Multi-dimensional visual evaluation method and system for provincial power market subject behaviors

Abstract

The invention discloses a provincial power market subject behavior multi-dimensional visual evaluation method and system, and the method comprises the steps: constructing a power market subject behavior evaluation index system, and scoring all indexes. And determining an index weight by using the AHP, and checking the consistency. And combining an NSGA-II genetic algorithm with an analytic hierarchy process, and calculating a comprehensive evaluation score according to evaluation results of multiple simulations. And drawing a key power market subject behavior multi-dimensional portrait based on a power market subject behavior comprehensive evaluation result. According to the provincial power market subject behavior multi-dimensional visual evaluation method and system provided by the invention, the NSGA-II genetic algorithm and the analytic hierarchy process are integrated, the condition of the provincial power market subject behavior is comprehensively and effectively evaluated, a multi-dimensional evaluation tool evaluates the provincial power market subject behavior from different angles, and effective support is provided for later decision making.

Description

Technical Field

[0001] The present invention relates to the technical field of power market analysis, and in particular to a multi-dimensional visual evaluation method and system for the behavior of provincial power market entities. Background Art

[0003] Traditional evaluation methods are often limited to single-dimensional analysis, which makes it difficult to fully reflect the complexity and multidimensionality of market players' behaviors. In addition, the presentation of evaluation results is often not intuitive enough, making it difficult to provide decision makers with clear market insights. Therefore, developing a method and system that can comprehensively consider multiple evaluation dimensions and intuitively present evaluation results through visualization is of great significance to improving the transparency and management efficiency of the power market.

[0004] The multi-dimensional visualization evaluation method builds a comprehensive evaluation system by integrating indicators of multiple dimensions such as economy, reliability, and environmental impact. This method can not only provide richer and more in-depth market behavior analysis, but also help market regulators and participants better understand market dynamics and make more scientific decisions. At the same time, with the development of information technology and data visualization technology, it has become possible to intuitively display complex data in the form of graphics, charts, etc., which provides technical support for the multi-dimensional visualization evaluation of the behavior of power market players.

[0005] The healthy development of the power market also requires a sound market power assessment mechanism to prevent market monopoly and unfair competition. The development trend of market power assessment research shows that the assessment method is gradually changing from market share-based assessment to a more comprehensive assessment method that considers load, congestion, and participant behavior. This requires the assessment system to be able to adapt to the ever-changing market environment and provide dynamic and real-time assessment results. Summary of the invention

[0006] In view of the above-mentioned problems, the present invention is proposed.

[0007] Therefore, the technical problem solved by the present invention is that the development trend of market power evaluation research requires the evaluation system to be able to adapt to the ever-changing market environment and provide dynamic and real-time evaluation results, but the evaluation methods in the prior art are not satisfactory.

[0008] In order to solve the above technical problems, the present invention provides the following technical solutions: a multi-dimensional visualization evaluation method for the behavior of provincial power market entities, comprising: constructing an evaluation index system for the behavior of power market entities and scoring each index.

[0009] AHP was used to determine the indicator weights and test the consistency.

[0010] The NSGA-II genetic algorithm is combined with the analytic hierarchy process to calculate the comprehensive evaluation score based on the evaluation results of multiple simulations.

[0011] Based on the comprehensive evaluation results of the behaviors of power market players, a multi-dimensional portrait of the behaviors of key power market players is drawn.

[0012] As a preferred scheme of the multi-dimensional visualization evaluation method of the behavior of provincial power market entities described in the present invention, the construction of the power market entity behavior evaluation index system includes constructing a three-level index, dividing the power market entity behavior evaluation index system, including 3 target layers, 9 criterion layers and 25 indicator layers, which comprehensively covers all aspects of the behavior of power market entities.

[0013] Scoring of various indicators is the process of experts scoring various indicators of the electricity market subject behavior evaluation system.

[0014] As a preferred solution of the multi-dimensional visualization evaluation method for the behavior of provincial power market entities described in the present invention, the method of determining the indicator weights by using AHP includes establishing a multi-level indicator layer according to the evaluation system framework of the behavior of power market entities. Experts assign weights to the indicators at each level for the behavior of power market entities, and construct a judgment matrix A=(a ij ) n×n .

[0015] The indicators at all levels are compared pairwise and assigned relative importance weights. The weight scale ranges from 1 to 9.

[0016] Construct judgment matrix A = (a ij ) n×n , a ij Indicates the importance of index i relative to index j. A=(a ij ) n×n is an n×n matrix, a ij =1 / a ji , diagonal element a ii =1.

[0017] First, initialize the judgment matrix A, expressed as:

[0018]

[0019] Among them, a ij Assigned by experts, a ij =1 / a ji .

[0020] The indicators at each level of the indicator layer are compared pairwise and the values ​​are substituted into the judgment matrix.

