Method for determining maintenance scheduling information of power equipment based on genetic algorithm

Abstract

The embodiment of the invention provides a method for determining maintenance scheduling information of power equipment based on a genetic algorithm. The method comprises the steps that the following steps are repeatedly executed until a preset condition is met, individuals of an initial population are randomly generated, the individuals represent maintenance scheduling information of power equipment in a power grid system, and the individuals have fitness values; the fitness value indicates the rationality of the scheduling scheme represented by the maintenance scheduling information; performing genetic iterative optimization processing on the initial population to obtain a filial generation population; taking the offspring population as an initial population; wherein when a preset condition is met, the newly generated maintenance scheduling information of the power equipment represented by the individual with the highest fitness value in the filial generation population is the final maintenance scheduling information of the power equipment. The method is used for improving the rationality of the maintenance items of the power equipment and the scheduling scheme of the test platform.

Description

Technical Field

[0001] This application relates to the field of power equipment maintenance technology, and in particular to a method for determining maintenance scheduling information for power equipment based on a genetic algorithm. Background Technology

[0002] A power system can contain various types of electrical equipment. As the power system reaches the end of its service life, the electrical equipment may require batch maintenance. Each piece of electrical equipment may require maintenance based on multiple maintenance items, and these maintenance items are usually carried out on a test platform.

[0003] In some technologies, the scheduling and allocation of testing platforms for each power device is determined manually based on the maintenance items required for repair. However, in these technologies, the manually determined scheduling and allocation schemes for power device maintenance can be unreasonable.

[0004] Therefore, there is an urgent need for a scheme that can reasonably determine the maintenance and scheduling information for power equipment maintenance projects and testing platforms. Summary of the Invention

[0005] The method for determining maintenance scheduling information of power equipment based on genetic algorithms provided in this application is used to improve the rationality of maintenance projects and test platform scheduling schemes for power equipment.

[0006] In a first aspect, embodiments of this application provide a method for determining maintenance scheduling information of power equipment based on a genetic algorithm, including:

[0007] Repeat the following steps until the preset conditions are met. The individuals in the initial population are randomly generated. Each individual represents maintenance and scheduling information for power equipment in the power grid system, and each individual has a fitness value. The maintenance and scheduling information represents a scheduling scheme for maintenance projects on power equipment, and the fitness value indicates the rationality of the scheduling scheme represented by the maintenance and scheduling information.

[0008] Genetic iterative optimization is performed on the initial population to obtain the offspring population; the individuals in the offspring population represent the maintenance and scheduling information of the newly generated power equipment.

[0009] Use the offspring population as the initial population;

[0010] Among them, the maintenance and scheduling information of the newly generated power equipment represented by the individual with the highest fitness value in the offspring population when the preset conditions are met is the final maintenance and scheduling information of the power equipment.

[0011] In one possible implementation, genetic iterative optimization is performed on the initial population to obtain the offspring population, including:

[0012] A selection operation is performed on the initial population to obtain the first intermediate population; wherein the fitness value of individuals in the first intermediate population is greater than or equal to a preset value;

[0013] The order of maintenance items in the scheduling scheme represented by some individuals in the first intermediate population is changed to obtain the changed individuals;

[0014] The offspring population is constructed based on the changed individuals and the unchanged individuals in the first intermediate population.

[0015] In one possible implementation, the method further includes:

[0016] Based on the maintenance and scheduling information of the power equipment represented by the individual, the fitness value of the individual is determined according to the preset fitness function.

[0017] In one possible implementation, the fitness value of an individual is determined based on the maintenance and scheduling information of the power equipment represented by that individual, and a preset fitness function, including:

[0018] Based on the maintenance scheduling information, the maintenance project completion time, average waiting time, utilization variance, and number of spatiotemporal conflicts are determined respectively. Among them, the maintenance project completion time represents the time required for the power equipment to complete all maintenance projects; the average waiting time represents the average time required for the power equipment to transfer between adjacent test platforms; the utilization variance represents the difference in the idle level of different test platforms when the power equipment completes maintenance projects; and the number of spatiotemporal conflicts represents the number of times the power equipment needs to perform the next maintenance project if the previous maintenance project has not been completed.

[0019] Based on the maintenance project completion time, average waiting time, utilization variance, and number of spatiotemporal conflicts, the fitness value of an individual is determined using a preset fitness function.

[0020] In one possible implementation, the preset condition indicates that the number of times the genetic iterative optimization process is performed is greater than or equal to the maximum number of iterations, and / or that the fitness value converges.

[0021] In one possible implementation, the maintenance scheduling information for power equipment includes at least one of the following: maintenance project information for power equipment, test platform information for power equipment, and timing coordination information for power equipment.

[0022] Among them, the maintenance project information represents the maintenance projects that need to be carried out on the power equipment and the order of maintenance projects; the test platform information represents the test platform required for the power equipment to carry out maintenance projects; and the timing coordination information represents the interval time required for the power equipment to be transferred between adjacent test platforms.

[0023] In one possible implementation, the timing coordination information includes: transition time and preparation time;

[0024] When the preparation time is greater than the transfer time, the timing coordination information represents the interval time required for the transfer of power equipment between adjacent test platforms as the preparation time.

[0025] Otherwise, the timing coordination information characterizes the interval time required for the transfer of power equipment between adjacent test platforms as the transfer time.

[0026] Secondly, embodiments of this application provide a device for determining maintenance scheduling information of power equipment based on a genetic algorithm, comprising:

[0027] The processing module is used to repeatedly execute the following steps until a preset condition is met. The individuals in the initial population are randomly generated, each representing maintenance and scheduling information of power equipment in the power grid system, and each individual has a fitness value. The maintenance and scheduling information represents a scheduling scheme for maintenance projects of power equipment, and the fitness value indicates the rationality of the scheduling scheme represented by the maintenance and scheduling information.

[0028] Genetic iterative optimization is performed on the initial population to obtain the offspring population; the individuals in the offspring population represent the maintenance and scheduling information of the newly generated power equipment.

