A regional pumped storage development capacity multi-dimensional evaluation system and method based on data feature modeling and beta distribution

Abstract

This invention relates to the field of hydropower technology, specifically to a multi-dimensional assessment system and method for regional pumped storage development capacity based on data feature modeling and Beta distribution. The assessment method involves constructing a multi-layered Beta distribution model, introducing AHP scores, FCE scores, and TOPSIS scores as raw data, and optimizing them to obtain a more objective assessment report. Applying this assessment system to the aforementioned method, through a data-driven approach combined with reasonable statistical calibration, enhances the objectivity, dynamism, and accuracy of the assessment method, ensuring more scientific and rational support in complex decision-making.

Description

Technical Field

[0001] This invention relates to the field of hydropower technology, and more specifically, to a multi-dimensional evaluation system and method for regional pumped storage development capacity based on data feature modeling and Beta distribution. Background Technology

[0002] Against the backdrop of escalating global climate change and heightened environmental awareness, adjusting the energy structure has become a crucial issue of intense global competition. The application of renewable energy continues to expand, and pumped storage, as a key energy storage technology, plays an indispensable role in balancing electricity supply and demand, ensuring grid security, and promoting the effective utilization of renewable energy. Pumped storage power plants can store energy during periods of low electricity demand and release it during peak demand periods, thereby improving the overall efficiency and flexibility of the power system.

[0003] However, traditional evaluation methods often rely on expert experience and intuition. While these methods can reflect project characteristics to some extent, the lack of sufficient data support often leads to evaluation results that are subject to uncertainty and subjectivity. Furthermore, with socio-economic development and technological advancements, existing evaluation results may no longer be suitable for the current situation, and traditional methods struggle to dynamically adjust to adapt to new data.

[0004] The implementation of pumped storage projects requires comprehensive consideration of multiple factors, including the suitability of the geographical location, the convenience of grid connection, the completeness of transportation infrastructure, the support capacity of economic development, residents' affordability, and potential spatial constraints and population density. These factors have complex interactions, and traditional single-dimensional assessment methods are insufficient to fully reflect the impact of these interactions on project feasibility.

[0005] It is worth noting that the construction and operation of pumped storage power stations is a long-term investment, thus requiring accurate forecasts of energy development trends over the next few decades. Traditional assessment methods often overlook the long-term potential and sustainability of projects, focusing too much on short-term economic benefits, which may negatively impact the long-term planning and development of the projects.

[0006] Therefore, there is an urgent need to develop a new evaluation method that can not only integrate multiple data sources, but also dynamically adjust weights based on historical data to adapt to the ever-changing external environment and development needs. Summary of the Invention

[0007] This invention provides a multi-dimensional assessment system and method for regional pumped storage development capacity based on data feature modeling and Beta distribution, which can solve the problems of strong subjectivity and difficulty in dynamic updating in traditional assessment methods.

[0008] The multi-dimensional assessment method for regional pumped storage development capacity based on data feature modeling and Beta distribution according to the present invention includes:

[0009] A scoring input layer for the scoring method is constructed, and various indicators related to the regional pumped storage development capacity are collected. The AHP method, FCE method and TOPSIS method are used to score each indicator to obtain the AHP score, FCE score and TOPSIS score.

[0010] A theoretical distribution construction layer is constructed, specific distribution parameters are set for the AHP method, FCE method and TOPSIS method, the Beta distribution density function is constructed, and quantiles are generated.

[0011] An absolute level assessment layer is constructed. Based on the AHP score, FCE score, and TOPSIS score, a score position calculation model is built to obtain the score position and quantitative rating score. Based on the score position, a development potential calculation model is built to obtain the development potential score.

[0012] Construct a comprehensive capability assessment layer and calculate the average development potential scores of each indicator under the AHP method, FCE method and TOPSIS method;

[0013] A comprehensive evaluation layer is constructed. Based on the quantitative rating scores and development potential scores of various indicators under the AHP method, FCE method and TOPSIS method, a basic indicator calculation model is built to obtain the basic capability score, development potential score and balance score, and then the weighted calculation is performed to obtain the comprehensive score.

[0014] A feature analysis layer is constructed. Based on the quantitative rating scores of various indicators under the AHP, FCE and TOPSIS methods, a score feature analysis model is constructed to obtain the score dispersion and coefficient of variation. Based on the development potential scores of various indicators under the AHP, FCE and TOPSIS methods, a feature analysis model is constructed to obtain the potential mean, potential dispersion and dominant development direction.

[0015] Preferably, the indicators in the scoring input layer of the scoring method include development demand degree (A1), resource endowment degree (A2), economic carrying capacity (A3), and construction constraint degree (A4).

[0016] Preferably, constructing the Beta distribution density function in the theoretical distribution construction layer includes:

[0017] The formula for constructing the Beta distribution is as follows:

[0018]

[0019] Where x is one of the AHP score, FCE score, and TOPSIS score, x∈[0,1], and α and β are distribution parameters.

