Represents the cost required to complete the N to-be-completed tasks when the first duration is longer than the preset duration, n represents the number of tasks, m represents the number of resource nodes, represents a task Whether it is in the resource node implement, for task length, For resource nodes CPU execution speed, For resource nodes Resource usage cost per unit time.

It should be noted that by setting the weight parameter, the relative importance of task completion time and resource usage cost is expressed.

Step 103: Calculate the first function according to the target algorithm to obtain the target solution;

It should be understood that the target algorithm may be a heuristic algorithm capable of solving a function with constraints.

In step 103, the target solution may be a local optimal solution of the first function or a global optimal solution of the first function.

Step 104: Schedule the resource node to process the target task according to the target resource scheduling plan determined based on the target solution.

In step 104, after obtaining the target solution of the first function, a task execution sequence table of each resource node is generated, and then the task number is added to the task execution sequence table in the order of the time when the task is submitted. The task number in the execution sequence table executes the corresponding task.

In the embodiment of the present invention, the type of the target task and the running status information of the resource node are obtained; in the case that the type of the target task is a preset type, the first task is determined based on the target task and the running status information. A function, wherein the preset type indicates that the target task is any to-be-completed task from the 2nd to N-th to-be-completed tasks among the N to-be-completed tasks, and the N to-be-completed tasks are The tasks are arranged in order, and N is an integer greater than 1; the first function is calculated according to the target algorithm to obtain the target solution; the resource nodes are scheduled to process the target task according to the target resource scheduling plan determined based on the target solution . When there are unfinished tasks on a resource node, tasks can be assigned to other resource nodes that have completed tasks, thereby shortening the total task execution time.

Optionally, in some embodiments, the target algorithm includes at least one of a genetic algorithm and a greedy algorithm.

In the embodiment of the present invention, the target algorithm includes a genetic algorithm and a greedy algorithm, so that when using the genetic algorithm to solve the constrained resource scheduling problem, in order to ensure the diversity of the population, initialization, crossover, mutation, etc. Instead of discarding individuals that do not meet the constraints, the stage uses a greedy algorithm to adjust individuals that do not meet the constraints, so that the adjusted individuals have less task completion time and resource node usage costs, ultimately improving global convergence. Accuracy.

Optionally, in some embodiments, when the target algorithm includes a genetic algorithm and a greedy algorithm, calculating the first function according to the target algorithm to obtain the target solution includes:

According to the greedy algorithm and the required resource type of the first individual, the target resource node of the first individual is determined in the resource list. The first individual is an individual that does not meet the preset constraints. The individual Determined based on the genetic algorithm;

It should be understood that the resource availability of the target resource node meets the task requirement of the first individual.

It should be understood that the above preset constraints are: , represents a task resource node Medium resource type consumption, For resource nodes China resources available amount, Indicates the available resources of CPU, memory and bandwidth respectively.

Determine a first population according to the target resource node of the first individual, and the first population includes the target resource node of the first individual;

It should be understood that the first population includes multiple individuals and resource nodes corresponding to each individual.

According to the genetic algorithm, iteratively calculate the first population and record the number of iterations;

When the number of iterations of the first population reaches the preset number of iterations, the individual with the highest fitness in the current population is determined as the target solution of the first function, and the current population is the preset number of iterations for the first population. Let the number of iterations be the iteratively calculated population.

It should be understood that the preset number of iterations may be between 100 and 2000.

Optionally, in some embodiments, the iterative calculation of the first population according to a genetic algorithm includes:

Calculate the fitness of individuals within the first population according to a genetic algorithm;

According to the genetic algorithm, the fitness of individuals in the first population and the preset fitness, the second population is determined and iteratively calculated.

In this embodiment of the present invention, the formula for calculating the fitness of individuals in the first group may be: ,can also be ; and perform normalization processing on it. The normalization processing formula is as follows: ;in, and are the maximum and minimum fitness in the population respectively.

At the same time, the Individuals whose fitness value is greater than the preset value are determined as the second population.

In the embodiment of the present invention, by performing normalization processing on the fitness in the above manner, the impact of the fitness on an order of magnitude can be reduced.

