Differentiated operation and maintenance optimization method and system considering risk loss and maintenance cost

By establishing a risk loss assessment model and using genetic algorithms to optimize operation and maintenance strategies, the problem of low decision-making accuracy and efficiency in operation and maintenance management of distribution networks is solved, data consistency and cost reduction are achieved, and the operation reliability of distribution networks is improved. Sexual and economic benefits.

CN119005380APending Publication Date: 2024-11-22GUIZHOU POWER GRID CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410907164.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-08
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

There is a lack of a method to comprehensively consider the impact of fault events in the existing distribution network operation and maintenance management, resulting in low decision-making accuracy and efficiency, and data errors and subjective judgments affect the optimization results.

Method used

Establish a risk loss assessment model, analyze the correlation between failure events and evaluation indicators through Pearson correlation coefficient, quantify the loss cost, and use genetic algorithm to determine differentiated operation and maintenance strategies, optimize the operation and maintenance strategy update cycle, and realize dynamic planning of operation and maintenance strategies and verification.

Benefits of technology

It improves the accuracy and efficiency of operation and maintenance management decision-making, ensures data consistency, reduces risk losses and maintenance costs, and enhances the operating reliability and economic benefits of the distribution network.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119005380A_ABST
    Figure CN119005380A_ABST
Patent Text Reader

Abstract

The invention discloses a differentiated operation and maintenance optimization method and system considering risk loss and maintenance cost, relates to the field of operation and maintenance management of a power distribution network, establishes a risk loss assessment model comprehensively considering the influence of a fault event on assessment indexes and loss cost, quantifies the loss, ensures the accuracy and consistency of data, and improves the reliability of the operation and maintenance management of the power distribution network. According to the risk loss assessment model and the quantitative loss, the fault events are divided according to the high risk level, the middle risk level and the low risk level, the genetic algorithm is used for determining the optimization target of the differentiated operation and maintenance strategy, and the optimal individual serves as the optimal solution of the differentiated operation and maintenance strategy. According to the optimal solution of the differentiated operation and maintenance strategy, the updating time period of the differentiated operation and maintenance strategy is set, the optimized differentiated operation and maintenance strategy is verified and simulated, the effectiveness of the operation and maintenance strategy is kept, and the performance and benefits of a power distribution network system are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of distribution network operation and maintenance management, and specifically to a differentiated operation and maintenance optimization method and system that takes risk loss and maintenance cost into consideration. Background Art

[0002] Operation and maintenance management plays an important role in the distribution network. It implements optimized operation and maintenance management for potential fault events and improves the overall operation level of the distribution network.

[0003] The current differentiated operation and maintenance strategy optimization of distribution networks has high requirements for the accuracy and completeness of real-time data. When there are errors in the data, it will lead to deviations in the optimization results and affect the final decision-making effect. The lack of comprehensive consideration limits the ability to make real-time decisions, and it involves subjective judgment and experience adjustments, leading to different results. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: how to improve the operation and maintenance management efficiency and decision-making accuracy of the distribution network.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a differentiated operation and maintenance optimization method considering risk loss and maintenance cost, which comprises the following steps:

[0007] Establish a risk loss assessment model that comprehensively considers the impact of failure events on assessment indicators and loss costs.

[0008] The losses are quantified according to the risk loss assessment model, and the failure events are classified into different levels.

[0009] The optimization target of the differentiated operation and maintenance strategy is determined according to the level division, and the optimal individual is taken as the optimal solution of the differentiated operation and maintenance strategy.

[0010] Set the update time period of the differentiated operation and maintenance strategy based on the optimal solution, and perform verification and simulation.

[0011] As a preferred solution of the differentiated operation and maintenance optimization method considering risk loss and maintenance cost described in the present invention, wherein: the establishment of a risk loss assessment model that comprehensively considers the impact of fault events on assessment indicators and loss costs includes determining assessment indicators that are related to risks and directly or indirectly quantify losses based on the characteristics and operation and maintenance objectives of the distribution network, connecting to the distribution network management API interface to collect distribution network fault data, checking whether there are errors and inconsistent information in the distribution network fault data, and preparing preliminary data items for filling and replacement, randomly selecting K center points in the distribution network fault data, and assigning each data sample therein to the category where the center point closest to it is located, re-acquiring the center point based on the assigned sample data, repeating the iterative assignment and re-acquisition steps until the center point no longer changes, and selecting the characteristic value related to the fault event and the evaluation indicator through the Pearson correlation coefficient.