[0021] As a preferred solution of the multi-dimensional visualization evaluation method for the behavior of provincial power market entities described in the present invention, wherein: the use of AHP to determine the index weights also includes calculating the maximum eigenvalue λ of the judgment matrix max and its corresponding eigenvector It is expressed as:

[0022]

[0023] Among them, W i represents the geometric mean weight of the i-th indicator, a ij represents the element in the i-th row and j-th column of the judgment matrix A, n represents the total number of indicators, Represents the normalized weight of the indicator.

[0024] The consistency index CI is introduced to perform consistency test. If the consistency ratio CR is less than 0.1, the consistency test is passed. The consistency test is expressed as:

[0025]

[0026] Among them, λ max It represents the maximum eigenvalue of the judgment matrix, RI represents the random consistency index, which is determined by the total number of indicators n.

[0027] As a preferred scheme of the multi-dimensional visualization evaluation method of the behavior of provincial power market entities described in the present invention, the steps of combining the NSGA-II genetic algorithm with the hierarchical analysis method include indicator weight optimization, weight change interval generation, random scoring, and comprehensive calculation according to the optimization model.

[0028] The indicator weight optimization includes that after adjusting the score of a certain indicator, if the evaluation result does not change much, the indicator cannot play a distinguishing role and the weight is set to 0. If the evaluation result changes greatly, a large weight is given to the indicator.

[0029] The weight change interval generation includes determining the weight value change interval through fuzzy theory to determine the change space of the optimized weight. Take the fuzzy sets A1, A2, A3, A4, and A5, which represent the five levels of weights, namely, very small, small, moderate, large, and very large, and generate the corresponding membership function. Select the Gaussian membership function that is more in line with the actual situation, expressed as:

[0030]

[0031] Among them, μA i represents the membership of the i-th fuzzy set, x represents the weight value, ranging from 0 to 1. iIt represents the central value of the i-th fuzzy set, σ represents the standard deviation, which controls the width of the Gaussian function, and i represents the index of the fuzzy set, which corresponds to 5 levels: very small, small, moderate, large, and very large.

[0032] Randomly generating scores includes generating a corresponding number of groups of random numbers according to the total number of evaluation indicators to simulate the evaluation process. Each group of data contains m random integers between 0 and 100 as the initial score values ​​of each indicator, expressed as:

[0033]

[0034] Where P represents probability, represents the sum of random variables, n represents the number of random variables, μ represents the mean of the random variables, σ 2 represents the variance of the random variable, t represents the integral variable, x represents the upper limit of the probability integral, {x n} represents a sequence of random variables that obey independent and identical distribution, E(x i )=μ,D(x i )=σ 2 ,i=1,2...n, which is satisfied for all x∈R.

[0035] For a random variable x that follows a uniform distribution i , when n is sufficiently large, there is a random variable Obey N(0,1).

[0036]

[0037] Among them, X1,…,X k represents a random variable, indicating the number of occurrences of different outcomes. n represents the total number of sampling times, n i represents the number of occurrences of the i-th outcome, p i represents the probability of the ith outcome.

[0038] Suppose a random experiment has k outcomes A1, A2, ...A k , assuming that the number of their occurrences is recorded as random variables X1, X2…X k , their probability distributions are p1, p2…p k , in the results of n samplings, A1 appears n1 times, A2 appears n2 times, ..., A n Appearance k The probability of an event P follows a multinomial distribution.

[0039] As a preferred solution of the multi-dimensional visualization evaluation method of the behavior of provincial power market entities described in the present invention, the comprehensive calculation based on the optimization model includes performing comprehensive calculation based on the optimization model combining the NSGA-II genetic algorithm and hierarchical analysis.

[0040] The objective function is expressed as:

[0041]

[0042] Among them, F1 represents the first objective function, maximizing the total sum of squared errors. m represents the total number of evaluation indicators, n represents the total number of weights, and w i represents the weight of the i-th indicator, r ij represents the score of the i-th weight and the j-th evaluation indicator, and M represents the average total score calculated based on n groups of random scores. F2 represents the second objective function, which minimizes the weight deviation and. w i 0 Indicates that the i-th indicator has the initial weight calculated by the AHP algorithm. M represents the average score, w i represents the weight of the i-th indicator, r ij represents the i-th weight and the score of the j-th evaluation metric.

[0043] The constraints are expressed as:

[0044]

[0045] w i >0

[0046] in, Indicates the upper limit of the weight change interval corresponding to the i-th indicator, Indicates the lower limit of the weight change interval corresponding to the i-th indicator.

[0047] As a preferred solution of the multi-dimensional visualization evaluation method for the behavior of provincial power market entities described in the present invention, the multi-dimensional portrait of the behavior of key power market entities based on the comprehensive evaluation results of the behavior of power market entities includes dividing the behavior data of power market entities into multiple attributes, including nine dimensions of the evaluation of the behavior of power market entities, namely registration information, transaction management, information disclosure, profitability, operational capacity, debt repayment capacity, growth capacity, safety management, and environmental protection. Result evaluation labels are established according to the characteristics of each attribute, and a label library is formed.

