Electric power market operation effect evaluation method based on sparrow search algorithm

Abstract

The invention discloses an electricity market operation effect evaluation method based on a sparrow search algorithm, and belongs to the technical field of electricity markets. In order to solve the problems that a traditional index system fusion technology is high in subjectivity, complex in calculation and simplified in relation and quantitative analysis cannot be conducted on the current market, a total evaluation layer, an evaluation layer and a specific description layer are designed through five first-level indexes including the market structure, the economical efficiency, the safety, the social welfare and the link friendliness; the indexes are fused from three dimensions of time, region and industry, the index system construction is completed, and the method is simple and effective. Various power market operation data of different types and different regions are effectively processed through a sparrow search algorithm; meanwhile, an index system is designed through three levels and three dimensions, the index system serves as the basis, first-level indexes serve as fitness functions, index weights are optimized, the defect that quantitative analysis cannot be conducted on the current market is overcome, and an artificial intelligence methodology and a tool box can be provided for decision making in the aspects of the electricity market and the like.

Description

Technical Field

[0001] The present invention belongs to the technical field of power market, and in particular relates to a method for evaluating the effectiveness of power market operation based on a sparrow search algorithm. Background Art

[0002] The importance of the evaluation method for the effectiveness of electricity market operations is reflected in the following aspects: (1) providing market operation data to support policy making with empirical data; (2) through evaluation, market supervision can be strengthened to ensure the fairness, transparency and stability of the electricity market and prevent market manipulation and unfair competition; (3) the evaluation method helps to identify inefficient links in market operation, optimize resource allocation and improve the operating efficiency of the electricity market; (4) the evaluation results can provide risk warnings for market participants, helping them to adjust their strategies in a timely manner and avoid potential risks; (5) the evaluation method can continuously monitor market changes and provide a basis for the continuous optimization and improvement of market mechanisms; (6) a fair and transparent evaluation mechanism can enhance the public's trust in the electricity market and promote social harmony and sustainable development.

[0003] Traditional indicator system fusion technology mainly relies on linear weighting method, analytic hierarchy process (AHP) and fuzzy comprehensive evaluation method. These methods determine the weight of each indicator through expert scoring or historical data, and then perform linear combination. However, these technologies have problems such as strong subjectivity, complex calculations, and inability to fully reflect the complex relationship between multiple indicators. They are difficult to adapt to the needs of dynamically changing environments. There is an urgent need for smarter and more optimized fusion methods to improve the scientificity and accuracy of the indicator system. Summary of the invention

[0004] In view of the problems that traditional indicator system fusion technology is highly subjective, computationally complex, and has simplified relationships, and that the current market cannot be quantitatively analyzed, the present invention provides a method for evaluating the effectiveness of power market operations based on a sparrow search algorithm, which can solve the two problems faced by traditional multi-source data fusion methods for evaluating the effectiveness of power market operations: (1) traditional indicator system fusion technology is highly subjective, computationally complex, and has simplified relationships; (2) the current market cannot be quantitatively analyzed; in addition, it can also provide an artificial intelligence methodology and toolbox for decision-making in power markets and even economic policies, market planning, etc. to a certain extent.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A method for evaluating the effectiveness of power market operation based on a sparrow search algorithm, the method comprising the following steps:

[0007] Step S1: extract indicators and decompose them into 5 first-level indicators, 17 second-level indicators, 40 third-level indicators, and 116 fourth-level indicators;

[0008] Step S2: Obtain 116 fourth-level indicators, where all the fourth-level indicators are quantifiable data, summarize them into 40 third-level indicators based on the fourth-level indicators, and determine the weights;

[0009] Furthermore, the specific operations of step S2 are:

[0010] Step S2.1: Use formula (1) to obtain the power generation enterprise structure index a 11 , use formula (2) to obtain the structure index a of the power sales company 12 , use formula (3) to obtain the power user structure index a 13 , use formula (4) to obtain the trading product indicator a 21 , use formula (5) to obtain the trading mode indicator a 22 , use formula (6) to obtain the transaction price index a 23 , use formula (7) to obtain the grid scale index a 31 , use formula (8) to obtain the grid structure index a 32 , use formula (9) to obtain the inter-regional power flow index a 33 ; The formula is as follows:

[0011]

[0012] In the formula, a 111 represents the installed capacity ratio, a 112 represents the proportion of power generation, a 113 represents the number of power generation enterprises, a 114 represents the size distribution, a 115 represents market share, both are level 4 indicators; w 11i is the weight;

[0013]

[0014] In the formula, a 121 represents the number of electricity sales companies, a 122 represents the market share, a 123 Indicates power diversity, all are four-level indicators; w 12i is the weight;

[0015]

[0016] In the formula, a 131 represents the proportion of industrial users, a 132 represents the proportion of commercial users, a 133 represents the proportion of residential users, a 134 Indicates the proportion of other users, all of which are level 4 indicators; w 13i is the weight;

[0017]

[0018] In the formula, a 211 Indicates medium- to long-term transactions, a 212 Indicates spot trading, a 213 Indicates auxiliary services, all of which are level 4 indicators; w 21i is the weight;

[0019]

[0020] In the formula, a 221 Indicates bilateral negotiation, a 222 represents centralized bidding, a 223 Indicates listing transaction, a 224 Indicates matching transactions, all are level 4 indicators; w 22i is the weight;

[0021]

[0022] In the formula, a 231 represents price convergence, a 232 Indicates the price fluctuation range, both are four-level indicators; 23i is the weight;

[0023]

[0024] In the formula, a 311 represents the total installed capacity, a 312 Indicates the maximum load, a 313 represents the annual power generation, a 314 Indicates annual electricity consumption, all of which are level 4 indicators; w 31i is the weight;

[0025]

[0026] In the formula, a 321 Indicates the voltage level distribution, a 322 Indicates power supply reliability, a 323 Indicates automation coverage, both are level 4 indicators; w 32i is the weight;

[0027]

[0028] In the formula, a 331 Indicates cross-region transactions, a 332 Indicates inter-provincial transactions, a 333 Indicates channel utilization, a 334 Indicates price linkage, both are level 4 indicators; w 33i is the weight;

[0029] Step S2.2: Use formula (10) to obtain the market clearing indicator b 11 , use formula (11) to obtain the resource optimization allocation efficiency b 12 , use formula (12) to obtain the power generation cost index b 21 , use formula (13) to obtain the electricity user cost index b 22 , use formula (14) to obtain the market competition behavior index b 23 , use formula (15) to obtain the employment and tax contribution index b 31 , use formula (16) to obtain the energy structure adjustment index b 32 ; The formula is as follows:

[0030]

[0031] Where b 111 Indicates the cleared power, b 112 represents the clearing price, b 113 represents the theoretical optimal price, b 114 Indicates the deviation, b 115 Indicates the effectiveness of clearing, all are level 4 indicators;

[0032]

[0033] Where b 121 represents the utilization rate of the generator set, b 122 represents the grid load rate, b 123 represents the clean energy consumption rate, b 124 Indicates the utilization rate of system spare capacity, both are level 4 indicators;

[0034]

[0035] Where b 211 represents the fuel cost, b 212 represents the operation and maintenance cost, b 213 It represents depreciation and amortization, which are all level 4 indicators;

[0036]

[0037] Where b 221 represents the average electricity price, b 222 Indicates the proportion of output value, b 223 Indicates the sensitivity of electricity prices, both are level 4 indicators;

[0038] b 23 =b 23 (14)

[0039] Where b 23 Indicates manipulative behavior, a level 4 indicator;

[0040]

[0041] Where b 311 Indicates employment pull, b 312 Indicates tax revenue, all are level 4 indicators;

[0042]

[0043] Where b 321 represents the energy consumption intensity, b 322 Indicates carbon emission intensity, all are four-level indicators;

[0044] Step S2.3: Use formula (17) to obtain the power supply and demand balance index c 11 , use formula (18) to obtain the reserve capacity adequacy index c 12 , use formula (19) to obtain the power shortage warning and response index c 13 , use formula (20) to obtain the system frequency stability index c 21 , use formula (21) to obtain the voltage qualification rate c 22 , use formula (22) to obtain the power grid failure rate and recovery index c 23 , use formula (23) to obtain the transaction default rate c 31 , use formula (24) to obtain the power grid peak load capacity index c 32 ; The formula is as follows:

[0045]

[0046] In the formula, c 111 represents the load factor, c 112 Indicates the supply-demand balance rate, both are level 4 indicators;

[0047]

[0048] In the formula, c 121 represents the ratio of standby capacity to maximum load, c 122 Indicates the ability to cope with unexpected load fluctuations, both are level 4 indicators;

[0049]

[0050] In the formula, c 131 represents the uncertainty of new energy, c 132 Indicates the margin of the power system, both are level 4 indicators;

