Power market multi-dimensional operation effect dynamic evaluation method and device

Abstract

The invention provides a power market multi-dimensional operation effect dynamic evaluation method and device. Belongs to the technical field of electricity market evaluation. The method comprises the steps of obtaining multi-dimensional operation index data of an electricity market of a to-be-evaluated day; calculating the information entropy of each operation index, and determining the subjective and objective fusion weight of each operation index according to the information entropy; performing weighted representation on the multi-dimensional operation indexes of the to-be-evaluated day, calculating the difference degrees of the weighted multi-dimensional operation indexes relative to the ideal state data and the non-ideal state data, and determining the closeness relative to the ideal state data according to the difference degrees; and determining a power market operation effect evaluation result of the to-be-evaluated day based on the proximity. According to the method, multi-dimensional information such as economy, safety, new energy utilization and a main body structure can be planned as a whole, dynamic quantitative description of the market operation state is achieved on the premise that manual experience intervention is reduced, and a more objective and reliable basis is provided for operation monitoring and auxiliary decision making.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of power market evaluation, and particularly relates to a multi-dimensional operation effect dynamic evaluation method and device for a power market. BACKGROUND

[0002] With the continuous advancement of the double carbon target, the energy structure is accelerating towards a high proportion of new energy, and the installed capacity of new energy such as wind power and photovoltaic is rising, gradually increasing the proportion in the power system and changing from a supplementary power source to a main power source. Correspondingly, the power market reform continues to deepen, the market transaction electricity scale and cross-provincial and cross-regional transaction frequency continue to increase, the spot transaction pilot and the construction of the electricity retail market are gradually promoted, and the operation mode and interest pattern of the power system have changed significantly.

[0003] Under this background, the strong volatility of new energy power generation and the power market transaction behavior are coupled with each other: the uncertainty of wind and light output on the power supply side easily leads to large fluctuations in market prices, the rapid development of new types of loads such as distributed power sources and electric vehicles on the load side increases the difficulty of load forecasting, and the cross-regional channel congestion on the grid side and the related costs generated thereby affect the overall economy of the market. The existing power market operation analysis mainly focuses on local indicators or post-statistics, and it is difficult to reflect the overall operation state of the market in a timely and systematic manner. Therefore, it is necessary to build a scientific, dynamic and multi-dimensional power market operation evaluation system, which can comprehensively depict the economy, safety, new energy utilization and market subject behavior in a unified framework, and provide quantitative support for market rule optimization and regulatory decision-making by real-time sensing of operation state changes.

[0004] Although various power market operation analysis and evaluation methods have been applied in engineering practice, there are still some deficiencies in general. For example, the existing evaluation mainly focuses on a single dimension or a few indicators, and mainly analyzes the statistics of local phenomena such as congestion costs, price fluctuations and transaction scales, and lacks overall description of economy, safety, new energy utilization and market subject structure, making it difficult to reflect the comprehensive state of market operation in a timely manner. At the same time, the index weight and grade division of some evaluation methods still mainly rely on artificial experience setting, and the evaluation results are easily affected by human factors, and the stability and adaptability need to be improved in the new operation scenarios of high proportion of new energy and power spot. In addition, the existing analysis mainly takes annual or monthly data as the object, and focuses on post summary, and the ability to identify short-term fluctuations and phase abnormalities of the power market operation state is insufficient, and it is difficult to meet the needs of fine monitoring and auxiliary decision-making of the market operation state.

[0005] Therefore, a new operation effect evaluation method for the electricity market is urgently needed, which can integrate multi-dimensional information such as economy, safety, new energy utilization and subject structure, and realize dynamic quantitative characterization of the market operation state under the premise of reducing manual experience intervention, thereby providing a more objective and reliable basis for operation monitoring and auxiliary decision-making. SUMMARY

[0006] The purpose of the present application is to provide a multi-dimensional operation effect dynamic evaluation method and device for the electricity market, which can integrate multi-dimensional information such as economy, safety, new energy utilization and subject structure, and realize dynamic quantitative characterization of the market operation state under the premise of reducing manual experience intervention, thereby providing a more objective and reliable basis for operation monitoring and auxiliary decision-making.

[0007] In order to achieve the above-mentioned purpose, the present application adopts the following technical solutions: In a first aspect, the present application provides a multi-dimensional operation effect dynamic evaluation method for the electricity market, comprising: obtaining multi-dimensional operation index data of the electricity market on the day to be evaluated, the multi-dimensional operation index data being a set of operation indexes for quantitatively representing the overall operation state of the electricity market in multiple dimensions; processing the multi-dimensional operation index data based on an information entropy method to obtain information entropy of each operation index, and determining subjective and objective fusion weights of each operation index according to the information entropy; weighting the multi-dimensional operation index on the day to be evaluated based on the subjective and objective fusion weights, and determining ideal values of each operation index under ideal operation state and non-ideal operation state respectively, combining the ideal values in order to form ideal state data and non-ideal state data of the electricity market, calculating the difference degree of the weighted multi-dimensional operation index with respect to the ideal state data and the non-ideal state data respectively, and determining the closeness of the weighted multi-dimensional operation index with respect to the ideal state data according to the difference degree; determining the operation effect evaluation result of the electricity market on the day to be evaluated based on the closeness.

[0008] Further, the step of calculating the information entropy of each operation index comprises: preprocessing the multi-dimensional operation index according to its positive attribute and negative attribute; calculating the information entropy of each preprocessed operation index; The preprocessing step comprises: obtaining the original value of the jth operation index in the multi-dimensional operation index under the ith sample standardizing the original value to obtain the standardized value wherein, for the benefit type operation index, the standardization is performed according to the following formula:

[0009] For the cost type operation index, normalization is performed according to the following formula:

[0010] wherein, represents the original value of the jth operation index in the ith sample, represents the maximum value of the jth operation index in all samples, represents the minimum value of the jth operation index in all samples; The step of calculating the information entropy of each pre-processed operation index comprises: On the basis of obtaining the normalized index value , the proportion of the jth operation index under the ith sample is calculated according to the following formula :

[0011] The information entropy of the jth operation index is calculated according to the following formula :

[0012] wherein, represents the number of samples participating in the entropy value calculation, represents the normalized proportion of the jth operation index under the ith sample, represents the information entropy of the jth operation index.

