Power transmission and transformation project economic evaluation method, system and equipment fusing adaptive fuzzy entropy weighting and multi-target grey wolf optimization algorithm, and medium

Abstract

The invention discloses a power transmission and transformation project economic evaluation method, system, equipment and medium fusing adaptive fuzzy entropy weighting and a multi-target grey wolf optimization algorithm, and belongs to the technical field of power system economic analysis, and the method comprises the steps: constructing an economic index system, building a fuzzy membership matrix, and calculating an index weight through combining fuzzy entropy and information entropy; a comprehensive weight is generated by adopting a self-adaptive fusion mechanism, then a multi-target weighted evaluation model is constructed, and finally multi-target search is performed by utilizing a swarm intelligence optimization algorithm. According to the invention, by constructing a self-adaptive weighting mechanism fusing the fuzzy entropy and the information entropy and combining the global search capability of the multi-target grey wolf optimization algorithm, multi-index weight dynamic optimization and multi-target cooperative solution in the economic evaluation of the power transmission and transformation project are realized; the method effectively overcomes the limitation of a traditional method in the aspects of weight distribution subjectivity, insufficient index coupling processing and multi-target balance, and forms a closed-loop evaluation system from index processing to intelligent decision making.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power system economic analysis, in particular to a power transmission and transformation project economic evaluation method, system, device and medium fusing adaptive fuzzy entropy empowerment and multi-objective grey wolf optimization algorithm. BACKGROUND

[0002] With the expansion of the scale and complexity of power transmission and transformation project construction, the importance of economic evaluation in project planning is increasingly prominent. However, the commonly used evaluation methods at present generally rely on static weight configuration, single optimization target and linear scoring model, and it is difficult to fully reflect the dynamic membership between multiple economic factors in actual engineering. For example, investment cost, operating expenditure and income return often exist coupling fluctuations in time dimension and space scene, and the traditional weighted method is difficult to adaptively adjust the influence degree of each index in different schemes. In addition, the fixed evaluation function cannot coordinate the conflicts of multiple objectives such as payback period, net present value and internal rate of return, which is easy to lead to distorted conclusion and unbalanced ranking.

[0003] In order to overcome the above limitations, the present application provides a power transmission and transformation project economic evaluation method fusing adaptive fuzzy entropy empowerment and multi-objective grey wolf optimization algorithm. The method first constructs a complete economic evaluation index system, and introduces fuzzy entropy and information entropy joint modeling to respectively depict the uncertainty and difference of each index, and realizes adaptive regulation of weight distribution through the fusion coefficient controlled by standard deviation. Subsequently, the grey wolf optimization algorithm is used to perform global search on the multi-objective weight space, and a multi-objective non-dominated solution set is constructed with the maximum net present value, the minimum investment cost, the optimal income rate and the shortest payback period as the target. By introducing Pareto sorting and dynamic parameter updating mechanism, the method effectively avoids premature convergence, and improves the rationality and coverage of the solution. SUMMARY

[0004] In view of the above problems, the present application provides a power transmission and transformation project economic evaluation method, system, device and medium fusing adaptive fuzzy entropy empowerment and multi-objective grey wolf optimization algorithm.

[0005] Therefore, the technical problem solved by the present application is: how to solve the technical problems that the current power transmission and transformation project economic evaluation method relies on static weight configuration and single target optimization model, which leads to difficulty in dynamically reflecting the coupling membership of multiple economic factors, inability to adaptively coordinate the multi-objective conflicts, and the traditional evaluation function is easy to appear distorted conclusion and ranking imbalance in complex scene.

[0006] To solve the above technical problems, the present application provides the following technical scheme: a power transmission and transformation project economic evaluation method fusing adaptive fuzzy entropy empowerment and multi-objective grey wolf optimization algorithm, comprising, The economic evaluation index is collected, an economic index system is constructed, and preprocessing is performed; through the economic evaluation index after preprocessing, the degree of fuzzy grade of each evaluation object is calculated through a fuzzy mapping method, so that a fuzzy membership matrix of the evaluation object is constructed; the fuzzy entropy value and the information entropy weight of each index are calculated based on the fuzzy membership matrix of the evaluation object; based on the fuzzy entropy value and the information entropy weight, a weighting mechanism is constructed by introducing a weighting coefficient, and a comprehensive weight vector is generated; based on the fuzzy membership matrix and the comprehensive weight vector, a multi-attribute decision method is used to construct a multi-objective weighted evaluation model; based on the multi-objective weighted evaluation model as an optimization target, a group intelligence optimization algorithm is introduced for searching, and an optimal solution is obtained.

