Evaluation method, system and device based on power market comprehensive evaluation index system
Through the combination of hierarchical analysis method, CRITIC method and VIKOR method, a comprehensive evaluation index system for the power market was constructed, which solved the problem that the existing technology could not comprehensively evaluate the operating conditions of the power market, and achieved market structure, transaction transparency, operational efficiency and Effective assessment of carbon emissions provides important decision-making guidance.
Patent Information
- Application Number
- CN202410978697.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-22
- Publication Date
- 2024-11-22
AI Technical Summary
The existing technology lacks a comprehensive evaluation index system to evaluate the market structure, market transaction transparency, operational efficiency, carbon emissions and information disclosure of the power market, and cannot fully reflect the operating conditions of the power market.
The hierarchical analysis method, CRITIC method and cooperative game combination empowerment method are used, and the VIKOR method of gray theory and prospect theory is combined to build a comprehensive evaluation index system based on the power market, calculate subjective and objective weights, and conduct a comprehensive evaluation of the power market.
A comprehensive assessment of the operating conditions of the power market is achieved, information loss and decision-maker risk preferences are taken into account, important theoretical guidance is provided, and the evaluation efficiency and accuracy of the power market is improved.
Smart Images

Figure CN119005779A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to an evaluation method, and more specifically to an evaluation method, system and device based on a comprehensive evaluation index system of an electricity market. Background Art
[0002] With the continuous advancement of power market reform, establishing a reasonable power market evaluation system to reflect the problems in market construction and operation has become the focus of the industry. The marketization of the power market faces market construction needs such as optimizing market structure, improving market transaction transparency, improving market operation efficiency, reducing carbon emissions, and increasing information disclosure. It is very necessary to design an indicator system including five dimensions of "structure-price-efficiency-low carbon-information" to reflect the market structure characteristics, market transaction conditions, market operation efficiency, carbon emissions, and information disclosure of the power market. However, there is currently no evaluation method for the indicator system including the five dimensions of "structure-price-efficiency-low carbon-information" to evaluate the power market. Summary of the invention
[0003] In view of the shortcomings of the prior art, the purpose of the present invention is to provide an evaluation method, system and device based on the comprehensive evaluation index system of the power market, which combines the analytic hierarchy process (AHP) and the CRITIC method, adopts the VIKOR method based on grey theory and prospect theory to conduct a comprehensive evaluation of the power market.
[0004] To achieve the above object, the present invention provides the following technical solution: an evaluation method based on a comprehensive evaluation index system of the power market, characterized in that it comprises the following steps:
[0005] Step 1: Calculate subjective weights using the analytic hierarchy process, which includes target layer A, criterion layer B and criterion layer C. Target layer A is the overall goal of the evaluation, with "optimal operation of the power market" as the goal; criterion layer B is the five aspects of the structure level, price-volume relationship, efficiency level, low-carbon development and information disclosure under the overall goal; criterion layer C is the specific indicators under each aspect of criterion layer B;
[0006] Step 2: Calculate the objective weight using the CRITIC method. The CRITIC method determines the indicator weight through two factors: one is the comparison strength expressed by the standard deviation. The larger the standard deviation, the greater the comparison strength; the other is the indicator conflict degree expressed by the correlation coefficient. The larger the correlation coefficient, the weaker the conflict degree.
[0007] Step 3: Obtain the subjective weight calculated in step 1, obtain the objective weight calculated in step 2, and calculate the comprehensive weight using the cooperative game combination weighting method based on the subjective weight and the objective weight;
[0008] Step 4: Based on the comprehensive weights obtained in step 3, the VIKOR evaluation method based on grey theory and prospect theory is used to evaluate the power market.
[0009] As a further improvement of the present invention, the specific steps of calculating the subjective weight using the hierarchical analysis method in step 1 are as follows:
[0010] Step 1, the specific steps of using the hierarchical analysis method to calculate the subjective weight in step 1 are as follows:
[0011] Step 1: Construct a judgment matrix to confirm the relative importance of each indicator in each layer, and assign values from 1 to 9. The matrix is as follows:
[0012]
[0013] Step 1 and 2: Calculate the geometric mean of each row of the judgment matrix H And normalize it to get the relative weight of each evaluation index The specific formula is as follows:
[0014]
[0015] In the formula, h ij is the element of the judgment matrix, r is the dimension of the judgment matrix;
[0016] Step 13: Perform consistency check on the judgment matrix constructed in step 11 to determine whether there is a contradiction in the evaluation process of step 11, such as indicator 1 is more important than indicator 2, indicator 2 is more important than indicator 3, and indicator 3 is more important than indicator 1. The specific details are shown in the following formula:
[0017]
[0018] Among them, τ is the maximum characteristic root of the judgment matrix H, CI is the consistency index, CR is the consistency ratio, RI is the random consistency index, and when CR < 0.1, the consistency test is passed;
[0019] Step 14: Based on the relative weights of each indicator generated in the second step in the corresponding layer, the global subjective weight W of each indicator can be calculated. Sj , the calculation formula is as follows:
[0020] w sj =w CjBi × BiA
[0021] Among them: the i-th indicator in the criterion layer C belongs to the j-th aspect in the criterion layer B, W CiBjrepresents the weight of the i-th indicator in the criterion layer C relative to the j-th aspect in the criterion layer B, W BjA represents the weight of the jth aspect in the criterion layer B relative to the target layer A.