[0013] Further, determining the subjective and objective fusion weight of each operation index comprises: determining the objective weight of each operation index according to the information entropy of each operation index; determining the subjective weight of each operation index based on the subjective evaluation of each operation index; fusing the objective weight and the subjective weight according to a preset weight fusion strategy to obtain the subjective and objective fusion weight of each operation index; The step of determining the objective weight of each operation index according to the information entropy of each operation index comprises: After calculating the information entropy of each operation index , the difference degree of the jth operation index is calculated according to the following formula :

[0014] The objective weight of the jth operation index is calculated according to the following formula :

[0015] wherein, is the number of operation indexes participating in the evaluation, is the information entropy of the jth running index, is the difference degree of the jth running index, is the objective weight of the jth running index; determining the subjective weight of each running index based on the subjective evaluation of each running index comprises: constructing a judgment matrix according to the subjective pairwise comparison results of the relative importance of each running index, obtaining the initial subjective weight vector of each running index by geometrically averaging each row element of the judgment matrix and normalizing the result obtained; calculating the maximum eigenvalue, consistency index and consistency ratio of the judgment matrix, when the consistency ratio is less than a preset threshold, taking the subjective weight vector as the subjective weight of each running index, otherwise adjusting the judgment matrix and recalculating until the consistency requirement is met.

[0016] Further, the step of obtaining the subjective and objective fusion weight of each running index comprises: calculating the subjective and objective fusion weight of each running index according to the following formula:

[0017] wherein, denotes the subjective and objective fusion weight of the jth running index, denotes the objective weight of the jth running index calculated based on the information entropy, denotes the subjective weight of the jth running index determined based on the subjective evaluation, is the subjective and objective weight coefficient.

[0018] Further, the step of representing the multi-dimensional running index of the day to be evaluated based on the subjective and objective fusion weight comprises: After determining the subjective and objective fusion weight of each running index, normalizing the multi-dimensional running index of the day to be evaluated in a vector normalization manner; multiplying the normalized value of each running index by the corresponding subjective and objective fusion weight to obtain the weighted normalized value of each running index, and combining the weighted normalized values in the order of the running index to form a weighted multi-dimensional running index.

[0019] Further, determining the proximity of the weighted multi-dimensional running index to the ideal state data comprises: calculating the positive ideal value of the benefit type running index according to the following formula and the negative ideal value :

[0020] calculating the positive ideal value of the cost type running index according to the following formula and the negative ideal value :

[0021] wherein, represents the weighted normalized value of the i-th evaluation object on the j-th operation index, i is the evaluation object index, and j is the operation index index; and the of each operation index are combined to form the ideal state data of the electricity market, and the of each operation index are combined to form the non-ideal state data of the electricity market; The distance between the weighted multi-dimensional operation index of the i-th evaluation object and the ideal state data and the non-ideal state data is calculated according to the following formula and :

[0022] wherein, is the number of operation indexes; The closeness of the i-th evaluation object to the ideal state data is calculated according to the following formula : .

[0023] Further, the electricity market multi-dimensional operation effect dynamic evaluation method, after determining the electricity market operation effect evaluation result of the day to be evaluated based on the closeness, further comprises: forming an electricity market operation health degree sequence based on the electricity market operation effect evaluation results of continuous multiple days, and identifying the operation trend, periodic fluctuation and phase anomaly of the electricity market based on the electricity market operation health degree sequence; The multi-dimensional operation index at least includes: a congestion cost index, a new energy consumption rate index, a cross-section overrun frequency index, and a small and medium-sized subject participation rate index; Determining the electricity market operation effect evaluation result of the day to be evaluated comprises: According to the numerical value of the closeness, the closeness is compared with a preset first threshold value and a second threshold value, the second threshold value is greater than the first threshold value, when the closeness is greater than or equal to the second threshold value, the day to be evaluated is determined as the electricity market operation effect is excellent;When the closeness is between the first threshold value and the second threshold value, the day to be evaluated is determined as the electricity market operation effect is good;When the closeness is less than or equal to the first threshold value, the day to be evaluated is determined as the electricity market operation effect needs to be prewarned.

[0024] In the second aspect of the present application, an electricity market multi-dimensional operation effect dynamic evaluation device is provided, comprising: A data acquisition module is used to acquire multi-dimensional operation index data of the electricity market of the day to be evaluated; The subjective and objective fusion weight calculation module is configured to calculate information entropy of each operation index and determine subjective and objective fusion weights of each operation index according to the information entropy; The proximity calculation module is configured to perform weighted representation on the multi-dimensional operation index of the day to be evaluated based on the subjective and objective fusion weights, determine ideal values of each operation index in the ideal operation state and the non-ideal operation state respectively, combine the ideal values in sequence to form ideal state data and non-ideal state data of the power market, calculate difference degrees of the weighted multi-dimensional operation index with respect to the ideal state data and the non-ideal state data respectively, and determine proximity of the weighted multi-dimensional operation index with respect to the ideal state data according to the difference degrees. The evaluation module is configured to determine an evaluation result of the power market operation effect of the day to be evaluated based on the proximity.

[0025] In a third aspect, the present application provides an electronic device including a processor and a memory, the processor being configured to execute a computer program stored in the memory to implement the power market multi-dimensional operation effect dynamic evaluation method.

[0026] In a fourth aspect, the present application provides a computer readable storage medium, the computer readable storage medium storing at least one instruction, the at least one instruction being executed by a processor to implement the power market multi-dimensional operation effect dynamic evaluation method.

[0027] Compared with the prior art, the present application has the following advantages: The power market multi-dimensional operation effect dynamic evaluation device, the electronic device and the computer readable storage medium provided by the present application also solve the problems proposed in the background part.

[0028] 1. This invention achieves a systematic, dynamic, and high-resolution assessment of the operational effectiveness of the power market by constructing a complete methodological chain encompassing indicator acquisition, entropy calculation, dynamic weighting, ideal state comparison, and proximity evaluation. Unlike traditional analysis methods that rely on single indicators or static weights, this invention constructs a unified evaluation framework for the multi-dimensional operational indicators acquired on the day of evaluation, enabling quantitative comparisons of key dimensions such as economic efficiency, safety, green development level, and market vitality within the same coordinate system. By explicitly specifying the target evaluation values ​​of operational indicators under ideal and non-ideal operating conditions, this invention forms a measurable and comparable target reference system. Simultaneously, based on the weighted multi-dimensional indicators, the degree of difference between them and ideal and non-ideal state data is calculated, allowing operational effectiveness to be quantified from the perspective of relative superiority and approximation rather than absolute value judgments. Finally, by calculating the proximity and using it to evaluate market operational effectiveness, this invention achieves single-valued, rankable, and graded output of operational status, facilitating rapid daily-level diagnosis, horizontal comparison, and trend tracking of operational quality. Overall, this invention provides an operational performance evaluation system for real-time monitoring, refined analysis, and decision support in the complex context of high-proportion renewable energy integration and deepening electricity market transactions, significantly improving the transparency and manageability of market operation.