[0012] The evaluation indicators include production capacity loss, power outage time, power supply reliability and safety accident probability.

[0013] As a preferred solution of the differentiated operation and maintenance optimization method considering risk loss and maintenance cost described in the present invention, wherein: the characteristic value related to the fault event and the evaluation index is selected by the Pearson correlation coefficient, and the expression is:

[0014]

[0015] Where r represents the Pearson coefficient, cov(x,y) represents the covariance between the fault event variable x and the evaluation index variable y, and Sd(x) and Sd(y) represent the standard deviation values ​​of the fault event variable x and the evaluation index variable y.

[0016] As a preferred solution of the differentiated operation and maintenance optimization method considering risk loss and maintenance cost described in the present invention, the quantified loss is aimed at production capacity loss, and the fault events are recorded, including marking the fault event type, the specific location of the fault event, the frequency of the fault event, and the duration of the fault event. The loss cost is determined according to the production capacity of the distribution network, the frequency of the fault event, and the duration of the fault event. The expression is:

[0017] A=Π[Capacity*Frequency*(t0-t1)]*r

[0018] Among them, A represents the loss cost, Capacity represents the production capacity of the distribution network, Frequency represents the frequency of fault occurrence, t0 and t1 represent the start time point and end time point of the fault respectively, and r represents the Pearson correlation coefficient between the fault and the evaluation index.

[0019] As a preferred solution of the differentiated operation and maintenance optimization method considering risk loss and maintenance cost described in the present invention, the level division is to classify the output value determined by the loss cost into high, medium and low risk fault events.

[0020] When a high-risk fault event occurs, increase the frequency of distribution network inspections, pay attention to potential high-risk fault types, fault frequency, fault duration and specific fault locations, establish a rapid response mechanism, and select backup equipment for replacement based on the loss cost.

[0021] When a medium-risk fault event occurs, the distribution network system will be periodically maintained and inspected based on the risk level and loss cost of the fault event, and a monitoring and alarm mechanism will be established.

[0022] When a low-risk failure event occurs, a preventive maintenance mechanism is established to conduct periodic inspections and maintenance of the distribution network system, and a monitoring and analysis mechanism is established.

[0023] As a preferred solution of the differentiated operation and maintenance optimization method considering risk loss and maintenance cost described in the present invention, wherein: the optimization target of the differentiated operation and maintenance strategy is determined by using a genetic algorithm to reduce the loss cost and the maintenance cost, the differentiated operation and maintenance strategy is represented as an individual, and the individual encoding method is defined as real number encoding, a set of initial differentiated operation and maintenance strategies are randomly generated, and a greedy algorithm is designed to generate an initial population in combination with random generation, and the initial population is selected as the current solution. The greedy strategy is used to select the best decision to improve the fitness function value in each step based on the currently generated individuals, and new individuals are iteratively generated and added back to the initial population. The expression is:

[0024] Z=f(a,b)

[0025] Among them, Z represents the final optimal solution individual of the greedy algorithm, a is the generated individual, b represents the optimal substructure, and f() represents the greedy best decision.

[0026] Select some individuals as the second initial population, select the population size, calculate the fitness value of each individual using the mean square error according to the optimization goal, select individuals based on the proportion of individual fitness values, calculate the sum of fitness values, and calculate the selection probability of each individual. The expression is:

[0027]

[0028] Among them, F represents the fitness value of a single individual, N represents the number of samples, and y pi Represents the result of individual prediction, y ti represents the corresponding true value, n represents the number of fitness values, S represents the total fitness value, F irepresents the fitness value of the ith individual, and C represents the selection probability of each individual.