[0029] Use the offspring population as the initial population;

[0030] Among them, the maintenance and scheduling information of the newly generated power equipment represented by the individual with the highest fitness value in the offspring population when the preset conditions are met is the final maintenance and scheduling information of the power equipment.

[0031] In one possible implementation, genetic iterative optimization is performed on the initial population to obtain the offspring population. The processing module is used for:

[0032] A selection operation is performed on the initial population to obtain the first intermediate population; wherein the fitness value of individuals in the first intermediate population is greater than or equal to a preset value;

[0033] The order of maintenance items in the scheduling scheme represented by some individuals in the first intermediate population is changed to obtain the changed individuals;

[0034] The offspring population is constructed based on the changed individuals and the unchanged individuals in the first intermediate population.

[0035] In one possible implementation, the processing module is further configured to:

[0036] Based on the maintenance and scheduling information of the power equipment represented by the individual, the fitness value of the individual is determined according to the preset fitness function.

[0037] In one possible implementation, based on the maintenance and scheduling information of the power equipment represented by the individual, and based on a preset fitness function, the fitness value of the individual is determined, and the processing module is used to:

[0038] Based on the maintenance scheduling information, the maintenance project completion time, average waiting time, utilization variance, and number of spatiotemporal conflicts are determined respectively. Among them, the maintenance project completion time represents the time required for the power equipment to complete all maintenance projects; the average waiting time represents the average time required for the power equipment to transfer between adjacent test platforms; the utilization variance represents the difference in the idle level of different test platforms when the power equipment completes maintenance projects; and the number of spatiotemporal conflicts represents the number of times the power equipment needs to perform the next maintenance project if the previous maintenance project has not been completed.

[0039] Based on the maintenance project completion time, average waiting time, utilization variance, and number of spatiotemporal conflicts, the fitness value of an individual is determined using a preset fitness function.

[0040] In one possible implementation, the preset condition indicates that the number of times the genetic iterative optimization process is performed is greater than or equal to the maximum number of iterations, and / or that the fitness value converges.

[0041] In one possible implementation, the maintenance scheduling information for power equipment includes at least one of the following: maintenance project information for power equipment, test platform information for power equipment, and timing coordination information for power equipment.

[0042] Among them, the maintenance project information represents the maintenance projects that need to be carried out on the power equipment and the order of maintenance projects; the test platform information represents the test platform required for the power equipment to carry out maintenance projects; and the timing coordination information represents the interval time required for the power equipment to be transferred between adjacent test platforms.

[0043] In one possible implementation, the timing coordination information includes: transition time and preparation time;

[0044] When the preparation time is greater than the transfer time, the timing coordination information represents the interval time required for the transfer of power equipment between adjacent test platforms as the preparation time.

[0045] Otherwise, the timing coordination information characterizes the interval time required for the transfer of power equipment between adjacent test platforms as the transfer time.

[0046] Thirdly, embodiments of this application provide an electronic device, including: a memory and a processor;

[0047] The memory stores instructions that the computer executes;

[0048] The processor executes computer execution instructions stored in memory, causing the processor to perform the first aspect and / or various possible implementations of the first aspect as described above.

[0049] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, are used to implement the first aspect and / or various possible implementations of the first aspect.

[0050] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the first aspect and / or various possible implementations of the first aspect.

[0051] The method for determining maintenance scheduling information of power equipment based on genetic algorithms provided in this application introduces genetic algorithms into the process of determining maintenance scheduling information of power equipment. Specifically, multiple individuals are randomly generated in an initial population, where each individual represents a scheduling scheme for a power equipment to perform a maintenance project. Based on the genetic algorithm, the initial population is repeatedly subjected to a genetic iterative optimization process until a preset condition is reached. The maintenance scheduling information of the power equipment represented by the individual with the highest fitness value when the preset condition is reached is taken as the final maintenance scheduling information, thereby improving the rationality of the maintenance scheduling information of power equipment. Attached Figure Description

[0052] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0053] Figure 1 A flowchart illustrating the method for determining maintenance and scheduling information of power equipment based on genetic algorithms provided in this application. Figure 1 ;

[0054] Figure 2 A flowchart illustrating the method for determining maintenance and scheduling information of power equipment based on genetic algorithms provided in this application. Figure 2 ;

[0055] Figure 3 A schematic diagram of the structure of the device for determining maintenance and scheduling information of power equipment based on genetic algorithms provided in this application;

[0056] Figure 4 A schematic diagram of the structure of the electronic device provided in this application.

[0057] The accompanying drawings have illustrated specific embodiments of this application, which will be described in more detail below. These drawings and descriptions are not intended to limit the scope of the concept in any way, but rather to illustrate the concept of this application to those skilled in the art through reference to specific embodiments. Detailed Implementation

[0058] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0059] First, let me explain the terms used in this application:

[0060] Genetic algorithm: This refers to a stochastic global search optimization algorithm that simulates phenomena such as replication, crossover, and mutation that occur in natural selection and inheritance processes. Starting from an initial population, through selection, crossover, and mutation operations, individuals better adapted to the environment are generated, resulting in a offspring population. Based on this offspring population, selection, crossover, and mutation operations are continued to generate new offspring populations corresponding to the previous parent population. This process is repeated until it converges to the most adapted offspring population, and the individuals in this most adapted offspring population are considered the high-quality solution to the problem.

[0061] Power systems contain various types of electrical equipment. As the power system comes into use, and maintenance deadlines are reached, batch maintenance of the electrical equipment may be necessary to ensure its insulation withstand voltage level and reliability. Each piece of equipment may require multiple maintenance items, and these items vary from piece to piece. Furthermore, these maintenance items typically need to be performed on a testing platform; therefore, the electrical equipment must be transferred to the corresponding testing platform for each maintenance item.

[0062] In some embodiments, maintenance projects for power equipment are scheduled manually. During the scheduling process, the projects are manually assigned based on the maintenance items required for each power piece of equipment, the order of the maintenance items, and the available testing platforms.