[0029] 2. This invention, through standardized preprocessing, information entropy calculation, objective weight extraction, and subjective weight determination based on AHP, achieves a dynamic weight generation mechanism that combines data-driven and policy-oriented approaches, significantly improving the scientific rigor, stability, and adaptability of multi-dimensional indicator weight allocation. First, after distinguishing between positive and negative attributes of operational indicators, this invention employs a linear standardization strategy to unify indicator dimensions, enabling comparisons of various economic, safety, and green development indicators on the same scale, fundamentally eliminating evaluation biases caused by differences in magnitude or direction between indicators. Second, this invention calculates the dispersion of each indicator across different sample days using the information entropy method and determines its objective weight accordingly. This automatically identifies key indicators with high volatility and strong information contribution, making weight allocation more consistent with the statistical characteristics of the operational data itself. Furthermore, this invention incorporates expert experience and management strategies through the AHP method, achieving a quantifiable expression of subjective weights, and ensures the rationality of subjective weights through a judgment matrix consistency check. Furthermore, by pre-setting a fusion strategy to comprehensively process subjective and objective weights, the weights can be dynamically adjusted according to factors such as changes in new energy output, load fluctuations, and market mechanisms. This ensures both the reflection of policy objectives and maintains sensitivity to changes in operational data. Overall, this multi-level, multi-source weight generation mechanism effectively enhances the evaluation system's adaptability to changing scenarios and achieves a more accurate representation of market operation status.

[0030] 3、The application constructs a unified multi-dimensional operation index vector through vectorization, normalization and weighted representation after obtaining the subjective and objective fusion weight, and uses the positive ideal solution and non-ideal solution to construct an evaluation reference space, so that the multi-dimensional index has the characteristics of geometric processing, thereby significantly improving the explainability and discrimination of comprehensive evaluation. By calculating the Euclidean distance between the weighted index and the ideal state data and the non-ideal state data, the application can convert the complex multi-dimensional operation information into a measurable proximity relationship, and quantize the relative advantages and disadvantages of the operation day in the form of closeness, so that the evaluation result is intuitive, coherent and easy to compare horizontally. In addition, the application divides the closeness into different levels such as excellent, good and early warning by setting the first threshold and the second threshold, forms a standardized operation effect determination rule, so that the evaluation result has both continuity and classification characteristics, and is more in line with the actual use requirements of supervision, power grid dispatching and market management. Further, the application uses the closeness of continuous days to construct a health degree time sequence, and provides data support for operation risk warning, load characteristic analysis and market mechanism optimization through sequence trend, periodic fluctuation and abnormal point identification. Overall, the application converts multi-dimensional operation information into executable and analyzable comprehensive evaluation results through weighted vector construction, TOPSIS evaluation model and threshold classification mechanism, which is beneficial to improve the fine degree and intelligent level of power market operation state monitoring. BRIEF DESCRIPTION OF DRAWINGS

[0031] The accompanying drawings constituting a part of the specification illustrate the present application and are used for explaining the present application, and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A flow chart of the power market multi-dimensional operation effect dynamic evaluation method of the embodiment of the application; Figure 2 An implementation flow chart of the power market multi-dimensional operation effect dynamic evaluation method of the embodiment of the application; Figure 3 A structure block diagram of the power market multi-dimensional operation effect dynamic evaluation device of the embodiment of the application; Figure 4 A structure block diagram of the electronic device of the embodiment of the application. DETAILED DESCRIPTION

[0032] The application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0033] The following detailed description is exemplary and intended to provide further detailed explanation of the invention. Unless otherwise specified, all technical terms used in this invention have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains. The terminology used in this invention is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention.

[0034] Example 1 The following embodiments are described according to the overall process of the present invention. Through methods and steps such as collecting, quality processing, dimensionless processing, objective weight calculation, subjective weight calculation, subjective and objective weight fusion, multi-indicator approximation calculation, and health calculation of multi-dimensional operation indicators of the power market, a comprehensive dynamic evaluation of the daily operation effect of the power market is achieved.

[0035] The method for dynamic evaluation of multi-dimensional operational effectiveness of the electricity market provided in this embodiment of the invention, such as... Figure 1 and Figure 2 As shown, it includes steps S1 to S4.

[0036] In step S1, multi-dimensional operational indicator data of the electricity market on the assessment date is obtained. The multi-dimensional operational indicator data is a set of operational indicators used to quantitatively characterize the overall operational status of the electricity market across multiple dimensions. These multi-dimensional operational indicators include at least: congestion cost indicators, renewable energy absorption rate indicators, frequency of exceeding capacity limits at power grid sections, and participation rate of small and medium-sized entities.

[0037] In this embodiment, the raw operational data for each day within the electricity market operation evaluation period is first obtained to form a raw indicator matrix. ,in Indicates the first On the day The raw values ​​for each indicator. These indicators include key metrics reflecting economic efficiency, green development, system safety, and market vitality, such as congestion costs, renewable energy absorption rate, number of cross-section exceedances, and participation rate of small and medium-sized entities. Due to differences in dimensions and orders of magnitude among different indicators, standardization is required to eliminate these dimensional differences in order to allow for comparison within the same evaluation system.

[0038] In step S2, the multidimensional operational indicator data is processed based on the information entropy method to obtain the information entropy of each operational indicator, and the objective weight of each operational indicator is determined based on the information entropy. The steps for calculating the information entropy of each operational indicator include: preprocessing the multidimensional operational indicators according to their positive and negative attributes, and then calculating the information entropy of each preprocessed operational indicator.

