Pumped storage power station weekly regulation external economic benefit intelligent evaluation method

Abstract

The application discloses a kind of pumped storage power station weekly regulation external economic benefit intelligent evaluation method, belong to electric power system economic evaluation technical field.The technical problem to be solved is that existing method lacks the modeling ability of weekly regulation time scale, external economic benefit has not formed unified evaluation system, weight determination relies on artificial experience, qualitative index lacks standardization quantization method, and the stability of evaluation result is insufficient.The technical solution points are to construct a multi-level evaluation index system for weekly regulation, to establish a weekly scale operation scheduling model for pumped storage-power generation-backup coordination to quantify each index, to determine the comprehensive weight by using a three-source fusion game weighting method combining AI virtual expert, AHP subjective weighting and entropy weight method objective weighting, to obtain the comprehensive evaluation result by combining fuzzy comprehensive evaluation model, and finally to output comparative analysis and optimal decision suggestion under different operation modes.

Description

Technical Field

[0001] This invention belongs to the field of power system economic evaluation technology, specifically relating to an intelligent evaluation method for the weekly regulation external economic benefits of pumped storage power stations. Background Technology

[0002] With the large-scale integration of new energy sources such as wind power and photovoltaics into the power system, the system operation exhibits significant volatility, uncertainty, and strong randomness, placing higher demands on the power system's flexible adjustment capabilities. Pumped storage power stations, as the most technologically mature and largest-scale physical energy storage form currently available, play crucial roles in the power system, including peak shaving and valley filling, frequency and phase regulation, backup support, and new energy consumption. Existing research and engineering applications have identified the following main methods for evaluating the economic efficiency and comprehensive benefits of pumped storage power stations: (1) Economic evaluation method based on financial indicators: traditional engineering economic indicators such as net present value (NPV), internal rate of return (IRR), and investment payback period are used for evaluation. This type of method is based on a deterministic cash flow model and is mainly used for project investment feasibility analysis.

[0003] (2) Revenue calculation method based on electricity market mechanism: calculate the revenue of peak shaving, frequency regulation and reserve capacity according to the rules of electricity ancillary services market, such as the PJM market ancillary service pricing mechanism (2020).

[0004] (3) Comprehensive evaluation methods based on multi-attribute decision-making: including the analytic hierarchy process (AHP), entropy weight method, TOPSIS and fuzzy comprehensive evaluation method (Saaty, 1980; Zadeh, 1965), used for multi-index comprehensive evaluation analysis.

[0005] The existing technology has the following main shortcomings: 1) There is no unified evaluation system for external economic benefits. External benefits such as peak shaving and valley filling, new energy consumption, and backup substitution are modeled in a scattered manner and lack a unified quantitative framework.

[0006] 2) Lack of weekly adjustment timescale modeling capability. Existing methods are mostly based on daily scale or static analysis, which cannot reflect the comprehensive impact of cross-day (weekly adjustment) energy transfer on the system.

[0007] 3) Weight determination relies on human experience and is highly subjective. The AHP method depends on the expert judgment matrix, which has problems such as human bias, poor repeatability and difficulty in scaling up.

[0008] 4) Qualitative indicators lack standardized quantification methods. Environmental and social benefits are mostly expressed using fuzzy scoring or empirical assignment, lacking a unified mathematical expression.

[0009] 5) Lack of uncertainty handling and comprehensive evaluation capabilities: Traditional methods struggle to handle multi-source information fusion and indicator uncertainty, resulting in insufficient stability of evaluation results. In view of this, the present invention is hereby proposed. Summary of the Invention

[0010] To address the aforementioned technical problems in the existing technology, this invention provides an intelligent evaluation method for the external economic benefits of weekly regulation of pumped storage power stations. This method solves the problem that the existing technology lacks a unified evaluation system and quantification method for the external economic benefits of weekly regulation operation scenarios of pumped storage power stations, and cannot accurately identify and quantify the unique external value brought about by cross-day energy transfer under the weekly regulation mode. Based on this, the problems derived from traditional evaluation methods, such as the strong subjectivity of weights, the difficulty in standardizing and quantifying qualitative indicators, and the insufficient stability of evaluation results, were simultaneously solved, ultimately achieving scientific evaluation and optimized decision-making for the weekly adjustment of external economic benefits.