[0051] c 21 =w 211 ×(1-c 211 / max(c 211 ))+w 212×(1 / c 212 ) (20)

[0052] In the formula, c 211 Indicates the fluctuation range, c 212 Indicates the recovery speed, all are level 4 indicators;

[0053]

[0054] In the formula, c 221 Indicates the voltage deviation rate, c 222 Indicates the percentage of qualified voltage, all of which are level 4 indicators;

[0055]

[0056] In the formula, c 231 represents the failure rate, c 232 Indicates the recovery speed, all are level 4 indicators;

[0057]

[0058] In the formula, c 311 represents the default rate of transaction contract, c 312 represents the default rate of electricity consumption, c 313 represents the payment default rate, c 314 represents the default rate of the subject, c 315 It represents the delayed delivery default rate, both of which are level 4 indicators;

[0059]

[0060] In the formula, c 321 represents the theoretical peak load regulation capability, c 322 Indicates peak load margin, all are level 4 indicators;

[0061] Step S2.4: Use formula (25) to obtain the residential electricity price to income ratio d 11 , use formula (26) to obtain the user satisfaction survey d 12 , use formula (27) to obtain the energy consumption per unit GDP d 21 , use formula (28) to obtain the energy efficiency improvement project d 22 , use formula (29) to obtain the power coverage rate d 31 , use formula (30) to obtain the electricity poverty alleviation rate d 32 , use formula (31) to obtain the employment d in the power industry 41 , use formula (32) to obtain the contribution rate of the power industry to GDP d 42 ; The formula is as follows:

[0062]

[0063] Where, d 111 represents the electricity price burden rate, d 112 represents the electricity price-to-income ratio, d 113 Indicates the electricity price elasticity coefficient, both are level 4 indicators;

[0064]

[0065] Where, d 121 represents the electricity price perceived burden rate, d 122 represents the electricity price rationality index, d 123 Indicates satisfaction with electricity price transparency, d 124 Indicates satisfaction with the cost-effectiveness of electricity prices, both are four-level indicators;

[0066]

[0067] Where, d 211 represents the energy consumption of GDP in each region, d 212 Indicates the energy consumption per unit of GDP of the industry, all of which are level 4 indicators;

[0068]

[0069] Where, d 221 Indicates the energy saving rate, d 222 Indicates the power saving rate, d 223 Indicates emission reduction rate, all are level 4 indicators;

[0070]

[0071] Where, d 311 represents the regional coverage, d 312 It represents the rural access rate, both are level 4 indicators;

[0072]

[0073] Where, d 321 represents the electricity price fairness index, d 322 It indicates the impact of electricity price adjustment on the poverty line, both are level 4 indicators;

[0074]

[0075] Where, d 411 represents the employment growth rate, d 412 represents per capita output value, d 413 represents labor productivity, d 414 Indicates job vacancy rate, both are level 4 indicators; 41i is the weight;

[0076]

[0077] Where, d 421 Indicates the proportion of GDP, d 422 Denotes the contribution rate to GDP growth, d 423 represents the tax contribution rate, both of which are level 4 indicators; w 42i is the weight;

[0078] Step S2.5: Use formula (33) to obtain the fair competition environment index e 11 , use formula (34) to obtain the clean energy incentive mechanism e 12 , using formula (35) to obtain the transmission and distribution price transparency e 21 , use formula (36) to obtain the power grid investment efficiency index e 22 , use formula (37) to obtain the openness of the electricity sales market e 31 , use formula (38) to obtain the user selection guarantee e 32 , use formula (39) to obtain the user's electricity price tolerance e 41 , use formula (40) to obtain the degree of user participation in the market e 42 ; The formula is as follows:

[0079]

[0080] In the formula, e 111 represents the growth rate of new power generation market share, e 112 represents the average bidding success rate, e 113 It indicates the ratio of differentiated electricity prices for homogeneous products, and both are level 4 indicators;

[0081]

[0082] In the formula, e 121 Indicates return on investment ROI, e 122 represents the subsidy coverage rate, e 123 Indicates the rate of increase in percentage, both are level 4 indicators;

[0083]

[0084] In the formula, e 211 represents the electricity price structure disclosure rate, e 212 represents the accessibility index of electricity price documents, e 213 Indicates the efficiency of resolving electricity price disputes, both are level 4 indicators;

[0085]

[0086] In the formula, e 221 represents the growth rate of transmission capacity, e 222 Indicates power supply reliability, all are level 4 indicators;

[0087]

[0088] In the formula, e 311 represents the subject diversity index, e 312 represents the competition ratio, e 313 Indicates cross-provincial and cross-region transaction currencies, all of which are level 4 indicators;

[0089]

[0090] In the formula, e 321 represents the degree of freedom of choice, e 322 Indicates the efficiency of handling user complaints, both are level 4 indicators;

[0091]

[0092] In the formula, e 411 represents the sensitivity of electricity price, e 412 represents the electricity price burden index, e 413 It represents the income elasticity of electricity price, and both are level 4 indicators;

[0093]

[0094] In the formula, e 421 represents the participation rate in electricity trading, e 422 represents the user-side response activity participation rate, e 423 Indicates the optimization adjustment ratio of user load curve, both are level 4 indicators;

[0095] The weights at each level are assigned initial values ​​using expert scoring, entropy weight method or sparrow search algorithm.

[0096] Step S3: Summarize the third-level indicators into 17 second-level indicators and determine the weights;

[0097] Furthermore, the specific operations of step S3 are:

[0098] The extracted third-level indicators are summarized to obtain 17 second-level indicators. The steps are as follows:

[0099] Step S3.1: Use formula (41) to obtain the market entity structure index a1, use formula (42) to obtain the market transaction structure index a2, and use formula (43) to obtain the power grid structure index a3; the formula is as follows:

[0100]

[0101] In the formula, a 11 represents the structural index of power generation enterprises, a 12 represents the structural index of the power sales company, a 13 Represents the structure index of power users, all of which are third-level indexes; w1i is the weight;

[0102]

[0103] In the formula, a 21 Indicates the trading product indicator, a 22 Represents a trading mode indicator, a 23 Indicates transaction price indicators, all of which are level 3 indicators; 2i is the weight;

[0104]

[0105] In the formula, a 31 represents the grid scale index, a 32 Represents the grid structure index, a 33 It represents the proportion of residential users in the inter-regional power flow index, which are all third-level indicators; 3i is the weight;

[0106] Step S3.2: Use formula (44) to obtain the market clearing index b1, use formula (45) to obtain the resource optimization allocation efficiency b2, and use formula (46) to obtain the power generation cost index b3;

[0107]

[0108] Where b 11 represents the market clearing indicator, b 12 Indicates the efficiency of resource optimization allocation, both are third-level indicators;

[0109]

[0110] Where b 21 represents the power generation cost index, b 22 represents the electricity user cost index, b 23 Indicates market competition behavior indicators, all of which are level 3 indicators;

[0111]

[0112] Where b 31 represents employment and tax contribution indicators, b 32 Indicates energy structure adjustment indicators, all of which are level 3 indicators;

[0113] Step S3.3: Use formula (47) to obtain the power supply and demand security index c1, use formula (48) to obtain the power grid operation security index c2, and use formula (49) to obtain the market transaction security index c3; the formula is as follows:

[0114]

[0115] In the formula, c 11 represents the power supply and demand balance index, c 12 represents the reserve capacity adequacy index, c 13 It represents the power shortage warning and response indicators, both of which are level 3 indicators;

[0116]

[0117] In the formula, c 21 Represents the system frequency stability index, c 22 Indicates the voltage qualification rate index, c 23 Indicates the power grid failure rate and recovery index, both of which are level 3 indicators;

[0118]

[0119] In the formula, c 31 represents the transaction default rate indicator, c 32 Indicates the peak load regulation capability index of power grid, all of which are level 3 indexes;

[0120] Step S3.4: Use formula (50) to obtain the electricity price affordability and user satisfaction index d1, use formula (51) to obtain energy efficiency and energy saving consumption d2, use formula (52) to obtain electricity service popularization and social equity d3, and use formula (53) to obtain employment and economic benefit index d4; the formula is as follows:

[0121]

[0122] Where, d 11 represents the ratio of residential electricity price to income, d 12 It represents the user satisfaction survey, both of which are level 3 indicators;

[0123]

[0124] Where, d 21 represents the energy consumption per unit of GDP, d 22 Indicates energy efficiency improvement projects, all of which are level 3 indicators;

[0125]

[0126] Where, d 31 represents the electricity coverage rate, d 32 It represents the electricity poverty alleviation rate, both are level 3 indicators;

[0127]

[0128] Where, d 41 represents employment in the power industry, d 42 Indicates the contribution rate of the power industry to GDP, both are third-level indicators;4i is the weight;