[0048] The tags in the tag library are classified into levels, including good, better, average, poor and bad.

[0049] According to the actual results of the behavior of the main players in the power market, corresponding labels are assigned to the parts to be profiled to achieve the characterization of the behavior results of the main players in the power market.

[0050] A multi-dimensional visual evaluation system for the behavior of provincial power market entities is characterized by comprising a scoring module, constructing an evaluation index system for the behavior of power market entities, and scoring each index.

[0051] Set up the weight module, use AHP to determine the indicator weights, and check the consistency.

[0052] The evaluation module combines the NSGA-II genetic algorithm with the analytic hierarchy process to calculate the comprehensive evaluation score based on the evaluation results of multiple simulations.

[0053] The visualization module draws a multi-dimensional portrait of the behavior of key power market players based on the comprehensive evaluation results of the behavior of power market players.

[0054] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0055] A computer-readable storage medium stores a computer program, which implements the steps of the method described above when executed by a processor.

[0056] The beneficial effects of the present invention are as follows: the NSGA-II genetic algorithm and the analytic hierarchy process are integrated to comprehensively and effectively evaluate the behavior of provincial power market players. The multi-dimensional evaluation tool evaluates the behavior of provincial power market players from different angles, providing effective support for subsequent decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0058] Figure 1 An overall flow chart of a provincial power market subject behavior multi-dimensional visualization evaluation method and system provided for the first embodiment of the present invention.

[0059] Figure 2 A method and system for multi-dimensional visualization evaluation of the behavior of power market entities at the provincial level, and a diagram for dividing the evaluation index system of the behavior of power market entities provided in the first embodiment of the present invention.

[0060] Figure 3 A method and system for multi-dimensional visualization evaluation of the behavior of provincial power market entities is provided as the first embodiment of the present invention, which provides a multi-dimensional portrait of power generation enterprises based on the power market entity behavior evaluation index system. DETAILED DESCRIPTION

[0061] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0062] Example 1, reference Figure 1 to Figure 3 , which is an embodiment of the present invention, provides a multi-dimensional visual evaluation method for the behavior of provincial power market entities, including:

[0063] S1: Construct an evaluation index system for the behavior of power market players and assign scores to each index.

[0064] A three-level indicator system is constructed to divide the behavior evaluation index system of power market players, including 3 target layers, 9 criterion layers and 25 indicator layers, which comprehensively covers all aspects of the behavior of power market players.

[0065] It should be noted that, based on the development status of my country's system and power market and the research and analysis, the evaluation index system of power market subject behavior is divided into three levels, which are 3 target levels, 9 criterion levels and 25 indicator levels from top to bottom. Figure 2 .

[0066] The steps for selecting evaluation indicators are as follows:

[0067] The target level indicators of the power market subject behavior evaluation index system include:

[0068] Market behavior, financial status, and social responsibility.

[0069] The criteria-level indicators of the power market subject behavior evaluation index system include:

[0070] Registration information, transaction management, information disclosure, profitability, operational capability, debt repayment capability, growth capability, safety management, environmental protection

[0071] Specifically, adhering to the principles of scientificity, dynamism, feasibility, flexibility and hierarchy, all aspects of the behavior of power market players are classified and sorted out, and the evaluation index system of power market player behavior is divided into nine aspects: registration information, transaction management, information disclosure, profitability, operational capability, debt repayment ability, growth capability, safety management and environmental protection.

[0072] The indicator level indicators of the power market subject behavior evaluation index system include:

[0073] The indicator layer indicators under the registration information include:

[0074] Integrity of registration information: In accordance with the electricity market access management measures, whether the registration information submitted by the power generation enterprise is complete and without omissions will be deducted from the full score.

[0075] Timeliness of registration information change: When a power generation enterprise changes its registration information, whether it submits an application for change within the prescribed time. Many provinces stipulate that it should apply to the power trading center for change within 5 working days. If it exceeds this time, it is considered that its registration information change is not timely. If the power generation enterprise fails to submit the application in time, points will be deducted from the full score.

[0076] The indicator layer indicators under transaction management include:

[0077] Timeliness of transaction information provision: whether the power generation enterprise provides its transaction information within the prescribed time when participating in the power market transaction in the current year. If it is not timely, points will be deducted from the full score.

[0078] Integrity of transaction information: According to the electricity market transaction rules, whether the transaction information provided by the power generation enterprise is complete and without omissions. If there are omissions, points will be deducted from the full score.

[0079] The transaction contract completion rate is the ratio of the contracted electricity volume that has been fulfilled in the market to the contracted electricity volume that has been signed. It indicates the proportion of market contract fulfillment by power generation enterprises and reflects the normal range of market transactions.

[0080] The indicator level indicators under information disclosure include:

[0081] Timely payment of deviation assessment fees: If the power generation company generates less electricity due to its own reasons, resulting in increased electricity costs for users, it needs to pay the difference in electricity charges based on the difference between the positive deviation electricity price and the signed transaction contract price. If the power generation company fails to pay the difference within the specified time, points will be deducted from the full score.