[0011] To achieve the above objectives, the technical solution of the present invention is as follows: Firstly, a smart evaluation method for the weekly regulation external economic benefits of pumped storage power stations includes: S1. Construct a multi-level external economic benefit evaluation index system for the weekly regulation operation scenario of pumped storage power stations; S2. Establish a weekly-scale operation and scheduling model for pumped storage power stations to simulate the pumping, power generation, and standby operation processes of the power stations on a weekly scale, and quantify the values ​​of each evaluation index. S3. Determine the comprehensive weight of each evaluation indicator; S4. Construct a fuzzy comprehensive evaluation model, and obtain the comprehensive evaluation result of the weekly adjustment of external economic benefits based on the comprehensive weights and the values ​​of each evaluation index. S5. Output the comprehensive evaluation results and conduct a comparative analysis of different operating modes.

[0012] Furthermore, the multi-level external economic benefit evaluation index system includes an objective layer, a criterion layer, and an indicator layer; The target layer is a comprehensive evaluation of the external economic benefits of weekly regulation. The criteria layer includes: power system regulation benefits, environmental benefits, and economic and social benefits; The indicator layer includes: power system service benefit indicators, environmental benefit indicators, and economic and social benefit indicators. The power system service benefit indicators include: peak shaving and valley filling benefits, frequency regulation benefits, phase regulation benefits, and emergency reserve benefits. The environmental benefit indicators include: energy conservation and emission reduction benefits and ecological service value. The economic and social benefit indicators include: benefits of promoting local industrial development, benefits of promoting local economic growth, and benefits of improving social security levels.

[0013] Furthermore, the weekly-scale operation scheduling model satisfies the following constraints: The power balance constraint is defined by the following formula:

[0014] The charging and discharging power constraint is specifically formulated as follows:

[0015]

[0016] The mutual exclusion constraint between power grid purchase and power abandonment is specifically formulated as follows:

[0017]

[0018] The energy storage constraint of the upper reservoir is given by the following formula:

[0019]

[0020]

[0021]

[0022] in, express The power generation capacity of thermal power, hydropower, nuclear power and gas turbine units at all times; express The power generation capacity of wind power at any given time; express The power generation capacity of photovoltaic systems at any given time; express The system receives external power at any given time. express Power generation capacity that stores energy at all times; express The power purchased from the power grid at any given time; express Real-time grid load; express The power constantly being transmitted outward; express Pumping power that stores energy at all times; express Power curtailment at any given moment; express The maximum power generation capacity available for the system's energy storage at any given time; express The maximum pumping power available for the system's energy storage at any given time; These are charge / discharge state variables; For the state variables of power grid purchase and abandonment; It is a positive number; express The amount of electricity generated by pumped-storage hydroelectric power. express The reservoir's energy storage capacity is constantly being replenished; This indicates the maximum energy storage capacity of the upper reservoir when it is full; express Pumping energy that is constantly pumping and storing water; The discharge efficiency of the pumped storage unit; The charging efficiency of pumped storage units; express The energy consumed in pumping water from the lower reservoir to the upper reservoir at all times; This represents the energy required to pump all the water from the lower reservoir to the upper reservoir when the lower reservoir is full.

[0023] Furthermore, the evaluation index values ​​quantified in step S2 include the monetized values ​​of peak shaving and valley filling benefits, frequency regulation benefits, phase regulation benefits, emergency reserve capacity replacement benefits, environmental emission reduction benefits, ecological contribution benefits, and social driving benefits.