[0063] However, due to the varying time required for each maintenance project, multiple resource conflicts can easily arise. For example, two test platforms may simultaneously wait for a single power device to undergo different maintenance projects; or, for instance, the same test platform may need to execute multiple maintenance projects concurrently. In the above embodiments, the power device allocation scheme obtained through manual allocation has inherent limitations, meaning there is a technical problem with the manually determined power device maintenance scheduling information being unreasonable.

[0064] The method for determining maintenance scheduling information of power equipment based on genetic algorithms provided in this application introduces genetic algorithms into the process of determining maintenance scheduling information of power equipment. Specifically, multiple individuals are randomly generated in an initial population, where each individual represents a scheduling scheme for a power equipment performing a maintenance project. Based on the genetic algorithm, the initial population is repeatedly subjected to a genetic iterative optimization process until a preset condition is met. The maintenance scheduling information of the power equipment represented by the individual with the highest fitness value when the preset condition is met is taken as the final maintenance scheduling information. This method solves the technical problem of unreasonable maintenance scheduling information of power equipment determined manually, thereby improving the rationality of the maintenance scheduling information of power equipment.

[0065] The technical solution of this application and how it solves the above-mentioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of this application will be described below with reference to the accompanying drawings.

[0066] Figure 1 A flowchart illustrating the method for determining maintenance and scheduling information of power equipment based on genetic algorithms provided in this application. Figure 1 ,like Figure 1 As shown, the method includes:

[0067] Repeat the following steps until the preset conditions are met:

[0068] Step 101. Perform genetic iterative optimization on the initial population to obtain the offspring population.

[0069] Among them, the individual representations of the offspring population contain maintenance and scheduling information for newly generated power equipment.

[0070] Step 102. Use the offspring population as the initial population.

[0071] The individuals in the initial population are randomly generated. Each individual represents the maintenance and scheduling information of power equipment in the power grid system, and each individual has a fitness value. The maintenance and scheduling information represents the scheduling scheme for maintenance projects of power equipment, and the fitness value indicates the rationality of the scheduling scheme represented by the maintenance and scheduling information.

[0072] For example, based on the idea of ​​a genetic algorithm, an initial population needs to be randomly generated first. This initial population includes multiple individuals, each representing maintenance and scheduling information for power equipment in the power grid system. Furthermore, the maintenance and scheduling information represents the scheduling scheme for maintenance projects on the power equipment.

[0073] For example, an individual in the initial population can represent a scheme for allocating suitable test platforms based on the maintenance items required for each power device. For instance, if only one power device needs maintenance, and the maintenance items for that device include A, B, and C, the available test platforms include Platform 1 and Platform 2.

[0074] Specifically, the first individual representation scheme in the initial population is: the power equipment performs maintenance item A on platform 1, maintenance item B on platform 2, and maintenance item C on platform 1. The second individual representation scheme in the initial population is: the power equipment performs maintenance item C on platform 2, maintenance item A on platform 1, and maintenance item B on platform 2. And so on. Other allocation schemes can be randomly generated in the initial population, with each allocation scheme representing an individual in the initial population.

[0075] By combining the ideas of genetic algorithms, the random individuals generated in the initial population can be subjected to genetic iterative optimization to obtain the offspring population corresponding to the initial population.

[0076] In this population, individuals in the initial group and their corresponding offspring groups all possess a fitness value. This fitness value indicates whether the scheduling plan for the maintenance project of the power equipment corresponding to the maintenance scheduling information represented by the individual is reasonable.

[0077] Specifically, genetic iterative optimization processing can include selection, crossover, and mutation operations. Selection involves choosing individuals with higher fitness values ​​from all individuals in the initial population to generate the offspring population. Crossover involves exchanging parts of the chromosomes of one or more individuals in the initial population to obtain the offspring population. Mutation involves mutating parts of the chromosomes of one or more individuals in the initial population to obtain the offspring population. Each offspring population represents the newly generated maintenance and scheduling information for power equipment.

[0078] Based on the above example, after performing genetic iterative optimization on the individuals in the initial population, a offspring population can be obtained; and the offspring population can be used as the initial population for the next repeated execution.

[0079] Repeat steps 101 and 102 until the preset conditions are met.

[0080] Among them, the maintenance and scheduling information of the newly generated power equipment represented by the individual with the highest fitness value in the offspring population when the preset conditions are met is the final maintenance and scheduling information of the power equipment.

[0081] For example, when a preset condition is met, it indicates that the offspring population has a high fitness value, meaning that the scheduling scheme for the power equipment maintenance project represented by the individuals in the offspring population is relatively reasonable. The maintenance scheduling information of the newly generated power equipment represented by the individual with the highest fitness value in the offspring population is then used as the final maintenance scheduling information for the power equipment, thus obtaining the most reasonable scheduling scheme for the power equipment maintenance project.

[0082] The method for determining maintenance scheduling information of power equipment based on genetic algorithms provided in this application introduces genetic algorithms into the process of determining maintenance scheduling information of power equipment. Specifically, multiple individuals are randomly generated in an initial population, where each individual represents a scheduling scheme for a power equipment performing a maintenance project. Based on the genetic algorithm, the initial population is repeatedly subjected to a genetic iterative optimization process until a preset condition is met. The maintenance scheduling information of the power equipment represented by the individual with the highest fitness value when the preset condition is met is taken as the final maintenance scheduling information, thus obtaining a reasonable scheduling scheme for the power equipment to perform maintenance projects, thereby improving the rationality of the maintenance scheduling information of power equipment.

[0083] Specifically, in light of the problem to be solved in this embodiment and the idea of ​​genetic algorithms, it is necessary to model the power equipment, maintenance projects, and test platforms, and to encode the chromosomes of individuals in the initial population.

[0084] For example, n electrical devices in a power system can be denoted as a device set. The m maintenance items required for power equipment can be denoted as the maintenance item set. The k test platforms that can be allocated for a maintenance project can be denoted as a test platform resource pool. Where n, m, and k are all positive integers greater than or equal to 1, and k ≤ m.