[0022] As a further improvement of the present invention, the specific steps of calculating the objective weight using the CRITIC method in step 2 are as follows:
[0023] Step 21: Standardize the data. The specific method is as follows: Assuming that there are m samples available and n evaluation indicators, the range standardization method of the data is shown in the following formula:
[0024]
[0025] M=max{a-min{X ij},max{X ij}-b} (3)
[0026]
[0027] Among them, X ij , Y ij They represent the original data and standardized data of the i-th sample on the j-th indicator, respectively. maxj is the maximum value of the jth index, X minj is the minimum value of the jth indicator. Formula (1) and (2) are the normalized formulas for positive and negative indicators respectively. Formula (3) and (4) are the normalized formulas for interval indicators. [a, b] is the optimal interval of interval indicators, a = 0, b = 1, and the following normalized matrix Y is obtained:
[0028]
[0029] Step 22: Calculate the contrast intensity CS of each indicator j , the calculation formula is as follows:
[0030]
[0031] Among them, σ j With CS j represents the standard deviation and contrast strength of the jth indicator, Y ij is the value of the jth indicator corresponding to the i-th sample;
[0032] Step 2 and 3: Calculate the conflict degree R of each indicator j , the calculation formula is as follows:
[0033]
[0034] Where: r jkis the correlation coefficient between index j and index k, is the standardized value of index j, is the normalized value of index k;
[0035] Step 2 and 3: Calculate the information carrying capacity of each indicator. The calculation formula is as follows:
[0036] CA j =CS j *R j
[0037] Among them: CA j It represents the information content of the jth indicator. The more information indicator j contains, the more important it is in the evaluation indicator system, and the greater the weight it is assigned.
[0038] Step 24: Calculate the objective weight w oj , the calculation formula is as follows:
[0039]
[0040] Among them, CA j Represents the information amount of the j-th indicator.
[0041] As a further improvement of the present invention, the specific steps of calculating the comprehensive weight using the cooperative game combination weighting method in step 3 are as follows:
[0042] Step 3.1: Construct the deviation minimization objective function:
[0043]
[0044] Among them, φ s ,φ o are the combination coefficients of subjective weight and objective weight respectively. When l=s, When l=O, is the transpose of the subjective weight, is the transpose of the objective weight;
[0045] Step 3.2: Construct a linear system of equations:
[0046]
[0047] Among them, w S is the subjective weight, w o is the objective weight;
[0048] Step 33: Normalize the combination coefficient. The calculation formula is as follows:
[0049]
[0050] in, are the normalized combination coefficients of subjective weight and objective weight respectively;
[0051] Step 3 and 4, calculate the combined weight w, the calculation formula is as follows:
[0052]
[0053] As a further improvement of the present invention, the specific steps of using the VIKOR evaluation method to evaluate the power market in step 4 are as follows:
[0054] Step 41, calculate the grey correlation coefficient between each index and the maximum value of the index;
[0055] Step 42, calculating the comprehensive prospect matrix of prospect theory based on the grey correlation coefficient calculated in step 41;
[0056] Step 43: Based on the calculation of step 42, the comprehensive prospect matrix is obtained, and the VIKOR method is used to sort it, determine the optimal compromise solution, and complete the evaluation of the power market.
[0057] As a further improvement of the present invention, the specific steps of calculating the grey correlation coefficient between each index and the maximum value of the index in step 41 are as follows:
[0058] Step 4: Define the mother sequence as the maximum value of each index in the standardized matrix, as shown in the following formula:
[0059] Step 4.12: Calculate the grey correlation coefficient, as shown in the following formula:
[0060]
[0061] In the formula, ρ represents the resolution coefficient, which is generally taken as ρ=0.5.
[0062] As a further improvement of the present invention, the specific steps of calculating the comprehensive prospect matrix of prospect theory in step 42 are as follows:
[0063] Step 421, calculate the value function v(η) by the following formula:
[0064]
[0065] Among them, α and β are the gain and loss sensitivity coefficients, and λ is the loss aversion coefficient, α=0.88, β=0.88, λ=2.25, represents the reference value of the jth indicator;
[0066] Step 422, calculate the decision weight function using the following formula:
[0067]
[0068] Among them, θ and δ are risk attitude coefficients, w j is the combined weight of the previous text, θ = 0.61, δ = 0.69
[0069] Step 423, calculate the comprehensive prospect value matrix V:
[0070]
[0071] Among them, v ij is the comprehensive prospect value, is the revenue value, is the loss value, is the decision weight of the benefit, is the decision weight of the loss.