[0024] Furthermore, determining the comprehensive weight of each evaluation indicator in step S3 includes: S31. Introduce an artificial intelligence model as a virtual expert, and combine it with historical operating data, industry standards, typical case libraries, and expert knowledge bases to generate an AI weight vector. The specific expression is as follows:

[0025] S32. The subjective weight vector is calculated using the subjective weighting method, and its specific expression is as follows:

[0026] S33. Based on the indicator sample data, the objective weight vector is calculated using an objective weighting method. The specific expression is as follows:

[0027] S34. The AI ​​weight vector, subjective weight vector and objective weight vector are fused to obtain the final comprehensive weight vector.

[0028] Furthermore, the subjective weighting method is the analytic hierarchy process (AHP), which specifically includes constructing pairwise comparison judgment matrices for the indicators. Solving for eigenvectors Then, normalization is performed to obtain the subjective weight vector.

[0029] Furthermore, the fusion of the AI ​​weight vector, subjective weight vector, and objective weight vector specifically includes: The specific formula for constructing AI-enhanced subjective weights is as follows:

[0030] in, The integration coefficient between experts and AI; By employing a game-theoretic combinatorial weighting method, the subjective and objective weights of the AI ​​enhancement are integrated to obtain the final comprehensive weight. The optimization objective is The constraints are + =1 and .

[0031] Furthermore, the construction of the fuzzy comprehensive evaluation model specifically includes: S41. Establish the factor set and evaluation set for the object to be evaluated; S42. Construct the membership functions corresponding to each evaluation index; S43. Based on the values ​​of each evaluation index and the membership function, form a fuzzy evaluation matrix; S44. Perform fuzzy operation on the comprehensive weight vector and the fuzzy evaluation matrix to obtain the comprehensive evaluation vector; S45. Based on the comprehensive evaluation vector, obtain the comprehensive score result of the weekly adjustment of external economic benefits.

[0032] Furthermore, step S44 specifically includes: Determine the comprehensive weight vector The comprehensive weight vector satisfies the normalization condition. ; Perform fuzzy operations on the comprehensive weight vector and the fuzzy evaluation matrix to obtain the comprehensive evaluation vector; The fuzzy operators used in the fuzzy computation are selected from the following four models: Model 1: Principal Factor Determining Operator The calculation formula is:

[0033] in, The first of the comprehensive evaluation vectors One element, The fuzzy evaluation matrix is ​​the first... Line number Column elements, To perform the smaller operation, For the larger operation; Model 2: Principal Factor Dominant Operator The calculation formula is:

[0034] in, This is a multiplication operation; Model 3: Principal Factor Emphasis Operator The calculation formula is:

[0035] in, For bounded sum operations, it is defined as ; Model 4: Weighted Average Operator The calculation formula is:

[0036] The main factor determining operator is suitable for scenarios where the main factor plays a dominant role, while the weighted average operator is suitable for scenarios where the influence of all factors needs to be considered in a balanced manner.

[0037] Furthermore, the comparative analysis of the different operating modes described in step S5 includes: Output the comprehensive score value of the weekly regulation operation mode and the comprehensive score value of the daily regulation operation mode; Analyze the differences in efficiency between weekly and daily adjustment operation modes; Sensitivity analysis of external economic benefits under different scheduling strategies; Identify and output optimal operating mode recommendations.

