Electric power spot market monitoring and evaluating method based on hesitant intuitionistic fuzzy cloud model

Abstract

The invention relates to an electric power spot market monitoring and evaluation method based on a hesitant intuition fuzzy cloud model, and aims to realize scientific supervision of a provincial electric power spot market by constructing a comprehensive supervision index system, fusing qualitative and quantitative analysis methods and an accurate supervision grading mechanism. The method comprises the following steps: firstly, constructing a supervision index system covering five first-level dimensions including a market structure, participant behaviors, an operation mechanism, information transparency and system security; secondly, determining the weight of each index by using an analytic hierarchy process (AHP); then, through a hesitant fuzzy language set (HFLS) and a cloud model, converting expert scores into quantifiable probability distribution; and finally, precise grading of supervision levels is completed through expected value, entropy and hyper-entropy parameter calculation of the cloud model, and customized suggestions are provided for supervision decision-making of the electric power spot market. Compared with the prior art, the supervision level of the electric power spot market can be comprehensively and accurately evaluated, the supervision strategy is optimized, the stability and transparency of market operation are improved, and a more scientific and efficient tool is provided for electric power market supervision.

Description

Technical Field

[0001] The present invention belongs to the technical field of power market supervision, and in particular relates to a power spot market monitoring and evaluation method based on a hesitant intuitionistic fuzzy cloud model, which is used to accurately identify risk characteristics in the spot market and provide support for formulating scientific and efficient supervision strategies. Background Art

[0002] With the deepening of global power market reform, provincial power spot market has gradually become an important part of power trading. The spot market faces complex regulatory challenges due to its real-time nature, price volatility and diversity of participants. In particular, with the continuous increase in the proportion of new energy, the uncertainty and dynamism of the market have increased significantly, making it difficult for traditional regulatory methods to comprehensively and accurately identify market risks.

[0003] The existing power market supervision technology has the following main deficiencies: 1) Imperfect supervision indicator system: Traditional methods often focus on single-dimensional analysis, which makes it difficult to fully cover multi-dimensional supervision needs such as market structure, participant behavior, operating mechanism, information transparency and system security. 2) Difficulty in dealing with complexity and uncertainty: Existing technologies have limited ability to deal with ambiguity, randomness and hesitation in expert subjective evaluation, and it is difficult to provide effective quantitative tools for complex market behavior. 3) Insufficient scientificity of supervision classification: Traditional quantitative assessment methods lack accuracy and practical applicability in risk classification, resulting in a lack of targeted supervision recommendations.

[0004] In order to deal with the above problems, an innovative monitoring and evaluation method is urgently needed, which can integrate qualitative analysis and quantitative calculation, and accurately capture the risk characteristics of the electricity spot market through a comprehensive indicator system and advanced analysis models. This paper proposes a provincial electricity spot market monitoring and evaluation system based on hesitant fuzzy language sets and cloud models, which can effectively solve the shortcomings of existing methods, realize quantitative analysis and scientific classification of market risks, and provide theoretical and technical support for improving market transparency, operational stability and system security. Summary of the invention

[0005] In view of the deficiencies in the prior art, the technical problem that the present invention intends to solve is to provide a method for monitoring and evaluating the electricity spot market based on a hesitant intuitionistic fuzzy cloud model.

[0006] The present invention solves the technical problem by adopting the following technical solution: A provincial power spot market monitoring and evaluation system based on hesitant fuzzy language sets and cloud model, characterized by comprising the following steps: (1) Establish a comprehensive regulatory indicator system.

[0007] (2) Determination of indicator weights: Invite experts to evaluate the indicators from four dimensions (market impact, volatility, independence and sensitivity).

[0008] (3) Constructing Hesitant Fuzzy Language Set: The Hesitant Fuzzy Language Set (HFLS) is used for expert scoring to quantify the impact of each indicator on the regulatory level.

[0009] (4) Building a cloud model: The cloud model is used to convert the hesitant fuzzy language set scores into a processable probability distribution, thus achieving the fusion of qualitative and quantitative data.

[0010] (5) Provincial electricity spot market regulatory grading: The scoring results of the secondary indicators are mapped to the regulatory level, and the regulatory levels of the primary indicators are weighted and summarized to ultimately form the overall regulatory level of the provincial electricity spot market.

[0011] The step (1) specifically includes the following steps: (1a) Based on the five first-level dimensions of market structure, participant behavior, operating mechanism, transparency and system security, the second-level indicators were determined through literature review and expert interviews.

[0012] (1b) Invite experts to evaluate the necessity of each indicator and provide feedback to ensure the scientificity and comprehensiveness of the system.

[0013] The step (2) specifically includes the following steps: (2a) Invite experts to evaluate the indicators based on four principles (market impact, volatility, independence and sensitivity). A judgment matrix is ​​constructed by pairwise comparison, covering both primary and secondary indicators.

[0014] (2b) Each row of the judgment matrix is ​​normalized using formula (1), and the average value of each row is calculated using formula (2) as the initial weight vector.