Optionally, the iterative calculation of the first population according to the genetic algorithm, the crossover probability and the mutation probability includes:

Calculate the fitness of the M individuals of the first population and the sum of the fitness of the M individuals, where M is a positive integer;

According to the fitness of the target individual and the sum of the fitnesses of the M individuals, the first probability of the target individual is determined, the target individual is any of the M individuals, and the first probability is the target The probability that an individual is selected into the second population;

The second population is determined according to the first probability of the target individual, and the second population is the population after one iteration of the first population.

In this embodiment of the present invention, the probability of an individual being selected is: ;in, is the normalized fitness of the i-th individual, and N is the total number of tasks.

In the embodiment of the present invention, through the above solution, individuals with high fitness can be selected with a higher probability than individuals with low fitness.

Optionally, in some embodiments, from the new population with probability Select two individuals for chromosome crossover, with probability Select an individual for chromosome mutation, generate a new individual, and process the new individual as follows: decode the individual elements and map the decoded values to intervals Within, the mapping formula is: when hour, ,when hour, . in and Represents the values before and after mapping respectively.

Furthermore, after the mapping of all elements is completed, a greedy algorithm is used to correct new individuals that do not meet the constraint conditions, that is, to determine the elements in the new individuals Whether the constraint conditions are met, if so, continue to judge the next element; if the constraint conditions are not met, find the corresponding resource type P, and generate an available resource list in ascending order of the available amount of resource P. This list records m resource nodes. The available amounts of three resources in The a resource node closest to the task demand, the value range of a is 1-5, and the corresponding fitness function value when the task _ti is assigned to a different resource node is calculated respectively, and the maximum fitness function value is The corresponding resource node number is assigned to e _i , and then continues to determine the next element. After all elements are processed, the individual is re-binary encoded and added to the population.

Optionally, when the first duration is less than the preset duration, the first function is:

;

Where, f _time represents the time required to complete the N tasks to be completed when the first duration is less than the preset duration, and f _cost represents the time required to complete the N tasks to be completed when the first duration is less than the preset duration. The cost of the task, the value range of α is 0 to 1, the value range of β is 0 to 1, and α+β=1, the running status information includes the first moment of each resource node, The first time is the time when the resource node completes processing of the to-be-completed task before the target task, the first duration is the difference between the second time and the current time, and the second time is the Describe the latest moment among the first moments.

Optionally, when the first duration is greater than the preset duration, the first function is:

;

in, Indicates the time required to complete the N to-be-completed tasks when the first duration is greater than the preset duration, Indicates the cost required to complete the N to-be-completed tasks when the first duration is longer than the preset duration, The value range of is 0 to 1, The value range of is 0 to 1, and , the running status information includes the first time of each resource node, the first time is the time when the resource node completes the processing of the to-be-completed task before the target task, and the first duration is the The difference between the second time and the current time. The second time is the latest time among the first time.

Referring to Figure 2, Figure 2 is a schematic structural diagram of a resource scheduling device 200 provided by an embodiment of the present invention. As shown in Figure 2, it includes the following modules:

Monitoring module 201 is used to obtain the type of target tasks and the running status information of resource nodes;

Determining module 202, configured to determine a first function according to the target task and the running status information when the type of the target task is a preset type, wherein the preset type represents the target task It is any to-be-completed task from the 2nd to N-th to-be-completed tasks among the N to-be-completed tasks, the N to-be-completed tasks are arranged in sequence, and N is an integer greater than 1;

Obtaining module 203 is used to calculate the first function according to the target algorithm and obtain the target solution;

The scheduling module 204 is configured to schedule the resource node to process the target task according to the target resource scheduling plan determined based on the target solution.

Optionally, the target algorithm includes at least one of a genetic algorithm and a greedy algorithm.