[0029] The selection probability of each individual generates a random number between 0 and 1. According to the order of the cumulative sum of the selection probabilities, the first individual that makes the cumulative sum greater than the random number is selected as the parent. The random number and parent selection operations are repeated to select other parent individuals, and the crossover point is randomly selected using single-point crossover.

[0030] The crossover point is a position point on the gene chromosome. Two parent individuals are cut at the crossover point, and the genes at the corresponding positions are exchanged to generate two new offspring individuals. Multiple crossover points are randomly selected using multi-point crossover, and multiple parent individuals are cut at the crossover points, and the genes at the corresponding positions are exchanged to generate new offspring individuals.

[0031] The uniform crossover method is used to determine the crossover operation based on the probability selection of each gene locus, and the gene loci of the parent individuals selected for crossover are exchanged to generate new offspring individuals. New differentiated operation and maintenance strategies are generated through a variety of crossover methods.

[0032] When the number of iterations reaches the threshold setting, the optimal individual that meets the termination condition is taken as the optimal solution of the differentiated operation and maintenance strategy.

[0033] As a preferred scheme of the differentiated operation and maintenance optimization method considering risk loss and maintenance cost described in the present invention, wherein: the update time period includes setting the update time period of the differentiated operation and maintenance strategy according to the optimal solution of the operation and maintenance strategy, and regularly collecting real-time operation data of the distribution network, the impact of fault events on evaluation indicators and the operation and maintenance strategy of risk fault events, and through dynamic planning to minimize the overall risk loss and maintenance cost, the optimized differentiated operation and maintenance strategy is verified and simulated.

[0034] Another object of the present invention is to provide a differentiated operation and maintenance optimization method system that takes into account risk losses and maintenance costs. It can reduce risk losses and maintenance costs by optimizing operation and maintenance strategies, thereby improving the operating efficiency and reliability of the distribution network, and solving the problem in the prior art that it is difficult to comprehensively consider the impact of fault events, quantify losses and formulate optimized operation and maintenance strategies.

[0035] To solve the above technical problems, the present invention provides the following technical solutions: a differentiated operation and maintenance optimization method system considering risk loss and maintenance cost, comprising: a risk loss assessment module, a loss cost quantification module, an operation and maintenance strategy optimization module, and a strategy verification and update module.

[0036] The risk loss assessment module comprehensively considers the impact of failure events on assessment indicators and loss costs, establishes an assessment model, and quantifies the risk loss of the task.

[0037] The loss cost quantification module records and classifies fault events and quantifies specific loss costs.

[0038] The operation and maintenance strategy optimization module generates an initial operation and maintenance strategy population, calculates individual fitness values, generates new differentiated operation and maintenance strategies using a greedy algorithm and multiple crossover methods, and finally determines the optimal individual that meets the termination conditions.

[0039] The strategy verification and update module sets the update time period of the operation and maintenance strategy according to the optimal solution, collects real-time operation data of the distribution network, and verifies and simulates the optimized differentiated operation and maintenance strategy through dynamic programming.

[0040] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of the differentiated operation and maintenance optimization method considering risk loss and maintenance cost as described above are implemented.

[0041] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the differentiated operation and maintenance optimization method considering risk loss and maintenance cost as described above.

[0042] The beneficial effects of the present invention are as follows: by comprehensively considering the assessment indicators related to the risk, a comprehensive risk assessment result is provided, and the accuracy and consistency of the data are ensured; correlation analysis is used to help understand the degree of association between the fault event and the assessment indicator, and to provide a basis for the subsequent loss cost calculation; by obtaining the loss cost, distribution network managers are helped to better understand the impact of the fault event on the economic benefits; by using the risk loss assessment model, the fault event is quantitatively analyzed and divided into high, medium and low risk levels, which helps the distribution network managers to better understand the risk levels of different fault events and to adopt corresponding operation and maintenance strategies in a targeted manner; genetic algorithms are used to help the system allocate resources more effectively during the operation and maintenance process, reduce costs, and improve the reliability and economic benefits of the system; the update cycle is set according to the optimal solution of the differentiated operation and maintenance strategy, which helps the system to adapt to new situations and changes in a timely manner, maintain the effectiveness of the operation and maintenance strategy, and improve the performance and benefits of the distribution network system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0044] Figure 1An overall flow chart of a differentiated operation and maintenance optimization method considering risk loss and maintenance cost provided in the first embodiment of the present invention;