[0129] Step S3.5: Use formula (54) to obtain the friendly index e1 of the power generation link, use formula (55) to obtain the friendly index e2 of the power transmission and distribution link, use formula (56) to obtain the friendly index e3 of the power sales link, and use formula (57) to obtain the friendly index e4 of the power consumption link;

[0130]

[0131] In the formula, e 11 represents the level playing field indicator, e 12 Indicates clean energy incentive mechanism, all are level 3 indicators;

[0132]

[0133] In the formula, e 21 Indicates the transparency of transmission and distribution prices, e 22 Represents the power grid investment efficiency index, all of which are level 3 indicators;

[0134]

[0135] In the formula, e 31 represents the openness of the electricity sales market, e 32 Indicates the protection of user choice rights, all of which are level 3 indicators;

[0136]

[0137] In the formula, e 41 Indicates the user's ability to bear electricity prices, e 42 Indicates the degree of user participation in the market, both are level 3 indicators;

[0138] The weights at each level are assigned initial values ​​using expert scoring, entropy weight method or sparrow search algorithm;

[0139] Step S4: sort out all the secondary indicators, take 5 primary indicators as the evaluation layer, and 116 fourth-level indicators as the specific description layer, collect and sort out data from three dimensions: time dimension, industry dimension and region dimension, and integrate the data to construct the overall evaluation layer of the power market, assign weights to the indicators at each level, and complete the calculation of the overall evaluation layer score;

[0140] Furthermore, the specific operations of step S4 are:

[0141] Step S4.1: Construct the overall evaluation layer of the power market. The total score is shown in formula (58):

[0142]

[0143] In the formula, i corresponds to a, b, c, d, and e, five first-level indicators. a represents the market structure indicator, b represents the market economy indicator, c represents the market security indicator, d represents the market social welfare indicator, and e represents the market link friendliness indicator; w i is the weight;

[0144] The above weights are assigned using the sparrow search algorithm, and the fitness function is designed with five primary indicators as shown in formula (59):

[0145]

[0146] Step S4.2: Calculate the fitness value using the Sparrow algorithm and optimize the weight using an iterative formula. The iterative formula is shown in (60):

[0147]

[0148] In the formula, X best (t) is the current best position, that is, the optimal weight, is a normally distributed random number with mean 0 and variance 1, X i (t) is the current position in round t, i.e., the weight; It represents the normal distribution with parameters lb and ub. According to the indicators, you can set the lower bound of the parameter as lb and the upper bound as ub. N represents the population size of the sparrow algorithm.

[0149] Compared with the prior art, the present invention has the following advantages:

[0150] Different from the existing technology, the present invention can effectively optimize weights and improve fusion accuracy through the sparrow search algorithm. It is widely used and adaptable to diversified indicator systems, thereby improving decision-making effects. Through the power market operation effectiveness evaluation method, it effectively combines the multi-source data fusion mechanism and can process various types of power market data. The evaluation method given by the indicator system can provide artificial intelligence methodology and toolbox for policy formulation and rule adjustment in the national power market. BRIEF DESCRIPTION OF THE DRAWINGS

[0151] Figure 1 It is a sparrow search algorithm flow chart of a method for evaluating the effectiveness of power market operation based on a sparrow search algorithm provided by the present invention;

[0152] Figure 2 The present invention provides a flow chart of a power market operation effectiveness evaluation method based on a sparrow search algorithm. DETAILED DESCRIPTION

[0153] In order to gain a deeper understanding of the present invention, we will provide a comprehensive and detailed description of the present invention. However, the present invention has multiple implementations and is not limited to the specific examples listed herein. The presentation of these examples is intended to deepen the comprehensive understanding of the disclosure of the present invention.

[0154] Example 1

[0155] (1) Experimental data

[0156] Taking the total score of the total evaluation layer as an example, the evaluation method of power market operation effectiveness based on the sparrow search algorithm is studied; the research data includes 5 first-level indicators, and the corresponding weights are assigned by average weight distribution and sparrow search algorithm;

[0157] (2) Experimental process

[0158] The total score of the overall evaluation layer is calculated using the following steps:

[0159] Step S1: Obtain 116 fourth-level indicators, where all the fourth-level indicators are quantifiable data, and summarize them into 40 third-level indicators based on the fourth-level indicators, and determine the weights; summarize them into 17 second-level indicators based on the third-level indicators, and determine the weights; organize all the second-level indicators and summarize them into 5 first-level indicators as the evaluation layer.

[0160] Step S2: Use the sparrow search algorithm to assign weights to the indicators at each level and complete the total score calculation of the overall evaluation layer;

[0161] Step S2.1: Initialize the population (116 four-level indicators); set the population size N, the maximum number of iterations T = 100, the weight range [lb, ub] = [0, 1], the safety threshold ST, and the discoverer ratio r; randomly generate the same number of sparrow positions (weight vectors) as the population size, and each position contains the weights of 116 four-level indicators;

[0162] Step S2.2: Define a fitness function with five primary indicators to evaluate the quality of each sparrow position; wherein the fitness function is defined as formula (59):

[0163]

[0164] In formula (59), i corresponds to a, b, c, d, and e, five first-level indicators. a represents the market structure indicator, b represents the market economy indicator, c represents the market security indicator, d represents the market social welfare indicator, and e represents the market link friendliness indicator. All of the above can be calculated using the formula;

[0165] Step S2.3: Calculate the fitness value using formula (61):

[0166] fitness j =f(Xj )for j=1,2,…,N (61)

[0167] In formula (61), j corresponds to N sparrow positions (weight vectors), X j represents the position of the jth sparrow;

[0168] Step S2.4: Sorting to determine the weight of a certain level of indicators; sorting by fitness value, the first P sparrows are discoverers, and the rest are joiners;

[0169] Step S2.5: Update the weight of the next level indicator; according to the update rules of the discoverer and the joiner, update the weight of the next level indicator respectively. Use formula (62) to calculate the proportion of discoverers:

[0170]

[0171] The finder position is calculated using formula (63):

[0172]

[0173] In formula (63), β is a random variable, is a normally distributed random number with a mean of 0 and a variance of 1, and ST is the safety threshold;

[0174] Use formula (60) to calculate the joiner position:

[0175]

[0176] Step S2.6: Update the next level fitness function; use the updated weight vector to recalculate the fitness value;

[0177] Step S2.7: Check convergence or number of iterations; check whether the algorithm has converged or reached the maximum number of iterations. If it has converged or reached the maximum number of iterations, go to step S28; otherwise, return to step S24 to continue iterating;

[0178] Step S2.8: Output the weight vectors of the first-level, second-level, third-level, and fourth-level indicators;

[0179] Step S2.9: Calculate the total score of the total evaluation layer using formula (58):

[0180]

[0181] The experimental results of this embodiment are shown in Table 1, which respectively test the results of using average weight distribution and sparrow search algorithm to assign values. The values ​​of the secondary indicators obtained by using the average distribution weights are: market entity structure index a1=0.75, market transaction structure index a2=0.63, power grid structure index a3=0.47, market efficiency index b1=0.72, cost-effectiveness index b2=0.62, social and economic contribution index b3=0.47, power supply and demand security index c1=0.81, power grid operation safety index c2=0.82, market transaction security index c3=0.54, electricity price affordability and user satisfaction index d1=0.52, energy efficiency and energy saving consumption d2=0.62, power service popularization and social equity d3=0.49, employment and economic benefit index d4=0.79, power generation link friendliness index e1=0.32, transmission and distribution link friendliness index e2=0.81, power sales link friendliness index e3=0.77, power consumption link friendliness index e4=0.76. The values ​​of the secondary indicators obtained by the sparrow search algorithm are as follows: market entity structure index a1=0.85, market transaction structure index a2=0.65, power grid structure index a3=0.46, market efficiency index b1=0.73, cost-effectiveness index b2=0.72, social and economic contribution index b3=0.45, power supply and demand security index e1=0.81, power grid operation safety index c2=0.85, market transaction security index c3=0.55, electricity price affordability and user satisfaction index d1=0.52, energy efficiency and energy saving consumption d2=0.72, power service popularization and social equity d3=0.50, employment and economic benefit index d4=0.81, power generation link friendliness index e1=0.31, transmission and distribution link friendliness index e2=0.77, power sales link friendliness index e3=0.79, power consumption link friendliness index e4=0.74.

[0182] Table 1 Comparison of different weight distribution methods for the total score of the overall evaluation layer

[0183]

[0184] The experiment shows that the sparrow search algorithm shows higher accuracy and stability in the overall evaluation score compared with the average weight distribution scheme. In order to verify the overall effectiveness, the two experiments used different weight distribution methods. From Table 1, it can be found that the sparrow search algorithm can more accurately reflect the relative importance of each indicator and improve the effectiveness of the evaluation system.

