CN-115330201-B - Power grid digital project pareto optimization method and system

CN115330201BCN 115330201 BCN115330201 BCN 115330201BCN-115330201-B

Abstract

The invention relates to a pareto optimal selection method and system for a power grid digital project, wherein the method comprises the steps of establishing an evaluation index system of the power grid digital project and an inter-project shared network according to power grid digital project quantitative evaluation related information, technical characteristics of the power grid digital project and development strategy information of a power grid company, establishing a digital project group multi-objective optimization model according to the evaluation index system and the inter-project shared network, solving to obtain a pareto optimal solution set, carrying out association rule mining according to the pareto optimal solution set, carrying out association rule sorting according to the association rule sorting by taking support degree, confidence degree and lifting degree as indexes, screening the non-dominant solution set obtained in advance according to the association rule sorting, and removing worst solution each time until an optimal digital project combination solution is left finally, so as to finish the optimization of the digital project. The method solves the problem of project combination optimization considering project interaction.

Inventors

LI JINCHAO
Lan xinyi
ZHU YE
YU JIE
LU SHIQIANG
CHEN ZHIYI
GENG XINZHOU
PAN JIANHONG
Dong Aidi
FAN JIASHU
ZHAO BO
LV CHANGHUI

Assignees

华北电力大学
华北电力大学
国家电网有限公司
国家电网有限公司
国网经济技术研究院有限公司
国网经济技术研究院有限公司
国网吉林省电力有限公司
国网吉林省电力有限公司
国网吉林省电力有限公司经济技术研究院
国网吉林省电力有限公司经济技术研究院

Dates

Publication Date: 20260421
Application Date: 20220815
Priority Date: 20220815

Claims (7)

1. A power grid digital project pareto optimization method, which is characterized by comprising the following steps: Establishing an evaluation index system of the power grid digital project and an inter-project sharing network according to the related information of the quantitative evaluation of the power grid digital project, the technical characteristics of the power grid digital project and the development strategic information of a power grid company, establishing the inter-project sharing network, wherein the method comprises the steps of processing two projects of the project sharing network through mapping to determine whether the two projects have a sharing relation, setting the number of simultaneously used technologies as the weight of the cooperative utilization advantage among the projects, and constructing the project sharing network Wherein Representing items A technique required simultaneously with the item y, Representing the number of technologies used for all projects; establishing a digital project group multi-objective optimization model according to the evaluation index system and the inter-project shared network, and solving to obtain a pareto optimal solution set; Mining association rules according to the pareto optimal solution set, and ordering the association rules by taking the support degree, the confidence degree and the lifting degree as indexes, wherein the ordering of the association rules adopts a TOPSIS method, and comprises the steps of normalizing a standard matrix formed by the support degree, the confidence degree and the lifting degree to obtain a decision matrix, and calculating a positive ideal solution according to the decision matrix And negative ideal solution According to the ideal solution And negative ideal solution Computing frequent sets The relative distance between each standard point and the negative ideal solution is obtained from the distance between the standard point and the ideal point , Describes the importance of relatively frequent items based on relative distance Obtaining the most frequent association rule; screening the non-dominant solution set obtained in advance according to the ordering of the association rule, removing the worst solution from each screening until an optimal digital item combination solution is left at last, and completing the optimization of the digital item, wherein the method comprises the following steps: Analysis No. 1 Association rules, in which the association rules are related to a set Storing the project group scheme with the association rule; Screening non-dominant project group scheme sets From the slave Delete not included in the set sum And updates the empty set ; Inspection slave Screening remaining project group scheme sets If (3) Only one project group scheme is left, and the project group scheme is stopped and output Otherwise, let The screening was repeated.
2. The method for optimizing pareto of digital projects of a power grid according to claim 1, wherein the establishing a multi-objective optimization model of the digital project group, solving to obtain an optimal pareto solution set, comprises: Project group scheme A chromosome for each individual that is a population, thereby generating an initial population; Establishing and calculating a fitness model and a penalty function, and determining Pareto grades in a solution set; non-dominant sorting is carried out on the initial population, and Pareto grades are all divided; after non-dominant sorting of the initial population is completed, crossover, mutation and selection operation of a genetic algorithm are carried out, and new individuals are generated and added into the population; From all populations Selection among individuals The individuals form a group, according to the fitness of each individual, the individual with the best fitness value is selected to enter the offspring population, and the process is repeated until the number of the individuals in the offspring population reaches , Is the population scale; Calculating the crowding degree of all individuals, so that the obtained solution is more uniform in a target space; And synthesizing the parent population and the offspring population into a new population according to the Pareto grade and the crowding degree, generating the new parent population from the new population according to a preset rule, and repeating until the preset termination condition is met.
3. The method for pareto preference for a digitized item of a power grid of claim 2 wherein said non-dominant ranking of the initial population, and said overall ranking of the population, comprises: Calculating each individual Is governed by the number of And a set of solutions governed by the individual Traversing the whole population, wherein the population scale is as follows The calculation complexity of the parameter is ; Parameters in the population Placing individuals into a first population set In, delete set and After the individuals in (a) are newly calculated, the number of the individuals to be subjected to the control is calculated Then will Is put into a second group and Repeating until the population level is divided completely.
4. The grid digitizing project pareto preferred method of claim 2, wherein the predetermined rules include: placing the whole population into the parent population according to the order of Pareto grades from low to high Until a certain layer of individuals can not be fully placed into the parent population ; Arranging individuals of the layer from large to small according to crowding degree, and sequentially putting into parent population Until the parent population Filling.
5. A grid digitization project pareto preference system for implementing a grid digitization project pareto preference method according to any one of claims 1 to 4, comprising: The first processing module is used for establishing an evaluation index system of the power grid digital project and an inter-project sharing network according to the related information of the quantitative evaluation of the power grid digital project, the technical characteristics of the power grid digital project and the development strategy information of a power grid company; The second processing module establishes a digital project group multi-objective optimization model according to the evaluation index system and the inter-project shared network, and solves to obtain a pareto optimal solution set; the third processing module is used for mining association rules according to the pareto optimal solution set, and ordering the association rules by taking the support degree, the confidence degree and the lifting degree as indexes; And the screening module screens the non-dominant solution set obtained in advance according to the ordering of the association rule, and the worst solution is removed by each screening until an optimal digital item combination solution is left finally, so that the digital item is optimized.
6. A computer readable storage medium storing one or more programs, wherein the one or more programs comprise instructions, which when executed by a computing device, cause the computing device to perform any of the methods of claims 1-4.
7. A computing device comprising one or more processors, memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing any of the methods of claims 1-4.