[0039] In this embodiment, standardization is divided into two types: linear standardization and vector normalization. In the objective weight calculation stage, linear max-min standardization is used. This method maps the minimum and maximum values ​​of each indicator to 0 and 1 respectively, and linearly stretches the intermediate value range, fully revealing the differences between historical samples. This helps to highlight the contribution of extreme values ​​and fluctuations in the probability distribution, thereby improving the sensitivity and discriminative power of the entropy weight method to indicator dispersion. The preprocessing steps include: If a certain indicator is a benefit-oriented indicator (the larger the value, the better), its standardized value It can be calculated using the following formula:

[0040] If a certain indicator is a cost-based indicator (the smaller the value, the better), its standardized value is calculated using the following formula:

[0041] in This represents the number of sample days. This method scales the indicator vector to a unit vector, enabling comparability of different indicators within the same vector space. In the general process description, this method uses linear standardization as the main process, while retaining vector normalization as an optional solution to accommodate standardization requirements in different implementation environments.

[0042] After standardization, it is necessary to calculate the objective weights of each indicator to reflect the dispersion of indicator data across different operating days. This embodiment uses the entropy weight method to calculate the objective weights. The steps for calculating the information entropy of each preprocessed operating indicator include: firstly, calculating the weight matrix of each indicator under the standardization matrix. The calculation method is as follows:

[0043] in Indicates the first The first indicator in the The proportion of each sample (operation day) is used to represent the weight of the first sample. The relative proportion of the day in this indicator column.

[0044] Then, the entropy value of each indicator is calculated based on the information entropy theory. The formula for calculating the entropy value is as follows:

[0045] Wherein, the definition is when hour, , The constant is used to ensure that the entropy value is normalized. This indicates the number of samples involved in the entropy calculation. This represents the standardized weight of the j-th performance indicator in the i-th sample. H (j) represents the information entropy of the jth operation index.

[0046] The step of determining the subjective and objective fusion weight of each operation index comprises: firstly, determining the objective weight of each operation index according to the information entropy of each operation index. Then, determining the subjective weight of each operation index based on the subjective evaluation of each operation index. Finally, fusing the objective weight and the subjective weight according to a preset weight fusion strategy to obtain the subjective and objective fusion weight of each operation index.

[0047] The step of determining the objective weight of each operation index according to the information entropy of each operation index comprises: after obtaining the entropy value, further calculating the difference coefficient of the index (the difference coefficient reflects the importance of the index): The greater the difference coefficient, the more obvious the difference between the indexes, and the greater the amount of information provided.

[0048] Finally, the above difference coefficient is normalized to obtain the objective weight of the index :

[0049] wherein, is the number of operation indexes participating in the evaluation, is the information entropy of the jth operation index, is the difference degree of the jth operation index, is the objective weight of the jth operation index. The above weight reflects the objective importance of each index based on the data discreteness.

[0050] The step of determining the subjective weight of each operation index based on the subjective evaluation of each operation index comprises: constructing a judgment matrix according to the subjective pairwise comparison results of the relative importance of each operation index, obtaining the initial subjective weight vector of each operation index by geometrically averaging each row element of the judgment matrix and normalizing the obtained results. Then, calculating the maximum eigenvalue, consistency index and consistency ratio of the judgment matrix. When the consistency ratio is less than a preset threshold, the subjective weight vector is taken as the subjective weight of each operation index, otherwise the judgment matrix is adjusted and recalculated until the consistency requirement is met.

[0051] ​Specifically, after obtaining the objective weight based on data difference, the experience judgment of the power market manager is introduced to make the evaluation system reflect both the objective data law and the industry experience demand. In this embodiment, the analytic hierarchy process (AHP) is used to construct the subjective weight system of the indexes. First, according to the relative importance between the evaluation indexes such as the blocking cost, the new energy consumption rate, the cross-section overrun times, and the participation rate of small and medium-sized subjects, the operation experts or market analysts compare each pair of indexes, as shown in Table 1 below. According to the Saaty scale method, the relative importance of different indexes is assigned a scale value of 1-9 and its reciprocal. According to these pairwise comparison results, a judgment matrix is constructed wherein represents the relative importance of the index relative to the index , satisfies , and .

[0052]

[0053] Table 1 After the judgment matrix is constructed, the geometric mean method is used to obtain the subjective weight of the indexes. For the first row of the judgment matrix, the geometric mean value of the row is obtained by multiplying all the elements in the row and taking the nth root (where n is the number of indexes). The formula is as follows:

[0054] wherein i is the index index, and j is the element index in the row. After obtaining the geometric mean values of all rows, they are normalized to obtain the subjective weight vector of each index:

[0055] wherein k is the traversal index of the normalized sum, represents the geometric mean value of all elements in the ith row of the judgment matrix, and represents the subjective weight of the ith index. In order to verify the consistency of the judgment matrix, the maximum eigenvalue and the consistency index of the judgment matrix need to be calculated. First, the vector is calculated by matrix multiplication, and the maximum eigenvalue of the judgment matrix is estimated according to the following formula:

[0056] wherein represents the ith component of the vector obtained by multiplying the matrix A and the weight vector , and represents the number of indexes participating in the judgment. After obtaining the maximum eigenvalue, the consistency index CI is calculated: ​​​​​​

[0057] At the same time, according to the number of indicators, the random consistency index RI is found, and the ratio of the two is taken as the consistency ratio CR:

[0058] If CR is less than 0.1, it is considered that the judgment matrix has acceptable consistency, and at this time the above subjective weight vector can be used as an effective weight for subsequent calculation. If CR does not meet the requirements, it is necessary to return to adjust the judgment matrix and recalculate until the consistency reaches the requirements.

[0059] In actual engineering, the judgment matrix can be filled by multiple experts independently, and the average matrix is taken to reduce individual bias. A preset matrix can also be formed in combination with an expert knowledge base to improve the efficiency of weight modeling.

[0060] The steps of obtaining the subjective and objective fusion weights of each operation index include: distributing the subjective weight and the objective weight proportion according to the market scene demand, and generating the subjective and objective fusion weights. Considering the subjective and objective factors, the subjective and objective weight coefficients are set focus on the objective, focus on the subjective), to obtain the subjective and objective fusion weights:

[0061] Among them, indicates the subjective and objective fusion weight of the jth operation index, indicates the objective weight of the jth operation index calculated based on information entropy, indicates the subjective weight of the jth operation index determined based on subjective evaluation, is the subjective and objective weight coefficient.

[0062] In step S3, the multi-dimensional operation index of the day to be evaluated is weighted based on the subjective and objective fusion weight, and the ideal value of each operation index in the ideal operation state and the non-ideal operation state is determined. The ideal values are sequentially combined to form the ideal state data and the non-ideal state data of the power market, the difference degree of the weighted multi-dimensional operation index with respect to the ideal state data and the non-ideal state data is calculated, and the closeness of the weighted multi-dimensional operation index with respect to the ideal state data is determined according to the difference degree.