Optionally, when the target algorithm includes a genetic algorithm and a greedy algorithm, the obtaining module includes:

The first determination sub-module is used to determine the target resource node of the first individual in the resource list according to the greedy algorithm and the required resource type of the first individual. The first individual does not meet the preset Individuals of constraints, the individuals are determined based on the genetic algorithm;

The second determination sub-module is used to determine the first population according to the target resource node of the first individual, where the first population includes the target resource node of the first individual;

A calculation submodule, configured to iteratively calculate the first population according to the genetic algorithm and record the number of iterations;

The third determination sub-module is used to determine the individual with the highest fitness in the current population as the target solution of the first function when the number of iterations of the first population reaches the preset number of iterations. The current population is the population obtained by iterative calculation of the first population through a preset number of iterations.

Optionally, the calculation submodule includes:

The first calculation subunit is used to calculate the fitness of individuals in the first population according to a genetic algorithm;

The first determination subunit is used to determine the second population and perform iterative calculations based on the genetic algorithm, the fitness of individuals in the first population, and the preset fitness threshold.

Optionally, the calculation submodule includes:

The second calculation subunit is used to calculate the fitness of the M individuals of the first population and the sum of the fitnesses of the M individuals, where M is a positive integer;

The second determination subunit is used to determine the first probability of the target individual based on the fitness of the target individual and the sum of the fitnesses of the M individuals, where the target individual is any of the M individuals, so The first probability is the probability that the target individual is selected into the second population;

The third determination subunit is used to determine the second population according to the first probability of the target individual. The second population is the population after one iteration of the first population.

Optionally, when the first duration is less than the preset duration, the first function is:

;

in, Indicates the time required to complete the N to-be-completed tasks when the first duration is less than the preset duration, Indicates the cost required to complete the N to-be-completed tasks when the first duration is less than the preset duration, The value range of is 0 to 1, The value range of is 0 to 1, and , the running status information includes the first time of each resource node, the first time is the time when the resource node completes the processing of the to-be-completed task before the target task, and the first duration is the The difference between the second time and the current time. The second time is the latest time among the first time.

Optionally, when the first duration is greater than the preset duration, the first function is:

;

in, Indicates the time required to complete the N to-be-completed tasks when the first duration is greater than the preset duration, Indicates the cost required to complete the N to-be-completed tasks when the first duration is longer than the preset duration, The value range of is 0 to 1, The value range of is 0 to 1, and , the running status information includes the first time of each resource node, the first time is the time when the resource node completes the processing of the to-be-completed task before the target task, and the first duration is the The difference between the second time and the current time, the second time being the latest time among the first time.

An embodiment of the present invention also provides an electronic device. Referring to Figure 3, Figure 3 is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. Since the problem-solving principle of the electronic device is similar to the resource scheduling method in the embodiment of the present invention, the implementation of the electronic device can be referred to the implementation of the method, and repeated details will not be repeated.

As shown in Figure 3, the electronic device 300 includes: a processor 310, used to read the program in the memory 320 and perform the following processes:

Obtain the type of target task and the running status information of the resource node;

When the type of the target task is a preset type, a first function is determined based on the target task and the running status information, wherein the preset type indicates that the target task is N tasks to be completed. Any to-be-completed task from the 2nd to N-th to-be-completed task, the N to-be-completed tasks are arranged in sequence, and N is an integer greater than 1;

Calculate the first function according to the target algorithm to obtain the target solution;

According to the target resource scheduling plan determined based on the target solution, the resource node is scheduled to process the target task.

In FIG. 3 , the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 310 and various circuits of the memory represented by memory 320 are linked together. The bus architecture can also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are all well known in the art and therefore will not be described further herein. The bus interface provides the interface. The processor 310 is responsible for managing the bus architecture and general processing, and the memory 320 can store data used by the processor 310 when performing operations.

Optionally, the processor 310 is also used to read the program in the memory 320 and perform the following steps:

The target algorithm includes at least one of a genetic algorithm and a greedy algorithm.