[0045] Figure 2 This is a structural diagram of a differentiated operation and maintenance optimization system that takes into account risk loss and maintenance costs, provided in the second embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0047] Example 1

[0048] Reference Figure 1 As an embodiment of the present invention, a differentiated operation and maintenance optimization method considering risk loss and maintenance cost is provided, including:

[0049] S1. Based on the characteristics and operation and maintenance objectives of the distribution network, determine the assessment indicators that are related to the risks and directly or indirectly quantify the losses, including production capacity loss, power outage time, power supply reliability, and the probability of safety accidents.

[0050] S2. Connect to the distribution network management API interface to collect distribution network fault data, including fault event type, fault event frequency, fault event duration and specific fault location, check whether there are errors and inconsistent information in the distribution network fault data, and prepare preliminary data items for filling and replacement. Randomly select K center points in the distribution network fault data, and assign each data sample to the category of the center point closest to it. Re-acquire the center point based on the assigned sample data, and repeat the iterative assignment and re-acquisition steps until the center point no longer changes.

[0051] S3. Select the characteristic value related to the fault event and the evaluation index through the Pearson correlation coefficient. The specific formula of the Pearson correlation coefficient is:

[0052]

[0053] Where r represents the Pearson coefficient, cov(x,y) represents the covariance between the fault event variable x and the evaluation index variable y, Sd(x) and Sd(y) represent the standard deviation of the fault event variable x and the evaluation index variable y, and the Pearson correlation coefficient ranges from -1 to 1. The closer its absolute value is to 1, the stronger the correlation is, and the closer it is to 0, the weaker the correlation is. The strength of the correlation is used to determine the impact of the fault event on the evaluation index.

[0054] It should be further explained that the Pearson correlation coefficient is used to select the characteristic values ​​related to the fault event and the evaluation index, so as to accurately identify the correlation between the fault event and the evaluation index. The Pearson correlation coefficient can be used to quantitatively measure the impact of the fault event on the evaluation index. In this way, key fault events with a greater impact on the evaluation index can be screened out, thereby providing strong data support for subsequent operation and maintenance decisions.

[0055] Identify highly correlated fault events to avoid wasting resources by focusing on irrelevant or weakly correlated faults, thereby improving the efficiency of fault management. Based on the strength of the correlation, prioritize highly correlated fault events, which helps optimize the allocation of human and material resources and reduce unnecessary inspection and maintenance costs. Through data-driven analysis methods, provide a reliable basis to assist managers in making more scientific and reasonable operation and maintenance decisions, and enhance the overall reliability and stability of the system.

[0056] In this way, the system can perform fault management and resource allocation more specifically, avoiding loss of production capacity or safety accidents caused by ignoring important fault events, and ultimately improving the accuracy and reliability of system operation and maintenance.

[0057] S4. For production capacity loss, record the fault events, including marking the fault event type, specific location of the fault event, fault event frequency, and fault event duration, and fix the loss cost according to the distribution network production capacity, fault event frequency, and fault event duration. The specific fixed formula is:

[0058] A=Π[Capacity*Frequency*(t0-t1)]*r

[0059] Among them, A represents the loss cost, Capacity represents the production capacity of the distribution network, Frequency represents the frequency of fault occurrence, t0 and t1 represent the start time point and end time point of the fault respectively, and r represents the Pearson correlation coefficient between the fault and the evaluation index.

[0060] It should be further explained that the present invention achieves accurate quantification of production capacity loss through this step. Recording detailed information of the fault event and calculating the loss cost can provide managers with a clear economic loss assessment. This quantification method enables managers to better understand the actual impact of the fault event on the production of the distribution network, thereby formulating a more effective operation and maintenance strategy.