[0038] Beneficial effects of this invention: (1) This invention introduces an artificial intelligence model as a virtual expert, and incorporates historical operating data, industry standards, typical engineering cases and knowledge rules into the analysis process. While retaining the advantages of expert experience, it effectively reduces human randomness, improves the quality of judgment matrix construction, and significantly enhances the consistency, repeatability and stability of the weight generation process. (2) This invention can achieve a deep integration of empirical knowledge, statistical laws and intelligent reasoning ability, so that the final weight can reflect the system operation mechanism, reflect the data feature change law, and also have intelligent cognitive ability, and more realistically represent the importance of each evaluation indicator. (3) The present invention can dynamically correct and adaptively adjust the weight parameters according to the weekly regulation operation conditions of pumped storage power stations, the fluctuation characteristics of new energy output, changes in market transaction prices, system peak regulation and frequency regulation requirements and reserve capacity requirements, so that the evaluation model can fit the actual operating environment in real time, avoid the distortion of static models, and improve the timeliness and applicability of the evaluation results. (4) The present invention adopts a fuzzy comprehensive evaluation model to establish an evaluation level set and membership function, and maps indicators with different dimensions and different attributes to the same evaluation space, so as to realize the synergistic integration of quantitative and qualitative indicators, and greatly improve the feasibility and scientificity of comprehensive evaluation under complex indicator system. (5) The present invention establishes an evaluation system based on the weekly regulation operation characteristics, which can accurately identify the multi-dimensional external economic benefits of pumped storage power stations in the weekly cycle operation, and fully reflect their medium and long-term regulation value in the new power system. Attached Figure Description

[0039] Figure 1 A flowchart of an intelligent evaluation method for the weekly regulation external economic benefits of pumped storage power stations provided in an embodiment of the present invention. Detailed Implementation

[0040] The technical solution of the present invention will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are not all embodiments of the present invention. All other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the present invention.

[0041] It should be noted that, unless otherwise specifically stated, the relative arrangement and numerical expressions of the components and steps described in these embodiments should not be construed as limiting the scope of the invention.

[0042] The following description of exemplary embodiments is merely illustrative and is not intended to limit the invention or its application or use in any way. Techniques, methods, and apparatus known to those skilled in the art may not be discussed in detail herein, but where applicable, such techniques, methods, and apparatus should be considered part of this specification.

[0043] Example See Figure 1 , Figure 1 This is a flowchart of an intelligent evaluation method for the weekly regulation external economic benefits of a pumped storage power station proposed in this invention. Specific steps may include: S1. Construct a multi-level external economic benefit evaluation index system for the weekly regulation operation scenario of pumped storage power stations. This step establishes a three-level structured evaluation index system including the target layer, criterion layer and index layer to achieve a unified representation and systematic expression of the multi-dimensional external benefits generated by the weekly regulation operation of pumped storage power stations.

[0044] The target layer is a comprehensive evaluation of the external economic benefits of weekly regulation; the criteria layer includes three categories: power system regulation benefits, environmental benefits, and economic and social benefits; the indicator layer sets up nine specific evaluation indicators, namely: Power system service benefits include peak shaving and valley filling benefits, frequency regulation benefits, phase regulation benefits, and emergency backup benefits; environmental benefits include energy conservation and emission reduction benefits and ecological service value; and economic and social benefits include benefits that promote local industrial development, promote local economic growth, and improve social security levels.

[0045] S2. Establish a weekly-scale operation and scheduling model for pumped storage power stations to simulate the pumping, power generation, and standby operation processes of the power stations on a weekly scale, and quantify the values ​​of each evaluation index. This step first constructs a pumping-power-standby coordinated operation model that satisfies power balance, equipment operation, and reservoir storage constraints. The model constraints are as follows: The power balance constraint is defined by the following formula:

[0046] The charging and discharging power constraint is specifically formulated as follows:

[0047]

[0048] The mutual exclusion constraint between power grid purchase and power abandonment is specifically formulated as follows:

[0049]

[0050] The energy storage constraint of the upper reservoir is given by the following formula:

[0051]

[0052]

[0053]

[0054] in, express The power generation capacity of thermal power, hydropower, nuclear power and gas turbine units at all times; express The power generation capacity of wind power at any given time; express The power generation capacity of photovoltaic systems at any given time; express The system receives external power at any given time. express Power generation capacity that stores energy at all times; express The power purchased from the power grid at any given time; express Real-time grid load; express The power constantly being transmitted outward; express Pumping power that stores energy at all times; express Power curtailment at any given moment; express The maximum power generation capacity available for the system's energy storage at any given time; express The maximum pumping power available for the system's energy storage at any given time; These are charge / discharge state variables; For the state variables of power grid purchase and abandonment; It is a positive number; express The amount of electricity generated by pumped-storage hydroelectric power. express The reservoir's energy storage capacity is constantly being replenished; This indicates the maximum energy storage capacity of the upper reservoir when it is full; express Pumping energy that is constantly pumping and storing water; The discharge efficiency of the pumped storage unit; The charging efficiency of pumped storage units; express The energy consumed in pumping water from the lower reservoir to the upper reservoir at all times; This represents the energy required to pump all the water from the lower reservoir to the upper reservoir when the lower reservoir is full.