[0082] Information disclosure standardization: whether the power generation enterprise discloses information in a standardized and accurate manner in accordance with the requirements of the Information Disclosure Management Measures. If there is any non-standard information disclosure, points will be deducted from the full score.

[0083] Timeliness of information disclosure: whether the power generation enterprise discloses information in a timely manner in accordance with the requirements of the Power Market Information Disclosure Management Measures. If there is untimely disclosure of information, points will be deducted from the full score.

[0084] The indicator level indicators under profitability include:

[0085] Return on equity, net income after tax / net assets*100%; reflects the company's ability to generate net profit by using net assets, and is an important indicator to measure a company's profitability.

[0086] Cost-to-profit ratio, total profit / total cost*100%; reflects the revenue effect obtained by an enterprise by consuming a certain amount of funds. The larger the value of this indicator, the better the operating efficiency of the enterprise.

[0087] Return on assets, net profit after tax / average total assets*100%; measures the company's ability to create net profit per unit of assets and reflects the company's internal asset utilization.

[0088] The indicator level indicators under operational capability include:

[0089] The market share in the province, the cumulative trading volume of the power generation enterprise / total market trading volume*100%, reflects the competitiveness of the power generation enterprise in the local area. The larger the market share, the stronger the competitiveness.

[0090] Accounts receivable turnover rate, net income from credit sales / average balance of accounts receivable*100%; if the company's accounts receivable are collected in a timely manner, its funds will be used more efficiently, which reflects the company's accounts receivable turnover speed and management efficiency.

[0091] Return on total assets, net operating income / average total assets*100%; reflects the ability of an enterprise to make profits using all its assets and can reflect the efficiency of its asset operations.

[0092] The indicator level indicators under debt repayment capacity include:

[0093] Debt-to-asset ratio, total liabilities / total assets*100%; reflects the company's debt level, debt repayment ability and financial management ability, and is an important indicator of financial risk management.

[0094] Current ratio, current assets / current liabilities*100%; it can evaluate a company's ability to convert its existing assets into cash to repay debts before short-term debts mature, reflecting the company's short-term debt repayment ability.

[0095] Quick ratio, quick assets / current liabilities*100%; it can evaluate the ability of a company's current assets to be immediately converted into cash to repay debts, reflecting the company's short-term debt repayment ability.

[0096] The indicator level indicators under growth capability include:

[0097] The growth rate of total assets is the increase in total assets at the end of this year / total assets at the end of the previous year*100%. It can evaluate the speed of expansion of the company's asset scale and reflect the company's capital accumulation ability and development potential.

[0098] Operating profit growth rate, this year's operating profit growth / last year's operating profit*100%; reflects the increase or decrease in a company's profits and can predict the company's future development.

[0099] The indicator level indicators under safety management include:

[0100] Equipment failure rate, downtime waiting time + maintenance time / total planned usage time * 100%; it can measure the company's equipment management level and production safety level.

[0101] The technical level of equipment, the leading degree of the company's production equipment and production technology, and more advanced equipment and technology can provide a certain guarantee for the company's production safety.

[0102] Safety awareness, the degree of identification of safety hazards and risks in production, and whether the means of preventing major risk accidents are complete reflect the degree to which power generators have perfected emergency plans for potential accidents and emergencies.

[0103] The indicator level indicators under environmental protection include:

[0104] Environmental rating, a corporate environmental credit rating provided by the environmental protection department, reflects the environmental behavior and environmental protection level of the power generation company.

[0105] Renewable energy quota completion rate, the company's completed renewable energy power purchases / renewable energy quota power; reflects the power generation company's completion of renewable energy quotas.

[0106] The non-hydro renewable energy quota completion rate is the enterprise's completed non-hydro renewable energy power purchase / non-hydro renewable energy quota power*100%; it reflects the power generation enterprise's completion of the non-hydro renewable energy quota.

[0107] Scoring of various indicators is the process of experts scoring various indicators of the electricity market subject behavior evaluation system.

[0108] S2: Use AHP to determine the indicator weights and test consistency.

[0109] According to the framework of the evaluation system of the behavior of the power market players, a multi-level indicator layer is established. Experts assign weights to the indicators at each level for the behavior of the power market players and construct a judgment matrix A = (a ij ) n×n .

[0110] The indicators at all levels are compared pairwise and assigned relative importance weights. The weight scale ranges from 1 to 9.

[0111] Construct judgment matrix A = (a ij ) n×n , a ijIndicates the importance of index i relative to index j. A=(a ij ) n×n is an n×n matrix, a ij =1 / a ji , diagonal element a ii =1.

[0112] First, initialize the judgment matrix A, expressed as:

[0113]

[0114] Among them, a ij Assigned by experts, a ij =1 / a ji .