[0063] ​After obtaining the subjective and objective fusion weights, this embodiment further employs the idea of ​​approximating the ideal solution ranking to evaluate the comprehensive operational effect of each operating day. In this stage, vector normalization is used to normalize the indicator data. Vector normalization normalizes each indicator column to a unit vector space by the sum of squares, ensuring that different indicators are in a unified scale system for Euclidean distance calculation, reducing the interference of dimensional differences on geometric distance. Combined with the subjective and objective fusion weights, this ensures the stability and numerical consistency of multidimensional distance calculations. For any indicator column, its standardized values ​​can be... Calculate using the following formula:

[0064] Based on the standardized indicator matrix, each indicator is weighted according to the final subjective-objective fusion weight. Let the standardized indicator matrix be... ,in For the first The evaluation object (operational day) on the [number]th [day] The standardized values ​​for each indicator, with a weighted average of subjective and objective factors, are: Then the weighted standardized matrix The elements are calculated using the following formula:

[0065] After weighted standardization, the data for each indicator has been dimensionless, directionally consistent, and weighted, thus meeting the requirements for multi-indicator distance calculation.

[0066] To calculate the distance between each evaluation object and the ideal state, it is necessary to first determine the positive and negative ideal solutions. For benefit-type indicators (the larger the value, the better), in the... In terms of each indicator, its positive ideal value The maximum value among the weighted standardized values ​​in this column, representing the negative ideal value. The minimum value. For cost-related indicators (the smaller the value, the better), the ideal value is... Minimum value, negative ideal value This represents the maximum value. Following this rule, positive and negative ideal solutions are determined for each index column, forming an ideal solution vector:

[0067]

[0068] in, This represents the weighted normalized value of the i-th evaluation object on the j-th operational indicator, where i is the index of the evaluation object and j is the index of the operational indicator.

[0069] And will each operating indicator The data is combined to form the ideal state of the electricity market, including various operating indicators. This data is combined to form the non-ideal state data of the electricity market.

[0070] After obtaining the positive and negative ideal solutions, the Euclidean distance between each operating day and the positive and negative ideal solutions is calculated to reflect the degree of closeness between the operating day and the ideal state and the degree of difference between the operating day and the worst-case state. For the , The distance is calculated using the following formula for each operating day:

[0071]

[0072] in, This represents the number of indicators. The smaller the distance mentioned above, the closer the operating day is to the positive ideal solution in the indicator space. Distance The larger the value, the further the operating day is from the negative ideal solution.

[0073] Based on the above distance results, the degree of closeness to the ideal state for this operating day is further calculated to serve as the final evaluation value of the overall operating performance. The formula for calculating the degree of closeness is as follows:

[0074] in, The range of values ​​is The closer the proximity to 1, the better the operational performance on that day. The closer the proximity to 0, the worse the operational performance. This indicator serves as the final comprehensive evaluation indicator for the multi-dimensional operation of the power market in this embodiment. It can be used to construct a health sequence, thereby enabling a visual display and dynamic trend analysis of the operational status.

[0075] In practical systems, proximity can be used as a market health index and can be classified into health levels based on empirical thresholds to identify operational anomalies, assist in the formulation of scheduling strategies, or determine whether market mechanisms need to be adjusted.

[0076] In step S4, the evaluation result of the power market operation performance on the day to be evaluated is determined based on the proximity score. After calculating the proximity score, this embodiment uses the proximity score to determine the evaluation result of the power market operation performance on each operating day within the evaluation period. The greater the proximity score, the closer the operating day is to the ideal operating state constituted by multiple key indicators, and the better the overall operating performance. The smaller the proximity score, the more the market operation performance on the operating day deviates from the ideal level. In this embodiment, a power market operation health sequence is formed based on the power market operation performance evaluation results over multiple consecutive days, and the operating trend, periodic fluctuations, and phased anomalies of the power market are identified based on the power market operation health sequence.

[0077] In this embodiment, the health status can be intuitively divided based on the proximity value range, assisting operators in identifying operational anomalies or assessing the market's condition. Combining electricity market operation experience, health status grading ranges can be set; for example, operating days with higher proximity values ​​correspond to better operating levels, while operating days with lower proximity values ​​correspond to operating deviations or days requiring attention. The specific health status range division method can be flexibly set according to actual operational requirements without affecting the core implementation process of this invention. In the application system, multiple levels can be set based on the proximity value range, such as: 0.8-1.0 is rated as excellent, 0.6-0.8 as good, and <0.6 as warning, etc., to support visualized health status presentation, retrospective analysis of historical abnormal days, and decision support in dispatching and market operation management.

[0078] For example, the proximity score can be compared with a preset first threshold and a second threshold. If the second threshold is greater than the first threshold, and the proximity score is greater than or equal to the second threshold, the evaluation date is considered to have excellent electricity market operation performance. If the proximity score is between the first and second thresholds, the evaluation date is considered to have good electricity market operation performance. If the proximity score is less than or equal to the first threshold, the evaluation date is considered to have electricity market operation performance requiring warning.

[0079] In this invention, the process of acquiring objective weights is decoupled from the multi-indicator approximation calculation process. Linear minimax standardization and vector normalization are selected respectively. Through the phased use of these two standardization methods, structural decoupling between the weight learning module and the multi-indicator evaluation module is achieved. On the one hand, this enhances the sensitivity of objective weights to differences in historical sample intervals, making the weight allocation more reflective of the true fluctuation characteristics of the indicators. On the other hand, it ensures the geometric stability of the Euclidean distance calculation, reducing the coupling impact of a single standardization method on the final evaluation result when used throughout the entire process. Therefore, this invention can obtain robust weight identification results and stable multi-dimensional approximation evaluation results simultaneously without increasing model complexity, improving the reliability and interpretability of the comprehensive evaluation of the power market operation effect.

[0080] In a specific application scenario of this invention, as shown in Table 2 below, three typical operating days—January 5th, January 12th, and January 19th—of a certain regional electricity market are used as evaluation objects. An evaluation system is constructed using four indicators: congestion cost, renewable energy absorption rate, number of cross-section overruns, and participation rate of small and medium-sized entities. The multi-dimensional operational effects are then specifically calculated. First, raw operating data for the above three days are collected to form a raw indicator matrix. The raw data for congestion cost are 320, 85, and 210, respectively; the raw data for renewable energy absorption rate are 92.8%, 96.5%, and 88.2%, respectively; the data for the number of cross-section overruns are 3, 0, and 5, respectively; and the data for the participation rate of small and medium-sized entities are 58%, 42%, and 51%, respectively. This data comes from the dispatch automation system, settlement system, and renewable energy monitoring platform, and can comprehensively reflect the market operation status on the three days.