[0055] Based on the above model, typical weekly load curve data of the power grid, wind power and photovoltaic new energy output curve data, pumped storage unit parameter data, and electricity price data are input to simulate the pumped storage, peak power generation, and reserve support operation process of the pumped storage units on a continuous 7×24-hour weekly scale. After the simulation is completed, the peak shaving and valley filling benefits, frequency regulation benefits, phase regulation benefits, and emergency reserve capacity replacement benefits are calculated respectively. The environmental emission reduction benefits, ecological contribution benefits, and social driving benefits are then monetized to form the original quantitative datasets for each evaluation indicator, providing input for subsequent weighting and comprehensive evaluation.

[0056] S3. Determine the comprehensive weight of each evaluation indicator; This step employs an AI-driven, subjective, and objective-based weighting method to construct a weight generation mechanism that combines expert experience, data-driven approaches, and intelligent assistance. Specifically, it includes: S31. Introduce an artificial intelligence model as a virtual expert, combining historical operational data, industry standards, typical case libraries, and expert knowledge bases to assist in reasoning about the importance relationships of indicators, generating an independent AI weight vector, the specific expression of which is:

[0057] S32. Use the Analytic Hierarchy Process (AHP) to perform subjective weighting calculations and construct pairwise comparison judgment matrices for the indicators. Solving for eigenvectors Then, normalization is performed to obtain a subjective weight vector that reflects the expert's decision-making preferences. The specific expression is as follows:

[0058] Simultaneously, a consistency check is performed on the judgment matrix, the specific expression of which is: .

[0059] S33. Based on the obtained indicator sample data matrix The information entropy and dispersion of each indicator are calculated using the entropy weight method, resulting in an objective weight vector that reflects the contribution and discriminative ability of the indicator data. The specific expression is as follows:

[0060] The objective weight calculation formula for a single indicator is as follows:

[0061] in, Let be the information entropy of the j-th indicator.

[0062] S34. The AI ​​weight vector, subjective weight vector, and objective weight vector are fused to obtain the final comprehensive weight vector; an AI-enhanced subjective weight vector is constructed. ,in The integration coefficient between experts and AI can be adjusted according to actual evaluation needs; Using a game theory-based weighting method, the subjective and objective weights of AI enhancement are combined in a game equilibrium, resulting in a final comprehensive weight. The optimization objective is The constraints are + =1, Thus, the final index weight vector applicable to the weekly adjustment scenario is obtained.

[0063] S4. Construct a fuzzy comprehensive evaluation model, and obtain the comprehensive evaluation result of the weekly adjustment of external economic benefits based on the comprehensive weights and the values ​​of each evaluation index. This step addresses the issues of ambiguous indicator boundaries, scale heterogeneity, and evaluation uncertainty, achieving a unified and integrated evaluation of multiple indicators. Specifically, it includes: S41. Based on the needs of actual work and research, establish a factor set for the object to be evaluated. Factors refer to the various attributes of the object to be evaluated, which are also the specific content of the object to be evaluated.