[0115] The indicators at each level of the indicator layer are compared pairwise and the values ​​are substituted into the judgment matrix.

[0116] Calculate the maximum eigenvalue λ of the judgment matrix max and its corresponding eigenvector It is expressed as:

[0117]

[0118] Among them, W i represents the geometric mean weight of the i-th indicator, a ij represents the element in the i-th row and j-th column of the judgment matrix A, n represents the total number of indicators, Represents the normalized weight of the indicator.

[0119] The consistency index CI is introduced to perform consistency test. If the consistency ratio CR is less than 0.1, the consistency test is passed. The consistency test is expressed as:

[0120]

[0121] Among them, λ max It represents the maximum eigenvalue of the judgment matrix, RI represents the random consistency index, which is determined by the total number of indicators n.

[0122] S3: Combine the NSGA-II genetic algorithm with the analytic hierarchy process to calculate the comprehensive evaluation score based on the evaluation results of multiple simulations.

[0123] The steps of combining NSGA-II genetic algorithm with analytic hierarchy process include index weight optimization, weight change interval generation, random score generation, and comprehensive calculation according to the optimization model.

[0124] The indicator weight optimization includes that after adjusting the score of a certain indicator, if the evaluation result does not change much, the indicator cannot play a distinguishing role and the weight is set to 0. If the evaluation result changes greatly, a large weight is given to the indicator.

[0125] The weight change interval generation includes determining the weight value change interval through fuzzy theory to determine the change space of the optimized weight. Take the fuzzy sets A1, A2, A3, A4, and A5, which represent the five levels of weights, namely, very small, small, moderate, large, and very large, and generate the corresponding membership function. Select the Gaussian membership function that is more in line with the actual situation, expressed as:

[0126]

[0127] Among them, μA i represents the membership of the i-th fuzzy set, x represents the weight value, ranging from 0 to 1. i It represents the central value of the i-th fuzzy set, σ represents the standard deviation, which controls the width of the Gaussian function, and i represents the index of the fuzzy set, which corresponds to 5 levels: very small, small, moderate, large, and very large.

[0128] Randomly generating scores includes generating a corresponding number of groups of random numbers according to the total number of evaluation indicators to simulate the evaluation process. Each group of data contains m random integers between 0 and 100 as the initial score values ​​of each indicator, expressed as:

[0129]

[0130] Where P represents probability, represents the sum of random variables, n represents the number of random variables, μ represents the mean of the random variables, σ 2 represents the variance of the random variable, t represents the integral variable, x represents the upper limit of the probability integral, {x n} represents a sequence of random variables that obey independent and identical distribution, E(x i )=μ,D(x i )=σ 2 ,i=1,2...n, which is satisfied for all x∈R.

[0131] For a random variable x that follows a uniform distribution i , when n is sufficiently large, there is a random variable Obey N(0,1).

[0132]

[0133] Among them, X1,…,X k represents a random variable, indicating the number of occurrences of different outcomes. n represents the total number of sampling times, ni represents the number of occurrences of the i-th outcome, p i represents the probability of the ith outcome.

[0134] Suppose a random experiment has k outcomes A1, A2, ...A k , assuming that the number of their occurrences is recorded as random variables X1, X2…X k , their probability distributions are p1, p2…p k , in the results of n samplings, A1 appears n1 times, A2 appears n2 times, ..., A n Appearance k The probability of an event P follows a multinomial distribution.

[0135] Comprehensive calculations are performed based on the optimization model that combines the NSGA-II genetic algorithm with hierarchical analysis.

[0136] The objective function is expressed as:

[0137]

[0138] Among them, F1 represents the first objective function, maximizing the total sum of squared errors. m represents the total number of evaluation indicators, n represents the total number of weights, and w i represents the weight of the i-th indicator, r ij represents the score of the i-th weight and the j-th evaluation indicator, and M represents the average total score calculated based on n groups of random scores. F2 represents the second objective function, which minimizes the weight deviation and. w i 0 Indicates that the i-th indicator has the initial weight calculated by the AHP algorithm. M represents the average score, w i represents the weight of the i-th indicator, r ij represents the i-th weight and the score of the j-th evaluation metric.

[0139] The constraints are expressed as:

[0140]

[0141] w i >0

[0142] in, Indicates the upper limit of the weight change interval corresponding to the i-th indicator, Indicates the lower limit of the weight change interval corresponding to the i-th indicator.

[0143] S4: Based on the comprehensive evaluation results of the behaviors of power market players, draw a multi-dimensional portrait of the behaviors of key power market players.

[0144] The behavior data of power market entities are divided into multiple attributes, including nine dimensions of power market entity behavior evaluation, namely registration information, transaction management, information disclosure, profitability, operation ability, debt repayment ability, growth ability, safety management, and environmental protection. Result evaluation labels are established according to the characteristics of each attribute, and a label library is formed.

[0145] The tags in the tag library are classified into levels, including good, better, average, poor and bad.