[0085] Furthermore, assume that both n and m are 3, meaning there are currently 3 electrical devices that need maintenance. The maintenance items that need to be performed are the maintenance items. Maintenance items and maintenance items Power equipment The maintenance items that need to be performed are the maintenance items. and maintenance items Power equipment The maintenance items that need to be performed are the maintenance items. .

[0086] Assume k is 2, meaning there are now two test platforms capable of performing the maintenance tasks for each of the three power devices mentioned above. Power devices Maintenance items Use of test platform Maintenance items to be carried out Use of test platform Maintenance items to be carried out Use of test platform Power equipment Maintenance items Use of test platform Maintenance items to be carried out Use of test platform Power equipment Maintenance items Use of test platform .

[0087] Based on the modeling approach described in the previous example, individuals in the initial population are encoded. Each individual represents the maintenance and scheduling information of the power equipment.

[0088] In one example, the maintenance scheduling information for power equipment includes at least one of the following: maintenance project information for power equipment, test platform information for power equipment, and timing coordination information for power equipment.

[0089] Among them, the maintenance project information represents the maintenance projects that need to be carried out on the power equipment and the order of maintenance projects; the test platform information represents the test platform required for the power equipment to carry out maintenance projects; and the timing coordination information represents the interval time required for the power equipment to be transferred between adjacent test platforms.

[0090] For example, combining the modeling methods of the aforementioned examples, chromosome encoding is performed on the power equipment maintenance and scheduling information represented by each individual.

[0091] Specifically, maintenance item information for power equipment can be represented in matrix form, denoted as a maintenance item matrix. Maintenance item information indicates the maintenance items required for each piece of electrical equipment and the order in which these items are performed. For example, electrical equipment... The maintenance items that need to be performed are the maintenance items. Maintenance items and maintenance items Power equipment The maintenance items that need to be performed are the maintenance items. and maintenance items Power equipment The maintenance items that need to be performed are the maintenance items. At this time, the maintenance project matrix The expression for can be shown in the following formula (1):

[0092] Formula (1)

[0093] in, This indicates an invalid placeholder, which in practice can be mapped to the number 0. This can be understood in the maintenance item matrix. In the matrix, each row represents a piece of electrical equipment, and each element in the row represents the maintenance item to be inspected for that equipment. Furthermore, the order of the maintenance items from left to right within the row represents the sequence of these items. That is, in the maintenance item matrix... In the diagram, the j-th element in the i-th row represents the electrical equipment. The j-th maintenance item that needs to be inspected .

[0094] Specifically, the test platform information for power equipment can be represented in matrix form, denoted as the test platform matrix. Test platform information, which characterizes the test platform required when performing maintenance projects on power equipment.

[0095] It should be noted that the experimental platform matrix Maintenance Project Matrix The dimensions are the same. Therefore, in the experimental platform matrix In the diagram, the j-th element in the i-th row represents the electrical equipment. The j-th maintenance item that needs to be inspected The necessary testing platform.

[0096] For example, electrical equipment Maintenance items Use of test platform Maintenance items to be carried out Use of test platform Maintenance items to be carried out Use of test platform Power equipment Maintenance items Use of test platform Maintenance items to be carried out Use of test platform Power equipment Maintenance items Use of test platform At this time, the experimental platform matrix The expression for can be shown in the following formula (2):

[0097] Formula (2)

[0098] in, This indicates an invalid placeholder, which in practical applications can be mapped to the number 0. This can be understood in the experimental platform matrix. An invalid placeholder in the code indicates that there is no corresponding maintenance item.

[0099] Specifically, the timing coordination information of power equipment can be represented in vector form, denoted as virtual time window gene segment vector. Timing coordination information, characterizing the interval time required for the transfer of power equipment between adjacent test platforms, can be understood as the virtual time window gene segment vector. For the i-th power device, represents the interval time required for the i-th power device to be transferred between adjacent test platforms.

[0100] Furthermore, the virtual time window gene segment vector of the i-th power device .in, This represents the time interval required to transfer the i-th power equipment between the test platform corresponding to the first maintenance project and the test platform corresponding to the second maintenance project. This represents the time interval required to transfer the i-th power equipment between the test platform corresponding to the second maintenance project and the test platform corresponding to the third maintenance project. The interval time required to transfer the i-th power equipment between the test platform corresponding to the (m-1)-th maintenance item and the test platform corresponding to the m-th maintenance item.

[0101] Furthermore, it takes time to transport electrical equipment to different platforms, and time is also needed for each test platform to prepare for maintenance.

[0102] Therefore, in one example, the timing coordination information includes: transition time and preparation time;

[0103] When the preparation time is greater than the transfer time, the timing coordination information represents the interval time required for the transfer of power equipment between adjacent test platforms as the preparation time.

[0104] Otherwise, the timing coordination information characterizes the interval time required for the transfer of power equipment between adjacent test platforms as the transfer time.

[0105] For example, transfer time refers to the time required for power equipment to be transferred from the test platform corresponding to the previous maintenance project to the equipment parking room, and then to the test platform corresponding to the next maintenance project when multiple maintenance projects are carried out in succession.

[0106] Preparation time refers to the time required for the test platform to prepare for the next maintenance item of the power equipment.

[0107] For example, in general, the preparation time is longer than the transfer time. Therefore, in order to ensure that the test platform for the next maintenance project is ready to execute the next maintenance project, the interval time represented by the timing coordination information is the preparation time.

[0108] If the preparation time is less than or equal to the transition time, then the interval time represented by the timing coordination information is the transition time.

[0109] For example, for the virtual time window gene segment vector of the i-th power device The j-th element .in, This indicates the transfer time, i.e., the time when the i-th power device is on the test platform. and test platform Transition time between scenes; This represents the preparation time, specifically the time when the i-th power equipment undergoes its (j+1)-th maintenance item, corresponding to the test platform. Preparation time for the (j+1)th maintenance item; This represents the function that takes the maximum value.