[0007] As a preferred scheme of the power transmission and transformation project economic evaluation method fusing adaptive fuzzy entropy weighting and a multi-objective grey wolf optimization algorithm, wherein the collection of economic evaluation indexes and the construction of an economic index system and preprocessing include, Several evaluation index data related to the economy of the power transmission and transformation project are collected.

[0008] The collected original evaluation index data is standardized to eliminate dimensional differences.

[0009] The standardized data is constructed into an index data matrix, including the standardized evaluation indexes.

[0010] As a preferred scheme of the power transmission and transformation project economic evaluation method fusing adaptive fuzzy entropy weighting and a multi-objective grey wolf optimization algorithm, wherein the calculation of the degree of fuzzy grade of each evaluation object through a fuzzy mapping method includes, The fuzzy semantic division standard corresponding to each economic index is determined.

[0011] The degree of belonging to different fuzzy grades is calculated for the standardized value of each evaluation object on each index.

[0012] The calculated membership degree results are organized and arranged according to the evaluation object and index dimensions.

[0013] A fuzzy membership matrix with membership degree as an element is formed, which completely characterizes the fuzzy attribute characteristics of each object on different indexes.

[0014] As a preferred scheme of the power transmission and transformation project economic evaluation method fusing adaptive fuzzy entropy weighting and a multi-objective grey wolf optimization algorithm, wherein the calculation of the fuzzy entropy value and the information entropy weight of each index based on the fuzzy membership matrix of the evaluation object includes, The preprocessed economic evaluation index is taken as the fuzzy membership degree, a fuzzy matrix is constructed, and the fuzzy entropy is calculated.

[0015] Calculate the distribution characteristic matrix of each index under different schemes based on the pretreated economic evaluation index.

[0016] Solve the information entropy based on the distribution characteristic matrix under different schemes to obtain the weight vector under the information entropy method.

[0017] As a preferred scheme of the power transmission and transformation project economic evaluation method fusing adaptive fuzzy entropy weighting and multi-objective grey wolf optimization algorithm, wherein the introduction of the weighting coefficient, the construction of the adaptive fusion weighting mechanism, and the generation of the comprehensive weight vector include, The dynamic weighting coefficient is introduced to establish the fusion mechanism of the fuzzy entropy weight and the information entropy weight.

[0018] The fusion proportion of the two types of weights is adaptively adjusted according to the index data distribution characteristics.

[0019] The comprehensive weight vector considering uncertainty and discrimination is generated through the weighted fusion algorithm.

[0020] The beneficial effects of the preferred technical scheme are that by constructing an adaptive fusion mechanism based on data characteristics, the applicability limitations caused by the fixed ratio of subjective and objective weights in traditional weighting methods are effectively solved. The method adjusts the fusion proportion of the fuzzy entropy weight and the information entropy weight in real time through the dynamic weighting coefficient, considers the inherent uncertainty of the index data, and retains its inherent discrimination characteristics, so that the finally generated comprehensive weight vector can accurately reflect the fluctuation characteristics of the actual engineering data.

[0021] As a preferred scheme of the power transmission and transformation project economic evaluation method fusing adaptive fuzzy entropy weighting and multi-objective grey wolf optimization algorithm, wherein the multi-attribute decision method is used to construct a multi-objective weighted evaluation model, including, The fuzzy membership matrix and the comprehensive weight vector are weighted and fused.

[0022] An evaluation function is established by comprehensively considering the membership and importance of each index.

[0023] A multi-attribute decision model is constructed, which can evaluate multiple economic objectives simultaneously.

[0024] The beneficial effects of the preferred technical scheme are that by systematically integrating the fuzzy membership matrix and the comprehensive weight vector, an evaluation function with multi-dimensional perception ability is constructed. The multi-attribute decision model not only considers the membership degree of each index under different fuzzy levels, but also integrates the weight distribution optimized by the adaptive mechanism, so that the evaluation process can reflect both the quantitative characteristics and the qualitative attributes of the index. By establishing a multi-attribute decision model, the coordinated evaluation of multiple economic objectives such as net present value, investment cost, and return rate is realized, effectively overcoming the limitations of traditional single objective evaluation.