[0146] According to the actual results of the behavior of the main players in the power market, corresponding labels are assigned to the parts to be profiled to achieve the characterization of the behavior results of the main players in the power market.

[0147] It should be noted that all assigned evaluation labels are integrated to generate a complete multi-dimensional portrait. Data visualization tools are used to draw graphs based on the assigned labels. Radar charts are used for visualization, making the evaluation results of each dimension clear at a glance.

[0148] The above embodiment also includes a multi-dimensional visual evaluation system for the behavior of provincial power market entities, specifically:

[0149] The scoring module constructs an evaluation index system for the behavior of power market players and scores each indicator.

[0150] Set up the weight module, use AHP to determine the indicator weights, and check the consistency.

[0151] The evaluation module combines the NSGA-II genetic algorithm with the analytic hierarchy process to calculate the comprehensive evaluation score based on the evaluation results of multiple simulations.

[0152] The visualization module draws a multi-dimensional portrait of the behavior of key power market players based on the comprehensive evaluation results of the behavior of power market players.

[0153] The computer device may be a server. The computer device includes a processor, a memory, an input / output interface (I / O for short) and a communication interface. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface is connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data cluster data of a power monitoring system. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method is implemented.

[0154] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory may include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0155] Example 2 is an embodiment of the present invention, which provides a method and system for multi-dimensional visualization evaluation of the behavior of provincial power market entities. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0156] In order to verify the effectiveness of the multi-dimensional visualization evaluation method of the behavior of provincial power market players, seven power market players in a province were selected as experimental subjects, namely Enterprise A, Enterprise B, Enterprise C, Enterprise D, Enterprise E, Enterprise F and Enterprise G. These companies have different registration information, transaction management levels, information disclosure levels and other related indicators. In the experiment, we will construct an evaluation index system for the behavior of power market players, apply the AHP method to determine the weights, and combine the NSGA-II genetic algorithm for comprehensive evaluation, and finally draw a multi-dimensional portrait of each company.

[0157] Implementation process:

[0158] Constructing an evaluation index system for the behavior of power market players:

[0159] According to the invention content, a three-level indicator system is established, including 3 target layers, 9 criterion layers and 25 indicator layers. The specific indicators are as follows:

[0160] Target layer: Comprehensive evaluation of power market players

[0161] Standards layer: registration information, transaction management, information disclosure, profitability, operational capacity, debt repayment capacity, growth capacity, safety management, environmental protection

[0162] Indicator layer: broken down into specific evaluation indicators, such as registered capital, transaction frequency, completeness of information disclosure, net profit margin, asset utilization, current ratio, operating income growth rate, safety accident record, pollutant emissions, etc.

[0163] Score each indicator:

[0164] Invite 5 industry experts to score 25 specific indicators of each enterprise, with the score ranging from 0 to 100. The results of the expert scoring will be used to construct the judgment matrix.

[0165] Using AHP to determine the indicator weights:

[0166] Construct a judgment matrix: According to the expert scores, compare the indicators at each level in pairs to construct a judgment matrix. Taking transaction management and profitability as an example, if transaction management is more important than profitability and the value is 3, then fill in 3 in the corresponding position in the judgment matrix.

[0167] Calculate eigenvalues ​​and eigenvectors: Use the AHP method to calculate the maximum eigenvalue and eigenvector of the judgment matrix to obtain the initial weight of each indicator.

[0168] Consistency test: Calculate the consistency index CI and consistency ratio CR. If CR<0.1, the consistency test is passed, otherwise the judgment matrix needs to be adjusted.

[0169] Combined with NSGA-II genetic algorithm for comprehensive calculation:

[0170] Indicator weight optimization: Optimize the initial weight. If an indicator has little impact on the evaluation result, its weight is set to 0, otherwise it is given a larger weight.

[0171] Weight change interval generation: Fuzzy theory and Gaussian membership function are used to generate weight change intervals to ensure the rationality of weight adjustment.

[0172] Randomly generate scores: To simulate the evaluation process, corresponding groups of random numbers are generated according to the 25 evaluation indicators. Each group of data contains 25 random integers from 0 to 100 as the initial score values ​​of each indicator.

[0173] Comprehensive calculation of optimization model: Apply NSGA-II genetic algorithm to calculate the comprehensive evaluation score based on the optimization model to obtain the final score of each enterprise.

[0174] Drawing multi-dimensional portraits:

[0175] Data mapping and label assignment: Map the comprehensive score of each enterprise to nine dimensions and assign corresponding evaluation labels.

[0176] Generate multi-dimensional portraits: Use radar charts to display the performance of each enterprise in different dimensions, forming an intuitive multi-dimensional portrait. The experimental results are shown in Table 1.

[0177] Table 1 Experimental results

[0178]

[0179]

[0180] From the above test results table, we can see that there are obvious differences in the performance of each enterprise in different dimensions. First, comparing the comprehensive scores of enterprise A and enterprise D, enterprise A's comprehensive score is 85, while enterprise D's comprehensive score is 75, showing a significant advantage. This difference is mainly reflected in registration information, transaction management, information disclosure and profitability.