[0020]

[0021] The cumulative Beta distribution is given by the following formula:

[0022]

[0023] The formula for calculating quantiles is:

[0024] Q(p)=F -1 (p;α,β)={x|F(x;α,β)=p} (3)

[0025] Preferably, constructing the score location calculation model in the absolute level evaluation layer includes:

[0026] The probability density discretization formula is as follows:

[0027]

[0028] The formula for calculating the density value sequence is:

[0029] Y = {y i =f(x) i ;α,β)|i=0,1,...,N-1} (5)

[0030] The formula for calculating the score position is:

[0031]

[0032] The formula for calculating the quantitative rating score is as follows:

[0033]

[0034] Preferably, constructing a development potential calculation model includes:

[0035] The current position is determined by the following formula:

[0036] p c =P(x) (8)

[0037] In the formula p c Current position;

[0038] The target threshold is determined by the following formula:

[0039] T(p c )=min{p∈{0.9,0.75,0.5,0.25}|p>p c} (9)

[0040] In the formula, T(p) c ) is the target threshold;

[0041] The formula for calculating development distance is as follows:

[0042]

[0043] In the formula, Δ(x) represents the development distance;

[0044] The formula for calculating development potential score is as follows:

[0045]

[0046] In the formula, D(x) is the development potential score.

[0047] Preferably, the construction of the basic indicator calculation model in the comprehensive evaluation layer includes:

[0048] Basic computational ability assessment:

[0049]

[0050] Among them, C b Basic ability assessment, M=3, s i =L(x i ) score Let be the quantitative rating score of the i-th method, where the score is one of the AHP method, FCE method, and TOPSIS method;

[0051] Calculate the development potential score:

[0052]

[0053] In the formula, C p To score development potential, M=3, D(x) i ) is x i The development potential score of the location.

[0054] Calculate the balance score:

[0055]

[0056] Among them, C e For balance score,

[0057] Preferably, the formula for constructing the comprehensive score in the comprehensive evaluation layer is as follows:

[0058] S=w1C b +w2C p +w3C e (15)

[0059] Where w1 = 0.5, w2 = 0.3, w3 = 0.2, C b Basic ability score, Cp To score development potential, C e This is for the balance score.

[0060] Preferably, constructing a score feature analysis model in the feature analysis layer includes:

[0061] The formula for calculating the score dispersion is as follows:

[0062]

[0063] In the formula, σ s The score dispersion;

[0064] The formula for calculating the coefficient of variation is:

[0065]

[0066] In the formula, CV s is the coefficient of variation.

[0067] Preferably, constructing the feature analysis model in the feature analysis layer includes:

[0068] The formula for calculating the mean potential is:

[0069]

[0070] In the formula, This represents the average potential.

[0071] The formula for calculating the potential dispersion is as follows:

[0072]

[0073] In the formula, σ D Potential dispersion;

[0074] The formula for calculating the dominant development direction is as follows:

[0075] d * =argmax i {D(x i )} (20)

[0076] In the formula, d * The dominant direction.

[0077] The multi-dimensional evaluation system for regional pumped storage development capacity based on data feature modeling and Beta distribution according to the present invention includes: a data input module, a data preprocessing module, a feature extraction and weight allocation module, a comprehensive evaluation model construction module, an intelligent grading and result output module, a dynamic adjustment mechanism module, and a dynamic adjustment mechanism module.

[0078] The data input module is used to collect various indicators related to the development capacity of pumped storage, form raw indicator data, and send it to the data preprocessing module.

[0079] The data preprocessing module includes a data cleaning unit, a data standardization unit, and a data fusion unit. The data cleaning unit is responsible for removing invalid or erroneous raw indicator data; the data standardization unit converts raw indicator data from different sources into a unified format and unit; and the data fusion unit is responsible for integrating various raw indicator data types into a consistent dataset.

[0080] The feature extraction and weight allocation module is used to construct a judgment matrix based on the dataset and obtain the weights of each indicator.

[0081] The comprehensive evaluation model construction module constructs a Beta distribution density function based on the AHP evaluation model, FCE evaluation model, and TOPSIS evaluation model to obtain an evaluation report.

[0082] The intelligent grading and result output module grades the data based on the evaluation report and generates charts from the evaluation report.

[0083] The dynamic adjustment mechanism module is used to update the original indicator data.

[0084] Beneficial effects:

[0085] This invention provides a theoretical analysis of the scoring tendencies of different evaluation methods (AHP, FCE, and TOPSIS) and calibrates them by setting reasonable Beta distribution parameters to eliminate scoring biases in specific applications. This helps to achieve a more comprehensive and balanced evaluation, thereby obtaining more valuable evaluation results. Attached Figure Description

[0086] Figure 1 This is the overall flowchart of the multi-dimensional evaluation system for regional pumped storage development capacity based on data feature modeling and Beta distribution of the present invention;

[0087] Figure 2 for Figure 1 A schematic diagram of the hierarchical analytic hierarchy process (AHP);

[0088] Figure 3 for Figure 1 A schematic diagram of the structure of Fuzzy Comprehensive Evaluation (FCE);

[0089] Figure 4 for Figure 1 Schematic diagram of the Top-Dominant Solution Distance Method (TOPSIS);

[0090] Figure 5This is a flowchart of the multi-dimensional evaluation system method for regional pumped storage development capacity based on data feature modeling and Beta distribution, as presented in this invention. Detailed Implementation

[0091] It should be noted that:

[0092] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations thereof. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0093] The term "and / or" simply describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Additionally, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0094] Example 1

[0095] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0096] Seen in Figure 1-5 This embodiment provides a multi-dimensional assessment method for regional pumped storage development capacity based on data feature modeling and Beta distribution, including:

[0097] A scoring input layer for the scoring method is constructed, and various indicators related to the regional pumped storage development capacity are collected. The AHP method, FCE method and TOPSIS method are used to score each indicator to obtain the AHP score, FCE score and TOPSIS score.