[0061] Specifically, this step helps managers identify which failure events have the greatest impact on production capacity, prioritize high-frequency, high-loss failure events, optimize resource allocation, improve failure handling efficiency, and reduce overall operation and maintenance costs.

[0062] S102. Classify the failure events into high, medium and low risk levels according to the risk loss assessment model and quantified losses;

[0063] Furthermore, based on the risk loss assessment model and quantified losses, failure events are divided into high, medium and low risk levels.

[0064] Furthermore, the operation and maintenance strategy for high-risk fault events is to increase the inspection frequency of the distribution network, and focus on the potential high-risk fault types, fault frequency, fault duration and specific location of the fault; select backup equipment based on the loss cost for rapid replacement in the event of a fault; and establish a rapid response mechanism to adjust the operation of the distribution network system and dispatch personnel to respond to high-risk fault events.

[0065] Furthermore, the operation and maintenance strategy for medium-risk fault events is: based on the risk level and loss cost of the fault event, the distribution network system is maintained and inspected regularly every fifteen days, and a monitoring and alarm mechanism is established to detect and respond to medium-risk fault events.

[0066] Furthermore, the operation and maintenance strategy for low-risk fault events is to establish a preventive maintenance mechanism, regularly inspect and maintain the distribution network system every thirty days, and establish a monitoring and analysis mechanism for reasonable decision-making on low-risk fault events.

[0067] S103. Determine the optimization target of the differentiated operation and maintenance strategy by using a genetic algorithm, and use the optimal individual as the optimal solution of the differentiated operation and maintenance strategy;

[0068] Furthermore, the optimization goal of the differentiated operation and maintenance strategy is determined by using a genetic algorithm to reduce loss costs and maintenance costs. The differentiated operation and maintenance strategy is represented as an individual, and the individual encoding method is defined as real number encoding. A set of initial differentiated operation and maintenance strategies is randomly generated. The greedy algorithm is combined with random generation to generate an initial population. The greedy algorithm defines a fitness function, selects the initial population as the current solution, and uses a greedy strategy based on the currently generated individuals to select the best decision to improve the fitness function value in each step. New individuals are iteratively generated and added back to the initial population. The specific formula is:

[0069] Z=f(a,b)

[0070] Among them, Z represents the final optimal solution individual of the greedy algorithm, a represents the generated individual, b represents the optimal substructure, f() represents the greedy best decision, selects some individuals as the second initial population, selects the population size, and calculates the fitness value of each individual based on the optimization goal using the mean square error. The individual is selected based on the proportion of the individual fitness values, and the sum of the fitness values ​​is calculated. The selection probability of each individual is calculated. The specific calculation formula is:

[0071]

[0072] Among them, F represents the fitness value of a single individual, N represents the number of samples, and y pi Represents the result of individual prediction, y ti represents the corresponding true value, n represents the number of fitness values, S represents the total fitness value, F i Represents the fitness value of the i-th individual, C represents the selection probability of each individual, generates a random number between 0 and 1, selects the first individual whose cumulative sum is greater than the random number as the parent in the order of the cumulative sum of the selection probabilities, repeats the iterative random number and parent selection operation to select other parent individuals, randomly selects the intersection point using single-point crossover, the intersection point is the position point on the gene chromosome, cuts the two parent individuals at the intersection point, exchanges the genes at the corresponding positions, generates two new offspring individuals, and randomly selects multiple intersection points using multi-point crossover, cuts multiple parent individuals at the intersection point, exchanges the genes at the corresponding positions, generates new offspring individuals, and uses uniform crossover for each gene site, probabilistically selects the crossover operation, selects the crossover to execute the gene exchange of the parent individual at the gene site, generates new offspring individuals, generates new differentiated operation and maintenance strategies through multiple crossover methods, defines the termination condition to be met as reaching the maximum number of iterations of 20 times, and returns the optimal individual that meets the termination condition as the optimal solution of the differentiated operation and maintenance strategy.