[0064] Establish a judgment set A judgment set, also called a comment set, is a collection of comments made on the object being evaluated. It is used to represent the degree of merit or demerit of the evaluation factors. =Five levels: Excellent, Good, Average, Poor, Very Poor; S42. Construct the membership function corresponding to each evaluation indicator. For each evaluation indicator, construct the corresponding membership function based on its physical meaning and value range to characterize the degree of membership of the indicator to each evaluation level. Membership degree is a mathematical measure of the uncertainty of the membership relationship between factors and a fuzzy set. In solving practical problems, the membership function is generally determined first, followed by fuzziness assessment. However, the membership function usually requires specific methods, such as fuzzy statistics, binary comparison ranking, fuzzy distribution, and fuzzy computation. It must be pointed out that determining the membership function is essentially an objective process; the determined membership function should conform to objective reality. However, in actual problem-solving, certain subjective techniques and judgment experiences are permissible. Therefore, the determination of membership degree often carries a strong subjective element and is not uniquely determined. Whether the membership function conforms to reality depends not primarily on the membership value of individual elements, but on whether it correctly reflects the overall characteristics of the change from membership to non-membership.

[0065] S43. Based on the values ​​of each evaluation index and the membership function, form a fuzzy evaluation matrix. ,in The degree of membership of the indicator to the corresponding comment; After constructing the hierarchical fuzzy subsets, each factor (indicator) of the evaluated object needs to be standardized one by one, that is, the membership degree of a single factor is determined by calculating the membership function, thus obtaining the fuzzy relation matrix:

[0066] in, For relative to the index Give comments The degree of membership.

[0067] S44. Perform fuzzy operation on the comprehensive weight vector and the fuzzy evaluation matrix to obtain the comprehensive evaluation vector; Determine the weight of each factor: The final weights satisfy: .

[0068] Fuzzy computation can select main factor determining operator, main factor dominant operator, main factor prominent operator or weighted average operator according to the evaluation needs. Among them, the weighted average operator is suitable for scenarios that need to balance the influence of all factors. The Zadeh operator is generally used in fuzzy matrix composition operations. It can be represented in multiple forms. An improved model is applied based on the original fuzzy comprehensive evaluation model, incorporating operators from the original model... By using other operators, the following evaluation models can be obtained: Mode 1: —Main Factor Determining Type

[0069] The comprehensive evaluation results of this model The value is determined only by and In a certain operation, the smaller value is selected first, and then the larger value is selected. The focus is on the main factors, while other factors have little impact on the result. Sometimes, this operation can lead to situations where the decision result is not easy to distinguish.

[0070] Model 2: —Main factor dominant type

[0071] In this model, for Multiply by a weight less than 1 ,show When considering multiple factors The correction values ​​are related to the primary factors, while secondary factors are ignored.

[0072] Model 3: —Main Factor Prominence Type

[0073] In this model, the operation For a bounded sum, that is Because the weight allocation satisfies ,so Therefore,

[0074] In general practical applications, when the main factor (the factor with the highest weight) plays a dominant role in the comprehensive evaluation, Model 1 should generally be used; when Model 1 fails, Model 2 and Model 3 can be used.

[0075] Model 4: —Weighted average

[0076] Model 4 balances all factors according to their weights, making it suitable for situations where multiple factors are considered.

[0077] S45. Normalize the comprehensive evaluation vector, determine the evaluation level of the weekly adjustment of external economic benefits based on the principle of maximum membership degree, and convert it into the corresponding comprehensive score result. This step enables the unified evaluation of quantitative and qualitative indicators.

[0078] Evaluation Vector The operator " The selection of “” should refer to step 6 above, and the final evaluation result should be normalized.

[0079]

[0080] In conclusion, if Then, comments are made on the object of evaluation. .

[0081] In complex systems, many factors need to be considered, each with a small and difficult-to-determine weight. Using a single-level comprehensive evaluation might result in the loss of much useful information due to the insignificant weights, leading to inaccurate results. Therefore, all factors should be divided into several broad categories to more accurately determine their relative importance and weights within a smaller scope before conducting a comprehensive evaluation. This is known as multi-level comprehensive evaluation.

[0082] S5. Output the comprehensive evaluation results and conduct a comparative analysis of different operating modes.