[0098] like Figure 2The Analytic Hierarchy Process (AHP) evaluation process shown aims to conduct in-depth analysis of multifaceted data to ultimately arrive at a comprehensive evaluation result. The entire process is divided into several key layers. In the data preparation layer, various raw data are collected, including key data such as development needs, resource endowments, economic carrying capacity, and construction constraints. This data forms the foundation of the analysis, covering all important aspects of the evaluation object. Next is data preprocessing, which includes Z-score standardization, extreme value handling, and interval transformation. Z-score standardization eliminates differences in data dimensions, making them comparable; extreme value handling addresses outliers; and interval transformation ensures all data falls within a unified interval, facilitating subsequent calculations. In the feature calculation layer, the intrinsic characteristics of the data are analyzed in depth by calculating feature values ​​such as correlation coefficient, coefficient of variation, and information entropy. The correlation coefficient is used to determine the correlation between indicators, the coefficient of variation reflects the dispersion of the data, and information entropy measures the degree of data disorder; these indicators collectively help to understand the complexity of the data. The judgment matrix construction layer is a crucial step in constructing the A1-A4 sub-criteria judgment matrices and the criterion-level judgment matrix. These matrices express the relative importance of each sub-criteria and the relationships between criteria, forming the basis for weight calculation. At the weight calculation layer, consistency checks are performed by calculating eigenvalues ​​and eigenvectors to ensure the rationality of the judgment matrix, and weights are normalized. This accurately determines the relative importance of each indicator, making the evaluation results more objective and reasonable. Finally, at the scoring calculation layer, scores are calculated for different dimensions to obtain scores for development demand, resource endowment, economic carrying capacity, and construction constraints. By synthesizing the scores from each dimension, the final AHP score is calculated, providing a clear evaluation basis for decision-making.

[0099] The AHP score is obtained through the following steps:

[0100] A theoretical distribution construction layer is constructed, specific distribution parameters are set for the AHP method, FCE method and TOPSIS method, the Beta distribution density function is constructed, and quantiles are generated.

[0101] An absolute level assessment layer is constructed. Based on the AHP score, FCE score, and TOPSIS score, a score position calculation model is built to obtain the score position and quantitative rating score. Based on the score position, a development potential calculation model is built to obtain the development potential score.

[0102] Construct a comprehensive capability assessment layer and calculate the average development potential scores of each indicator under the AHP method, FCE method and TOPSIS method;

[0103] A comprehensive evaluation layer is constructed. Based on the quantitative rating scores and development potential scores of various indicators under the AHP method, FCE method and TOPSIS method, a basic indicator calculation model is built to obtain the basic capability score, development potential score and balance score, and then the weighted calculation is performed to obtain the comprehensive score.

[0104] A feature analysis layer is constructed. Based on the quantitative rating scores of various indicators under the AHP, FCE and TOPSIS methods, a score feature analysis model is constructed to obtain the score dispersion and coefficient of variation. Based on the development potential scores of various indicators under the AHP, FCE and TOPSIS methods, a feature analysis model is constructed to obtain the potential mean, potential dispersion and dominant development direction.

[0105] Preferably, the indicators in the scoring input layer of the scoring method include development demand degree (A1), resource endowment degree (A2), economic carrying capacity (A3), and construction constraint degree (A4).

[0106] The development demand (A1), resource endowment (A2), economic carrying capacity (A3), and construction constraints (A4) are obtained through the following steps:

[0107] I. Development Demand Level (A1):

[0108] 1. Regional renewable energy characteristic quantities:

[0109] Renewable energy installed capacity R i,t Where i represents the region identifier and t represents the time; the renewable energy development coefficient α i It is used to characterize the regional potential for renewable energy development.

[0110] 2. Characteristics of Electricity Load

[0111] Peak-to-valley difference P i,t , used to characterize the regional electricity load characteristics;

[0112] Regional load factor β i It is used to characterize the concentration of regional industrial load.

[0113] 3. Grid absorption characteristics

[0114] Wind and solar curtailment rate A i,t This characterizes the capacity to absorb renewable energy.

[0115] Power grid adaptability coefficient γ i This characterizes the regional power grid's capacity to accept power.

[0116] For the evaluation region i, a data matrix D is formed on the time series T. i :

[0117]

[0118] Among them, D i To meet the development needs.