[0185] Example 2

[0186] (1) Experimental data

[0187] Taking the market efficiency score of the total evaluation layer as an example, the evaluation method of power market operation effectiveness based on the sparrow search algorithm is studied; the research data includes two first-level indicators, and the corresponding weights are assigned by average weight distribution and sparrow search algorithm;

[0188] (2) Experimental process

[0189] The market efficiency score of the overall evaluation layer is calculated using the following steps:

[0190] Step S1: Obtain 52 fourth-level indicators, where all the fourth-level indicators are quantifiable data, and summarize them into 16 third-level indicators based on the fourth-level indicators, and determine the weights; summarize them into 6 second-level indicators based on the third-level indicators, and determine the weights; organize all the second-level indicators and summarize them into 2 first-level indicators as the evaluation layer.

[0191] Step S2: Use the sparrow search algorithm to assign weights to the indicators at each level to complete the calculation of the market efficiency score of the overall evaluation layer;

[0192] Step S2.1: Initialize the population (52 four-level indicators); set the population size N, the maximum number of iterations T = 100, the weight range [lb, ub] = [0, 1], the safety threshold ST, and the discoverer ratio r; randomly generate the same number of sparrow positions (weight vectors) as the population size, and each position contains the weights of 52 four-level indicators;

[0193] Step S2.2: define a fitness function with two first-level indicators to evaluate the quality of each sparrow position; wherein the fitness function is defined as formula (59);

[0194] Step S2.3: Calculate the fitness value using formula (61);

[0195] Step S2.4: Sorting to determine the weight of a certain level of indicators; sorting by fitness value, the first P sparrows are discoverers, and the rest are joiners;

[0196] Step S2.5: Update the weight of the next level indicator; according to the update rules of the discoverer and the joiner, update the weight of the next level indicator respectively. Use formula (62) to calculate the proportion of discoverers P; use formula (63) to calculate the discoverer position; use formula (60) to calculate the joiner position;

[0197] Step S2.6: Update the next level fitness function; use the updated weight vector to recalculate the fitness value;

[0198] Step S2.7: Check convergence or number of iterations; check whether the algorithm has converged or reached the maximum number of iterations. If it has converged or reached the maximum number of iterations, go to step S28; otherwise, return to step S24 to continue iterating;

[0199] Step S2.8: Output the weight vectors of the first-level, second-level, third-level, and fourth-level indicators;

[0200] Step S2.9: Calculate the market efficiency score of the overall evaluation layer using formula (64):

[0201]

[0202] In formula (64), i corresponds to a and b, two first-level indicators. a represents the market structure indicator and b represents the market economy indicator. The above can be calculated using the formula to obtain the market efficiency score s. ab .

[0203] The experimental results of this embodiment are shown in Table 2, which respectively test the results of using average weight distribution and sparrow search algorithm assignment. The values ​​of the secondary indicators obtained by using average weight distribution are: market subject structure index a1 = 0.75, market transaction structure index a2 = 0.63, power grid structure index a3 = 0.47, market efficiency index b1 = 0.72, cost-effectiveness index b2 = 0.62, and social and economic contribution index b3 = 0.47. The values ​​of the secondary indicators obtained by using the sparrow search algorithm are: market subject structure index a1 = 0.85, market transaction structure index a2 = 0.65, power grid structure index a3 = 0.57, market efficiency index b1 = 0.62, cost-effectiveness index b2 = 0.89, and social and economic contribution index b3 = 0.49.

[0204] Table 2 Comparison of different weight allocation methods for market efficiency scores at the overall evaluation level

[0205] Indicator a Index b <![CDATA[Weight w a > <![CDATA[Weight w b > Market efficiency score Average weight distribution 0.72 0.80 0.50 0.50 0.76 Sparrow search algorithm 0.82 0.81 0.63 0.37 0.82

[0206] The experiment shows that the sparrow search algorithm significantly improves the discrimination and reliability of the evaluation score. In order to verify the overall effectiveness, the two experiments used different weight allocation methods. From Table 2, it can be found that the sparrow search algorithm can provide decision makers with a more scientific and reasonable evaluation basis, verifying its superiority in the evaluation of complex market environments.

[0207] Example 3

[0208] (1) Experimental data

[0209] Taking the fairness and competition score of the overall evaluation layer as an example, the evaluation method of power market operation effectiveness based on the Mahjong Soso algorithm is studied; the research data includes 1 first-level indicator, and the corresponding weight is 1;

[0210] (2) Experimental process

[0211] The fairness and competition score for the overall evaluation layer is calculated using the following steps:

[0212] Step S1: Obtain 22 fourth-level indicators, where all the fourth-level indicators are quantifiable data, summarize them into 8 third-level indicators based on the fourth-level indicators, and determine the weights; summarize them into 4 second-level indicators based on the third-level indicators, and determine the weights; organize all the second-level indicators and summarize them into 1 first-level indicator as the evaluation layer.

[0213] Step S2: Assign weights to the indicators at each level to complete the calculation of fairness and competition scores at the overall evaluation level;

[0214] Step S2.1: Initialize the population (22 four-level indicators); set the population size N, the maximum number of iterations T = 100, the weight range [lb, ub] = [0, 1], the safety threshold ST, and the discoverer ratio r; randomly generate the same number of sparrow positions (weight vectors) as the population size, and each position contains the weights of 22 four-level indicators;

[0215] Step S2.2: define a fitness function with two first-level indicators to evaluate the quality of each sparrow position;

[0216] Among them, the fitness function is defined as formula (59);

[0217] Step S2.3: Calculate the fitness value using formula (61);

[0218] Step S2.4: Sorting to determine the weight of a certain level of indicators; sorting by fitness value, the first P sparrows are discoverers, and the rest are joiners;

[0219] Step S2.5: Update the weight of the next level indicator; according to the update rules of the discoverer and the joiner, update the weight of the next level indicator respectively. Use formula (62) to calculate the proportion of discoverers P; use formula (63) to calculate the discoverer position; use formula (60) to calculate the joiner position;

[0220] Step S2.6: Update the next level fitness function; use the updated weight vector to recalculate the fitness value;

[0221] Step S2.7: Check convergence or number of iterations; check whether the algorithm has converged or reached the maximum number of iterations. If it has converged or reached the maximum number of iterations, go to step S28; otherwise, return to step S24 to continue iterating;

[0222] Step S2.8: Output the weight vectors of the first-level, second-level, third-level, and fourth-level indicators;

[0223] Step S2.9: Calculate the fairness and competition score of the overall evaluation layer using formula (65):

[0224] s e =w e ×e (65)

[0225] In formula (65), e represents the market link friendliness index, which can be calculated using the formula to obtain the fairness and competition score s e .

[0226] The experimental results of this embodiment are shown in Table 3, which respectively test the results of using average weight distribution and sparrow search algorithm assignment. The values ​​of the secondary indicators obtained by using average weight distribution are: power generation link friendliness index e1 = 0.32, power transmission and distribution link friendliness index e2 = 0.81, power sales link friendliness index e3 = 0.77, and power consumption link friendliness index e4 = 0.76. The values ​​of the secondary indicators obtained by using the sparrow search algorithm are: power generation link friendliness index e1 = 0.52, power transmission and distribution link friendliness index e2 = 0.83, power sales link friendliness index e3 = 0.79, and power consumption link friendliness index e4 = 0.78.

[0227] Table 3 Comparison of different weight distribution methods for fairness and competition scores in the overall evaluation layer

[0228] Indicator <![CDATA[Weight w e > Fairness and Competition Score Average weight distribution 0.72 1.00 0.72 Sparrow search algorithm 0.92 1.00 0.92

[0229] The experiment shows that the sparrow search algorithm shows high accuracy and stability. In order to verify the overall effectiveness, the two experiments used different weight allocation methods. From Table 3, it can be found that the sparrow search algorithm ensures that the evaluation reflects the principle of market fairness and encourages healthy competition. The results emphasize the key role of comprehensive professional insights and data analysis in building an efficient evaluation model, especially in the evaluation scenario of complex market mechanisms.

[0230] Example 4

[0231] (1) Experimental data

[0232] Taking the economic benefit score of the total evaluation layer as an example, the evaluation method of power market operation effectiveness based on the sparrow search algorithm is studied; the research data includes 1 first-level indicator, and the corresponding weight is 1;

[0233] (2) Experimental process

[0234] The fairness and competition score for the overall evaluation layer is calculated using the following steps:

[0235] Step S1: Obtain 20 fourth-level indicators, where all the fourth-level indicators are quantifiable data, and summarize them into 7 third-level indicators based on the fourth-level indicators, and determine the weights; summarize them into 3 second-level indicators based on the third-level indicators, and determine the weights; organize all the second-level indicators and summarize them into 1 first-level indicator as the evaluation layer.