Optionally, when the target algorithm includes a genetic algorithm and a greedy algorithm, calculating the first function according to the target algorithm to obtain the target solution includes:

According to the greedy algorithm and the required resource type of the first individual, the target resource node of the first individual is determined in the resource list. The first individual is an individual that does not meet the preset constraints. The individual Determined based on the genetic algorithm;

Determine a first population according to the target resource node of the first individual, and the first population includes the target resource node of the first individual;

According to the genetic algorithm, iteratively calculate the first population and record the number of iterations;

When the number of iterations of the first population reaches the preset number of iterations, the individual with the highest fitness in the current population is determined as the target solution of the first function, and the current population is the preset number of iterations for the first population. Let the number of iterations be the iteratively calculated population.

Optionally, the iterative calculation of the first population according to the genetic algorithm includes:

Calculate the fitness of individuals within the first population according to a genetic algorithm;

According to the genetic algorithm, the fitness of individuals in the first population and the preset fitness threshold, the second population is determined and iteratively calculated.

Optionally, in some embodiments, the iterative calculation of the first population according to the genetic algorithm, the crossover probability and the mutation probability includes:

Calculate the fitness of the M individuals of the first population and the sum of the fitnesses of the M individuals, where M is a positive integer;

According to the fitness of the target individual and the sum of the fitnesses of the M individuals, the first probability of the target individual is determined, the target individual is any of the M individuals, and the first probability is the target The probability that an individual is selected into the second population;

The second population is determined according to the first probability of the target individual, and the second population is the population after one iteration of the first population.

Optionally, in some embodiments, when the first duration is less than the preset duration, the first function is:

;

in, Indicates the time required to complete the N to-be-completed tasks when the first duration is less than the preset duration, Indicates the cost required to complete the N to-be-completed tasks when the first duration is less than the preset duration, The value range of is 0 to 1, The value range of is 0 to 1, and , the running status information includes the first time of each resource node, the first time is the time when the resource node completes the processing of the to-be-completed task before the target task, and the first duration is the The difference between the second time and the current time. The second time is the latest time among the first time.

Optionally, in some embodiments, when the first duration is greater than the preset duration, the first function is:

;

in, Indicates the time required to complete the N to-be-completed tasks when the first duration is greater than the preset duration, Indicates the cost required to complete the N to-be-completed tasks when the first duration is longer than the preset duration, The value range of is 0 to 1, The value range of is 0 to 1, and , the running status information includes the first time of each resource node, the first time is the time when the resource node completes the processing of the to-be-completed task before the target task, and the first duration is the The difference between the second time and the current time. The second time is the latest time among the first time.

The electronic device provided by the embodiments of the present invention can execute the above method embodiments, and its implementation principles and technical effects are similar, and will not be described again in this embodiment.

In addition, the computer-readable storage medium of the embodiment of the present invention is used to store a computer program, and the computer program can be executed by a processor to implement the following steps:

Obtain the type of target task and the running status information of the resource node;

When the type of the target task is a preset type, a first function is determined based on the target task and the running status information, wherein the preset type indicates that the target task is N tasks to be completed. Any to-be-completed task from the 2nd to N-th to-be-completed task, the N to-be-completed tasks are arranged in sequence, and N is an integer greater than 1;

Calculate the first function according to the target algorithm to obtain the target solution;

According to the target resource scheduling plan determined based on the target solution, the resource node is scheduled to process the target task.

Optionally, when the target algorithm includes a genetic algorithm and a greedy algorithm, calculating the first function according to the target algorithm to obtain the target solution includes:

According to the greedy algorithm and the required resource type of the first individual, the target resource node of the first individual is determined in the resource list. The first individual is an individual that does not meet the preset constraints. The individual Determined based on the genetic algorithm;

Determine a first population according to the target resource node of the first individual, and the first population includes the target resource node of the first individual;

According to the genetic algorithm, iteratively calculate the first population and record the number of iterations;

When the number of iterations of the first population reaches the preset number of iterations, the individual with the highest fitness in the current population is determined as the target solution of the first function, and the current population is the preset number of iterations for the first population. Let the number of iterations be the iteratively calculated population.

Optionally, the iterative calculation of the first population according to the genetic algorithm includes:

Calculate the fitness of individuals within the first population according to a genetic algorithm;

According to the genetic algorithm, the fitness of individuals in the first population and the preset fitness threshold, the second population is determined and iteratively calculated.