[0025] As a preferred scheme of the power transmission and transformation engineering economic evaluation method fusing adaptive fuzzy entropy weighting and multi-objective grey wolf optimization algorithm, the search of the introduced swarm intelligence optimization algorithm includes, The multi-objective weighted evaluation model is set as the objective function of the optimization algorithm, and a multi-dimensional optimization target system is established.

[0026] The improved swarm intelligence optimization algorithm, the wolf pack leadership mechanism and the wolf pack following mechanism are used to complete the parallel exploration and development of the multi-objective space.

[0027] In the iteration process, a dynamic adaptive parameter adjustment strategy is introduced, and the search step and direction are automatically adjusted according to the population distribution characteristics.

[0028] The Pareto optimal solution screening mechanism is used, the solution set diversity is maintained through non-dominated sorting and congestion degree calculation, and a solution set that optimally balances multiple economic targets is output.

[0029] The beneficial effects of the preferred technical scheme are that by constructing a multi-objective grey wolf optimization search mechanism, the problem that the traditional optimization method is easily trapped in local optimum in a complex economic target space is effectively solved. The leadership-following mechanism is used to realize the parallel exploration of the multi-objective space, the dynamic parameter adjustment strategy is used to maintain the search activity of the algorithm in the iteration process, and the Pareto optimal solution screening mechanism is used to ensure the diversity and convergence of the solution set. Finally, a non-dominated solution set that optimally balances investment cost, net present value, yield and other economic targets is output.

[0030] The application provides a power transmission and transformation engineering economic evaluation system fusing adaptive fuzzy entropy weighting and multi-objective grey wolf optimization algorithm.

[0031] To solve the above technical problems, the application provides the following technical scheme: a power transmission and transformation engineering economic evaluation system fusing adaptive fuzzy entropy weighting and multi-objective grey wolf optimization algorithm, which comprises a data preprocessing and index system construction module, a fuzzy processing and entropy analysis module, an adaptive weight fusion module, a multi-attribute decision modeling module, an intelligent optimization solving module and a decision support and visualization module.

[0032] The data preprocessing and index system construction module collects economic evaluation indexes to construct an economic index system and performs preprocessing.

[0033] The fuzzy processing and entropy analysis module calculates the fuzzy level of each evaluation object through the fuzzy mapping method based on the preprocessed economic evaluation indexes, so as to construct a fuzzy membership matrix of the evaluation object.

[0034] The adaptive weight fusion module calculates the fuzzy entropy value and information entropy weight of each index based on the fuzzy membership matrix of the evaluation object.

[0035] The multi-attribute decision modeling module introduces a trade-off coefficient based on the fuzzy entropy value and information entropy weight, constructs an adaptive fusion weighting mechanism, and generates a comprehensive weight vector.

[0036] The intelligent optimization solving module constructs a multi-objective weighted evaluation model based on the fuzzy membership matrix and the comprehensive weight vector using a multi-attribute decision method.

[0037] The decision support and visualization module introduces a multi-objective grey wolf optimization algorithm based on the multi-objective weighted evaluation model as an optimization target to search for an optimal solution.

[0038] The application provides a computer device, including a memory and a processor, the memory stores a computer program, characterized in that the processor implements the steps of the power transmission and transformation project economic evaluation method of the fusion adaptive fuzzy entropy weighting and multi-objective grey wolf optimization algorithm when executing the computer program.

[0039] The application provides a computer readable storage medium, which stores a computer program, characterized in that the computer program implements the steps of the power transmission and transformation project economic evaluation method of the fusion adaptive fuzzy entropy weighting and multi-objective grey wolf optimization algorithm when executed by a processor.

[0040] The application has the beneficial effects that: the application constructs an evaluation and optimization framework integrating multi-source index processing, adaptive weight adjustment and intelligent search to solve the technical bottlenecks of strong subjectivity in weight distribution, insufficient coupling membership processing between multiple indexes and lack of multi-objective balance of optimization results in the prior art. The method introduces fuzzy entropy and information entropy joint modeling to dynamically perceive the uncertainty and distinguish degree of each economic index, and realizes adaptive regulation and control of the weighting result based on a weight evolution mechanism. At the same time, the multi-objective grey wolf optimization algorithm is used to perform global search in the weight space, and an optimal solution considering multiple factors such as investment cost, income capacity and risk recovery period is obtained through non-dominated sorting and Pareto frontier extraction. Finally, a closed-loop economic evaluation process from index construction, weight learning to solution set extraction is realized, and a stable, transparent and intelligent adaptive multi-objective quantitative decision tool is provided for power transmission and transformation projects. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without any creative effort based on these drawings.