[0236] Step S2: Assign weights to the indicators at each level to complete the calculation of the economic benefit score of the overall evaluation layer;

[0237] Step S2.1: Initialize the population (20 four-level indicators); set the population size N, the maximum number of iterations T = 100, the weight range [lb, ub] = [0, 1], the safety threshold ST, and the discoverer ratio r; randomly generate the same number of sparrow positions (weight vectors) as the population size, and each position contains the weights of 20 four-level indicators;

[0238] Step S2.2: define a fitness function with two first-level indicators to evaluate the quality of each sparrow position; wherein the fitness function is defined as formula (59);

[0239] Step S2.3: Calculate the fitness value using formula (61);

[0240] Step S2.4: Sorting to determine the weight of a certain level of indicators; sorting by fitness value, the first P sparrows are discoverers, and the rest are joiners;

[0241] Step S2.5: Update the weight of the next level indicator; according to the update rules of the discoverer and the joiner, update the weight of the next level indicator respectively. Use formula (62) to calculate the proportion of discoverers P; use formula (63) to calculate the discoverer position; use formula (60) to calculate the joiner position;

[0242] Step S2.6: Update the next level fitness function; use the updated weight vector to recalculate the fitness value;

[0243] Step S2.7: Check convergence or number of iterations; check whether the algorithm has converged or reached the maximum number of iterations. If it has converged or reached the maximum number of iterations, go to step S28; otherwise, return to step S24 to continue iterating;

[0244] Step S2.8: Output the weight vectors of the first-level, second-level, third-level, and fourth-level indicators;

[0245] Step S2.9: Calculate the economic benefit score of the overall evaluation layer using formula (66):

[0246] s b =w b ×b (66)

[0247] In formula (66), b represents the market economy index, which can be calculated using the formula to obtain the economic benefit score s b .

[0248] The experimental results of this embodiment are shown in Table 4, which respectively test the results of using average weight distribution and sparrow search algorithm assignment. The values ​​of the secondary indicators obtained by using average weight distribution are: market efficiency index b1 = 0.72, cost-effectiveness index b2 = 0.62, and social and economic contribution index b3 = 0.47. The values ​​of the secondary indicators obtained by using the sparrow search algorithm are: market efficiency index b1 = 0.82, cost-effectiveness index b2 = 0.78, and social and economic contribution index b3 = 0.53.

[0249] Table 4 Comparison of different weight distribution methods for economic benefit scores of the overall evaluation layer

[0250] Index b <![CDATA[Weight w b > Economic efficiency score Average weight distribution 0.89 1.00 0.89 Mahjong search algorithm 0.91 1.00 0.91

[0251] The experiment shows that the sparrow search algorithm shows high accuracy and stability. In order to verify the overall effectiveness, the two experiments used different weight allocation methods. From Table 4, it can be found that the sparrow search algorithm shows the best evaluation accuracy and practicality when measuring economic benefits, effectively improving the scientific nature of the evaluation and the effectiveness of decision-making.

[0252] Example 5

[0253] (1) Experimental data

[0254] Taking the environmental protection score of the total evaluation layer as an example, the evaluation method of power market operation effectiveness based on the sparrow search algorithm is studied; the research data includes two first-level indicators, and the corresponding weights are assigned by average weight distribution and sparrow search algorithm;

[0255] (2) Experimental process

[0256] The environmental protection score of the overall evaluation layer is calculated using the following steps:

[0257] Step S1: Obtain 41 fourth-level indicators, where all the fourth-level indicators are quantifiable data, and summarize them into 16 third-level indicators based on the fourth-level indicators, and determine the weights; summarize them into 7 second-level indicators based on the third-level indicators, and determine the weights; organize all the second-level indicators and summarize them into 2 first-level indicators as the evaluation layer.

[0258] Step S2: Use the sparrow search algorithm to assign weights to the indicators at each level to complete the calculation of the environmental protection score of the overall evaluation layer;

[0259] Step S2.1: Initialize the population (41 four-level indicators); set the population size N, the maximum number of iterations T = 100, the weight range [lb, ub] = [0, 1], the safety threshold ST, and the discoverer ratio r; randomly generate the same number of sparrow positions (weight vectors) as the population size, and each position contains the weights of 41 four-level indicators;

[0260] Step S2.2: define a fitness function with two first-level indicators to evaluate the quality of each sparrow position; wherein the fitness function is defined as formula (59);

[0261] Step S2.3: Calculate the fitness value using formula (61);

[0262] Step S2.4: Sorting to determine the weight of a certain level of indicators; sorting by fitness value, the first P sparrows are discoverers, and the rest are joiners;

[0263] Step S2.5: Update the weight of the next level indicator; according to the update rules of the discoverer and the joiner, update the weight of the next level indicator respectively. Use formula (62) to calculate the proportion of discoverers P; use formula (63) to calculate the discoverer position; use formula (60) to calculate the joiner position;

[0264] Step S2.6: Update the next level fitness function; use the updated weight vector to recalculate the fitness value;

[0265] Step S2.7: Check convergence or number of iterations; check whether the algorithm has converged or reached the maximum number of iterations. If it has converged or reached the maximum number of iterations, go to step S28; otherwise, return to step S24 to continue iterating;

[0266] Step S2.8: Output the weight vectors of the first-level, second-level, third-level, and fourth-level indicators;

[0267] Step S2.9: Calculate the environmental protection score of the overall evaluation layer using formula (67):

[0268] s ce =w c ×c+w e ×e (67)

[0269] In formula (67), c represents the market safety index, and e represents the market link friendliness index. The above can be calculated using the formula to obtain the environmental protection score s ce .

[0270] The experimental results of this embodiment are shown in Table 5, which respectively test the results of using average weight distribution and sparrow search algorithm assignment. The values ​​of the secondary indicators obtained by using average weight distribution are: power supply and demand security index c1 = 0.81, power grid operation security index c2 = 0.82, market transaction security index c3 = 0.54, power generation link friendliness index e1 = 0.32, power transmission and distribution link friendliness index e2 = 0.81, power sales link friendliness index e3 = 0.77, power consumption link friendliness index e4 = 0.76. The values ​​of the secondary indicators obtained by using the sparrow search algorithm are: power supply and demand security index c1 = 0.82, power grid operation security index c2 = 0.90, market transaction security index c3 = 0.55, power generation link friendliness index e1 = 0.32, power transmission and distribution link friendliness index e2 = 0.87, power sales link friendliness index e3 = 0.86, power consumption link friendliness index e4 = 0.78.

[0271] Table 5 Comparison of different weight allocation methods for market efficiency scores at the overall evaluation level

[0272] Index c Indicator <![CDATA[Weight w c > <![CDATA[Weight w e > Market efficiency score Average weight distribution 0.70 0.73 0.50 0.50 0.72 Sparrow search algorithm 0.72 0.88 0.68 0.32 0.77

[0273] The experiment shows that the sparrow search algorithm greatly enhances the accuracy and robustness of the evaluation model compared with the average weight distribution scheme. In order to verify the overall effectiveness, the two experiments used different weight distribution methods. From Table 5, it can be found that the sparrow search algorithm can significantly improve the market adaptability and analytical ability of the evaluation system, providing strong support for the accurate evaluation of the efficiency of the market mechanism.

[0274] Example 6

[0275] (1) Experimental data

[0276] Taking the safety and stability score of the overall evaluation layer as an example, the evaluation method of power market operation effectiveness based on the sparrow search algorithm is studied; the research data includes 1 first-level indicator, and the corresponding weight is 1;

[0277] (2) Experimental process

[0278] The safety and stability score of the overall evaluation layer is calculated using the following steps:

[0279] Step S1: Obtain 19 fourth-level indicators, where all the fourth-level indicators are quantifiable data, and summarize them into 8 third-level indicators based on the fourth-level indicators, and determine the weights; summarize them into 3 second-level indicators based on the third-level indicators, and determine the weights; organize all the second-level indicators and summarize them into 1 first-level indicator as the evaluation layer.