Optionally, the iterative calculation of the first population according to the genetic algorithm, the crossover probability and the mutation probability includes:

Calculate the fitness of the M individuals of the first population and the sum of the fitnesses of the M individuals, where M is a positive integer;

According to the fitness of the target individual and the sum of the fitnesses of the M individuals, the first probability of the target individual is determined, the target individual is any of the M individuals, and the first probability is the target The probability that an individual is selected into the second population;

The second population is determined according to the first probability of the target individual, and the second population is the population after one iteration of the first population.

Optionally, when the first duration is less than the preset duration, the first function is:

;

in, Indicates the time required to complete the N to-be-completed tasks when the first duration is less than the preset duration, Indicates the cost required to complete the N to-be-completed tasks when the first duration is less than the preset duration, The value range of is 0 to 1, The value range of is 0 to 1, and , the running status information includes the first time of each resource node, the first time is the time when the resource node completes the processing of the to-be-completed task before the target task, and the first duration is the The difference between the second time and the current time. The second time is the latest time among the first time.

Optionally, when the first duration is less than the preset duration, the first function is:

;

in, Indicates the time required to complete the N to-be-completed tasks when the first duration is greater than the preset duration, Indicates the cost required to complete the N to-be-completed tasks when the first duration is longer than the preset duration, The value range of is 0 to 1, The value range of is 0 to 1, and , the running status information includes the first time of each resource node, the first time is the time when the resource node completes the processing of the to-be-completed task before the target task, and the first duration is the The difference between the second time and the current time. The second time is the latest time among the first time.

In the several embodiments provided in this application, it should be understood that the disclosed methods and devices can be implemented in other ways. For example, the device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or can be integrated into another system, or some features can be ignored, or not implemented. On the other hand, the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, and the indirect coupling or communication connection of the devices or units may be in electrical, mechanical or other forms.

In addition, each functional unit in various embodiments of the present invention may be integrated into one processing unit, each unit may be physically included separately, or two or more units may be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium and includes a number of instructions to cause a computer device (which can be a personal computer, a server, or a network device, etc.) to execute some steps of the sending and receiving methods described in various embodiments of the present invention. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM), random access memory (Random Access Memory, RAM), magnetic disk or optical disk and other media that can store program code. .

The above is the preferred embodiment of the present invention. It should be pointed out that for those of ordinary skill in the art, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications can also be made. should be regarded as the protection scope of the present invention.

Claims (7)