[0119] II. Resource Endowment (A2):

[0120] 1. Geographical condition assessment index set G, including:

[0121] Topographical drop h i The unit is meters;

[0122] Available site area a i The unit is square kilometers;

[0123] Water resource endowment coefficient w i ';

[0124] Geological condition coefficient g i ∈[0,1].

[0125] 2. The power grid access condition index set E includes:

[0126] Voltage level v i The set of values ​​is V = {110, 220, 330, 500} kV;

[0127] Power grid stability coefficient s i ∈[0,1];

[0128] Distance d from substation s,i The unit is kilometers;

[0129] Distance d from the load center l,i The unit is kilometers.

[0130] 3. Traffic condition index set T, including:

[0131] Highway reachable distance r d,i The unit is kilometers;

[0132] Railway reachable distance r t,i The unit is kilometers;

[0133] Road Class I i The set of values ​​is L = {1, 2, 3, 4};

[0134] Construction convenience coefficient c i ∈[0,1].

[0135] For evaluation region i, construct evaluation matrix M. i :

[0136]

[0137] After standardization, each indicator yields a standardized score matrix S. i :

[0138]

[0139] Among them, each standardized score satisfies: S x,i ∈[0,100].

[0140] By introducing the weighting coefficient matrix W, the final resource endowment can be obtained:

[0141]

[0142] in:

[0143] III. Economic Carrying Capacity (A3):

[0144] 1. The set of economic development indicators E includes:

[0145] GDP per capita i (t), in ten thousand yuan / person;

[0146] Economic growth rate α i (t);

[0147] Regional population base P i The unit is 10,000 people;

[0148] Fiscal revenue scale F i (t), in units of 100 million yuan;

[0149] Fiscal growth rate β i (t).

[0150] 2. The energy economic indicators set U includes:

[0151] Energy consumption coefficient per unit of GDP e i (t), satisfying the time decay function e i (t)=e i (0)(1-η) t Where η is the annual energy efficiency improvement rate.

[0152] Benchmark electricity price p b (t), satisfying: p b (t)=p b (0)(1+γ) t Where γ is the annual growth rate of electricity prices.

[0153] 3. Set A of indicators of residents' ability to pay includes:

[0154] per capita disposable income i (t), in ten thousand yuan / person;

[0155] Revenue growth rate δ i (t);

[0156] Electricity price affordability coefficient C i (t), the calculation formula is:

[0157]

[0158] Among them, Q r This is the annual baseline electricity consumption for residents.

[0159] For the evaluation region i over time series t, construct an economic condition evaluation matrix M. i (t):

[0160]

[0161] Introducing the economic cycle factor ω(t):

[0162]

[0163] Where T is the length of the economic cycle, and ∈ is the fluctuation amplitude coefficient.

[0164] Ultimately, the standardized economic carrying capacity S is obtained. i (t):

[0165] S i (t)=f(M i (t),ω(t))∈[0,100]

[0166] IV. Construction Constraints (A4):

[0167] 1. Spatial constraint index set S, including:

[0168] Total area A i The unit is square kilometers;

[0169] R of ecological protection zones p (t), which satisfies the dynamic evolution equation:

[0170] R p (t)=R p (0)+λt

[0171] Where λ is the annual protection intensity growth rate, and R p (t)≤R max .

[0172] 2. Population density constraint index set P, including:

[0173] Regional population N i (t), satisfying:

[0174] N i (t)=N i (0)(1+r i ) t

[0175] Where, r i This refers to the natural population growth rate.

[0176] Urbanization rate U i (t), satisfying:

[0177] U i (t)=U i (0)(1+μ) t

[0178] Where μ represents the annual urbanization growth rate.

[0179] Population density D i (t), calculation formula:

[0180]

[0181] 3. Load constraint index set L, including:

[0182] Load center capacity C i (t), the unit is 10,000 kilowatts;

[0183] Industrial density coefficient η i ;

[0184] Load growth rate α i ;

[0185] Load evolution equation:

[0186] C i (t)=C i (0)(1+η i α i ) t

[0187] For the evaluation region i over the time series t, construct the constraint matrix K. i (t):

[0188]

[0189] Based on this constraint matrix, the regional construction constraint degree Ω can be obtained. i (t):

[0190] Ω i (t)={x|g(K i (t),x)≤0}

[0191] Among them, g(K) i (t),x) is the set of constraint function.

[0192] Please refer to Figure 2 The Analytic Hierarchy Process (AHP) is a structured decision support method designed to solve complex, multi-level decision-making problems. First, AHP systematizes the problem by establishing a four-layer progressive evaluation structure. The target layer (L0) is defined as the comprehensive score of regional development capacity, while the criteria layer (L1) consists of development demand (A1), resource endowment (A2), economic carrying capacity (A3), and construction constraints (A4). Based on this, the sub-criteria layer (L2) refines the specific evaluation indicators under each criterion, and the alternative layer (L3) lists the regions to be evaluated. This hierarchical structure helps to clarify the evaluation objectives and direction.

[0193] In the objective construction of the judgment matrix, the criterion-level judgment matrix is ​​first established:

[0194]

[0195] In the formula, I i Let ρ be the information entropy of index i. i For the correlation coefficient with the target, CV i is the coefficient of variation.