[0072] As a further improvement of the present invention, the specific steps of using the VIKOR method to sort in step 43 are as follows:
[0073] Step 431: Determine the positive ideal solution and negative ideal solution of the comprehensive prospect value matrix. The specific formula is as follows:
[0074]
[0075]
[0076] Step 432: Calculate the group effect value. The specific formula is as follows:
[0077]
[0078] Step 433, calculate the individual regret value, the specific formula is as follows:
[0079]
[0080] Step 434: Calculate the comprehensive evaluation value. The specific formula is as follows:
[0081]
[0082] Among them, Q i The smaller it is, the better the power market operation is, and the higher the ranking is. ξ is the decision coefficient, and ξ=0.5 is taken to take into account both group utility maximization and individual regret minimization. + , Z - , D + , D - They are the maximum and minimum group utility values and the maximum and minimum individual regret values under the VIKOR method respectively;
[0083] Step 4, 3, and 5: Sample selection and comparison to determine the optimal compromise solution. The specific method is: i , D i , Q i Sort the values from small to large, select Q i The top two A 1 , A 2 As an alternative, it is considered optimal when it meets the following two conditions;
[0084] Q 1 , Q 2 The first and second Qs are ranked i value;
[0085] A 1 In Z i , D i It is also the first in the ranking.
[0086] Another aspect of the present invention provides an online evaluation system for power market, characterized by comprising:
[0087] Data acquisition module, used to obtain historical data of the power market;
[0088] The weight calculation module is used to calculate the weight of each indicator in the evaluation indicator system;
[0089] The result evaluation module is used to analyze and sort the evaluation results calculated based on historical data.
[0090] On the other hand, the present invention provides an online electricity market evaluation device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, it implements the online electricity market evaluation method as described in any one of claims 1 to 8.
[0091] The beneficial effects of the present invention are as follows: the present invention constructs an evaluation matrix using various indicators of the operation of the power market, adopts the subjective weight of the hierarchical analysis method and the objective weighting method of the CRITIC method, and combines the weights based on the cooperative game theory method. The VIKOR method based on the grey theory and prospect theory is constructed, making the grey correlation an important tool for measuring the operation of the power market, taking full account of the reduction of information loss and the full use of original data, and introducing the decision-making preferences of decision makers when facing uncertain risks, thereby providing important theoretical guidance for the decision-making of the power market, thus realizing the evaluation of the power market in a simple and effective way. BRIEF DESCRIPTION OF THE DRAWINGS
[0092] Figure 1 The module block diagram of the online evaluation system for the electricity market;
[0093] Figure 2 The block diagram of the online evaluation device for the electricity market. DETAILED DESCRIPTION
[0094] The present invention will be further described in detail with reference to the given embodiments below.
[0095] This embodiment is an evaluation method based on the comprehensive evaluation index system of the power market, starting from optimizing the market structure, stimulating the activity of market players, enhancing the transparency of market transactions, improving the efficiency of market operation, strengthening the control of market risks, and reducing carbon emissions. Construct an index system for comprehensive evaluation of the Inner Mongolia power market in five aspects, including structure, price-volume relationship, efficiency, low-carbon development, and information disclosure, as shown in the following table:
[0096]
[0097]
[0098] After the comprehensive evaluation index system of the power market is constructed, the evaluation of the power market is achieved through the following steps:
[0099] Step 1: Calculation of subjective weights based on analytic hierarchy process
[0100] The Analytic Hierarchy Process (AHP) was proposed by Professor TLSaaty, an American operations researcher, in the 1970s. The basic idea is to classify and hierarchize each indicator, then compare the importance of indicators in the same level, and finally quantify and calculate the weight of each indicator. Usually AHP has three levels. The target level A is the overall goal of the evaluation. This model takes "optimal operation of the electricity market" as the goal; the criterion level B is several aspects divided under the overall goal. The criterion level B of this model includes five aspects: structural level, price-volume relationship, efficiency level, low-carbon development, and information disclosure; the criterion level C is the specific indicator under each aspect of the criterion level B. The specific calculation steps of AHP are as follows:
[0101] (1) Constructing a judgment matrix
[0102] First, we consulted with relevant professionals and experts and scholars to confirm the relative importance of each indicator at each level, and assigned values from 1 to 9. The corresponding meanings of the values are shown in the following table:
[0103] Table 3-1 AHP importance scale and its corresponding meaning
[0104]
[0105] According to the importance scale value, the judgment matrix between each indicator under each criterion layer can be established, as shown in formula (1):
[0106]
[0107] (2) Calculate relative weights using the square root method
[0108] Calculate the geometric mean of each row of the judgment matrix H And normalize it to get the relative weight of each evaluation index As shown in formula (2) and formula (3):
[0109]
[0110] (3)Consistency test
[0111] The consistency test of the judgment matrix is used to determine whether there is a contradiction in the evaluation process of the first step, such as indicator 1 is more important than indicator 2, indicator 2 is more important than indicator 3, and indicator 3 is more important than indicator 1.
[0112]
[0113] Among them, τ is the maximum eigenvalue root of the judgment matrix H, CI is the consistency index, CR is the consistency ratio, RI is the random consistency index, and when CR < 0.1, the consistency test is passed.