[0181] In the registration information dimension, Company A scored 90, significantly higher than Company D's 80, which indicates that Company A has more advantages in terms of registered capital, registration time and registration location, and has stronger market competitiveness.

[0182] In the transaction management dimension, Enterprise A scored 80 and Enterprise D scored 65, showing that Enterprise A is better in terms of transaction records and management standards. Enterprise A has a higher transaction frequency and management level, which enables it to better grasp transaction opportunities and optimize transaction processes in market competition.

[0183] In terms of information disclosure, Company A scored 75 and Company D scored 60, indicating that Company A has an advantage in terms of completeness and transparency of information disclosure. Company A's information disclosure is more comprehensive and transparent, which helps to enhance the trust of investors and regulators.

[0184] In terms of profitability, Company A scored 88 and Company D scored 78, showing the significant advantages of Company A in terms of net profit margin and gross profit margin. Company A has better financial performance and stronger profitability, which is crucial for the long-term development and market position of the company.

[0185] In addition, in terms of operational capacity, debt repayment capacity, growth capacity, safety management and environmental protection, Enterprise A also showed certain advantages. For example, in terms of safety management, Enterprise A scored 90, while Enterprise D scored 80, which shows that Enterprise A did a better job in production safety and accident prevention, ensuring the safety and stability of the production process.

[0186] The optimization model combining NSGA-II genetic algorithm and analytic hierarchy process can accurately evaluate the performance of each enterprise in different dimensions, and ensure the scientificity and fairness of the evaluation results through reasonable weight adjustment and optimization. The above test data show that the proposed multi-dimensional visualization evaluation method can comprehensively and objectively reflect the comprehensive performance of the main players in the power market, and by drawing multi-dimensional portraits, it can intuitively show the advantages and disadvantages of each enterprise, providing strong support for the management and decision-making of the power market.

[0187] Overall, the invention has significant innovation and advantages in multi-dimensional comprehensive evaluation and visualization. Compared with the existing technology, this method can not only more accurately evaluate the comprehensive performance of power market entities, but also realize the automation and intelligence of the evaluation process through the optimization model, greatly improving the efficiency and reliability of the evaluation. These innovative and novel effects have been fully verified in the experimental data, indicating that the invention has broad prospects and potential great value in practical applications.

[0188] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A multi-dimensional visual evaluation method for the behavior of provincial power market entities, characterized in that: include: Construct an evaluation index system for the behavior of power market players and assign scores to each index; Use AHP to determine the indicator weights and test consistency; The NSGA-II genetic algorithm is combined with the analytic hierarchy process to calculate the comprehensive evaluation score based on the evaluation results of multiple simulations; Based on the comprehensive evaluation results of the behaviors of power market players, a multi-dimensional portrait of the behaviors of key power market players is drawn.

2. The multi-dimensional visual evaluation method for the behavior of provincial power market entities as claimed in claim 1 is characterized by: The construction of the power market subject behavior evaluation index system includes constructing a three-level index system to divide the power market subject behavior evaluation index system into three target layers, nine criterion layers and 25 indicator layers, which comprehensively covers all aspects of the power market subject behavior; Scoring of various indicators is the process of experts scoring various indicators of the electricity market subject behavior evaluation system.

3. The multi-dimensional visual evaluation method for the behavior of provincial power market entities as claimed in claim 2 is characterized by: The method of using AHP to determine the index weights includes establishing a multi-level index layer according to the framework of the power market subject behavior evaluation system; experts assign weights of each level of indexes to the power market subject behavior, and construct a judgment matrix A=(a ij ) n×n ; Indicators at all levels are compared pairwise and weighted according to relative importance; The weight scale includes 1 to 9; Construct judgment matrix A = (a ij ) n×n , a ij Indicates the importance of index i relative to index j; A = (a ij ) n×n is an n×n matrix, a ij =1 / a ji , diagonal element a ii =1; First, initialize the judgment matrix A, expressed as: Among them, a ij Assigned by experts, a ij =1 / a ji ; The indicators at each level of the indicator layer are compared pairwise and the values ​​are substituted into the judgment matrix.

4. The multi-dimensional visual evaluation method for the behavior of provincial power market entities as claimed in claim 3 is characterized by: The method of determining the index weights by using AHP also includes calculating the maximum eigenvalue λ of the judgment matrix. max and its corresponding eigenvector It is expressed as: Among them, W i represents the geometric mean weight of the i-th indicator, a ij represents the element in the i-th row and j-th column of the judgment matrix A, n represents the total number of indicators, represents the normalized weight of the indicator; The consistency index CI is introduced to perform consistency test. If the consistency ratio CR is less than 0.1, the consistency test is passed. The consistency test is expressed as: Among them, λ max It represents the maximum eigenvalue of the judgment matrix, and RI represents the random consistency index, which is determined by the total number of indicators n.