[0196] This judgment matrix is ​​based on the contribution of historical data. Its elements are determined by calculating the information entropy, correlation coefficient, and coefficient of variation of each indicator. This ensures that the judgment matrix reflects the relative importance of the indicators in decision-making.

[0197] Subsequently, the judgment matrix for the sub-criteria layer is constructed as follows:

[0198]

[0199] By constructing a sub-criteria layer judgment matrix, the relative importance of each sub-indicator under each criterion is calculated:

[0200]

[0201] Where: e i For information entropy, h i For redundancy, s i This is the sensitivity coefficient.

[0202] By calculating relative importance, information entropy, redundancy, and sensitivity coefficients are combined to quantify the relative weight of each sub-indicator. This ensures the objectivity and accuracy of the evaluation.

[0203] In the matrix consistency optimization phase, the optimization model is first constructed:

[0204]

[0205] The constraints are:

[0206]

[0207] The algorithm iteratively optimizes the process by first initializing the judgment matrix A; then calculating the consistency ratio CR; if CR ≥ 0.1, a correction is made.

[0208]

[0209] Finally, repeat the steps until the consistency requirements are met.

[0210] In terms of weight calculation, the eigenvalue method is used to calculate the eigenvalues:

[0211] (A-λI)W=0

[0212] The eigenvalues ​​are then normalized to obtain the weights of each indicator.

[0213]

[0214] In the multi-level comprehensive scoring, the score of each evaluation object is first calculated by combining local weights. The specific formula combines the score of the k-th evaluation object, the weight of the i-th indicator, and the standardized indicator value. Finally, the global score is calculated by summing the weights and standardized indicator values ​​of each level, taking into account the number of levels L and the number of indicators in each level, thus achieving a comprehensive evaluation of all evaluation objects.

[0215] The formula for combining local weights is:

[0216]

[0217] Where S k For the score of the k-th evaluation object, w i S is the weight of the i-th indicator. ki These are the standardized indicator values.

[0218] AHP score calculation:

[0219]

[0220] Where L is the number of levels, n l Let w be the number of indicators at level l. i l S represents the weight of the i-th indicator in the l-th layer. ki l These correspond to standardized indicator values.

[0221] The Analytic Hierarchy Process (AHP) provides a scientific and feasible solution to complex decision-making problems through its systematic hierarchical structure, objective judgment matrix construction, and rigorous consistency optimization.

[0222] Please refer to Figure 3 Fuzzy Comprehensive Evaluation (FCE) is an effective method for quantitative and qualitative evaluation of complex systems. First, a five-level quantitative evaluation scale is constructed: V = {v1, v2, v3, v4, v5}, specifically including {poor (20), relatively poor (40), average (60), relatively good (80), and good (100)}, and the corresponding quantitative mapping function is defined:

[0223]

[0224] A clear division of evaluation levels is achieved. Next, a dynamic membership function is designed, employing a modified Gaussian function form for membership calculation. The central value is determined using the mean of historical data, and basic and variation adjustment coefficients are introduced. The calculation of the dynamic fuzziness parameter combines the index variation coefficient and the sample mean. This process ensures both the flexibility and accuracy of the evaluation.

[0225] The membership degree calculation formula based on the improved Gaussian function is as follows:

[0226]

[0227] The center value is determined:

[0228] c k =20(k+1), k=0,1,2,3,4

[0229] Dynamic fuzziness parameters:

[0230]

[0231] In the formula, β is the basic adjustment coefficient, ranging from [0.1, 0.3], γ is the variation adjustment coefficient, ranging from [0.2, 0.5], and CV... x The coefficient of variation of the index. This is the sample mean.

[0232] In constructing the fuzzy relation matrix, for each level of each indicator, the elements of its fuzzy relation matrix are calculated, and the tail decay coefficient is used to reflect the relative influence of different levels. For the j-th level of the i-th indicator:

[0233]

[0234] In the formula, δ is the tail attenuation coefficient, with a value of 0.1.

[0235] Subsequently, multi-level fuzzy comprehensive operations are performed. First, fuzzy comprehensive operations are conducted at the sub-criteria level, combining the weights of each sub-criteria with their fuzzy relationships to obtain the comprehensive result of the sub-criteria. Then, synthesis is performed at the criterion level, further integrating the results of each sub-criteria through the weights of each criterion, thereby forming a comprehensive evaluation system.

[0236] Sub-criterion layer fuzzy synthesis:

[0237]

[0238] Criterion-layer fuzzy synthesis:

[0239] B = W[B1; B2; B3; B4]

[0240] Finally, based on the clarification process using the center-of-gravity method, the FCE score is obtained:

[0241]

[0242] This score is derived by weighting the comprehensive results of each indicator with its corresponding central value, providing a scientific basis for decision-making. Overall, the fuzzy comprehensive evaluation algorithm, through flexible parameter settings and hierarchical calculation methods, achieves effective evaluation of multidimensional complex problems.