[0110] To facilitate understanding, a dispatching plan for the maintenance of a single piece of electrical equipment will be explained. This equipment requires maintenance items to be performed in the following order: , as well as The corresponding test platform is: , as well as For individuals in the initial population, the maintenance and scheduling information for the power equipment represents includes: a maintenance item matrix. Experimental platform matrix Virtual time window gene segment vector It can be understood that the scheduling scheme represented by this individual is: the power equipment on the test platform... Perform maintenance projects After completion, it took 5 minutes to transfer to the test platform. and carry out maintenance projects. After completion, it took 8 minutes to transfer to the test platform. and carry out maintenance projects. .

[0111] In the above example, based on practical applications, the key parameters required for scheduling during the maintenance of power equipment in a power system are encoded. This allows us to obtain the individuals in the population of the genetic algorithm. This lays the foundation for subsequently obtaining a reasonable scheduling scheme based on the genetic algorithm. Furthermore, by considering parameters at multiple levels in the scheduling scheme, the rationality of the scheduling scheme is ensured.

[0112] Figure 2 A flowchart illustrating the method for determining maintenance and scheduling information of power equipment based on genetic algorithms provided in this application. Figure 2 ,like Figure 2 As shown, in this embodiment... Figure 1 Based on the illustrated embodiment, step 101 will be described in detail, the method including:

[0113] Step 201. Perform a selection operation on the initial population to obtain the first intermediate population.

[0114] Among them, the fitness value of individuals in the first intermediate population is greater than or equal to the preset value.

[0115] For example, roulette wheel selection or tournament selection methods can be used to select individuals with higher fitness values ​​from the initial population for breeding. Roulette wheel selection assigns the probability of an individual being selected as a member of the first intermediate population based on its fitness value in the initial population. It can be understood that the higher the fitness value of an individual in the initial population, the more likely it is to be selected as a member of the first intermediate population. Tournament selection involves selecting some individuals from the initial population as participants in a tournament, and then selecting the individual with the highest fitness value from among the participants as a member of the first intermediate population; or selecting individuals with a fitness value greater than or equal to a preset value from among the participants as members of the first intermediate population.

[0116] Based on the two methods described above, the first intermediate population corresponding to the initial population can be obtained. It should be noted that the two methods for selecting the initial population described above can be implemented in combination or separately.

[0117] Step 202. Change the order of maintenance items in the scheduling scheme represented by some individuals in the first intermediate population to obtain the changed individuals.

[0118] For example, based on the principles of genetic algorithms, modifications are made to some individuals in the first intermediate population, which can be understood as crossover and mutation. This involves changing the order of maintenance items in the scheduling scheme represented by some individuals in the first intermediate population.

[0119] Specifically, in one optional implementation, the order of maintenance items in the scheduling scheme is changed, including:

[0120] The maintenance item matrix represented by a subset of individuals selected from the first intermediate population. In this process, two elements in the same row are swapped to obtain the modified individual. This is known as mutation processing.

[0121] Specifically, in one optional implementation, the order of maintenance items in the scheduling scheme is changed, including:

[0122] The first individual will be selected from the first intermediate population, representing the maintenance item matrix. One or more elements in the matrix, and the maintenance item matrix represented by the second individual selected from the first intermediate population. Swap the elements at the corresponding positions in the array.

[0123] Correspondingly, the experimental platform matrix represented by the first entity... The corresponding elements in the matrix, and the experimental platform matrix represented by the second entity. Swap the corresponding elements in the array.

[0124] Accordingly, the virtual time window gene segment vector corresponding to the first body exchange is redefined. And redetermine the virtual time window gene segment vector corresponding to the second body exchange. That is, cross-processing.

[0125] Based on the first and second individuals after the exchange, the changed individuals are obtained.

[0126] Step 203. Based on the changed individuals and the unchanged individuals in the first intermediate population, construct the offspring population.

[0127] For example, based on the changed individuals obtained in step 202 and the unchanged individuals in the first intermediate population, the offspring population corresponding to the initial population is constructed.

[0128] It can be understood that the change operation in step 202 is performed on a subset of individuals selected from the first intermediate population. Within the first intermediate population, there are still individuals that have not undergone the change. Based on the changed individuals obtained in step 202 and the unchanged individuals in the first intermediate population, a offspring population is constructed.

[0129] In the above example, a genetic algorithm is used to perform iterative optimization on the maintenance items and scheduling schemes of the assigned test platforms for power equipment maintenance in a power system. The specific iterative optimization operations include at least selection, crossover, and mutation. Based on this genetic iterative optimization, a comprehensive global search can be performed on the scheduling schemes represented by individual components, gradually approaching the more reasonable scheduling scheme among all possibilities. This improves the rationality of the final determined power equipment maintenance scheduling information.

[0130] As can be seen from the foregoing embodiments, the rationality of the scheduling scheme corresponding to the maintenance and scheduling information of power equipment represented by individuals in the population is evaluated through the fitness in the genetic algorithm. Therefore, it is necessary to determine the fitness value of each individual.

[0131] In one example, the method further includes: determining the fitness value of an individual based on a preset fitness function, according to the maintenance and scheduling information of the power equipment represented by the individual.

[0132] For example, a preset fitness function can be determined by combining the core optimization objectives. For instance, the fitness function can be preset based on one or more of the following objectives: minimizing total cost, minimizing total time, maximizing reliability, and load balancing.

[0133] In one alternative implementation, based on single-objective optimization, the preset fitness function can be the reciprocal of the total time.

[0134] In one optional implementation, based on multi-objective optimization, the preset fitness function can be a weighted sum of the reciprocal of the total time and the reciprocal of the total cost.

[0135] By combining a preset fitness function and determining the maintenance and scheduling information of the power equipment represented by each individual, the fitness value of each individual can be determined. Based on the fitness value of each individual, the selection and modification operations of the initial population described above can be performed. Furthermore, based on the fitness value of each individual, the maintenance and scheduling information of the power equipment represented by the individual with the highest fitness value can only be used as the final maintenance and scheduling information when preset conditions are met.