5. The multi-dimensional visual evaluation method for the behavior of provincial power market entities as claimed in claim 4 is characterized by: The steps of combining the NSGA-II genetic algorithm with the hierarchical analysis method include optimizing the index weights, generating weight change intervals, randomly generating scores, and performing comprehensive operations according to the optimization model; The indicator weight optimization includes: after adjusting the score of a certain indicator, if the evaluation result does not change much, then the indicator cannot play a distinguishing role and the weight is set to 0; if the evaluation result changes greatly, then a large weight is given to the indicator; The weight variation interval generation includes, in order to determine the variation space of the optimization weight, determining the variation interval of the weight value by using fuzzy theory; Take the fuzzy sets A1, A2, A3, A4, and A5, which represent five levels of weight: very small, small, moderate, large, and very large, respectively, and generate the corresponding membership function; select the Gaussian membership function that is more consistent with the actual situation, expressed as: Among them, μA i represents the membership of the i-th fuzzy set, x represents the weight value, ranging from 0 to 1; c i represents the central value of the i-th fuzzy set, σ represents the standard deviation, which controls the width of the Gaussian function, and i represents the index of the fuzzy set, which corresponds to five levels: very small, small, moderate, large, and very large. Randomly generating scores includes generating a corresponding number of groups of random numbers according to the total number of evaluation indicators to simulate the evaluation process. Each group of data contains m random integers between 0 and 100 as the initial score values ​​of each indicator, expressed as: Where P represents probability, represents the sum of random variables, n represents the number of random variables, μ represents the mean of the random variables, σ 2 represents the variance of the random variable, t represents the integral variable, x represents the upper limit of the probability integral, {x n } represents a sequence of random variables that obey independent and identical distribution, E(x i )=μ,D(x i )=σ 2 ,i=1,2...n, which is satisfied for all x∈R; For a random variable x that follows a uniform distribution i , when n is sufficiently large, there is a random variable Obey N(0,1); Among them, X1,…,X k represents a random variable, indicating the number of occurrences of different outcomes; n represents the total number of sampling times, n i represents the number of occurrences of the i-th outcome, p i represents the probability of the i-th outcome; Suppose a random experiment has k outcomes A1, A2, ...A k , assuming that the number of their occurrences is recorded as random variables X1, X2…X k , their probability distributions are p1, p2…p k , in the results of n samplings, A1 appears n1 times, A2 appears n2 times, ..., A n Appearance k The probability of an event P follows a multinomial distribution.

6. The multi-dimensional visual evaluation method for the behavior of provincial power market entities as claimed in claim 5 is characterized by: The performing comprehensive calculation according to the optimization model includes performing comprehensive calculation according to the optimization model combining the NSGA-II genetic algorithm with the hierarchical analysis; The objective function is expressed as: Among them, F1 represents the first objective function, maximizing the total sum of squared errors; m represents the total number of evaluation indicators, n represents the total number of weights, and w i represents the weight of the i-th indicator, r ij represents the score of the i-th weight and the j-th evaluation indicator, M represents the average total evaluation score calculated based on n groups of random scores; F2 represents the second objective function, minimizing the weight deviation and; w i 0 Indicates that the i-th indicator has the initial weight calculated by the AHP algorithm; M represents the average score, w i represents the weight of the i-th indicator, r ij represents the i-th weight and the score of the j-th evaluation indicator; The constraints are expressed as: in, Indicates the upper limit of the weight change interval corresponding to the i-th indicator, Indicates the lower limit of the weight change interval corresponding to the i-th indicator.

7. The multi-dimensional visual evaluation method for the behavior of provincial power market entities as claimed in claim 6 is characterized by: The method of drawing a multi-dimensional portrait of the behavior of key power market entities based on the comprehensive evaluation results of the behavior of power market entities includes dividing the behavior data of power market entities into multiple attributes, including nine dimensions of the evaluation of the behavior of power market entities, namely registration information, transaction management, information disclosure, profitability, operation ability, debt repayment ability, growth ability, safety management, and environmental protection; establishing a result evaluation label according to the characteristics of each attribute, and forming a label library; The tags in the tag library are classified into levels, including good, better, average, poor and bad; According to the actual results of the behavior of the main players in the power market, corresponding labels are assigned to the parts to be profiled to achieve the characterization of the behavior results of the main players in the power market.

8. A dynamic load capacity management system for oil-immersed power transformers using the method according to any one of claims 1 to 7, characterized in that: Scoring module, which builds an evaluation index system for the behavior of power market players and scores each index; Set up a weight module, use AHP to determine the indicator weights, and check consistency; The evaluation module combines the NSGA-II genetic algorithm with the analytic hierarchy process to calculate the comprehensive evaluation score based on the evaluation results of multiple simulations; The visualization module draws a multi-dimensional portrait of the behavior of key power market players based on the comprehensive evaluation results of the behavior of power market players.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images