[0114] (4) Calculate the subjective weight of each indicator
[0115] According to the relative weight of each indicator in its own layer, the global subjective weight w of each indicator can be calculated. sj , the calculation formula is as follows:
[0116] w sj =w CjBi × BiA (6)
[0117] Among them: the jth indicator in the indicator layer C belongs to the i-th aspect in the criterion layer B, w CjBi represents the weight of the jth indicator in the indicator layer C relative to the ith aspect in the criterion layer B, w BiA represents the weight of the i-th aspect in the criterion layer B relative to the target layer A.
[0118] Step 2: Objective weight calculation based on CRITIC method
[0119] In terms of the calculation of objective weights, considering the limited scale of the data collected this time, it is not appropriate to use methods such as principal component analysis that require a large amount of data support. At the same time, compared with the entropy weight method and the variance method, the CRITIC method comprehensively considers the impact of the degree of variation of the indicator on the weight and the conflict between the indicators. Therefore, this embodiment uses the CRITIC method as the calculation method of the objective weight. The CRITIC method mainly determines the indicator weight through two factors. One is the contrast intensity expressed by the standard deviation. The larger the standard deviation, the greater the contrast intensity; the other is the degree of indicator conflict expressed by the correlation coefficient. The larger the correlation coefficient, the stronger the conflict. The specific calculation steps of the CRITIC method are as follows:
[0120] (1) Data standardization
[0121] Assuming that there are m samples available and n evaluation indicators, the range standardization method of the data is shown in equations (7) and (8).
[0122]
[0123] M=max{a-min{X ij},max{X ij}-b}(9)
[0124]
[0125] Among them, X ij , Y ij They represent the original data and the standardized data of the i-th sample on the j-th indicator, respectively. Standardization can help eliminate symbols and dimensions and unify the data range, which is convenient for subsequent calculations. Formula (7) and Formula (8) are the standardized formulas for positive indicators and negative indicators, respectively. Formula (9) and Formula (10) are the standardized formulas for interval indicators. [a, b] is the optimal interval of interval indicators, a = 0, b = 1.
[0126] Get the normalized matrix Y
[0127]
[0128] (2) Comparative strength of each indicator CS j
[0129]
[0130] Among them, σ j With CS j represents the standard deviation and contrast strength of the jth indicator, Y ij is the value of the jth indicator corresponding to the ith sample.
[0131] (3) Conflict degree R of each indicatorj
[0132]
[0133] Where: r jk is the correlation coefficient between index j and index k, is the standardized value of index j, is the normalized value of index k.
[0134] (4) Information carrying capacity of each indicator CA j
[0135] CA j =CS j *R j (15)
[0136] Among them: CA j It represents the amount of information of the jth indicator. The more information indicator j contains, the more important it is in the evaluation index system and the greater the weight assigned to it.
[0137] (5) Objective weight w oj
[0138]
[0139] Step 3: Calculation of comprehensive weight based on cooperative game
[0140] In order to complement the subjective weight method to reasonably reflect the opinions of experts and scholars and the objective weight method to reflect the advantages of objective data information, the evaluation model will use a comprehensive weight method that combines subjective and objective weights to calculate the weights of each indicator. This embodiment is based on the idea of cooperative game, combining the subjective weight method of the hierarchical analysis method and the objective weight method of the CRITIC method to construct a game combination weighting method. The calculation method of the cooperative game combination weighting method is as follows:
[0141] (1) Deviation minimization objective function
[0142]
[0143] Among them, φ s ,φ o are the combination coefficients of subjective weight and objective weight respectively. When l=s, When l=o, is the transpose of the subjective weight, is the transpose of the objective weights.
[0144] (2) Linear equations
[0145]
[0146] (3) Normalization of combination coefficients
[0147]
[0148] in, are the normalized combination coefficients of subjective weight and objective weight respectively.
[0149] (4) Combination weight w
[0150]
[0151] Step 4: VIKOR evaluation method based on grey theory and prospect theory
[0152] This embodiment constructs a VIKOR method based on grey theory and prospect theory to conduct a comprehensive evaluation and analysis of the operation status of the power market. The traditional VIKOR method is a compromise sorting method that ranks limited decision-making options with the goal of maximizing the group effect value and minimizing the individual regret value, but it ignores the risk preference of decision makers. This embodiment introduces grey theory and prospect theory, making the grey correlation coefficient an important tool for measuring the operation status of the power market, and fully considering the reduction of information loss and the full utilization of original data. At the same time, the introduction of prospect theory can take into account the decision preferences of decision makers when facing uncertainty risks, thereby providing important theoretical guidance for decision-making in the power market.
[0153] (1) Calculate the grey correlation coefficient matrix between each index and the maximum value of the index
[0154] 1 Define the parent sequence as the maximum value of each index in the standardized matrix
[0155]
[0156] 2 Calculate the grey correlation coefficient
[0157]
[0158] Here, ρ represents the resolution coefficient, which is generally taken as ρ=0.5.