[0280] Step S2: Assign weights to the indicators at each level to complete the calculation of the safety and stability score of the overall evaluation layer;

[0281] Step S2.1: Initialize the population (19 four-level indicators); set the population size N, the maximum number of iterations T = 100, the weight range [lb, ub] = [0, 1], the safety threshold ST, and the discoverer ratio r; randomly generate the same number of sparrow positions (weight vectors) as the population size, and each position contains the weights of 19 four-level indicators;

[0282] Step S2.2: define a fitness function with two first-level indicators to evaluate the quality of each sparrow position; wherein the fitness function is defined as formula (59);

[0283] Step S2.3: Calculate the initial fitness; use formula (61) to calculate the fitness value;

[0284] Step S2.4: Sorting to determine the weight of a certain level of indicators; sorting by fitness value, the first P sparrows are discoverers, and the rest are joiners;

[0285] Step S2.5: Update the weight of the next level indicator; according to the update rules of the discoverer and the joiner, update the weight of the next level indicator respectively. Use formula (62) to calculate the proportion of discoverers P; use formula (63) to calculate the discoverer position; use formula (60) to calculate the joiner position;

[0286] Step S2.6: Update the next level fitness function; use the updated weight vector to recalculate the fitness value;

[0287] Step S2.7: Check convergence or number of iterations; check whether the algorithm has converged or reached the maximum number of iterations. If it has converged or reached the maximum number of iterations, go to step S28; otherwise, return to step S24 to continue iterating;

[0288] Step S2.8: Output the weight vectors of the first-level, second-level, third-level, and fourth-level indicators;

[0289] Step S2.9: Calculate the safety and stability score of the overall evaluation layer using formula (68):

[0290] s c =w c ×c (68)

[0291] In formula (68), c represents the market security index, which can be calculated using the formula to obtain the security and stability score s c .

[0292] The experimental results of this embodiment are shown in Table 6, which respectively test the results of using average weight distribution and sparrow search algorithm assignment. The values ​​of the secondary indicators obtained by using average weight distribution are: power supply and demand security index c1 = 0.80, power grid operation security index c2 = 0.82, and market transaction security index c3 = 0.54. The values ​​of the secondary indicators obtained by using the sparrow search algorithm are: power supply and demand security index c1 = 0.81, power grid operation security index c2 = 0.87, and market transaction security index c3 = 0.55.

[0293] Table 6 Comparison of different weight distribution methods for safety and stability scores of the overall evaluation layer

[0294] Index c <![CDATA[Weight w c > Safety and stability Average weight distribution 0.79 1.00 0.79 Mahjong search algorithm 0.89 1.00 0.89

[0295] The experiment shows that the sparrow search algorithm shows high accuracy and stability. In order to verify the overall effectiveness, the two experiments used different weight allocation methods. From Table 6, it can be found that the sparrow search algorithm can more accurately and comprehensively evaluate the security and stability performance of the system, providing a more reliable and sophisticated evaluation tool to ensure the safe and stable operation of the system.

[0296] Example 7

[0297] (1) Experimental data

[0298] Taking the user satisfaction score of the overall evaluation layer as an example, the evaluation method of power market operation effectiveness based on the sparrow search algorithm is studied; the research data includes 1 first-level indicator, and the corresponding weight is 1;

[0299] (2) Experimental process

[0300] The user satisfaction score of the overall evaluation layer is calculated using the following steps:

[0301] Step S1: Obtain 23 fourth-level indicators, where all the fourth-level indicators are quantifiable data, and summarize them into 8 third-level indicators based on the fourth-level indicators, and determine the weights; summarize them into 4 second-level indicators based on the third-level indicators, and determine the weights; organize all the second-level indicators and summarize them into 1 first-level indicator as the evaluation layer.

[0302] Step S2: Assign weights to the hierarchical indicators to complete the calculation of the user satisfaction score of the overall evaluation layer;

[0303] Step S2.1: Initialize the population (23 four-level indicators); set the population size N, the maximum number of iterations T = 100, the weight range [lb, ub] = [0, 1], the safety threshold ST, and the discoverer ratio r; randomly generate the same number of sparrow positions (weight vectors) as the population size, and each position contains the weights of 23 four-level indicators;

[0304] Step S2.2: define a fitness function with two first-level indicators to evaluate the quality of each sparrow position; wherein the fitness function is defined as formula (59);

[0305] Step S2.3: Calculate the fitness value using formula (61);

[0306] Step S2.4: Sorting to determine the weight of a certain level of indicators; sorting by fitness value, the first P sparrows are discoverers, and the rest are joiners;

[0307] Step S2.5: Update the weight of the next level indicator; according to the update rules of the discoverer and the joiner, update the weight of the next level indicator respectively. Use formula (62) to calculate the proportion of discoverers P; use formula (63) to calculate the discoverer position; use formula (60) to calculate the joiner position;

[0308] Step S2.6: Update the next level fitness function; use the updated weight vector to recalculate the fitness value;

[0309] Step S2.7: Check convergence or number of iterations; check whether the algorithm has converged or reached the maximum number of iterations. If it has converged or reached the maximum number of iterations, go to step S28; otherwise, return to step S24 to continue iterating;

[0310] Step S2.8: Output the weight vectors of the first-level, second-level, third-level, and fourth-level indicators;

[0311] Step S2.9: Calculate the user satisfaction score of the overall evaluation layer;

[0312] Formula (69) is used to calculate the user satisfaction score of the overall evaluation layer:

[0313] s d =w d ×d (69)

[0314] In formula (69), d represents the market social welfare index, which can be calculated by the formula to obtain the user satisfaction score s d .

[0315] The experimental results of this embodiment are shown in Table 7, which tests the results of using average weight distribution and sparrow search algorithm assignment. The values ​​of the secondary indicators obtained by using average weight distribution are: electricity price affordability and user satisfaction index d1 = 0.52, energy efficiency and energy saving consumption d2 = 0.62, electricity service popularization and social equity d3 = 0.49, employment and economic benefit index d4 = 0.79. The values ​​of the secondary indicators obtained by using the sparrow search algorithm are: electricity price affordability and user satisfaction index d1 = 0.53, energy efficiency and energy saving consumption d2 = 0.65, electricity service popularization and social equity d3 = 0.52, employment and economic benefit index d4 = 0.80.

[0316] Table 7 Comparison of different weight allocation methods for user satisfaction scores at the overall evaluation level

[0317] Index d <![CDATA[Weight w d > User satisfaction score Average weight distribution 0.87 1.00 0.87 Sparrow search algorithm 0.89 1.00 0.89

[0318] The experiment shows that the sparrow search algorithm shows high accuracy and stability. In order to verify the overall effectiveness, the two experiments used different weight allocation methods. From Table 7, it can be found that the sparrow search algorithm can accurately reflect user preferences and significantly improve the discrimination and accuracy of satisfaction rating indicators.

[0319] It can be found that the method of the present invention can ensure reasonable weight distribution and quantitative market analysis to a certain extent. At the same time, the experiment of this embodiment shows that compared with the traditional single data source analysis, the above indicators have improved the operational efficiency evaluation by 20%, the market stability index prediction accuracy by 18%, and the consistency of user satisfaction evaluation by 15%. This innovative method provides strong data support for power market monitoring and strategy formulation.

[0320] Based on the above experimental results, the following conclusions can be drawn:

[0321] (1) The sparrow search algorithm can effectively optimize weights and improve fusion accuracy. It is widely used and adaptable to a variety of indicator systems, thus improving decision-making results.

[0322] (2) A method for evaluating the effectiveness of power market operations is proposed, which is effectively combined with the sparrow search algorithm and can process various types of power market data. The evaluation method given by the indicator system can provide an artificial intelligence methodology and toolbox for policy formulation and rule adjustment in the national power market.

[0323] The contents not described in detail in the specification of the present invention belong to the prior art known to the professional and technical personnel in the field. Although the illustrative specific embodiments of the present invention are described above to facilitate the understanding of the present invention by the technical personnel in the field, it should be clear that the present invention is not limited to the scope of the specific embodiments. For the ordinary technical personnel in the field, as long as various changes are within the spirit and scope of the present invention defined and determined by the attached claims, these changes are obvious, and all inventions and creations using the concept of the present invention are protected.

Claims

1. A method for evaluating the effectiveness of power market operation based on sparrow search algorithm, characterized in that: The method comprises the following steps: Step S1: extract indicators and decompose them into 5 first-level indicators, 17 second-level indicators, 40 third-level indicators, and 116 fourth-level indicators; Step S2: Obtain 116 fourth-level indicators, where all the fourth-level indicators are quantifiable data, summarize them into 40 third-level indicators based on the fourth-level indicators, and determine the weights; Step S3: Summarize the third-level indicators into 17 second-level indicators and determine the weights; Step S4: Arrange all secondary indicators, take 5 primary indicators as the evaluation layer and 116 fourth-level indicators as the specific description layer, collect and organize data from three dimensions: time dimension, industry dimension and regional dimension, and integrate the data to construct the overall evaluation layer of the power market, assign weights to indicators at each level, and complete the calculation of the overall evaluation layer score.