[0042] Figure 1 The overall flow chart of the power transmission and transformation project economic evaluation method fusing adaptive fuzzy entropy weighting and multi-objective grey wolf optimization algorithm is provided for an embodiment of the present application.

[0043] Figure 2 The overall framework chart of the power transmission and transformation project economic evaluation system fusing adaptive fuzzy entropy weighting and multi-objective grey wolf optimization algorithm is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to make the present application more apparent and easy to understand, the specific embodiments of the present application will be described in detail in the following with reference to the drawings of the specification. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without any creative effort should belong to the protection scope of the present application.

[0045] Embodiment 1, refer to Figure 1 For an embodiment of the present application, the embodiment provides a power transmission and transformation project economic evaluation method fusing adaptive fuzzy entropy weighting and multi-objective grey wolf optimization algorithm, comprising: S1, collecting economic evaluation indexes, constructing an economic index system and preprocessing.

[0046] S2, through the preprocessed economic evaluation indexes, calculating the fuzzy grade degree of each evaluation object through a fuzzy mapping method, so as to construct a fuzzy membership matrix of the evaluation object.

[0047] S3, calculating the fuzzy entropy value and information entropy weight of each index based on the fuzzy membership matrix of the evaluation object.

[0048] S4, based on the fuzzy entropy value and information entropy weight, introducing a trade-off coefficient, constructing an adaptive fusion weighting mechanism, and generating a comprehensive weight vector.

[0049] S5, based on the fuzzy membership matrix and the comprehensive weight vector, constructing a multi-objective weighted evaluation model by using a multi-attribute decision method.

[0050] S6, based on the multi-objective weighted evaluation model as an optimization target, introducing a swarm intelligence optimization algorithm for searching, and obtaining an optimal solution.

[0051] The present application realizes the leap of power transmission and transformation project economic evaluation from single target decision to multi-target collaborative optimization by constructing the technical closed loop of "fuzzification processing-double entropy fusion empowerment-group intelligence optimization". The method adopts a fuzzy mapping method to process index uncertainty, constructs an adaptive empowerment mechanism through double measurement of fuzzy entropy and information entropy, effectively overcomes the subjectivity and static nature of weight configuration in traditional evaluation, then organically fuses fuzzy evaluation and dynamic weight through a multi-attribute decision model, and finally realizes global optimization in a multi-economic target space by using a group intelligence optimization algorithm, thereby improving the scientificity, adaptability and decision reliability of economic evaluation.

[0052] Embodiment 2 is an embodiment of the present application, which provides a power transmission and transformation project economic evaluation method based on adaptive fuzzy entropy empowerment and multi-target grey wolf optimization algorithm, based on the previous embodiment, comprising: The collection of economic evaluation indexes in S1 constructs an economic index system and performs preprocessing, including steps A1-A3: A1, collect several evaluation index data related to the economic nature of the power transmission and transformation project.

[0053] A2, standardize the collected original evaluation index data to eliminate dimensional differences.

[0054] A3, construct the standardized data into an index data matrix, including the standardized evaluation indexes.

[0055] Specifically, according to the investment evaluation requirements of the power transmission and transformation project, m economic index vectors are set Each index corresponds to n candidate project schemes. The original data is processed by dimensionless processing to form a standardized matrix , wherein: , wherein, represents the normalized value, represents the original value of the jth index in the ith scheme, represents the minimum value of the jth economic index vector, represents the maximum value of the jth economic index vector.

[0056] In the embodiments of the present application, the fuzzification mapping method in S2, i.e. the fuzzy membership function, specifically, a plurality of fuzzy evaluation grades (such as "excellent, good, medium, and poor") are pre-set for each economic indicator, and a clear numerical boundary is set for each grade. For the standardized value of any indicator, the degree of membership to each grade is calculated by a piecewise linear function: when the value is in the core interval of a certain grade, the membership degree is 1; when the value is in the transition interval of adjacent grades, the membership degree linearly changes between 0 and 1; when the value is far away from the grade interval, the membership degree is 0. Finally, each indicator value corresponds to a membership degree vector describing its degree of belonging to each grade.

[0057] In an alternative embodiment, the fuzzification mapping method can be a smooth fuzzification mapping using a Gaussian membership function. This scheme defines a center value and a standard deviation for each fuzzy evaluation grade, thereby constructing a bell-shaped curve. For any indicator value, the degree of membership to a certain grade is determined by the distance between the value and the center value of the grade, and the closer the distance, the higher the membership degree, and the smooth calculation is performed by a Gaussian function. This method can generate smooth membership transition, and is particularly suitable for handling fuzziness near the boundary value.