[0159] (2) Calculate the comprehensive prospect matrix of prospect theory
[0160] Kahneman and Tversky (1979) proposed the prospect theory, which takes into account the limited rationality and subjective preferences of decision makers and avoids the influence of subjective judgment on decision results to a certain extent. In the cumulative prospect theory, the prospect value is calculated by the value function and the weight function.
[0161] 1 Value function v(η)
[0162]
[0163] The value function reflects the risk preference of the power market operator, α and β are the profit and loss sensitivity coefficients, and λ is the loss aversion coefficient, α = 0.88, β = 0.88, λ = 2.25 (Kahneman and Tversky, 1979). Represents the reference value of the jth indicator. The reference point plays a vital role in the decision-making process because decision makers are more concerned about the difference between the results and expectations. In order to more fully consider the risk attitude of decision makers, this embodiment draws on Wu et al. (2019) to use the positive ideal solution of the grey correlation coefficient as the reference point of the loss function to calculate the negative prospect value, and the negative ideal solution as the reference point of the benefit function to calculate the positive prospect value. The positive ideal solution represents the optimal solution for each indicator. When it is used as a reference point, if the actual grey correlation coefficient does not reach the positive ideal solution, then there is a certain "loss". According to the loss aversion principle of prospect theory, decision makers may be more willing to take risky actions and try to adjust various indicators to make the actual grey correlation coefficient closer to the positive ideal solution. The negative ideal solution represents the worst solution for each indicator, that is, there may be unstable electricity prices and poor information disclosure quality in the power market. When it is used as a reference point, if the actual grey correlation coefficient is better than the worst state of the power market, then the decision maker will see potential "benefits". The calculation formulas for the positive ideal solution and the negative ideal solution are as follows:
[0164]
[0165] 2 Decision Weight Function
[0166]
[0167] Among them, θ and δ are risk attitude coefficients, w j is the combined weight of the previous text, θ = 0.61, δ = 0.69 (Kahneman and Tversky, 1979).
[0168] 3 Calculate the comprehensive prospect value matrix V
[0169] The comprehensive prospect value takes into account the asymmetric response of decision makers to gains and losses. The higher the comprehensive prospect value, the better the operating status of the electricity market.
[0170]
[0171] Among them, v ij is the comprehensive prospect value, is the revenue value, is the loss value, is the decision weight of the benefit, is the decision weight of the loss.
[0172] (3) Sorting using the VIKOR method
[0173] 1. Determine the positive and negative ideal solutions of the comprehensive prospect value matrix
[0174]
[0175] 2 Calculate the group effect value
[0176]
[0177] 3 Calculate individual regret value
[0178]
[0179] 4 Calculate the comprehensive evaluation value
[0180]
[0181] Among them, Q i The smaller it is, the better the power market operation is, and the higher the ranking is. ξ is the decision coefficient, and ξ=0.5 is taken to take into account both group utility maximization and individual regret minimization. + , Z - , D + , D - They are the maximum and minimum group utility values and the maximum and minimum individual regret values under the VIKOR method respectively.
[0182] 5. Sample selection and comparison to determine the optimal compromise solution
[0183] According to Z i , D i , Q i Sort the values from small to large. Select Q i The top two A 1 , A 2 As an alternative, it is considered optimal when the following two conditions are met.
[0184] 1 Q 1 , Q 2 The first and second Qs are ranked i value.
[0185] A 1 In Z i , D i It is also the first in the ranking.
[0186] This embodiment provides the following calculation examples
[0187] The implementation process of the power market operation evaluation is to first construct an evaluation matrix using various indicators of power market operation, and use the subjective weight of the hierarchical analysis method and the objective weighting method of the CRITIC method, and combine the weighting based on the cooperative game theory method, and finally use the VIKOR method based on grey theory and prospect theory to comprehensively evaluate the power market. The example selects a regional power market as the research object. This paper selects data from January to March 2023 for analysis. By processing and mining the original data, the initial values of each indicator in this article can be obtained.
[0188] 4.1 Subjective weight calculation based on analytic hierarchy process
[0189] This paper invites 10 power market and scientific research and education experts to participate in the construction of the judgment matrix in the hierarchical analysis method, and compares them pairwise according to their importance. After effectively collecting the questionnaires, the relevant questionnaires obtained are sorted and analyzed, and then the AB and BC judgment matrices can be gradually obtained according to the expert evaluation results.
[0190] A total of 10 questionnaires were distributed this time, and 10 valid questionnaires were collected by combining online and offline methods. After analyzing the results of the questionnaire survey, this paper chose to use the arithmetic average method. According to the established power market evaluation index system, the hierarchical analysis method was used to establish the power market judgment matrix at different levels, and the weight values were calculated respectively. The results are shown in Table 3. The results show that the indicators at the information disclosure level B5 have the highest subjective weight in the evaluation system, followed by the indicators at the efficiency level B3.