[0081]

[0082] Table 2 Example of raw operating data for a certain electricity market Because the indicators have different dimensions and significant differences in magnitude, they need to be standardized before calculating objective weights. A distinction needs to be made between positive indicators (the larger the better, such as the renewable energy absorption rate and the participation rate of small and medium-sized entities) and negative indicators (the smaller the better, such as congestion costs and the number of times a section exceeds its limit), and both positive and negative indicators should be standardized separately. Taking congestion cost as an example, as a negative indicator, the original data is: [320, 85, 210]. , The standardized formula is Thus, the standardized matrix is ​​obtained as [0, 1, 0.4681]. Taking the renewable energy absorption rate as an example, as a positive indicator, the original data is: [92.8, 96.5, 88.2]. , The standardized formula is Thus, the standardized matrix is ​​obtained as [0.5542,1,0]. The calculated standardized matrix is ​​shown in Table 3 below:

[0083] Table 3 Standardization Matrix of a Certain Electricity Market For each metric, calculate the percentage of the time period and the entropy value of that metric. Taking congestion cost as an example, the sum of this metric across all time periods... , January 19 The calculated percentages for each time period are [0, 0.6812, 0.3188]. The entropy value of this indicator is calculated as follows:

[0084] The coefficient of difference for this indicator is .

[0085] The calculated entropy values ​​and difference coefficients for each indicator are shown in Table 4 below:

[0086] Table 4. Entropy values ​​and difference coefficients of various indicators in a certain electricity market. The weights of each indicator after normalization are shown in Table 5 below:

[0087] Table 5 Weights of Various Indicators in a Certain Electricity Market Then, by integrating expert experience and policy requirements through the Analytic Hierarchy Process (AHP), subjective weights are generated to enhance the influence of production experience factors.

[0088] In this embodiment, the judgment matrix for the four indicators—blockage cost, number of cross-section overruns, renewable energy absorption rate, and participation rate of small and medium-sized entities—is as follows:

[0089] Among the elements a 12 =3 indicates that the cost of blocking is slightly more important than the number of times the cross-section exceeds the limit. a 13 =5 indicates that congestion costs are significantly more important than the renewable energy absorption rate. a 14 =7 indicates that the cost of blocking is significantly more important than the participation rate of small and medium-sized entities.

[0090] Calculate the geometric mean of each row of the judgment matrix:

[0091]

[0092]

[0093]

[0094] Normalizing the geometric mean yields the subjective weight vector: ,

[0095]

[0096] .

[0097] The subjective weights of the four indicators: cost of blockage, number of times the cross-section exceeds the limit, renewable energy consumption rate, and participation rate of small and medium-sized entities. .

[0098] Then, a consistency check is performed. First, the product of the judgment matrix and the weights is calculated. AW :

[0099] Then calculate the largest eigenvalue. :

[0100] Then calculate the consistency index :

[0101] get .

[0102] Calculate the test coefficient : get The subjective weights are valid as they pass the consistency test.

[0103] Then, subjective and objective weights are allocated according to market scenario needs to generate a combined subjective and objective weight.

[0104] Taking into account both subjective and objective factors, a weighting coefficient for subjective and objective factors is established. ( Emphasis on objectivity (Focusing on subjective factors), a weighted average of subjective and objective factors is obtained: Set the subjective and objective weighting coefficients as follows: As shown in Table 6 below, the subjective and objective fusion weights of each indicator are calculated:

[0105] Table 6 Weights of Various Indicators in a Certain Electricity Market Next, the TOPSIS method is used to calculate the market health proximity based on a combination of subjective and objective weights.

[0106] The indicator data is re-standardized using vector normalization. Taking blocking cost as an example, the original data is [320, 85, 210], and the standardization formula is:

[0107] The resulting standardized matrix is: [0.8162, 0.2168, 0.5356]. The calculated standardized matrix is ​​shown in Table 7 below:

[0108] Table 7 Standardization Matrix of TOPSIS Method in a Certain Electricity Market Multiplying the standardized data as shown in Table 7 by the weights determined by the entropy weighting method as shown in the table yields the weighted standardization matrix:

[0109] Table 8. TOPSIS Weighted Standardization Matrix for a Certain Electricity Market For each indicator, distinguish between benefit-based indicators (the larger the better) and cost-based indicators (the smaller the better), and calculate positive / negative ideal solutions separately. Taking congestion cost as an example, as a cost-based indicator, the values ​​for all solutions are [0.206, 0.0547, 0.1352], and the minimum value is taken as the positive ideal solution. The negative ideal solution takes the maximum value. The calculated positive / negative ideal solutions for each index are shown in Table 9 below:

[0110] Table 9 Positive / Negative Ideal Solutions of TOPSIS Method for a Certain Electricity Market Calculate the Euclidean distance to the positive / negative ideal solution for different date parameters, and calculate the relative proximity.

[0111] Taking January 5th (peak day) as an example, the parameter data are [0.206, 0.1405, 0.1352, 0.1597], and the positive ideal solution for each parameter is [0.0547, 0.1462, 0.0000, 0.1597]. According to the Euclidean distance formula for the positive ideal solution: The calculation yields:

[0112] The negative ideal solutions for each parameter are [0.206, 0.1336, 0.2252, 0.1156]. According to the Euclidean distance formula for the negative ideal solution: The calculation yields: .

[0113] The relative proximity to January 5th (peak) is: The calculated Euclidean distances and relative proximity of the positive / negative ideal solutions for different typical days are shown in Table 10 below:

[0114] Table 10. TOPSIS Euclidean Distance and Relative Proximity in a Certain Electricity Market The greater the relative similarity, the better the solution. Based on the rating system: 0.8-1.0 is rated as excellent, 0.6-0.8 as good, and <0.6 as a warning. The resulting electricity market health ratings are shown in Table 11 below.

[0115] Table 11 Health Rating of a Certain Electricity Market This invention achieves a precise characterization of the health of the electricity market by constructing a dynamic evaluation mechanism that integrates objective operational data with subjective policy guidance. Compared with traditional evaluation methods that rely on a single indicator or fixed weights, this invention can maintain real-time sensitivity and adaptability to the market's operational status in the context of high-proportion renewable energy integration and deepening market-oriented reforms.