[0058] In another alternative embodiment, the fuzzification mapping method can also be to handle two-pole evaluation problems using an S-shaped membership function. This scheme is mainly suitable for indicators that only need to distinguish between "good" and "poor" two states. It maps the indicator value to the degree of membership to the "good" grade by an S-shaped curve function. The function changes sharply in the middle stage, and can clearly represent the grade transition caused by the slight change of the indicator value near the critical point, and is suitable for decision-making scenarios that need to clearly distinguish between pass and fail.

[0059] Further, the degree of fuzzy grade of each evaluation object is calculated by the fuzzification mapping method in S2 to construct a fuzzy membership matrix of the evaluation objects, including steps B1-B4: B1, determine the fuzzy semantic division standard corresponding to each economic indicator.

[0060] B2, for the standardized value of each evaluation object on each indicator, calculate the degree of membership to different fuzzy grades.

[0061] B3, organize and arrange the calculated membership degree results according to the evaluation object and indicator dimensions.

[0062] B4, form a fuzzy membership matrix with membership degrees as elements, which completely represents the fuzzy attribute characteristics of each object on different indicators.

[0063] Further, the fuzzy membership matrix is represented as , μij represents the fuzzy membership degree of the i-th scheme to the j-th indicator.

[0064] In the embodiments of the present application, the fuzzy semantic division standard in B1 is the fuzzy evaluation grade and the boundary condition. Specifically, in the implementation, first, according to the economic evaluation specification of power transmission and transformation project, each economic index is divided into four evaluation grades of "excellent, good, medium, and poor"; then, the field experts determine the numerical boundaries corresponding to each grade by the Delphi method, wherein the "excellent" grade corresponds to the industry leading level, the "good" grade corresponds to the good level, the "medium" grade corresponds to the standard level, and the "poor" grade corresponds to the non-standard level; and finally, the grade threshold interval of each index is formed.

[0065] In an alternative embodiment, the fuzzy semantic division standard can be a quartile grading method based on data distribution characteristics. This scheme first collects a large amount of historical engineering data, statistically analyzes the numerical values of each index, and divides the index values into four equal intervals according to their size, which correspond to the four fuzzy grades. The lowest 25% of the data interval is defined as "poor", the 25%-50% interval is defined as "medium", the 50%-75% interval is defined as "good", and the highest 25% interval is defined as "excellent".

[0066] In another alternative embodiment, the fuzzy semantic division standard can also be a dynamic grading system based on target achievement. This scheme takes the expected target value of the engineering project as the benchmark and divides the grades according to the degree of target completion: more than 120% is "excellent", 100%-120% is "good", 80%-100% is "medium", and less than 80% is "poor". The boundaries of each grade are dynamically adjusted according to the target value of the specific project.

[0067] Further, the calculation of the fuzzy entropy value and the information entropy weight of each index based on the fuzzy membership matrix of the evaluation object in S3 includes steps C1-C3: C1, the pre-processed economic evaluation index is taken as the fuzzy membership degree, a fuzzy matrix is constructed, and the fuzzy entropy is calculated.

[0068] The calculation of the fuzzy entropy is represented as, wherein, denotes the normalization factor.

[0069] C2, the distribution feature matrix of each index under different schemes is calculated based on the pre-processed economic evaluation index.

[0070] C3, the information entropy is solved based on the distribution feature matrix under different schemes to obtain the weight vector under the information entropy method.

[0071] Further, the information entropy is represented as, The weight vector is represented as, wherein, represents the relative proportion of the i-th scheme under the j-th index, represents the information entropy of the j-th index, represents the information entropy weight.

[0072] In the embodiments of the present application, the distribution feature matrix in C2, i.e., the probability matrix, specifically includes that for each economic index, the total value in all schemes is calculated, and then the value of each scheme on the index is divided by the total value to obtain the relative proportion of the scheme on the index. The relative proportions of all schemes on all indexes are organized according to the original matrix row-column structure, i.e., a matrix reflecting the distribution characteristics of the index values of each scheme is constructed.