[0136] It should be noted that the fitness value of individuals in both the initial population and the offspring population can be calculated using a preset fitness function.

[0137] In the example above, the fitness value of each individual in the population can be determined by the preset fitness function, which lays the foundation for subsequent selection operations based on fitness values ​​and for determining the final maintenance scheduling information when preset conditions are met.

[0138] Furthermore, in conjunction with the aforementioned examples, a detailed explanation is given regarding the preset fitness function and how to determine the fitness value based on the maintenance and scheduling information of the power equipment represented by the individual.

[0139] In one example, based on maintenance scheduling information, the completion time of maintenance projects, average waiting time, utilization variance, and number of spatiotemporal conflicts are determined respectively.

[0140] Among them, the maintenance project completion time represents the time required for the power equipment to complete all maintenance projects; the average waiting time represents the average time required for the power equipment to transfer between adjacent test platforms; the utilization variance represents the difference in the idleness of different test platforms when the power equipment completes maintenance projects; and the number of time-space conflicts represents the number of times the power equipment needs to perform the next maintenance project if the previous maintenance project has not been completed.

[0141] For example, the maintenance project completion time refers to the total time required for all electrical equipment to complete its corresponding maintenance project. Specifically, this is based on the maintenance project matrix in the maintenance scheduling information. It can be seen that each piece of electrical equipment requires specific maintenance items, and each maintenance item has a corresponding time consumption. Therefore, by summing the time consumed by each piece of electrical equipment to complete its corresponding maintenance item, we can obtain the maintenance time for each piece of electrical equipment; then, by summing the maintenance times of all pieces of electrical equipment, we can obtain the completion time of each maintenance item.

[0142] Optionally, the completion time of the maintenance project can be recorded as... .

[0143] For example, average waiting time refers to the average time required for all electrical equipment to be transferred between adjacent test platforms. Specifically, this is based on the virtual time window segment vector in the maintenance scheduling information. The average waiting time of the i-th power device is obtained by averaging the elements in the table; then the average waiting time of all power devices is averaged to obtain the average waiting time.

[0144] Optionally, the average waiting time can be denoted as .

[0145] For example, utilization variance refers to the difference in idle time among different test platforms when power equipment completes maintenance projects. Specifically, it is based on the test platform matrix in the maintenance scheduling information. It can be seen that for each power equipment maintenance project, there is a corresponding test platform. The frequency of each test platform appearing in the test platform matrix is ​​counted. That is, the test platform... In the test platform matrix The number of times it occurs is denoted as a1; experimental platform In the test platform matrix The number of times it appears is denoted as a2; and so on, until all test platforms are obtained in the test platform matrix. Number of times it appears.

[0146] The variance of the number of trials for all test platforms is calculated to obtain the utilization variance.

[0147] It is understandable that if a certain test platform appears too frequently, it will result in a large utilization variance value. This indicates that the test platform is busy while other test platforms are idle, suggesting that the test platform allocation scheme is unreasonable.

[0148] Optionally, the utilization variance can be denoted as .

[0149] For example, the number of spatiotemporal conflicts refers to the number of times a power device needs to perform a subsequent maintenance task before the previous one is completed. Specifically, this is based on the maintenance task matrix in the maintenance scheduling information. It can be seen that each piece of electrical equipment requires specific maintenance items, and each maintenance item has a corresponding time consumption. Furthermore, based on the virtual time window gene segment vector in the maintenance scheduling information... The elements in the diagram indicate the interval time required for each power device to perform adjacent maintenance items on adjacent test platforms.

[0150] If the time spent on a certain maintenance item in the maintenance item matrix is ​​less than the interval time represented by the element of the corresponding virtual time window gene segment vector, then a count is performed to obtain the number of spatiotemporal conflicts.

[0151] For example, electrical equipment is undergoing maintenance project A on platform one, which takes 10 minutes. After maintenance project A, the equipment needs to be transferred to platform two for maintenance project B. If the element in the corresponding virtual time window gene segment vector represents the interval required for the transfer between platform one and platform two as 5 minutes, this indicates a spatiotemporal conflict, and a count is made. In practical applications, this interval may be preparation time; that is, platform two may be ready to perform maintenance project B, while the electrical equipment is still performing maintenance project A on platform one and has not yet completed it, thus indicating a spatiotemporal conflict.

[0152] Optionally, the number of time-space conflicts can be recorded as .

[0153] Based on the maintenance project completion time, average waiting time, utilization variance, and number of spatiotemporal conflicts, the fitness value of an individual is determined using a preset fitness function.

[0154] For example, by substituting the maintenance project completion time, average waiting time, utilization variance, and number of spatiotemporal conflicts determined in the aforementioned example into a preset fitness function, the fitness value of an individual can be determined.

[0155] The fitness function can be expressed as shown in formula (3):

[0156] Formula (3)

[0157] In formula (3), Indicates the completion time of the maintenance project; This indicates the average waiting time; Indicates the variance of utilization rate; Indicates the number of time-space conflicts; This is the weighting coefficient, and its value can be set to 0.4; This is the weighting coefficient, and its value can be set to 0.3; This is the weighting coefficient, and its value can be set to 0.2; This is the weighting coefficient, and its value can be set to 0.1.

[0158] In the example above, by using a pre-defined fitness function and combining it with the maintenance and scheduling information of the power equipment represented by individuals in the population, the fitness value of each individual can be determined. Furthermore, a fitness function that considers multiple optimization objectives can ensure that the final determined maintenance and scheduling information for the power equipment, and the corresponding scheduling scheme, is more reasonable in multiple dimensions. For example, it can achieve faster completion of all maintenance projects for the power equipment, shorter waiting times for maintenance projects, more efficient allocation of testing platforms, and fewer spatiotemporal conflicts.

[0159] In conjunction with the foregoing embodiments, in order to determine the final maintenance and scheduling information for the power equipment, it is necessary to repeatedly iterate through steps 101 and 102 until the preset conditions are met.

[0160] In one example, the preset condition indicates that the number of times the genetic iterative optimization process is performed is greater than or equal to the maximum number of iterations, and / or the fitness value converges.