2. According to claim 1, a method for evaluating the effectiveness of power market operation based on a sparrow search algorithm is characterized in that: The step S2 obtains 116 fourth-level indicators, wherein the fourth-level indicators are all quantifiable data, and the fourth-level indicators are summarized into 40 third-level indicators. The specific operation of determining the weights is as follows: Step S2.1: Use formula (1) to obtain the power generation enterprise structure index a 11 , use formula (2) to obtain the structure index a of the power sales company 12 , use formula (3) to obtain the power user structure index a 13 , use formula (4) to obtain the trading product indicator a 21 , use formula (5) to obtain the trading mode indicator a 22 , use formula (6) to obtain the transaction price index a 23 , use formula (7) to obtain the grid scale index a 31 , use formula (8) to obtain the grid structure index a 32 , use formula (9) to obtain the inter-regional power flow index a 33 ; Wherein, formula (1) is expressed as: In the formula, a 111 represents the installed capacity ratio, a 112 represents the proportion of power generation, a 113 represents the number of power generation enterprises, a 114 represents the size distribution, a 115 represents market share, both are level 4 indicators; w 11i is the weight; Formula (2) is expressed as: In the formula, a 121 represents the number of electricity sales companies, a 122 represents the market share, a 123 Indicates power diversity, all are four-level indicators; w 12i is the weight; Formula (3) is expressed as: In the formula, a 131 represents the proportion of industrial users, a 132 represents the proportion of commercial users, a 133 represents the proportion of residential users, a 134 Indicates the proportion of other users, all of which are level 4 indicators; w 13i is the weight; Formula (4) is expressed as: In the formula, a 211 Indicates medium- to long-term transactions, a 212 Indicates spot trading, a 213 Indicates auxiliary services, all of which are level 4 indicators; w 21i is the weight; Formula (5) is expressed as: In the formula, a 221 Indicates bilateral negotiation, a 222 represents centralized bidding, a 223 Indicates listing transaction, a 224 Indicates matching transactions, all are level 4 indicators; w 22i is the weight; Formula (6) is expressed as: In the formula, a 231 represents price convergence, a 232 Indicates the price fluctuation range, both are four-level indicators; 23i is the weight; Formula (7) is expressed as: In the formula, a 311 represents the total installed capacity, a 312 Indicates the maximum load, a 313 represents the annual power generation, a 314 Indicates annual electricity consumption, all of which are level 4 indicators; w 31i is the weight; Formula (8) is expressed as: In the formula, a 321 Indicates the voltage level distribution, a 322 Indicates power supply reliability, a 323 Indicates automation coverage, both are level 4 indicators; w 32i is the weight; Formula (9) is expressed as: In the formula, a 331 Indicates cross-region transactions, a 332 Indicates inter-provincial transactions, a 333 Indicates channel utilization, a 334 Indicates price linkage, both are level 4 indicators; w 33i is the weight; Step S2.2: Use formula (10) to obtain the market clearing indicator b 11 , use formula (11) to obtain the resource optimization allocation efficiency b 12 , use formula (12) to obtain the power generation cost index b 21 , use formula (13) to obtain the electricity user cost index b 22 , use formula (14) to obtain the market competition behavior index b 23 , use formula (15) to obtain the employment and tax contribution index b 31 , use formula (16) to obtain the energy structure adjustment index b 32 ; Among them, formula (10) is expressed as: Where b 111 Indicates the cleared power, b 112 represents the clearing price, b 113 represents the theoretical optimal price, b 114 Indicates the deviation, b 115 Indicates the effectiveness of clearing, both are level 4 indicators; w 11i is the weight; Formula (11) is expressed as: Where b 121 represents the utilization rate of the generator set, b 122 represents the grid load rate, b 123 represents the clean energy consumption rate, b 124 Indicates the utilization rate of system spare capacity, both are level 4 indicators; w 12i is the weight; Formula (12) is expressed as: Where b 211 represents the fuel cost, b 212 represents the operation and maintenance cost, b 213 represents depreciation and amortization, both are level 4 indicators; w 21i is the weight; Formula (13) is expressed as: Where b 221 represents the average electricity price, b 222 Indicates the proportion of output value, b 223 Indicates the sensitivity of electricity price, both are level 4 indicators; 22i is the weight; Formula (14) is expressed as: b 23 =b 23 (14) In the formula, b 23 Indicates manipulative behavior, a level 4 indicator; Formula (15) is expressed as: Where b 311 Indicates employment pull, b 312 represents tax revenue, all of which are level 4 indicators; 31i is the weight; Formula (16) is expressed as: Where b 321 represents the energy consumption intensity, b 322 Indicates carbon emission intensity, both are four-level indicators; w 32i is the weight; Step S2.3: Use formula (17) to obtain the power supply and demand balance index c 11 , use formula (18) to obtain the reserve capacity adequacy index c 12 , use formula (19) to obtain the power shortage warning and response index c 13 , use formula (20) to obtain the system frequency stability index c 21 , use formula (21) to obtain the voltage qualification rate c 22 , use formula (22) to obtain the power grid failure rate and recovery index c 23 , use formula (23) to obtain the transaction default rate c 31 , use formula (24) to obtain the power grid peak load capacity index c 32 ; Among them, formula (17) is expressed as: In the formula, c 111 represents the load factor, c 112 Indicates the supply-demand balance rate, both are level 4 indicators; w 11i is the weight; Formula (18) is expressed as: In the formula, c 121 represents the ratio of standby capacity to maximum load, c 122 Indicates the ability to cope with unexpected load fluctuations, both are level 4 indicators; 12i is the weight; Formula (19) is expressed as: In the formula, c 131 represents the uncertainty of new energy, c 132 Indicates the margin of the power system, both are level 4 indicators; w 13i is the weight; Formula (20) is expressed as: c 21 =w 211 ×(1-c 211 / max(c 211 ))+w 212 ×(1 / c 212 ) (20) In the formula, c 211 Indicates the fluctuation range, c 212 Indicates the recovery speed, both are level 4 indicators; w 211 and w 212 is the weight; Formula (21) is expressed as: In the formula, c 221 Indicates the voltage deviation rate, c 222 Indicates the percentage of qualified voltage, all of which are level 4 indicators; w 22i is the weight; Formula (22) is expressed as: In the formula, c 231 represents the failure rate, c 232 Indicates the recovery speed, both are level 4 indicators; w 23i is the weight; Formula (23) is expressed as: In the formula, c 311 represents the default rate of transaction contract, c 312 represents the power default rate, c 313 represents the payment default rate, c 314 represents the default rate of the subject, c 315 represents the delayed delivery default rate, both of which are level 4 indicators; w 31i is the weight; Formula (24) is expressed as: In the formula, c 321 represents the theoretical peak load regulation capability, c 322 represents the peak regulation margin, which is a four-level indicator; w 32i is the weight; Step S2.4: Use formula (25) to obtain the residential electricity price to income ratio d 11 , use formula (26) to obtain the user satisfaction survey d 12 , use formula (27) to obtain the energy consumption per unit GDP d 21 , use formula (28) to obtain the energy efficiency improvement project d 22 , use formula (29) to obtain the power coverage rate d 31 , use formula (30) to obtain the electricity poverty alleviation rate d 32 , use formula (31) to obtain the employment d in the power industry 41 , use formula (32) to obtain the contribution rate of the power industry to GDP d 42 ; Wherein, formula (25) is expressed as: Where, d 111 represents the electricity price burden rate, d 112 represents the electricity price-to-income ratio, d 113 Indicates the electricity price elasticity coefficient, which is a four-level indicator; w 11i is the weight; Formula (26) is expressed as: Where, d 121 represents the electricity price perceived burden rate, d 122 represents the electricity price rationality index, d 123 Indicates satisfaction with electricity price transparency, d 124 Indicates the satisfaction with the cost-effectiveness of electricity prices, both are four-level indicators; w 12i is the weight; Formula (27) is expressed as: Where, d 211 represents the energy consumption of GDP in each region, d 212 Indicates the energy consumption per unit GDP of the industry, both are level 4 indicators; w 21i is the weight; Formula (28) is expressed as: Where, d 221 Indicates the energy saving rate, d 222 Indicates the power saving rate, d 223 represents the emission reduction rate, which are all level 4 indicators; w 22i is the weight; Formula (29) is expressed as: Where, d 311 represents the regional coverage, d 312 represents the rural access rate, both are level 4 indicators; w 31i is the weight; Formula (30) is expressed as: Where, d 321 represents the electricity price fairness index, d 322 Indicates the impact of electricity price adjustment on the poverty line, both are level 4 indicators; 32i is the weight; Formula (31) is expressed as: Where, d 411 represents the employment growth rate, d 412 represents per capita output value, d 413 represents labor productivity, d 414 Indicates job vacancy rate, both are level 4 indicators; w 41i is the weight; Formula (32) is expressed as: Where, d 421 Indicates the proportion of GDP, d 422 Denotes the contribution rate to GDP growth, d 423 represents the tax contribution rate, both of which are level 4 indicators; w 42i is the weight; Step S2.5: Use formula (33) to obtain the fair competition environment index e 11 , use formula (34) to obtain the clean energy incentive mechanism e 12 , using formula (35) to obtain the transmission and distribution price transparency e 21 , use formula (36) to obtain the power grid investment efficiency index e 22 , use formula (37) to obtain the openness of the electricity sales market e 31 , use formula (38) to obtain the user selection guarantee e 32 , use formula (39) to obtain the user's electricity price tolerance e 41 , use formula (40) to obtain the degree of user participation in the market e 42 ; Wherein, formula (33) is expressed as: In the formula, e 111 represents the growth rate of new power generation market share, e 112 represents the average bidding success rate, e 113 It represents the ratio of differentiated electricity prices for homogeneous products, and both are level 4 indicators; 11i is the weight; Formula (34) is expressed as: In the formula, e 121 Indicates return on investment ROI, e 122 represents the subsidy coverage rate, e 123 Indicates the rate of increase in the proportion, both are level 4 indicators; w 12i is the weight; Formula (35) is expressed as: In the formula, e 211 represents the electricity price structure disclosure rate, e 212 represents the accessibility index of electricity price documents, e 213 Indicates the efficiency of electricity price dispute resolution, both are level 4 indicators; w 21i is the weight; Formula (36) is expressed as: In the formula, e 221 represents the growth rate of transmission capacity, e 222 Indicates power supply reliability, all of which are level 4 indicators; 22i is the weight; Formula (37) is expressed as: In the formula, e 311 represents the subject diversity index, e 312 represents the competition ratio, e 313 Indicates cross-province and cross-region transaction currencies, all of which are level 4 indicators; w 31i is the weight; Formula (38) is expressed as: In the formula, e 321 represents the degree of freedom of choice, e 322 Indicates the efficiency of handling user complaints, both are level 4 indicators; 32i is the weight; Formula (39) is expressed as: In the formula, e 411 represents the sensitivity of electricity price, e 412 represents the electricity price burden index, e 413 represents the income elasticity of electricity prices, both of which are four-level indicators; w 41i is the weight; Formula (40) is expressed as: In the formula, e 421 represents the participation rate in electricity trading, e 422 represents the user-side response activity participation rate, e 423 Indicates the optimization adjustment ratio of user load curve, both are level 4 indicators; w 42i is the weight; The weights at each level are assigned initial values ​​using expert scoring, entropy weight method or sparrow search algorithm.