[0083] The core results output in this step include: quantitative values ​​of each evaluation indicator, subjective weights, objective weights, and comprehensive weights of the indicators, fuzzy comprehensive evaluation vectors, and comprehensive scores for the weekly regulation operation mode. Based on this, the same evaluation process is used to calculate the comprehensive score for the daily regulation operation mode, analyzing the benefit differences between weekly and daily regulation operation modes; sensitivity analysis of external economic benefits under different dispatch strategies is conducted to identify key influencing factors; finally, the optimal operation mode recommendation is identified and output, providing a basis for planning decisions and operational optimization of pumped storage power stations.

[0084] The above specific embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to examples, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for intelligent evaluation of the external economic benefits of weekly regulation of a pumped storage power station, characterized in that, include: S1. Construct a multi-level external economic benefit evaluation index system for the weekly regulation operation scenario of pumped storage power stations; S2. Establish a weekly-scale operation and scheduling model for pumped storage power stations to simulate the pumping, power generation, and standby operation processes of the power stations on a weekly scale, and quantify the values ​​of each evaluation index. S3. Determine the comprehensive weight of each evaluation indicator; S4. Construct a fuzzy comprehensive evaluation model, and obtain the comprehensive evaluation result of the weekly adjustment of external economic benefits based on the comprehensive weights and the values ​​of each evaluation index. S5. Output the comprehensive evaluation results and conduct a comparative analysis of different operating modes.

2. The intelligent evaluation method for the external economic benefits of weekly regulation of pumped storage power stations according to claim 1, characterized in that, The multi-level external economic benefit evaluation index system includes an objective layer, a criterion layer, and an indicator layer. The target layer is a comprehensive evaluation of the external economic benefits of weekly regulation. The criteria layer includes: power system regulation benefits, environmental benefits, and economic and social benefits; The indicator layer includes: power system service benefit indicators, environmental benefit indicators, and economic and social benefit indicators. The power system service benefit indicators include: peak shaving and valley filling benefits, frequency regulation benefits, phase regulation benefits, and emergency reserve benefits. The environmental benefit indicators include: energy conservation and emission reduction benefits and ecological service value. The economic and social benefit indicators include: benefits of promoting local industrial development, benefits of promoting local economic growth, and benefits of improving social security levels.

3. The intelligent evaluation method for the external economic benefits of weekly regulation of pumped storage power stations according to claim 1, characterized in that, The weekly-scale operation scheduling model satisfies the following constraints: The power balance constraint is defined by the following formula: The charging and discharging power constraint is specifically formulated as follows: The mutual exclusion constraint between power grid purchase and power abandonment is specifically formulated as follows: The energy storage constraint of the upper reservoir is given by the following formula: in, express The power generation capacity of thermal power, hydropower, nuclear power and gas turbine units at all times; express The power generation capacity of wind power at any given time; express The power generation capacity of photovoltaic systems at any given time; express The system receives external power at any given time. express Power generation capacity that stores energy at all times; express The power purchased from the power grid at any given time; express Real-time grid load; express The power constantly being transmitted outward; express Pumping power that stores energy at all times; express The amount of power abandoned at any given moment; express The maximum power generation capacity available for the system's energy storage at any given time; express The maximum pumping power available for the system's energy storage at any given time; These are charge / discharge state variables; For the state variables of power grid purchase and abandonment; It is a positive number; express The amount of electricity generated by pumped-storage hydroelectric power. express The reservoir's energy storage capacity is constantly being replenished; This indicates the maximum energy storage capacity of the upper reservoir when it is full; express Pumping energy that is constantly pumping and storing water; The discharge efficiency of the pumped storage unit; The charging efficiency of pumped storage units; express The energy consumed in pumping water from the lower reservoir to the upper reservoir at all times; This represents the energy required to pump all the water from the lower reservoir to the upper reservoir when the lower reservoir is full.

4. The intelligent evaluation method for the external economic benefits of weekly regulation of pumped storage power stations according to claim 1, characterized in that, The evaluation index values ​​calculated in step S2 include the monetary conversion values ​​of peak shaving and valley filling benefits, frequency regulation benefits, phase regulation benefits, emergency reserve capacity replacement benefits, environmental emission reduction benefits, ecological contribution benefits, and social driving benefits.