[0161] For example, since steps 101 and 102 are repeated, genetic iterative optimization is performed on the initial population in step 101. Therefore, the genetic iterative optimization process is repeated multiple times. The number of times the genetic iterative optimization process is performed is counted, and if it is determined that the number is greater than or equal to the maximum number of iterations, it indicates that the preset condition has been met.

[0162] For example, individuals in the initial population and individuals in the offspring population both have fitness values. In step 101, the offspring population is obtained, and the average fitness values ​​of the individuals in the offspring population can be calculated.

[0163] Specifically, the initial population undergoes genetic iterative optimization to obtain the first generation population, and the average fitness value of individuals in the first generation population is calculated. Using the first generation population as the initial population, it undergoes genetic iterative optimization to obtain the second generation population, and the average fitness value of individuals in the second generation population is calculated. This process continues until the difference between the average fitness values ​​of adjacent generation populations is less than a preset threshold, at which point the fitness values ​​are considered to have converged. This indicates that the preset condition has been met.

[0164] It should be noted that the implementation methods of the preset conditions in the above two examples can be implemented individually or in combination.

[0165] In the above example, determining whether the preset conditions have been reached by using the fitness value and / or the number of iterations ensures that a sufficient number of genetic iteration optimization processes are performed to conduct a full global search of the scheduling scheme. It also ensures that during the local search process, the final maintenance scheduling information is closer to the theoretically most reasonable scheduling scheme by judging the convergence of the fitness value.

[0166] The method for determining maintenance scheduling information of power equipment based on genetic algorithms provided in this application introduces genetic algorithms into the process of determining maintenance scheduling information of power equipment. Specifically, multiple individuals are randomly generated in an initial population, where each individual represents a scheduling scheme for a power equipment performing a maintenance project. Based on the genetic algorithm, the initial population is repeatedly subjected to a genetic iterative optimization process until a preset condition is met. The maintenance scheduling information of the power equipment represented by the individual with the highest fitness value when the preset condition is met is taken as the final maintenance scheduling information. This method improves the rationality of the maintenance scheduling information of power equipment and obtains a reasonable scheduling scheme for power equipment to perform maintenance projects.

[0167] Figure 3 A schematic diagram of the device for determining maintenance and scheduling information of power equipment based on genetic algorithms provided in this application is shown below. Figure 3 As shown, the device 30 for determining maintenance scheduling information of power equipment based on genetic algorithms provided in this embodiment includes:

[0168] Processing module 301 is used to repeatedly execute the following steps until a preset condition is met. The individuals in the initial population are randomly generated, each representing maintenance and scheduling information of power equipment in the power grid system, and each individual has a fitness value. The maintenance and scheduling information represents a scheduling scheme for maintenance projects of power equipment, and the fitness value indicates the rationality of the scheduling scheme represented by the maintenance and scheduling information.

[0169] Genetic iterative optimization is performed on the initial population to obtain the offspring population; the individuals in the offspring population represent the maintenance and scheduling information of the newly generated power equipment.

[0170] Use the offspring population as the initial population;

[0171] Among them, the maintenance and scheduling information of the newly generated power equipment represented by the individual with the highest fitness value in the offspring population when the preset conditions are met is the final maintenance and scheduling information of the power equipment.

[0172] In one possible implementation, genetic iterative optimization is performed on the initial population to obtain the offspring population. The processing module 301 is used for:

[0173] A selection operation is performed on the initial population to obtain the first intermediate population; wherein the fitness value of individuals in the first intermediate population is greater than or equal to a preset value;

[0174] The order of maintenance items in the scheduling scheme represented by some individuals in the first intermediate population is changed to obtain the changed individuals;

[0175] The offspring population is constructed based on the changed individuals and the unchanged individuals in the first intermediate population.

[0176] In one possible implementation, the processing module 301 is further configured to:

[0177] Based on the maintenance and scheduling information of the power equipment represented by the individual, the fitness value of the individual is determined according to the preset fitness function.

[0178] In one possible implementation, based on the maintenance and scheduling information of the power equipment represented by the individual, and based on a preset fitness function, the fitness value of the individual is determined, and the processing module 301 is used for:

[0179] Based on the maintenance scheduling information, the maintenance project completion time, average waiting time, utilization variance, and number of spatiotemporal conflicts are determined respectively. Among them, the maintenance project completion time represents the time required for the power equipment to complete all maintenance projects; the average waiting time represents the average time required for the power equipment to transfer between adjacent test platforms; the utilization variance represents the difference in the idle level of different test platforms when the power equipment completes maintenance projects; and the number of spatiotemporal conflicts represents the number of times the power equipment needs to perform the next maintenance project if the previous maintenance project has not been completed.

[0180] Based on the maintenance project completion time, average waiting time, utilization variance, and number of spatiotemporal conflicts, the fitness value of an individual is determined using a preset fitness function.

[0181] In one possible implementation, the preset condition indicates that the number of times the genetic iterative optimization process is performed is greater than or equal to the maximum number of iterations, and / or that the fitness value converges.

[0182] In one possible implementation, the maintenance scheduling information for power equipment includes at least one of the following: maintenance project information for power equipment, test platform information for power equipment, and timing coordination information for power equipment.

[0183] Among them, the maintenance project information represents the maintenance projects that need to be carried out on the power equipment and the order of maintenance projects; the test platform information represents the test platform required for the power equipment to carry out maintenance projects; and the timing coordination information represents the interval time required for the power equipment to be transferred between adjacent test platforms.

[0184] In one possible implementation, the timing coordination information includes: transition time and preparation time;

[0185] When the preparation time is greater than the transfer time, the timing coordination information represents the interval time required for the transfer of power equipment between adjacent test platforms as the preparation time.

[0186] Otherwise, the timing coordination information characterizes the interval time required for the transfer of power equipment between adjacent test platforms as the transfer time.

[0187] The device for determining maintenance and scheduling information of power equipment based on genetic algorithm provided in this embodiment can execute the method provided in the above method embodiment. Its implementation principle and technical effect are similar, and will not be described in detail here.