[0191] Table 3 Subjective weights of the power market evaluation index system based on the analytic hierarchy process
[0192]
[0193]
[0194] 4.2 Objective weight calculation based on CRITIC method
[0195] For quantitative evaluation methods, the most widely used one is the hierarchical analysis, which has the defect of strong subjectivity, and the evaluation accuracy is insufficient when one of the methods is used as an evaluation method alone. Therefore, it is necessary to increase the application of objective weighting method in power market evaluation. Combining the hierarchical analysis method can take into account the advantages of subjective and objective weighting methods to obtain more reasonable indicator weights. This paper adopts the CRITIC method as the calculation method of objective weights. The CRITIC method mainly determines the indicator weights through two factors. One is the contrast intensity expressed by the standard deviation. The larger the standard deviation, the greater the contrast intensity; the other is the indicator conflict degree expressed by the correlation coefficient. The larger the correlation coefficient, the stronger the conflict degree. This paper uses the CRITIC method to obtain the objective weights of the power market evaluation indicator system as shown in Table 4. The results show that the efficiency level indicators (C5 and C6) have the highest objective weight in the evaluation system, especially the electricity price change rate C5, which reaches 39%.
[0196] Table 4 Objective weights of the power market evaluation index system based on the CRITIC method
[0197]
[0198]
[0199] 4.3 Comprehensive weight calculation based on cooperative game
[0200] In view of the fact that AHP is too subjective due to its over-reliance on evaluators, and the problem that the CRITIC method simply considers sample data and ignores the relative importance of indicators, this paper combines subjective and objective weights. AHP is used to subjectively weight the power market operation evaluation indicators, and the CRITIC method is used to objectively weight the power market operation evaluation indicators. This method effectively avoids the limitations of the single subjective weighting method of the power market operation evaluation indicators. In the power market operation evaluation indicators of this paper, it can ensure that the evaluation results are consistent with the actual situation, and it can also better reflect the actual situation of the experts' evaluation of the power market operation. The specific method is to use MALTAB to solve the combination coefficient and obtain the weight combination coefficient of each group. The comprehensive weight values of indicators based on game theory are shown in Table 5. The results show that the efficiency level indicators (C5 and C6) have the highest combined weight in the evaluation system, among which the electricity price change rate C5 accounts for 28%, the electricity change rate C6 accounts for 11%, and the weight of the information disclosure level (C9 and C10) accounts for the second largest proportion.
[0201] Table 4 Combination weights of the power market evaluation index system based on cooperative game
[0202]
[0203]
[0204] 4.4 VIKOR method for power market evaluation based on grey theory and prospect theory
[0205] This paper introduces the grey theory and prospect theory, fully considers the information loss and the risk preference of decision makers, and uses the VIKOR method to comprehensively evaluate the development level of the power market. This evaluation reflects the operation status of the power market, provides theoretical guidance for the decision-making of the power market, and guides the healthy operation of the power market.
[0206] According to the standardized matrix of each indicator of the power market and formula (23), the grey correlation coefficient matrix of each indicator is obtained:
[0207]
[0208] According to the positive ideal solution, negative ideal solution, equation (24) and equation (25) of the grey correlation coefficient matrix, we can obtain the profit matrix V + And the loss matrix V - :
[0209]
[0210] According to the combination weight w and formula (26), the decision weight of the profit matrix and the decision matrix of the loss matrix are obtained:
[0211] π + =(0.14,0.15,0.13,0.14,0.31,0.19,0.15,0.17,0.22,0.19)
[0212] π - =(0.12,0.13,0.11,0.12,0.32,0.18,0.13,0.15,0.20,0.17)
[0213] According to formula (28), the comprehensive prospect value matrix is obtained:
[0214]
[0215] According to equations (29) and (30), the positive ideal solution and negative ideal solution of the comprehensive prospect value matrix are calculated:
[0216] S j + =(0.10,0.11,0.09,0.10,0.22,0.13,0.11,0.12,0.15,0.13)
[0217] S j - =(-0.18,-0.21,-0.16,-0.19,-0.50,-0.28,-0.21,-0.23,-0.32,-0.27)
[0218] According to equations (31) to (33), the group utility value Z, individual regret value D and comprehensive evaluation value Q are calculated. The results are shown in Table 5.
[0219] Table 5 VIKOR summary of power market evaluation
[0220] VIKOR Q Ranking Z Ranking D Ranking January 0.75 3 0.40 2 0.28 3 February 0.70 2 0.72 3 0.14 2 March 0.00 1 0.07 1 0.03 1
[0221] Taking the evaluation results of the power market transactions from January to March as an example, the results are shown in the table above. The power market evaluation values of March and February ranked first and second respectively, and the difference in their power market evaluation values ΔQ>0.5, and the Q, D, and Z rankings in March were all 1. Therefore, the comprehensive operation of the power market in March was the best. The comprehensive operation of the power market in February was second, with Q ranking 2, Z ranking 3, and D ranking 2. The comprehensive operation of the power market in January was the worst, with Q ranking 3, Z ranking 2, and D ranking 3. In addition, the operation of the power market needs to comprehensively consider five aspects: market structure, market transaction fluctuations, market efficiency, green and low-carbon, and information disclosure, in order to achieve the purpose of improving the operation effect of the power market, preventing power market risks, and ensuring the smooth operation of the power market. At the same time, we should focus on improving the efficiency of power market operations, reducing the volatility of electricity prices and electricity, improving the timeliness of market information disclosure, and expanding information disclosure channels.