[0116] First, this invention identifies fluctuations and information differences among operational indicators using the entropy weight method. This automatically strengthens the weights of key indicators reflecting the utilization level of new energy sources, forming an adaptive indicator system for scenarios with a high proportion of new energy. This helps identify absorption bottlenecks, improve the utilization efficiency of wind and solar energy, and reduce wind and solar curtailment, thus supporting the operation of a green and friendly market under the new power system. Second, based on multi-dimensional operational indicators such as congestion costs, new energy absorption rate, frequency of exceeding limits at power sections, and participation rate of small and medium-sized entities, this invention constructs a comprehensive evaluation framework of "efficiency-safety-greenness-vitality." It also uses the TOPSIS method to quantify the comprehensive advantages and disadvantages among multiple indicators, breaking through the limitations of traditional single-dimensional analysis and significantly enhancing the panoramic perception capability of the power market's operational status. Furthermore, through the dynamic fusion of subjective and objective weights, this invention can flexibly adjust indicator weights in scenarios such as new energy output disturbances and load changes to adapt to the phased changes in the operating environment. This enables early identification and warning of potential operational risks, providing support for market intervention strategies and operational optimization. In summary, this invention constructs a closed-loop health analysis system for the power market, encompassing "dynamic perception, precise assessment, and intelligent early warning," through the synergistic application of a data-driven dynamic weighting mechanism and a multi-dimensional coupled evaluation model. This system can improve market operation efficiency and security in the context of high-proportion renewable energy access, and has significant engineering application value and promotion prospects.

[0117] Example 2 like Figure 3 As shown, based on the same inventive concept as the above embodiments, the present invention also provides a dynamic evaluation device for multi-dimensional operational effectiveness of the electricity market, comprising: The data acquisition module is used to acquire multi-dimensional operational indicator data of the electricity market on the evaluation date.

[0118] The subjective-objective fusion weight calculation module is used to calculate the information entropy of each operating indicator and determine the subjective-objective fusion weight of each operating indicator based on the information entropy.

[0119] The proximity calculation module is used to weight the multi-dimensional operating indicators on the evaluation date based on the subjective and objective fusion weights, and to determine the ideal values ​​of each operating indicator under ideal and non-ideal operating conditions. The ideal values ​​are then combined in sequence to form ideal and non-ideal state data of the power market. The module calculates the degree of difference between the weighted multi-dimensional operating indicators and the ideal and non-ideal state data, and determines the proximity of the weighted multi-dimensional operating indicators to the ideal state data based on the degree of difference.

[0120] The evaluation module is used to determine the evaluation results of the power market operation performance on the evaluation date based on proximity.

[0121] Example 3 like Figure 4 As shown, the present invention also provides an electronic device 100 for realizing a method for dynamic evaluation of multi-dimensional operational effectiveness in the power market; The electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on at least one processor 102, and at least one communication bus 104.

[0122] The memory 101 can be used to store computer programs 103. The processor 102 implements the dynamic evaluation method for multi-dimensional operation effect of the power market in Embodiment 1 by running or executing the computer programs stored in the memory 101 and calling the data stored in the memory 101.

[0123] The memory 101 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the electronic device 100 (such as audio data), etc. In addition, the memory 101 may include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0124] At least one processor 102 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 102 may be a microprocessor or any conventional processor. Processor 102 is the control center of electronic device 100, connecting various parts of electronic device 100 via various interfaces and lines.

[0125] The memory 101 in the electronic device 100 stores multiple instructions to implement a dynamic evaluation method for multi-dimensional operational effectiveness in the electricity market, and the processor 102 can execute multiple instructions to achieve the following: Obtain multi-dimensional operational indicator data of the electricity market on the assessment date; Calculate the information entropy of each operational indicator, and determine the subjective and objective fusion weights of each operational indicator based on the information entropy; Based on the subjective and objective fusion weighting, the multi-dimensional operation indicators of the evaluation date are weighted and represented, and the ideal values ​​of each operation indicator under ideal and non-ideal operation conditions are determined. The ideal values ​​are combined in sequence to form ideal and non-ideal state data of the power market. The degree of difference between the weighted multi-dimensional operation indicators and the ideal and non-ideal state data is calculated. The closeness of the weighted multi-dimensional operation indicators to the ideal state data is determined based on the degree of difference. The evaluation results of the power market operation effectiveness on the assessment date are determined based on proximity.

[0126] Example 4 If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, and read-only memory (ROM).

[0127] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0128] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0129] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0130] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0131] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0132] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A dynamic evaluation method for multi-dimensional operational effectiveness of the electricity market, characterized in that, include: Obtain multi-dimensional operational indicator data of the power market on the date to be evaluated. The multi-dimensional operational indicator data is a set of operational indicators used to quantitatively characterize the overall operational status of the power market in multiple dimensions. The multidimensional operational indicator data is processed based on the information entropy method to obtain the information entropy of each operational indicator, and the subjective and objective fusion weight of each operational indicator is determined based on the information entropy. Based on the aforementioned subjective and objective fusion weights, the multi-dimensional operating indicators for the evaluation date are weighted and represented. The ideal values ​​of each operating indicator under ideal and non-ideal operating conditions are determined respectively. The ideal values ​​are combined in sequence to form ideal and non-ideal operating conditions data of the electricity market. The degree of difference between the weighted multi-dimensional operating indicators and the ideal and non-ideal operating conditions data is calculated. The degree of difference is used to determine the closeness of the weighted multi-dimensional operating indicators to the ideal operating conditions data. The evaluation result of the power market operation performance on the assessment date is determined based on the proximity.

2. The method for dynamic evaluation of multi-dimensional operational effectiveness of the electricity market according to claim 1, characterized in that, The steps for calculating the information entropy of each operational indicator include: The multidimensional operational indicators are preprocessed according to their positive and negative attributes; Calculate the information entropy of each preprocessed operational indicator; The preprocessing steps include: The original value of the j-th operational indicator in the i-th sample of the multidimensional operational indicators. Standardize the values ​​to obtain the standardized values. For efficiency-related operational indicators, standardization is performed according to the following formula: For cost-based operating indicators, standardization is performed according to the following formula: in, This represents the original value of the j-th performance indicator in the i-th sample. This represents the maximum value of the j-th performance indicator across all samples. This represents the minimum value of the j-th performance indicator among all samples; The steps for calculating the information entropy of each preprocessed operational indicator include: Obtaining standardized indicator values Based on this, the weight of the j-th operating indicator in the i-th sample is calculated according to the following formula. : Calculate the information entropy of the j-th operating indicator using the following formula. : in, This indicates the number of samples involved in the entropy calculation. This represents the standardized weight of the j-th performance indicator in the i-th sample. Let represent the information entropy of the j-th operating metric.