1. A resource scheduling method, characterized in that the method includes: Obtain the type of the target task and the running status information of the resource node. The running status information of the resource node includes: whether there is a task being executed and the completion time of executing the remaining tasks; When the type of the target task is a preset type, a first function is determined based on the target task and the running status information, wherein the preset type indicates that the target task is N tasks to be completed. Any to-be-completed task from the 2nd to N-th to-be-completed task, the N to-be-completed tasks are arranged in sequence, and N is an integer greater than 1; Calculate the first function according to a target algorithm to obtain a target solution, and the target algorithm includes a genetic algorithm and a greedy algorithm; When the first duration is less than the preset duration, the first function is: min(αftime+βfcost); Where, f _time represents the time required to complete the N tasks to be completed when the first duration is less than the preset duration, and f _cost represents the time required to complete the N tasks to be completed when the first duration is less than the preset duration. The cost of the task, the value range of α is 0 to 1, the value range of β is 0 to 1, and α+β=1, the running status information includes the first moment of each resource node, The first time is the time when the resource node completes processing of the to-be-completed task before the target task, the first duration is the difference between the second time and the current time, and the second time is the Describe the latest of the first moments; In the case where the first duration is greater than the preset duration, the first function is: min(γgtime+δgcost); Among them, g _time represents the time required to complete the N tasks to be completed when the first duration is greater than the preset duration, and g _cost represents the time required to complete the N tasks to be completed when the first duration is greater than the preset duration. The cost of the task, the value range of γ is 0 to 1, the value range of δ is 0 to 1, and γ+δ=1, the running status information includes the first moment of each resource node, The first time is the time when the resource node completes processing of the to-be-completed task before the target task, the first duration is the difference between the second time and the current time, and the second time is the The latest time in the first time; according to the target resource scheduling plan determined based on the target solution, schedule the resource node to process the target task. 2. The resource scheduling method according to claim 1, characterized in that, when the target algorithm includes a genetic algorithm and a greedy algorithm, the first function is calculated according to the target algorithm, and the target solution obtained includes: : According to the greedy algorithm and the required resource type of the first individual, the target resource node of the first individual is determined in the resource list. The first individual is an individual that does not meet the preset constraints. The individual Determined based on the genetic algorithm; Determine a first population according to the target resource node of the first individual, and the first population includes the target resource node of the first individual; According to the genetic algorithm, iteratively calculate the first population and record the number of iterations; When the number of iterations of the first population reaches the preset number of iterations, the individual with the highest fitness in the current population is determined as the target solution of the first function, and the current population is the preset number of iterations for the first population. Let the number of iterations be the iteratively calculated population. 3. The resource scheduling method according to claim 2, wherein the iterative calculation of the first population according to the genetic algorithm includes: Calculate the fitness of individuals within the first population according to a genetic algorithm; According to the genetic algorithm, the fitness of individuals in the first population and the preset fitness threshold, the second population is determined and iteratively calculated. 4. The resource scheduling method according to claim 2, wherein the iterative calculation of the first population according to the genetic algorithm, crossover probability and mutation probability includes: Calculate the fitness of the M individuals of the first population and the sum of the fitnesses of the M individuals, where M is a positive integer; According to the fitness of the target individual and the sum of the fitnesses of the M individuals, the first probability of the target individual is determined, the target individual is any of the M individuals, and the first probability is the target The probability that an individual is selected into the second population; The second population is determined according to the first probability of the target individual, and the second population is the population after one iteration of the first population. 5. A resource scheduling device, characterized in that the device includes: A monitoring module, used to obtain the type of the target task and the running status information of the resource node. The running status information of the resource node includes: whether there are tasks being executed and the completion time of executing the remaining tasks; Determining module, configured to determine a first function according to the target task and the running status information when the type of the target task is a preset type, wherein the preset type indicates that the target task is Any to-be-completed task from the 2nd to N-th to-be-completed tasks among the N to-be-completed tasks, the N to-be-completed tasks are arranged in sequence, and N is an integer greater than 1; Obtaining module, used to calculate the first function according to a target algorithm to obtain a target solution, and the target algorithm includes a genetic algorithm and a greedy algorithm; When the first duration is less than the preset duration, the first function is: min(αftime+βfcost); Where, f _time represents the time required to complete the N tasks to be completed when the first duration is less than the preset duration, and f _cost represents the time required to complete the N tasks to be completed when the first duration is less than the preset duration. The cost of the task, the value range of α is 0 to 1, the value range of β is 0 to 1, and α+β=1, the running status information includes the first moment of each resource node, The first time is the time when the resource node completes processing of the to-be-completed task before the target task, the first duration is the difference between the second time and the current time, and the second time is the Describe the latest of the first moments; In the case where the first duration is greater than the preset duration, the first function is: min(γgtime+δgcost); Among them, g _time represents the time required to complete the N tasks to be completed when the first duration is greater than the preset duration, and g _cost represents the time required to complete the N tasks to be completed when the first duration is greater than the preset duration. The cost of the task, the value range of γ is 0 to 1, the value range of δ is 0 to 1, and γ+δ=1, the running status information includes the first moment of each resource node, The first time is the time when the resource node completes processing of the to-be-completed task before the target task, the first duration is the difference between the second time and the current time, and the second time is the Describe the latest of the first moments; A scheduling module, configured to schedule the resource node to process the target task according to the target resource scheduling plan determined based on the target solution. 6. An electronic device, comprising: a transceiver, a memory, a processor, and a computer program stored on the memory and executable on the processor; characterized in that the processor is used to read the memory The program in implements the steps in the method according to any one of claims 1 to 4. 7. A readable storage medium for storing a computer program, characterized in that, when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 4 are implemented.