[0243] Please refer to Figure 4 The TOPSIS evaluation algorithm is a widely used method in multi-attribute decision analysis. Based on the principles of distance measure and relative proximity, it supports scientific decision-making by constructing an optimized decision matrix, ideal solution, and evaluation mechanism.

[0244] First, the algorithm processes the decision matrix through vector normalization:

[0245]

[0246] To ensure the comparability of indicators with different dimensions, the analytic hierarchy process (AHP), entropy weighting, and coefficient of variation weighting were combined to form a relatively objective weight structure, making the impact of different indicators on decision-making results more accurate. The weight optimization and integration formula is as follows:

[0247]

[0248] In the formula, w j AHP For AHP weights, w j E For entropy weight, w j V For the coefficient of variation weights, α+β+γ=1.

[0249] To construct the dynamic ideal solution, the algorithm defines the positive ideal solution:

[0250]

[0251] Negative ideal solution:

[0252]

[0253] In the formula, σ j Let be the standard deviation of index j, and δ be the expansion coefficient, with values ​​ranging from [0.1, 0.3].

[0254] The merits of each evaluation object are measured by maximizing the positive ideal solution and minimizing the negative ideal solution. When defining the ideal solution, the standard deviation of each index and an expansion coefficient ranging from 0.1 to 0.3 are considered to ensure that the ideal solution has dynamic adaptability and can better reflect the actual situation.

[0255] When calculating the distance between each evaluation object and the ideal solution, the TOPSIS algorithm uses the Minkowski-Mahalanobis hybrid distance:

[0256]

[0257] In the formula, p is the distance parameter, taking values ​​[1,2], Σ is the covariance matrix, and V i Let i be the index vector for the evaluation object i.

[0258] This distance measure combines the flexibility of the Minkowski distance with the Mahalanobis distance's consideration of variable correlation, making the distance measure more generalized and accurate. Here, the distance parameter p ranges from 1 to 2. Furthermore, it incorporates the covariance matrix to fully account for the interrelationships between the indicators, ultimately forming the generalized distance between the indicator vector of the evaluation object i and the ideal solution.

[0259] Next, the TOPSIS algorithm introduces the relative proximity of the adjustment coefficients:

[0260]

[0261] The distance to the maximum negative ideal solution is corrected by using a balance coefficient λ (ranging from 0.4 to 0.6), making the proximity calculation more robust and adaptable.

[0262] Regarding the integration mechanism of evaluation results, TOPSIS first performs preprocessing standardization:

[0263]

[0264] Introducing IQR k(Interquartile range) makes the distribution of data more reasonable.

[0265] Then, during the generation of combined weights:

[0266]

[0267] Consider the relationship between methods r k (Average correlation coefficient) and CV k (Coefficient of variation) is used to ensure a more balanced and reasonable weighting of different evaluation methods.

[0268] Ultimately, TOPSIS passed the CR. k The scores are comprehensively adjusted using the consistency ratio and η (correction coefficient) (ranging from 0.1 to 0.2) to generate the TOPSIS score for each evaluated object.

[0269]

[0270] This scoring system comprehensively considers the ideal solution distance, weight, and consistency of various indicators, providing decision-makers with scientific decision support.

[0271] The TOPSIS evaluation algorithm ensures efficient evaluation under multi-dimensional indicators through the flexible application of dynamic ideal solutions, generalized distance measures, and combined weights, providing a solid methodological foundation for complex decision-making problems.

[0272] In this embodiment, constructing the Beta distribution density function in the theoretical distribution construction layer includes:

[0273] The formula for constructing the Beta distribution is as follows:

[0274]

[0275] Where x is one of the AHP score, FCE score, and TOPSIS score, x∈[0,1], and α and β are distribution parameters.

[0276]

[0277] The cumulative Beta distribution is given by the following formula:

[0278]

[0279] The formula for calculating quantiles is:

[0280] Q(p)=F -1 (p;α,β)={x|F(x;α,β)=p}

[0281] Preferably, constructing the score location calculation model in the absolute level evaluation layer includes:

[0282] The probability density discretization formula is as follows:

[0283]

[0284] The formula for calculating the density value sequence is:

[0285] Y = {y i =f(x) i ;α,β)|i=0,1,...,N-1}

[0286] The formula for calculating the score position is:

[0287]

[0288] The formula for calculating the quantitative rating score is as follows:

[0289]

[0290] Preferably, constructing a development potential calculation model includes:

[0291] The current position is determined by the following formula:

[0292] p c =P(x)

[0293] In the formula p c Current position;

[0294] The target threshold is determined by the following formula:

[0295] T(p c )=min{p∈{0.9,0.75,0.5,0.25}|p>p c}

[0296] In the formula, T(p) c ) is the target threshold;

[0297] The formula for calculating development distance is as follows:

[0298]

[0299] In the formula, Δ(x) represents the development distance;

[0300] The formula for calculating development potential score is as follows:

[0301]

[0302] In the formula, D(x) is the development potential score.