[0222] In this embodiment, if Figure 1 As shown, an online evaluation system for the power market equipped with the above evaluation method is provided, and the system includes:
[0223] Data acquisition module, used to obtain historical data of the power market;
[0224] The weight calculation module is used to calculate the weight of each indicator in the evaluation indicator system;
[0225] The result evaluation module is used to analyze and sort the evaluation results calculated based on historical data.
[0226] Based on the above system, Figure 2 As shown, this embodiment further provides an online electricity market evaluation device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the above-mentioned online electricity market evaluation method is executed to realize the evaluation of the electricity market.
[0227] In summary, the evaluation method based on the comprehensive evaluation index system of the power market in this embodiment designs an evaluation index system for the operation of the power spot market according to the operation characteristics of the centralized power spot market in the pilot areas of my country, and effectively discovers problems existing in the operation of the spot market from multiple dimensions, providing guarantee for the safe, stable, economical and efficient operation of the spot market. The power spot market monitoring and evaluation analysis system based on the index system has been applied in multiple spot markets and has achieved good results.
[0228] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technicians in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.
Claims
1. An evaluation method based on a comprehensive evaluation index system for the power market, characterized in that: The steps include: Step 1: Calculate subjective weights using the analytic hierarchy process, which includes target layer A, criterion layer B and criterion layer C. Target layer A is the overall goal of the evaluation, with "optimal operation of the power market" as the goal; criterion layer B is the five aspects of the overall goal, namely, the structural level, price-volume relationship, efficiency level, low-carbon development and information disclosure; criterion layer C is the specific indicators under each aspect of criterion layer B; Step 2: Calculate the objective weight using the CRITIC method. The CRITIC method determines the indicator weight through two factors: one is the comparison strength expressed by the standard deviation. The larger the standard deviation, the greater the comparison strength; the other is the indicator conflict degree expressed by the correlation coefficient. The larger the correlation coefficient, the weaker the conflict degree. Step 3: Obtain the subjective weight calculated in step 1, obtain the objective weight calculated in step 2, and calculate the comprehensive weight using the cooperative game combination weighting method based on the subjective weight and the objective weight; Step 4: Based on the comprehensive weights obtained in step 3, the VIKOR evaluation method based on grey theory and prospect theory is used to evaluate the power market.
2. The evaluation method based on the comprehensive evaluation index system of the power market according to claim 1 is characterized by: The specific steps of calculating the subjective weight using the hierarchical analysis method in step 1 are as follows: Step 1: Construct a judgment matrix to confirm the relative importance of each indicator in each layer, and assign values from 1 to 9. The matrix is as follows: Step 1 and 2: Calculate the geometric mean of each row of the judgment matrix H And normalize it to get the relative weight of each evaluation index The specific formula is as follows: In the formula, h ij is the element of the judgment matrix, r is the dimension of the judgment matrix; Step 13: Perform consistency check on the judgment matrix constructed in step 11 to determine whether there is a contradiction in the evaluation process of step 11, such as indicator 1 is more important than indicator 2, indicator 2 is more important than indicator 3, and indicator 3 is more important than indicator 1. The specific details are shown in the following formula: Among them, τ is the maximum characteristic root of the judgment matrix H, CI is the consistency index, CR is the consistency ratio, RI is the random consistency index, and when CR < 0.1, the consistency test is passed; Step 14: Based on the relative weights of each indicator generated in the second step in the corresponding layer, the global subjective weight W of each indicator can be calculated. Sj , the calculation formula is as follows: In sj =in CjBi ×in BiA Among them: the i-th indicator in the criterion layer C belongs to the j-th aspect in the criterion layer B, W CiBj represents the weight of the i-th indicator in the criterion layer C relative to the j-th aspect in the criterion layer B, W BjA represents the weight of the jth aspect in the criterion layer B relative to the target layer A.
3. The evaluation method based on the comprehensive evaluation index system of the power market according to claim 2 is characterized by: The specific steps of calculating the objective weight using the CRITIC method in step 2 are as follows: Step 21: Standardize the data. The specific method is as follows: Assuming that there are m samples available and n evaluation indicators, the range standardization method of the data is shown in the following formula: M=max{a-min{X ij },max{X ij }-b} (3) Among them, X ij , Y ij They represent the original data and standardized data of the i-th sample on the j-th indicator, respectively. maxj is the maximum value of the jth index, X minj is the minimum value of the jth indicator. Formula (1) and (2) are the normalized formulas for positive and negative indicators respectively. Formula (3) and (4) are the normalized formulas for interval indicators. [a, b] is the optimal interval of interval indicators, a = 0, b = 1, and the following normalized matrix Y is obtained: Step 22: Calculate the contrast intensity CS of each indicator j , the calculation formula is as follows: Among them, σ j With CS j represents the standard deviation and contrast strength of the jth indicator, Y ij is the value of the jth indicator corresponding to the i-th sample; Step 2 and 3: Calculate the conflict degree R of each indicator j , the calculation formula is as follows: Where: r jk is the correlation coefficient between index j and index k, is the standardized value of index j, is the normalized value of index k; Step 2 and 3: Calculate the information carrying capacity of each indicator. The calculation formula is as follows: THAT j =CS j *R j Among them: CA j It represents the information content of the jth indicator. The more information indicator j contains, the more important it is in the evaluation indicator system, and the greater the weight it is assigned. Step 24: Calculate the objective weight w oj , the calculation formula is as follows: Among them, CA j Represents the information amount of the j-th indicator.