[0188] Figure 4 A schematic diagram of the structure of the electronic device provided in this application. Figure 4 As shown, the electronic device 40 provided in this embodiment includes at least one processor 401 and a memory 402. Optionally, the device 40 further includes a communication component 403. The processor 401, memory 402, and communication component 403 are connected via a bus 404.

[0189] In a specific implementation, at least one processor 401 executes computer execution instructions stored in memory 402, causing at least one processor 401 to perform the above-described method.

[0190] The specific implementation process of processor 401 can be found in the above method embodiments, and its implementation principle and technical effect are similar. It will not be repeated here.

[0191] In the above embodiments, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly implemented by a hardware processor, or implemented by a combination of hardware and software modules within the processor.

[0192] The memory may include random access memory (RAM) and may also include non-volatile memory (NVM), such as at least one disk storage device.

[0193] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized as address buses, data buses, control buses, etc. For ease of illustration, the buses shown in the accompanying drawings are not limited to a single bus or a single type of bus.

[0194] This application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0195] This application also provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the above-described method.

[0196] The aforementioned readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The readable storage medium can be any available medium accessible to a general-purpose or special-purpose computer.

[0197] An exemplary readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application Specific Integrated Circuit (ASIC). Alternatively, the processor and the readable storage medium can exist as discrete components in the device.

[0198] The division of units is merely a logical functional division; in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces, devices, or units, and may be electrical, mechanical, or other forms.

[0199] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0200] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0201] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0202] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0203] Finally, it should be noted that other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein, and is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for determining maintenance scheduling information for power equipment based on a genetic algorithm, characterized in that, include: Repeat the following steps until the preset conditions are met. The individuals in the initial population are randomly generated. Each individual represents maintenance and scheduling information for power equipment in the power grid system, and each individual has a fitness value. The maintenance and scheduling information represents a scheduling scheme for maintenance projects of the power equipment, and the fitness value indicates the rationality of the scheduling scheme represented by the maintenance and scheduling information. Genetic iterative optimization is performed on the initial population to obtain the offspring population; wherein, the individuals in the offspring population represent the maintenance and scheduling information of the newly generated power equipment; Use the offspring population as the initial population; Among them, the maintenance and scheduling information of the newly generated power equipment represented by the individual with the highest fitness value in the offspring population when the preset conditions are met is the final maintenance and scheduling information of the power equipment.

2. The method according to claim 1, characterized in that, Genetic iterative optimization is performed on the initial population to obtain the offspring population, including: A selection operation is performed on the initial population to obtain a first intermediate population; wherein the fitness value of individuals in the first intermediate population is greater than or equal to a preset value. The order of maintenance items in the scheduling scheme represented by some individuals in the first intermediate population is changed to obtain the changed individuals; Based on the changed individuals and the unchanged individuals in the first intermediate population, a offspring population is constructed.

3. The method according to claim 1, characterized in that, The method further includes: Based on the maintenance and scheduling information of the power equipment represented by the individual, and based on a preset fitness function, the fitness value of the individual is determined.

4. The method according to claim 3, characterized in that, Based on the maintenance and scheduling information of the power equipment represented by the individual, and based on a preset fitness function, the fitness value of the individual is determined, including: Based on the maintenance scheduling information, the maintenance project completion time, average waiting time, utilization variance, and number of spatiotemporal conflicts are determined respectively. Specifically, the maintenance project completion time represents the time required for the power equipment to complete all maintenance projects; the average waiting time represents the average time required for the power equipment to transfer between adjacent test platforms; the utilization variance represents the difference in idle time between different test platforms when the power equipment completes a maintenance project; and the number of spatiotemporal conflicts represents the number of times the power equipment needs to perform a subsequent maintenance project before completing the previous one. The fitness value of an individual is determined based on the completion time of the maintenance project, the average waiting time, the utilization variance, and the number of spatiotemporal conflicts, using a preset fitness function.

5. The method according to claim 1, characterized in that, The preset condition indicates that the number of times the genetic iterative optimization process is performed is greater than or equal to the maximum number of iterations, and / or that the fitness value converges.

6. The method according to any one of claims 1-5, characterized in that, The maintenance and scheduling information of the power equipment includes at least one of the following: maintenance project information of the power equipment, test platform information of the power equipment, and timing coordination information of the power equipment. The maintenance project information represents the maintenance projects required for the power equipment and the order of maintenance projects; the test platform information represents the test platform required for the power equipment to carry out maintenance projects; and the timing coordination information represents the interval time required for the power equipment to be transferred between adjacent test platforms.

7. The method according to claim 6, characterized in that, The timing coordination information includes: transition time and preparation time; When the preparation time is greater than the transfer time, the timing coordination information characterizes the interval time required for the power equipment to be transferred between adjacent test platforms as the preparation time. Otherwise, the timing coordination information represents the interval time required for the transfer of power equipment between adjacent test platforms as the transfer time.

8. A device for determining maintenance scheduling information of power equipment based on a genetic algorithm, characterized in that, include: The processing module is used to repeatedly execute the following steps until a preset condition is met. The individuals in the initial population are randomly generated, each representing maintenance and scheduling information of power equipment in the power grid system. Each individual has a fitness value, and the maintenance and scheduling information represents a scheduling scheme for maintenance projects of the power equipment. The fitness value indicates the rationality of the scheduling scheme represented by the maintenance and scheduling information. Genetic iterative optimization is performed on the initial population to obtain the offspring population; wherein, the individuals in the offspring population represent the maintenance and scheduling information of the newly generated power equipment; Use the offspring population as the initial population; Among them, the maintenance and scheduling information of the newly generated power equipment represented by the individual with the highest fitness value in the offspring population when the preset conditions are met is the final maintenance and scheduling information of the power equipment.

9. An electronic device, characterized in that, include: Memory, processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory, causing the processor to perform the method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method as described in any one of claims 1-7.

11. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method of any one of claims 1-7.

Images