[0303] Preferably, the construction of the basic indicator calculation model in the comprehensive evaluation layer includes:

[0304] Basic computational ability assessment:

[0305]

[0306] Among them, C b Basic ability assessment, M=3, s i =L(x i ) score Let be the quantitative rating score of the i-th method, where the score is one of the AHP method, FCE method, and TOPSIS method;

[0307] Calculate the development potential score:

[0308]

[0309] In the formula, C p To score development potential, M=3, D(x) i ) is x i The development potential score of the location.

[0310] Calculate the balance score:

[0311]

[0312] Among them, C e For balance score,

[0313] Preferably, the formula for constructing the comprehensive score in the comprehensive evaluation layer is as follows:

[0314] S=w1C b +w2C p +w3C e

[0315] Where w1 = 0.5, w2 = 0.3, w3 = 0.2, C b Basic ability score, C p To score development potential, C e This is for the balance score.

[0316] Preferably, constructing a score feature analysis model in the feature analysis layer includes:

[0317] The formula for calculating the score dispersion is as follows:

[0318]

[0319] In the formula, σ s The score dispersion;

[0320] The formula for calculating the coefficient of variation is:

[0321]

[0322] In the formula, CV s is the coefficient of variation.

[0323] Preferably, constructing the feature analysis model in the feature analysis layer includes:

[0324] The formula for calculating the mean potential is:

[0325]

[0326] In the formula, This represents the average potential.

[0327] The formula for calculating the potential dispersion is as follows:

[0328]

[0329] In the formula, σ D Potential dispersion;

[0330] The formula for calculating the dominant development direction is as follows:

[0331] d * =argmax i {D(x i )}

[0332] In the formula, d * The dominant direction.

[0333] The aforementioned method achieves intelligent score grading by constructing a Beta distribution density function and calculating theoretical quantiles, ensuring the objectivity and credibility of the assessment results. Simultaneously, this method comprehensively considers basic capabilities and development potential, allowing for quantitative analysis of development potential. It comprehensively reflects the overall development status within the region and, through detailed data feature analysis, helps to deeply understand regional development differences, providing crucial support for policy formulation and resource allocation. Finally, the data provided has high credibility and reference value.

[0334] Example 2

[0335] This embodiment provides a multi-dimensional evaluation system for regional pumped storage development capacity based on data feature modeling and Beta distribution, including: a data input module, a data preprocessing module, a feature extraction and weight allocation module, a comprehensive evaluation model construction module, an intelligent grading and result output module, and a dynamic adjustment mechanism module.

[0336] The data input module is used to collect various indicators related to the development capacity of pumped storage, form raw indicator data, and send it to the data preprocessing module.

[0337] The data preprocessing module includes a data cleaning unit, a data standardization unit, and a data fusion unit. The data cleaning unit is responsible for removing invalid or erroneous raw indicator data; the data standardization unit converts raw indicator data from different sources into a unified format and unit; and the data fusion unit is responsible for integrating various raw indicator data types into a consistent dataset.

[0338] The feature extraction and weight allocation module is used to construct a judgment matrix based on the dataset to obtain the weights of each indicator. Unlike traditional methods, this invention does not rely on expert ratings to determine the weights, but automatically calculates the importance weights of each indicator through data analysis.

[0339] The comprehensive evaluation model construction module constructs a Beta distribution density function based on the AHP evaluation model, FCE evaluation model, and TOPSIS evaluation model to obtain an evaluation report.

[0340] The intelligent grading and result output module grades the data based on the evaluation report and generates charts from the evaluation report.

[0341] The dynamic adjustment mechanism module is used to update the original indicator data. This mechanism allows for self-updating based on the latest original indicator data and information, ensuring that the evaluation results always conform to the actual situation. This mechanism not only improves the timeliness of the evaluation, but also enhances the adaptability and flexibility of the evaluation method.

[0342] The system effectively organizes and standardizes relevant indicators through data input, preprocessing, and fusion modules, ensuring data accuracy and consistency. Secondly, the feature extraction and weight allocation module objectively determines the importance of each indicator by automatically analyzing data rather than relying on expert scoring, improving the scientific rigor of weight allocation. The comprehensive evaluation module combines AHP, FCE, and TOPSIS models, fully utilizing Beta distribution to generate accurate evaluation reports, coupled with intelligent grading and result output, intuitively displaying the evaluation results. Furthermore, a dynamic adjustment mechanism ensures the system can be updated in real time, always reflecting the latest situation. This not only enhances the timeliness and adaptability of the evaluation but also provides policymakers with more reliable decision support, contributing to the sustainable development of regional pumped storage.