[0073] Specifically, the probability matrix is represented as, In an alternative embodiment, the distribution feature matrix can be a distribution representation matrix based on rank and order. This scheme first ranks all schemes under each economic index and assigns a rank, and then calculates the proportion of the rank of each scheme in the total rank. The distribution feature matrix constructed by this method can eliminate the dimension effect of the original data and highlight the relative position relationship of the schemes on the index.

[0074] In another alternative embodiment, the distribution feature matrix can also be a distribution representation matrix based on distance similarity. This scheme first determines the ideal optimal value of each economic index, then calculates the relative distance of the index value of each scheme from the ideal value, and finally normalizes the distance data into proportion form.

[0075] Further, the introduction of the trade-off coefficient in S4, the construction of the adaptive fusion weighting mechanism, and the generation of the comprehensive weight vector include steps D1-D3: D1, introduce a dynamic trade-off coefficient to establish a fusion mechanism of fuzzy entropy weight and information entropy weight.

[0076] D2, adaptively adjust the fusion proportion of the two types of weights according to the distribution characteristics of the index data.

[0077] D3, generate a comprehensive weight vector that takes into account uncertainty and discrimination through a weighted fusion algorithm.

[0078] Further, the comprehensive weight vector is represented as, wherein, wherein, is a fusion factor, represented as, wherein, denotes the standard deviation of the jth indicator, denotes the adaptive fusion ratio; denotes the final indicator weight.

[0079] Further, the multi-attribute decision method in S5 for constructing a multi-objective weighted evaluation model comprises steps E1-E3: E1, weighting fusion of the fuzzy membership matrix and the comprehensive weight vector.

[0080] E2, establishing an evaluation function that comprehensively considers the membership and importance of each indicator.

[0081] E3, constructing a multi-attribute decision model that can evaluate multiple economic objectives simultaneously.

[0082] This step applies all indicator weights to the normalized data to calculate the total score of each scheme. The higher the score of a scheme, the better it performs under multiple objectives.

[0083] According to the weighted method, the score of the scheme is calculated: wherein, denotes the comprehensive score of the ith scheme.

[0084] In the embodiments of the present application, the swarm intelligence optimization algorithm in S6, i.e., the multi-objective grey wolf optimization algorithm, specifically comprises the following steps: first, encoding the weight vector into the position of a grey wolf individual, and establishing an optimization function group composed of multiple objectives such as maximizing investment return rate and minimizing cost. The algorithm divides the optimal solution in each iteration into three leadership levels by simulating the social hierarchy of a wolf pack, and the remaining wolves adjust their own states according to the leadership level positions through a specific position update formula. This formula balances global exploration and local development by adjusting the convergence factor, which decreases dynamically with the number of iterations. At the same time, a non-dominated sorting mechanism is used to classify the solution set, and the distribution of the Pareto front is maintained through congestion distance calculation, finally outputting a set of non-dominated solutions that achieve the optimal balance among multiple economic objectives In an alternative embodiment, the swarm intelligence optimization algorithm can be a multi-objective particle swarm optimization algorithm. This scheme regards each weight vector as a particle in the search space, and the particle updates its speed and position by tracking the individual historical optimal position and the global optimal position of the group. To avoid premature convergence, dynamic inertia weight and crossover mutation operations are introduced, and a archive set mechanism is used to save non-dominated solutions, and the distribution of the solution set is maintained through congestion distance sorting, realizing the optimization search of multi-objective weights.

[0085] In another alternative embodiment, the swarm intelligence optimization algorithm can also be a multi-objective genetic algorithm. This scheme realizes the evolutionary optimization of the weight vector through genetic operations such as selection, crossover, mutation, etc. First, the initial weight population is non-dominantly sorted, then the excellent individuals are selected through the tournament selection, the new individuals are generated by using the simulated binary crossover and the polynomial mutation, and finally the excellent solutions are ensured not to be lost through the elite reservation strategy. After multiple generations of evolution, the uniformly distributed Pareto optimal solution set is output.

[0086] Further, the introduction of the swarm intelligence optimization algorithm for searching in S6 to obtain the optimal solution includes steps F1-F4: F1, set the multi-objective weighted evaluation model as the objective function of the optimization algorithm, and establish a multi-dimensional optimization target system.

[0087] F2, use an improved swarm intelligence optimization algorithm, through the wolf pack leadership mechanism and the wolf pack following mechanism, to complete the parallel exploration and development of the multi-objective space.

[0088] F3, introduce a dynamic self-adaptive parameter adjustment strategy in the iteration process, and automatically adjust the search step and direction according to the population distribution characteristics.