Description

Power grid digital project pareto optimization method and system Technical Field The invention relates to the field of optimization of power grid digital projects, in particular to a pareto optimization method and system for the power grid digital projects. Background The realization of enterprise digitization is a progressive process, the digitization items are specific actions for realizing enterprise digitization, and proper digitization items are selected from a plurality of digitization items with different investment limits, different effects and complicated relations in a limited time, so that the key of ensuring that enterprises rapidly and effectively improve the digitization degree and converting the investment into enterprise value and enterprise benefit is provided. The different digitized items have different roles, so that the indexes for evaluating the items are different, and the benefit indexes of almost all the items comprise a plurality of different indexes. Therefore, simply giving the items a ranking according to a certain overall evaluation value is not perfect, and it is necessary to optimize the digitized items from a plurality of dimensions and under a plurality of evaluation targets. Item combination selection has gained increasing interest and attention in the field of public administration, including industry companies, businesses, and military. The emphasis is on selecting project recommendations under limited resources to maximize the benefits of stakeholders using a variety of evaluation criteria. However, practitioners face two major challenges in selecting the best solution for the project portfolio. First, the wide interaction between items affects the actual value and risk of the item portfolio. Secondly, project portfolio optimization always has multiple objectives, and commonly used multi-objective optimization methods can effectively solve non-dominant solutions, but they raise a new problem of how to further select the best project portfolio from these solutions. Therefore, the project combination optimization fine selection method based on project interaction has important research significance. Research and development of groups of items in the existing literature can be summarized by 1) dividing the items into tasks with a great deal of attention on how to effectively implement the items, 2) evaluating the value of the items to determine a funding policy aimed at maximizing the overall utility of the items, and 3) analyzing how the synergistic effect of the items affects the value and expected performance of the items. In the subject, the focus of project portfolio selection is project planning rather than project engineering. From literature, project combination optimization is more attractive to researchers than project interaction. This can be divided into single-objective optimization and multi-objective optimization. The latter is more widely studied in the literature. Some studies categorize multi-objective optimizations and multi-criteria decisions as they directly transform multi-objectives into single objectives through weighted operations. Widely used algorithms for solving multi-objective problems include non-dominant ordered genetic algorithm (NSGA), non-dominant ordered and local search, intensity pareto evolutionary algorithm (SPEA), niche pareto genetic algorithm, decomposition-based multi-objective evolutionary algorithm, and the like. These algorithms have been successfully applied in different fields. However, since the decision maker always expects only one solution, a common problem with these algorithms is to strive to find the best pareto solution set, not the best solution. Therefore, how to further refine the pareto set to find the optimal solution is a technical problem that needs to be solved at present. Disclosure of Invention Aiming at the problems, the invention aims to provide the optimization method and the optimization system for the Internet digital project pareto, which overcome the subjective experience of the prior art, solve the project combination optimization problem considering project interaction and can be directly applied to enterprise practice. The method comprises the following steps of establishing an evaluation index system of a power grid digital project and an inter-project sharing network according to power grid digital project quantitative evaluation related information, technical characteristics of the power grid digital project and development strategy information of a power grid company, establishing a digital project group multi-objective optimization model according to the evaluation index system and the inter-project sharing network, solving to obtain a pareto optimal solution set, carrying out association rule mining according to the pareto optimal solution set, carrying out association rule sorting according to the pareto optimal solution set by taking support degree, confidence degree and lifting degree as