5. The intelligent evaluation method for the external economic benefits of weekly regulation of pumped storage power stations according to claim 1, characterized in that, Step S3, determining the overall weight of each evaluation indicator, includes: S31. Introduce an artificial intelligence model as a virtual expert, and combine it with historical operating data, industry standards, typical case libraries, and expert knowledge bases to generate an AI weight vector. The specific expression is as follows: S32. The subjective weight vector is calculated using the subjective weighting method, and its specific expression is as follows: S33. Based on the indicator sample data, the objective weight vector is calculated using an objective weighting method. The specific expression is as follows: S34. The AI ​​weight vector, subjective weight vector and objective weight vector are fused to obtain the final comprehensive weight vector.

6. The intelligent evaluation method for the external economic benefits of weekly regulation of pumped storage power stations according to claim 5, characterized in that, The subjective weighting method is the analytic hierarchy process (AHP), which specifically includes constructing pairwise comparison judgment matrices for the indicators. Solving for eigenvectors Then, normalization is performed to obtain the subjective weight vector.

7. The intelligent evaluation method for the external economic benefits of weekly regulation of pumped storage power stations according to claim 5, characterized in that, The fusion of the AI ​​weight vector, subjective weight vector, and objective weight vector specifically includes: The specific formula for constructing AI-enhanced subjective weights is as follows: in, The integration coefficient between experts and AI; By employing a game-theoretic combinatorial weighting method, the subjective and objective weights of the AI ​​enhancement are integrated to obtain the final comprehensive weight. The optimization objective is The constraints are + =1 and .

8. The intelligent evaluation method for the external economic benefits of weekly regulation of pumped storage power stations according to claim 1, characterized in that, The construction of the fuzzy comprehensive evaluation model specifically includes: S41. Establish the factor set and evaluation set for the object to be evaluated; S42. Construct the membership functions corresponding to each evaluation index; S43. Based on the values ​​of each evaluation index and the membership function, form a fuzzy evaluation matrix; S44. Perform fuzzy operation on the comprehensive weight vector and the fuzzy evaluation matrix to obtain the comprehensive evaluation vector; S45. Based on the comprehensive evaluation vector, obtain the comprehensive score result of the weekly adjustment of external economic benefits.

9. The intelligent evaluation method for the external economic benefits of weekly regulation of pumped storage power stations according to claim 8, characterized in that, Step S44 specifically includes: Determine the comprehensive weight vector The comprehensive weight vector satisfies the normalization condition. ; Perform fuzzy operations on the comprehensive weight vector and the fuzzy evaluation matrix to obtain the comprehensive evaluation vector; The fuzzy operators used in the fuzzy computation are selected from the following four models: Model 1: Principal Factor Determining Operator The calculation formula is: in, The first of the comprehensive evaluation vectors One element, The fuzzy evaluation matrix is ​​the first... Line 1 Column elements, To perform the smaller operation, For the larger operation; Model 2: Principal Factor Dominant Operator The calculation formula is: in, This is a multiplication operation; Model 3: Principal Factor Emphasis Operator The calculation formula is: in, For bounded sum operations, it is defined as ; Model 4: Weighted Average Operator The calculation formula is: The main factor determining operator is suitable for scenarios where the main factor plays a dominant role, while the weighted average operator is suitable for scenarios where the influence of all factors needs to be considered in a balanced manner.

10. The intelligent evaluation method for the external economic benefits of weekly regulation of pumped storage power stations according to claim 1, characterized in that, The comparative analysis of different operating modes in step S5 includes: Output the comprehensive score value of the weekly regulation operation mode and the comprehensive score value of the daily regulation operation mode; Analyze the differences in efficiency between weekly and daily adjustment operation modes; Sensitivity analysis of external economic benefits under different scheduling strategies; Identify and output optimal operating mode recommendations.

Images