[0089] F4, use a Pareto optimal solution screening mechanism to maintain the diversity of the solution set through non-dominant sorting and congestion calculation, and output the solution set that achieves the optimal balance among multiple economic objectives.

[0090] Embodiment 3, refer to Figure 2 As an embodiment of the present application, the embodiment provides a power transmission and transformation project economic evaluation system integrating adaptive fuzzy entropy weighting and multi-objective grey wolf optimization algorithm, comprising: a data preprocessing and index system construction module, a fuzzy processing and entropy analysis module, an adaptive weight fusion module, a multi-attribute decision modeling module, an intelligent optimization solving module, and a decision support and visualization module.

[0091] The data preprocessing and index system construction module collects economic evaluation indexes to construct an economic index system and performs preprocessing.

[0092] The fuzzy processing and entropy analysis module calculates the degree of fuzzy grade of each evaluation object through the fuzzy mapping method based on the preprocessed economic evaluation indexes, to construct a fuzzy membership matrix of the evaluation object.

[0093] The adaptive weight fusion module calculates the fuzzy entropy value and information entropy weight of each index based on the fuzzy membership matrix of the evaluation object.

[0094] The multi-attribute decision modeling module introduces a trade-off coefficient based on the fuzzy entropy value and information entropy weight, constructs an adaptive fusion weighting mechanism, and generates a comprehensive weight vector.

[0095] The intelligent optimization solution module adopts a multi-attribute decision method to construct a multi-objective weighted evaluation model based on a fuzzy membership matrix and a comprehensive weight vector.

[0096] The decision support and visualization module introduces a multi-objective grey wolf optimization algorithm to search based on the multi-objective weighted evaluation model as an optimization target, and obtains an optimal solution.

[0097] The embodiment also provides an electronic device suitable for a power transmission and transformation project economic evaluation method fusing adaptive fuzzy entropy weighting and a multi-objective grey wolf optimization algorithm, which comprises a memory and a processor.

[0098] The embodiment also provides a storage medium having a computer program stored thereon, the program being executed by a processor to implement the power transmission and transformation project economic evaluation method fusing adaptive fuzzy entropy weighting and a multi-objective grey wolf optimization algorithm.

[0099] The storage medium provided by the embodiment and the power transmission and transformation project economic evaluation method fusing adaptive fuzzy entropy weighting and a multi-objective grey wolf optimization algorithm provided by the above embodiment belong to the same inventive concept, and the technical details not described in the embodiment can be referred to the above embodiment, and the embodiment has the same beneficial effects as the above embodiment.

[0100] Through the above description of the embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application or the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a floppy disk, a read-only memory (ROM), a random access memory (RAM), a FLASH, a hard disk or an optical disk, etc., including a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods of various embodiments of the present application.

[0101] It should be noted that the above examples are only used to illustrate the technical solutions of the present application but not to limit the present application. Although the present application is described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or equivalently replaced, without departing from the spirit and scope of the technical solutions of the present application, and all of them should be covered in the scope of the claims of the present application.

Claims

1. A power transmission and transformation project economic evaluation method fusing adaptive fuzzy entropy weighting and multi-objective grey wolf optimization algorithm, characterized in that: Comprising, Collect economic evaluation indexes, construct an economic index system, and preprocess; Through the fuzzy mapping method, the fuzzy degree of each evaluation object is calculated to construct a fuzzy membership matrix of the evaluation object; Based on the fuzzy membership matrix of the evaluation object, the fuzzy entropy value and the information entropy weight of each index are calculated; Based on the fuzzy entropy value and the information entropy weight, a self-adaptive fusion weighting mechanism is constructed by introducing a trade-off coefficient to generate a comprehensive weight vector; Based on the fuzzy membership matrix and the comprehensive weight vector, a multi-attribute decision-making method is used to construct a multi-objective weighted evaluation model; Based on the multi-objective weighted evaluation model as the optimization target, a group intelligence optimization algorithm is introduced to search and obtain the optimal solution. 2.The power transmission and transformation project economic evaluation method of fusing adaptive fuzzy entropy weighting and multi-objective grey wolf optimization algorithm according to claim 1, characterized in that: The collection of economic evaluation indexes, the construction of an economic index system, and the preprocessing thereof include, Collecting a plurality of evaluation index data related to the economy of the power transmission and transformation project; Standardizing the collected original evaluation index data to eliminate dimensional differences; The standardized data is constructed into an index data matrix, which includes the standardized evaluation indexes.