[0073] It should be further explained that the present invention can determine a batch of fault events according to the risk level through step S102, and the batch of fault events is named as population A. Three specific differentiated operation and maintenance strategies are determined according to the risk level of population A. The present invention can randomly determine a batch of fault events through step S103, and the batch of fault events is named as population B, which is the initial population described in step S103. Each differentiated operation and maintenance strategy of population B is represented as an individual. Combined with the three specific differentiated operation and maintenance strategies determined by population A, the fitness of each individual is determined and population B is selected. The fitness of three specific differentiated operation and maintenance strategies for population A in the population, and the selection ratio of the three specific differentiated operation and maintenance strategies in the new individuals according to the fitness value, for example, a strategy in population B is closest to the differentiated operation and maintenance strategy for high-risk fault events in population A, and the random number generated according to the individual fitness of the differentiated operation and maintenance strategy for medium-risk fault events in population A is 0.3, then the differentiated operation and maintenance strategy for high-risk fault events of population A accounts for 70% of the differentiated operation and maintenance strategy for medium-risk fault events in population B. The differentiated operation and maintenance strategy field is exchanged according to the uniform crossover of the genetic algorithm, that is, the gene exchange in S103, to generate the optimal individual for the strategy of population B, that is, to generate the optimal solution for the strategy of population B.

[0074] S104. Setting the update time period of the differentiated operation and maintenance strategy according to the optimal solution of the differentiated operation and maintenance strategy, and verifying and simulating the optimized differentiated operation and maintenance strategy;

[0075] Furthermore, the update time period of the differentiated operation and maintenance strategy is set according to the optimal solution of the differentiated operation and maintenance strategy, and the real-time operation data of the distribution network, the impact of fault events on the evaluation indicators, and the operation and maintenance strategy of risk fault events are regularly collected to define the effect of the current operation and maintenance strategy and identify new risks and resource situations. The optimized differentiated operation and maintenance strategy is verified and simulated through dynamic planning to minimize the overall risk loss and maintenance cost, and it is judged whether to implement the updated differentiated operation and maintenance strategy based on the results of verification and simulation. When the strategy optimization result is good, the new strategy is applied to the operation and maintenance practice of the distribution network.

[0076] It should be further explained that by using genetic algorithms to determine the optimization objectives of differentiated operation and maintenance strategies, and taking the optimal individual as the optimal solution of differentiated operation and maintenance strategies, the loss cost and maintenance cost can be effectively reduced. Specifically, the genetic algorithm generates the initial population through multiple iterations and fitness evaluations, combined with the greedy algorithm, and gradually optimizes the operation and maintenance strategy through selection, crossover and mutation operations, thereby achieving optimal resource allocation, reducing costs, and improving system reliability and economic benefits.

[0077] Secondly, the update time period of the differentiated operation and maintenance strategy is set according to the optimal solution, and the real-time operation data of the distribution network and the impact of fault events are regularly collected to conduct dynamic planning and verification simulation to ensure the timeliness and optimality of the strategy. Through this design, the system can respond to changes in the distribution network in a timely manner, dynamically adjust the operation and maintenance strategy, effectively control the risk of failure, reduce economic losses, and improve the efficiency of operation and maintenance. At the same time, through continuous verification and simulation, it is ensured that the operation and maintenance strategy is always in the optimal state, further improving the overall performance and economic benefits of the distribution network.

[0078] This method provides comprehensive risk assessment results by comprehensively considering risk-related assessment indicators and ensures the accuracy and consistency of data, helping distribution network managers to better understand the impact of fault events on economic benefits and adopt corresponding operation and maintenance strategies in a targeted manner, thereby achieving the beneficial effects of reducing costs, improving system reliability and economic benefits.

[0079] Example 2

[0080] Reference Figure 2 , which is an embodiment of the present invention, provides a system for a differentiated operation and maintenance optimization method considering risk loss and maintenance cost, including: a risk loss assessment module, a loss cost quantification module, an operation and maintenance strategy optimization module, and a strategy verification and update module.

[0081] The risk loss assessment module comprehensively considers the impact of failure events on assessment indicators and loss costs, establishes an assessment model, and quantifies the risk losses of tasks.

[0082] The loss cost quantification module records and classifies failure events and quantifies the specific loss costs.