3. The method for dynamic evaluation of multi-dimensional operational effectiveness of the electricity market according to claim 2, characterized in that, The steps for determining the combined subjective and objective weights of each operational indicator include: The objective weight of each operational indicator is determined based on the information entropy of each indicator. The subjective weight of each operational indicator is determined based on the subjective evaluation of each operational indicator. The objective weights and subjective weights are fused according to a preset weight fusion strategy to obtain the subjective-objective fusion weights of each operating indicator. The steps for determining the objective weight of each operational indicator based on its information entropy include: The information entropy of each operating indicator was calculated. Then, the variance of the j-th operating indicator is calculated according to the following formula. : The objective weight of the j-th operating indicator is calculated using the following formula. : in, The number of operational indicators participating in the evaluation. Let the information entropy be the j-th operational metric. Let j be the degree of difference of the j-th operating indicator. Let be the objective weight of the j-th operational indicator; The subjective weights of each operational indicator are determined based on subjective evaluations, including: A judgment matrix is ​​constructed based on the subjective pairwise comparison results of the relative importance of each operational indicator. The initial subjective weight vector of each operational indicator is obtained by taking the geometric mean of the elements in each row of the judgment matrix and normalizing the result. Calculate the maximum eigenvalue, consistency index, and consistency ratio of the judgment matrix. If the consistency ratio is less than a preset threshold, use the subjective weight vector as the subjective weight of each running index. Otherwise, adjust the judgment matrix and recalculate it until the consistency requirements are met.

4. The method for dynamic evaluation of multi-dimensional operational effectiveness of the electricity market according to claim 3, characterized in that, The steps for obtaining the subjective and objective combined weights of each operational indicator include: The subjective and objective fusion weights of each operational indicator are calculated using the following formula: in, This represents the combined subjective and objective weighting of the j-th operational indicator. This represents the objective weight of the j-th operational indicator calculated based on information entropy. This represents the subjective weight of the j-th operational indicator, determined based on subjective evaluation. The subjective and objective weighting coefficients.

5. The method for dynamic evaluation of multi-dimensional operational effectiveness of the electricity market according to claim 4, characterized in that, The step of weighting the multidimensional operational indicators for the evaluation date based on the subjective and objective fusion weights includes: After determining the subjective and objective fusion weights of each operational indicator, the multidimensional operational indicators for the evaluation date are normalized using vector normalization. The normalized value of each operational indicator is multiplied by the corresponding subjective and objective fusion weight to obtain the weighted normalized value of each operational indicator. The weighted normalized values ​​are then combined in the order of the operational indicators to form the weighted multidimensional operational indicators.

6. The method for dynamic evaluation of multi-dimensional operational effectiveness of the electricity market according to claim 5, characterized in that, The degree of closeness of the weighted multidimensional operating indicators to the ideal state data includes: Calculate the positive ideal value of the efficiency-oriented operation indicator using the following formula. and negative ideal value : Calculate the positive ideal value of cost-type operating indicators using the following formula. and negative ideal value : in, This represents the weighted normalized value of the i-th evaluation object on the j-th operational indicator, where i is the index of the evaluation object and j is the index of the operational indicator. And will each operating indicator The data is combined to form the ideal state of the electricity market, including various operating indicators. Combining data to form non-ideal state data of the electricity market; The distance between the weighted multidimensional operating index of the i-th evaluation object and the ideal state data and the non-ideal state data is calculated according to the following formula. and : in, The number of operational indicators; The closeness of the i-th evaluation object to the ideal state data is calculated using the following formula. : 。 7. The method for dynamic evaluation of multi-dimensional operational effectiveness of the electricity market according to claim 6, characterized in that, After determining the evaluation results of the power market operation performance on the day to be evaluated based on the proximity, the process also includes: forming a power market operation health sequence based on the power market operation performance evaluation results over multiple consecutive days, and identifying the operation trend, periodic fluctuations and phased anomalies of the power market based on the power market operation health sequence. The multi-dimensional operation indicators include at least: congestion cost indicators, new energy absorption rate indicators, cross-section over-limit frequency indicators, and small and medium-sized entity participation rate indicators. The evaluation results of the electricity market operation performance on the assessment date include: Based on the magnitude of the proximity score, the proximity score is compared with a preset first threshold and a second threshold. If the second threshold is greater than the first threshold, the day to be evaluated is judged to have excellent power market operation performance when the proximity score is greater than or equal to the second threshold; if the proximity score is between the first threshold and the second threshold, the day to be evaluated is judged to have good power market operation performance; if the proximity score is less than or equal to the first threshold, the day to be evaluated is judged to have power market operation performance requiring warning.

8. A dynamic evaluation device for multi-dimensional operational effectiveness in the electricity market, characterized in that, include: The data acquisition module is used to acquire multi-dimensional operational indicator data of the electricity market on the date to be evaluated; The subjective-objective fusion weight calculation module is used to calculate the information entropy of each operating indicator and determine the subjective-objective fusion weight of each operating indicator based on the information entropy. The proximity calculation module is used to weight the multi-dimensional operating indicators of the evaluation date based on the subjective and objective fusion weights, and to determine the ideal values ​​of each operating indicator under ideal and non-ideal operating conditions. The ideal values ​​are then combined in sequence to form ideal and non-ideal state data of the power market. The module calculates the degree of difference between the weighted multi-dimensional operating indicators and the ideal and non-ideal state data, and determines the proximity of the weighted multi-dimensional operating indicators to the ideal state data based on the degree of difference. The evaluation module is used to determine the evaluation result of the power market operation performance on the evaluation date based on the proximity.

9. An electronic device, characterized in that, It includes a processor and a memory, the processor being used to execute a computer program stored in the memory to implement the dynamic evaluation method for multi-dimensional operational effectiveness of the electricity market as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, which, when executed by a processor, implements the dynamic evaluation method for multi-dimensional operational effectiveness of the electricity market as described in any one of claims 1 to 7.

Images