3. The power transmission and transformation project economic evaluation method of claim 2, wherein: The fuzzy mapping method is used to calculate the fuzzy degree of each evaluation object to construct a fuzzy membership matrix of the evaluation object, which includes, Determining the fuzzy semantic division standard corresponding to each economic index; For the standardized value of each evaluation object on each index, the degree of membership to different fuzzy levels is calculated; The membership degree results are arranged according to the evaluation object and index dimensions; A fuzzy membership matrix is formed with membership degree as an element, which completely represents the fuzzy attribute characteristics of each object on different indexes.

4. The power transmission and transformation project economic evaluation method of claim 3, wherein: The fuzzy entropy value and the information entropy weight of each index are calculated based on the fuzzy membership matrix of the evaluation object, which includes, The preprocessed economic evaluation indexes are used as fuzzy membership degrees to construct a fuzzy matrix and calculate the fuzzy entropy; Based on the preprocessed economic evaluation indexes, the distribution feature matrix of each index under different schemes is calculated; The information entropy is solved based on the distribution feature matrix under different schemes to obtain the weight vector under the information entropy method.

5. The power transmission and transformation project economic evaluation method of claim 4, wherein: The introduction of a trade-off coefficient to construct a self-adaptive fusion weighting mechanism to generate a comprehensive weight vector includes, A dynamic trade-off coefficient is introduced to establish a fusion mechanism of fuzzy entropy weight and information entropy weight; The fusion proportion of the two types of weights is adaptively adjusted according to the index data distribution characteristics; A comprehensive weight vector that takes into account uncertainty and discriminability is generated through a weighted fusion algorithm.

6. The power transmission and transformation project economic evaluation method of claim 4, wherein: The multi-attribute decision-making method is used to construct a multi-objective weighted evaluation model, which includes, The fuzzy membership matrix and the comprehensive weight vector are weighted and fused; An evaluation function that comprehensively considers the membership and importance of each index is established; A multi-attribute decision-making model that can evaluate multiple economic objectives is constructed.

7. The power transmission and transformation project economic evaluation method of claim 4, wherein: The introduction of a group intelligence optimization algorithm for searching to obtain the optimal solution includes, The multi-objective weighted evaluation model is set as the objective function of the optimization algorithm to establish a multi-dimensional optimization target system; An improved group intelligence optimization algorithm is used to complete the parallel exploration and development of the multi-objective space through the wolf pack leadership mechanism and the wolf pack following mechanism; In the iteration process, a dynamic adaptive parameter adjustment strategy is introduced to automatically adjust the search step and direction according to the population distribution characteristics; The Pareto optimal solution screening mechanism is used to maintain the diversity of the solution set through non-dominated sorting and congestion calculation, and a solution set achieving optimal balance among multiple economic targets is output.

8. A power transmission and transformation project economic evaluation system fusing adaptive fuzzy entropy weighting and multi-objective grey wolf optimization algorithm, applying the power transmission and transformation project economic evaluation method fusing adaptive fuzzy entropy weighting and multi-objective grey wolf optimization algorithm according to any one of claims 1-7, characterized in that, The method comprises the following steps: The data preprocessing and index system construction module, the fuzzy processing and entropy analysis module, the adaptive weight fusion module, the multi-attribute decision modeling module, the intelligent optimization solving module, and the decision support and visualization module; The data preprocessing and index system construction module collects economic evaluation indexes to construct an economic index system and performs preprocessing; The fuzzy processing and entropy analysis module calculates the degree of fuzzy grade of each evaluation object through the fuzzy mapping method based on the preprocessed economic evaluation indexes, to construct a fuzzy membership matrix of the evaluation object; The adaptive weight fusion module calculates the fuzzy entropy value and information entropy weight of each index based on the fuzzy membership matrix of the evaluation object; The multi-attribute decision modeling module introduces a trade-off coefficient to construct an adaptive fusion weighting mechanism based on the fuzzy entropy value and information entropy weight, to generate a comprehensive weight vector; The intelligent optimization solving module adopts a multi-attribute decision method to construct a multi-objective weighted evaluation model based on the fuzzy membership matrix and the comprehensive weight vector; The decision support and visualization module introduces a multi-objective grey wolf optimization algorithm to search for an optimal solution based on the multi-objective weighted evaluation model as an optimization target. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the power transmission and transformation project economic evaluation method of claim 1 to 7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the power transmission and transformation project economic evaluation method of claim 1 to 7.

Images