[0083] The operation and maintenance strategy optimization module generates the initial operation and maintenance strategy population, calculates the individual fitness value, uses the greedy algorithm and multiple crossover methods to generate new differentiated operation and maintenance strategies, and finally determines the optimal individual that meets the termination conditions.

[0084] The strategy verification and update module sets the update time period of the operation and maintenance strategy according to the optimal solution, collects real-time operation data of the distribution network, and verifies and simulates the optimized differentiated operation and maintenance strategy through dynamic planning.

[0085] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program code.

[0086] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0087] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0088] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0089] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A differentiated operation and maintenance optimization method considering risk loss and maintenance cost, characterized by: include: Establish a risk loss assessment model that comprehensively considers the impact of failure events on assessment indicators and loss costs; Quantify losses based on risk loss assessment models and classify failure events into different levels; Determine the optimization target of the differentiated operation and maintenance strategy based on the level classification, and take the optimal individual as the optimal solution of the differentiated operation and maintenance strategy; Set the update time period of the differentiated operation and maintenance strategy based on the optimal solution, and perform verification and simulation.

2. The differentiated operation and maintenance optimization method considering risk loss and maintenance cost as claimed in claim 1, characterized in that: The establishment of a risk loss assessment model that comprehensively considers the impact of fault events on assessment indicators and loss costs includes determining assessment indicators that are related to risks and directly or indirectly quantify losses based on the characteristics and operation and maintenance objectives of the distribution network, connecting to the distribution network management API interface to collect distribution network fault data, checking whether there are errors and inconsistent information in the distribution network fault data, and preparing preliminary data items for filling and replacement, randomly selecting K center points in the distribution network fault data, and assigning each data sample therein to the category where the center point closest to it is located, re-acquiring the center point based on the assigned sample data, repeating the iterative assignment and re-acquisition steps until the center point no longer changes, and selecting the characteristic value related to the fault event and the evaluation indicator through the Pearson correlation coefficient; The evaluation indicators include production capacity loss, power outage time, power supply reliability and safety accident probability.

3. The differentiated operation and maintenance optimization method considering risk loss and maintenance cost as claimed in claim 2 is characterized by: The Pearson correlation coefficient is used to select the characteristic value related to the fault event and the evaluation index, and the expression is: Where r represents the Pearson coefficient, cov(x,y) represents the covariance between the fault event variable x and the evaluation index variable y, and Sd(x) and Sd(y) represent the standard deviation values ​​of the fault event variable x and the evaluation index variable y.

4. The differentiated operation and maintenance optimization method considering risk loss and maintenance cost as claimed in claim 3 is characterized by: The quantitative loss is aimed at the loss of production capacity, and the fault events are recorded, including the type of fault event, the specific location of the fault event, the frequency of the fault event, and the duration of the fault event. The loss cost is determined according to the production capacity of the distribution network, the frequency of the fault event, and the duration of the fault event. The expression is: A=Π[Capacity*Frequency*(t0-t1)]*r Among them, A represents the loss cost, Capacity represents the production capacity of the distribution network, Frequency represents the frequency of fault occurrence, t0 and t1 represent the start time point and end time point of the fault respectively, and r represents the Pearson correlation coefficient between the fault and the evaluation index.

5. The differentiated operation and maintenance optimization method considering risk loss and maintenance cost as claimed in claim 4 is characterized by: The grading is to classify the output values ​​determined by the loss cost into high, medium and low risk failure events; When a high-risk fault event occurs, increase the inspection frequency of the distribution network, pay attention to the potential high-risk fault type, fault frequency, fault duration and specific location of the fault, establish a rapid response mechanism, and select backup equipment for replacement based on the loss cost; When a medium-risk fault event occurs, the distribution network system will be periodically maintained and inspected according to the risk level and loss cost of the fault event, and a monitoring and alarm mechanism will be established; When a low-risk failure event occurs, a preventive maintenance mechanism is established to conduct periodic inspections and maintenance of the distribution network system, and a monitoring and analysis mechanism is established.