[0343] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0344] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0345] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0346] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0347] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. A method for assessing regional pumped storage development capacity based on data feature modeling and Beta distribution, characterized in that, include: A scoring input layer for the scoring method is constructed, and various indicators related to the regional pumped storage development capacity are collected. The AHP method, FCE method and TOPSIS method are used to score each indicator to obtain the AHP score, FCE score and TOPSIS score. A theoretical distribution construction layer is constructed, specific distribution parameters are set for the AHP method, FCE method and TOPSIS method, the Beta distribution density function is constructed, and quantiles are generated. An absolute level assessment layer is constructed. Based on the AHP score, FCE score, and TOPSIS score, a score position calculation model is built to obtain the score position and quantitative rating score. Based on the score position, a development potential calculation model is built to obtain the development potential score. A comprehensive evaluation layer is constructed. Based on the quantitative rating scores and development potential scores of various indicators under the AHP method, FCE method and TOPSIS method, a basic indicator calculation model is built to obtain the basic capability score, development potential score and balance score, and then the weighted calculation is performed to obtain the comprehensive score. A feature analysis layer is constructed. Based on the quantitative rating scores of various indicators under the AHP, FCE and TOPSIS methods, a score feature analysis model is constructed to obtain the score dispersion and coefficient of variation. Based on the development potential scores of various indicators under the AHP, FCE and TOPSIS methods, a feature analysis model is constructed to obtain the potential mean, potential dispersion and dominant development direction. Constructing the absolute level assessment layer includes: Step 1: For a given score x, determine the score position. The probability density is discretized by dividing the interval [0,1] into N equal points. Calculate the density value sequence based on the equally divided [0,1] interval: Y={y i =f(x i ;a,b)|i=0,1,...,N-1} (5) Based on the density value sequence, determine the score position of score x: Based on the score position, a quantitative rating score is determined using the following method: The development potential calculation model includes: Based on the score position, the current position is determined: p c =P(x) (8) In the formula, p c Current position; Based on the current position, determine the target threshold: T(p c )=min{p∈{0.9,0.75,0.5,0.25}|p>p c } (9) In the formula, T is the target threshold; Based on the target threshold and the current position, the development distance is determined, and the formula for calculating the development distance is as follows: In the formula, Δ represents the development distance; Based on the development distance, a development potential score is determined, and the formula for calculating the development potential score is as follows: In the formula, D represents the development potential score; The scoring method's input layer includes indicators for development demand (A1), resource endowment (A2), economic carrying capacity (A3), and construction constraints (A4). Resource endowment (A2) includes a set of geographical condition assessment indicators, a set of power grid access condition indicators, and a set of transportation condition indicators; The construction constraint degree (A4) includes a set of spatial constraint indicators, a set of population density constraint indicators, and a set of load constraint indicators.

2. The method for assessing regional pumped storage development capacity based on data feature modeling and Beta distribution according to claim 1, characterized in that, The theoretical distribution construction layer includes: Step 1: Construct the Beta distribution: Where x is one of the AHP score, FCE score and TOPSIS score, x∈[0,1], B(α,β) represents the Beta function, and α and β are distribution parameters; Setting specific distribution parameters for the AHP, FCE, and TOPSIS methods includes: AHP method: f AHP (x)=f(x;4,2) FCE method: f FCE (x) = f(x; 3, 3) TOPSIS method: f TOPSIS (x) = f(x; 2, 4); Step 2: Quantile Calculation Construct the cumulative distribution function, the formula of which is: In the formula, F represents the cumulative distribution function; Calculate the quantiles, using the following formula: Q(p)=F -1 (p;α,β)={x|F(x;α,β)=p} (3) In the formula, Q represents the quantile.

3. The method for assessing regional pumped storage development capacity based on data feature modeling and Beta distribution according to claim 1, characterized in that, The construction of the basic indicator calculation model in the comprehensive evaluation layer includes: Step 1: Construct a basic indicator system Calculate the mean of the quantitative rating scores from each rating method to serve as the baseline competency score: Among them, C b Basic ability assessment, M=3, s i =L(x i ) score Let be the quantitative rating score of the i-th method, where the score is one of the AHP method, FCE method, and TOPSIS method; Calculate the average development potential score for each scoring method: In the formula, C p To score development potential, M=3, D(x) i ) is x i The development potential score of the location; Calculate the balance score: Among them, C e For balance score, 4. The method for assessing regional pumped storage development capacity based on data feature modeling and Beta distribution according to claim 3, characterized in that, The formula for constructing the comprehensive score in the comprehensive evaluation layer is as follows: S=w1C b +w2C p +w3C e (15) Where S represents the overall score, w1 = 0.5, w2 = 0.3, w3 = 0.2, and C b Basic ability score, C p To score development potential, C e This is for the balance score.

5. The method for assessing regional pumped storage development capacity based on data feature modeling and Beta distribution according to claim 3, characterized in that, The construction of the score feature analysis model in the feature analysis layer includes: Calculate the score dispersion: In the formula, σ s The score dispersion; The formula for calculating the coefficient of variation is: In the formula, CV s is the coefficient of variation.

6. The method for assessing regional pumped storage development capacity based on data feature modeling and Beta distribution according to claim 3, characterized in that, The construction of the feature analysis model in the feature analysis layer includes: The formula for calculating the mean potential is: In the formula, This represents the average potential. The formula for calculating the potential dispersion is as follows: In the formula, σ D Potential dispersion; The formula for calculating the dominant development direction is as follows: d * =argmax i {d(x i )} (20) In the formula, d * The dominant direction.

7. A regional pumped storage development capacity assessment system based on data feature modeling and Beta distribution, characterized in that, This method is used to perform the regional pumped storage development capacity assessment method based on data feature modeling and Beta distribution as described in any one of claims 1-6.

Images