4. The evaluation method based on the comprehensive evaluation index system of the power market according to claim 3 is characterized by: The specific steps of calculating the comprehensive weight using the cooperative game combination weighting method in step 3 are as follows: Step 3.1: Construct the deviation minimization objective function: Among them, φ s ,φ o are the combination coefficients of subjective weight and objective weight respectively. when is the transpose of the subjective weight, is the transpose of the objective weight; Step 3.2: Construct a linear system of equations: Among them, w s is the subjective weight, w o is the objective weight; Step 33: Normalize the combination coefficient. The calculation formula is as follows: in, are the normalized combination coefficients of subjective weight and objective weight respectively; Step 3 and 4, calculate the combined weight w, the calculation formula is as follows:
5. The evaluation method based on the comprehensive evaluation index system of the power market according to claim 4 is characterized by: The specific steps of using the VIKOR evaluation method to evaluate the power market in step 4 are as follows: Step 41, calculate the grey correlation coefficient between each index and the maximum value of the index; Step 42, calculating the comprehensive prospect matrix of prospect theory based on the grey correlation coefficient calculated in step 41; Step 43: Based on the calculation of step 42, the comprehensive prospect matrix is obtained, and the VIKOR method is used to sort it, determine the optimal compromise solution, and complete the evaluation of the power market.
6. The evaluation method based on the comprehensive evaluation index system of the power market according to claim 5 is characterized by: The specific steps of calculating the grey correlation coefficient between each index and the maximum value of the index in step 4-1 are as follows: Step 4: Define the mother sequence as the maximum value of each index in the standardized matrix, as shown in the following formula: Step 4.12: Calculate the grey correlation coefficient, as shown in the following formula: In the formula, ρ represents the resolution coefficient, which is generally taken as ρ=0.
5.
7. The evaluation method based on the comprehensive evaluation index system of the power market according to claim 6 is characterized by: The specific steps of calculating the comprehensive prospect matrix of prospect theory in step 42 are as follows: Step 421, calculate the value function v(η) by the following formula: Among them, α and β are the gain and loss sensitivity coefficients, and λ is the loss aversion coefficient, α=0.88, β=0.88, λ=2.25, represents the reference value of the jth indicator; Step 422, calculate the decision weight function using the following formula: Among them, θ and δ are risk attitude coefficients, w j is the combined weight of the previous text, θ = 0.61, δ = 0.69 Step 423, calculate the comprehensive prospect value matrix V: Among them, v ij is the comprehensive prospect value, is the revenue value, is the loss value, is the decision weight of the benefit, is the decision weight of the loss.
8. The evaluation method based on the comprehensive evaluation index system of the power market according to claim 7 is characterized by: The specific steps of using the VIKOR method to sort in step 43 are as follows: Step 431: Determine the positive ideal solution and negative ideal solution of the comprehensive prospect value matrix. The specific formula is as follows: Step 432: Calculate the group effect value. The specific formula is as follows: Step 433, calculate the individual regret value, the specific formula is as follows: Step 434: Calculate the comprehensive evaluation value. The specific formula is as follows: Among them, Q i The smaller it is, the better the power market operation is, and the higher the ranking is. ξ is the decision coefficient, and ξ=0.5 is taken to take into account both group utility maximization and individual regret minimization. + , Z - , D + , D - They are the maximum and minimum group utility values and the maximum and minimum individual regret values under the VIKOR method respectively; Step 4, 3, and 5: Sample selection and comparison to determine the optimal compromise solution. The specific method is: i , D i , Q i Sort the values from small to large, select Q i The top two options A1 and A2 are considered as alternatives and are considered optimal when they meet the following two conditions: Q 1 , Q 2 The first and second Qs are ranked i value; A1 in Z i , D i It is also the first in the ranking.
9. An online evaluation system for power market, characterized in that: include: Data acquisition module, used to obtain historical data of the power market; The weight calculation module is used to calculate the weight of each indicator in the evaluation indicator system; The result evaluation module is used to analyze and sort the evaluation results calculated based on historical data.
10. An online evaluation device for power market, characterized in that: The invention comprises a processor, a memory and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, the online electricity market evaluation method according to any one of claims 1 to 8 is implemented.
Citation Information
Cited By
Filling false roof reinforcement optimization method
CN120782327A