6. The differentiated operation and maintenance optimization method considering risk loss and maintenance cost as claimed in claim 5 is characterized by: The method of determining the optimization target of the differentiated operation and maintenance strategy includes using a genetic algorithm to determine that the optimization target of the differentiated operation and maintenance strategy is to reduce loss costs and maintenance costs, representing the differentiated operation and maintenance strategy as an individual, defining the individual encoding method as real number encoding, randomly generating a set of initial differentiated operation and maintenance strategies, combining the random generation with a greedy algorithm to generate an initial population, selecting the initial population as the current solution, using a greedy strategy based on the currently generated individuals, selecting the best decision to improve the fitness function value in each step, iteratively generating new individuals and adding them back to the initial population, and the expression is: Z=f(a,b) Among them, Z represents the final optimal solution individual of the greedy algorithm, a is the generated individual, b represents the optimal substructure, and f() represents the greedy best decision; Select some individuals as the second initial population, select the population size, calculate the fitness value of each individual using the mean square error according to the optimization goal, select individuals based on the proportion of individual fitness values, calculate the sum of fitness values, and calculate the selection probability of each individual. The expression is: Among them, F represents the fitness value of a single individual, N represents the number of samples, and y pi Represents the result of individual prediction, y ti represents the corresponding true value, n represents the number of fitness values, S represents the total fitness value, F i represents the fitness value of the i-th individual, and C represents the selection probability of each individual; The selection probability of each individual generates a random number between 0 and 1. According to the order of the cumulative sum of the selection probabilities, the first individual whose cumulative sum is greater than the random number is selected as the parent. The random number and parent selection operations are repeated to select other parent individuals. The crossover point is randomly selected using single-point crossover. The crossover point is a position point on the gene chromosome, and two parent individuals are cut at the crossover point, and the genes at the corresponding positions are exchanged to generate two new offspring individuals. Multiple crossover points are randomly selected by multi-point crossover, and multiple parent individuals are cut at the crossover points, and the genes at the corresponding positions are exchanged to generate new offspring individuals. The uniform crossover method is used to select the probability of each gene locus to judge the crossover operation, and the gene loci of the parent individuals selected for crossover are exchanged to generate new offspring individuals. New differentiated operation and maintenance strategies are generated through multiple crossover methods. When the number of iterations reaches the threshold setting, the optimal individual that meets the termination condition is taken as the optimal solution of the differentiated operation and maintenance strategy.

7. The differentiated operation and maintenance optimization method considering risk loss and maintenance cost according to claim 6 is characterized by: The update time period includes setting the update time period of the differentiated operation and maintenance strategy according to the optimal solution of the operation and maintenance strategy, and regularly collecting the real-time operation data of the distribution network, the impact of fault events on the evaluation indicators and the operation and maintenance strategy of risk fault events, and verifying and simulating the optimized differentiated operation and maintenance strategy through dynamic planning to minimize the overall risk loss and maintenance cost.

8. A system adopting the differentiated operation and maintenance optimization method considering risk loss and maintenance cost as described in any one of claims 1 to 7 is characterized by: It includes risk loss assessment module, loss cost quantification module, operation and maintenance strategy optimization module, and strategy verification and update module; The risk loss assessment module comprehensively considers the impact of failure events on assessment indicators and loss costs, establishes an assessment model, and quantifies the risk loss of tasks; The loss cost quantification module records and classifies fault events and quantifies specific loss costs; The operation and maintenance strategy optimization module generates an initial operation and maintenance strategy population, calculates individual fitness values, generates new differentiated operation and maintenance strategies using a greedy algorithm and multiple crossover methods, and finally determines the optimal individual that meets the termination conditions; The strategy verification and update module sets the update time period of the operation and maintenance strategy according to the optimal solution, collects real-time operation data of the distribution network, and verifies and simulates the optimized differentiated operation and maintenance strategy through dynamic programming.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the differentiated operation and maintenance optimization method considering risk loss and maintenance cost described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the differentiated operation and maintenance optimization method considering risk loss and maintenance cost as described in any one of claims 1 to 7 are implemented.