3. The method for evaluating the effectiveness of power market operation based on the sparrow search algorithm according to claim 2 is characterized in that: The step S3 summarizes the three-level indicators into 17 secondary indicators, and the specific operation of determining the weights is as follows: The extracted third-level indicators are summarized to obtain 17 second-level indicators. The steps are as follows: Step S3.1: Use formula (41) to obtain the market entity structure index a1, use formula (42) to obtain the market transaction structure index a2, and use formula (43) to obtain the power grid structure index a3; Wherein, formula (41) is expressed as: In the formula, a 11 represents the structural index of power generation enterprises, a 12 represents the structural index of the power sales company, a 13 Represents the structure index of power users, all of which are third-level indexes; w 1i is the weight; Formula (42) is expressed as: In the formula, a 21 Indicates the trading product indicator, a 22 Represents a trading mode indicator, a 23 Indicates transaction price indicators, all of which are level 3 indicators; 2i is the weight; Formula (43) is expressed as: In the formula, a 31 represents the grid scale index, a 32 represents the grid structure index, a 33 It represents the proportion of residential users in the inter-regional power flow index, which are all third-level indicators; 3i is the weight; Step S3.2: Use formula (44) to obtain the market clearing index b1, use formula (45) to obtain the resource optimization allocation efficiency b2, and use formula (46) to obtain the power generation cost index b3; Wherein, formula (44) is expressed as: Where b 11 represents the market clearing indicator, b 12 Indicates the efficiency of resource optimization allocation, both are third-level indicators; w 1i is the weight; Formula (45) is expressed as: Where b 21 represents the power generation cost index, b 22 represents the electricity user cost index, b 23 Indicates market competition behavior indicators, all of which are third-level indicators; w 2i is the weight; Formula (46) is expressed as: Where b 31 represents employment and tax contribution indicators, b 32 Represents energy structure adjustment indicators, all of which are third-level indicators; w 3i is the weight; Step S3.3: Use formula (47) to obtain the power supply and demand security index c1, use formula (48) to obtain the power grid operation security index c2, and use formula (49) to obtain the market transaction security index c3; Wherein, formula (47) is expressed as: In the formula, c 11 represents the power supply and demand balance index, c 12 represents the reserve capacity adequacy index, c 13 Indicates power shortage warning and response indicators, both of which are level 3 indicators; 1i is the weight; Formula (48) is expressed as: In the formula, c 21 Represents the system frequency stability index, c 22 Indicates the voltage qualification rate index, c 23 Indicates the power grid failure rate and recovery index, both of which are third-level indicators; w 2i is the weight; Formula (49) is expressed as: In the formula, c 31 represents the transaction default rate indicator, c 32 Indicates the peak load regulation capability index of power grid, which are all level 3 indexes; 3i is the weight; Step S3.4: Use formula (50) to obtain the electricity price affordability and user satisfaction index d1, use formula (51) to obtain energy efficiency and energy saving consumption d2, use formula (52) to obtain electricity service popularization and social equity d3, and use formula (53) to obtain employment and economic benefit index d4; Wherein, formula (50) is expressed as: Where, d 11 represents the ratio of residential electricity price to income, d 12 Represents user satisfaction survey, both are three-level indicators; w 1i is the weight; Formula (51) is expressed as: Where, d 21 represents the energy consumption per unit of GDP, d 22 Indicates energy efficiency improvement projects, all of which are level 3 indicators; w 2i is the weight; Formula (52) is expressed as: Where, d 31 represents the electricity coverage rate, d 32 represents the electricity poverty alleviation rate, both are level 3 indicators; w 3i is the weight; Formula (53) is expressed as: Where, d 41 represents employment in the power industry, d 42 Indicates the contribution rate of the power industry to GDP, both are third-level indicators; 4i is the weight; Step S3.5: Use formula (54) to obtain the friendly index e1 of the power generation link, use formula (55) to obtain the friendly index e2 of the power transmission and distribution link, use formula (56) to obtain the friendly index e3 of the power sales link, and use formula (57) to obtain the friendly index e4 of the power consumption link; Wherein, formula (54) is expressed as: In the formula, e 11 represents the level playing field indicator, e 12 Indicates the clean energy incentive mechanism, all of which are three-level indicators; w 1i is the weight; Formula (55) is expressed as: In the formula, e 21 Indicates the transparency of transmission and distribution prices, e 22 Represents the power grid investment efficiency index, which are all third-level indicators; w 2i is the weight; Formula (56) is expressed as: In the formula, e 31 represents the openness of the electricity sales market, e 32 Indicates the protection of user choice rights, all of which are level 3 indicators; 3i is the weight; Formula (57) is expressed as: In the formula, e 41 Indicates the user's ability to bear electricity prices, e 42 Indicates the degree of user participation in the market, both are three-level indicators; w 4i is the weight; The weights at each level are assigned initial values ​​using expert scoring, entropy weight method or sparrow search algorithm.

4. The method for evaluating the effectiveness of power market operation based on the sparrow search algorithm according to claim 3 is characterized in that: The step S4: sorting out all the secondary indicators, taking 5 primary indicators as the evaluation layer and 116 fourth-level indicators as the specific description layer, collecting and sorting data from three dimensions of time dimension, industry dimension and region dimension and integrating the data, constructing the overall evaluation layer of the power market, assigning weights to the indicators at each level, and completing the specific operations of calculating the overall evaluation layer score are as follows: Step S4.1: Construct the overall evaluation layer of the power market. The total score s is shown in formula (58): In the formula, i corresponds to a, b, c, d, and e, five first-level indicators. a represents the market structure indicator, b represents the market economy indicator, c represents the market security indicator, d represents the market social welfare indicator, and e represents the market link friendliness indicator; w i is the weight; The above weights are assigned using the sparrow search algorithm, and the fitness function is designed with five primary indicators as shown in formula (59): Step S4.2: Calculate the fitness value using the Sparrow algorithm and optimize the weight using an iterative formula. The iterative formula is shown in (60): Where, X best (t) is the current best position, that is, the optimal weight, is a normally distributed random number with mean 0 and variance 1, X i (t) is the current position in round t, i.e., the weight; It represents the normal distribution with parameters lb and ub. The lower bound of the parameter is set according to the indicator, recorded as lb, and the upper bound is recorded as ub. N represents the population size of the sparrow algorithm.

Images