[0015] (1) (2) (2c) Calculate the consistency ratio (CR) to ensure the consistency of the expert evaluation. CR is calculated using formula (3). When the CR value is less than 0.1, the matrix is ​​considered consistent.

[0016] (3) After ensuring consistency, the weights were aggregated and normalized to ensure that the sum of the weights was 1. Experts reviewed the results and made multiple iterative adjustments to ensure the scientificity and practicality of the weight distribution.

[0017] The step (3) specifically includes the following steps: (3a) Five fuzzy language levels are defined: “S0: low”, “S1: lower”, “S2: medium”, “S3: higher” and “S4: high”, and a fuzzy numerical range is assigned to each level to standardize the scale of indicator scoring.

[0018] (3b) Invite experts to select one or more fuzzy language levels for scoring based on their understanding of the relevance of the secondary indicators in market risk. The selected language levels are combined with the corresponding feasibility values ​​to form the hesitant fuzzy language set ,in is a set of language levels, is the set of hesitation values.

[0019] (3c) The language levels and feasibility scores selected by experts are converted into fuzzy numerical values ​​to enable comparison of all scoring results on a unified scale.

[0020] (3d) The experts’ scoring results and feasibility values ​​are summarized to form a comprehensive hesitant fuzzy language set for each secondary indicator, and a consistency check is performed to ensure the rationality of the scoring and minimize the bias.

[0021] (3e) After completing the aggregation and consistency processing, construct the final hesitant fuzzy language set for each secondary indicator, laying the foundation for the subsequent regulatory level classification.

[0022] The step (4) specifically includes the following steps: (4a) Calculate the expected value, entropy and super entropy of each secondary indicator according to formulas (4)-(6).

[0023] (4) (5) (6) (4b) Based on the expectation, entropy and super entropy of each secondary indicator, a series of cloud drops are generated to represent the distribution status of the indicator under different expert scores.

[0024] (4c) The generated cloud droplet values ​​are fitted with a normal distribution to form the final distribution curve of the cloud model, and the distribution curves of each indicator are hierarchically mapped to the standard cloud map of each regulatory level.

[0025] The step (5) specifically includes the following steps: (5a) Based on the results of the cloud model, the scores of the secondary indicators are mapped to a predefined regulatory level range, including five levels: low, medium, higher, high and very high.

[0026] (5b) Using the weighted method, the grading results of the secondary indicators under each primary indicator are weighted and summarized to generate a comprehensive supervision level for the primary indicator.

[0027] (5c) The weighted sum of the comprehensive regulatory levels of the first-level indicators is used to obtain the overall regulatory level of the provincial power spot market, which is used to clarify the regulatory needs of the market.

[0028] (5d) By analyzing the distribution of regulatory levels, we can identify the risk characteristics in the provincial electricity spot market and provide data support for the formulation of tailored regulatory strategies.

[0029] Compared with the prior art, the present invention has the following beneficial effects: 1. Comprehensive regulatory indicator system The present invention constructs a regulatory indicator system covering five primary dimensions: market structure, participant behavior, operating mechanism, information transparency and system security, which comprehensively covers the key regulatory needs of the electricity spot market and solves the shortcomings of existing methods in indicator coverage.

[0030] 2. Integrate qualitative and quantitative analysis By introducing the hesitant fuzzy language set (HFLS), the present invention can handle the linguistic ambiguity and hesitation expressed by experts in the evaluation process, realize the structured and standardized expression of qualitative information, and at the same time combine the cloud model to convert fuzzy language information into quantifiable probability distribution, thereby improving the scientificity and accuracy of risk assessment.

[0031] 3. Accurate risk grading capabilities The present invention utilizes the expectation, entropy and hyperentropy parameters of the cloud model to quantify the uncertainty and risk characteristics of the indicators. By constructing a standard cloud map, it realizes the accurate classification of the risks in the electricity spot market, overcoming the shortcomings of traditional methods in the scientificity and applicability of the classification.

[0032] 4. Flexible and adaptable The evaluation method of the present invention is not only applicable to the characteristics of different provincial power spot markets, but also can flexibly adjust the indicator weights and scoring criteria according to changes in market structure and operation mechanism, and has strong adaptability and scalability.

[0033] 5. Support the formulation of personalized regulatory strategies Through quantitative analysis of market risk distribution characteristics, the present invention can provide customized regulatory recommendations for the specific conditions of different markets, such as improving market transparency, optimizing operating mechanisms, or strengthening system security, providing decision-making support for regulatory agencies to formulate scientific and efficient strategies.

[0034] In summary, the present invention has significant advantages in indicator system construction, risk quantification analysis, regulatory classification, adaptability and practicality, and provides a more comprehensive and efficient solution for the supervision of provincial electricity spot markets. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is the overall flow chart of the present invention. DETAILED DESCRIPTION

[0036] Specific embodiments are given below in conjunction with the accompanying drawings. The specific embodiments are only used to introduce the technical solutions of the present invention in detail and are not intended to limit the protection scope of the present application.

[0037] like Figure 1 As shown, a power spot market monitoring and evaluation method based on the hesitant intuitionistic fuzzy cloud model includes the following steps: (1) Establish a comprehensive regulatory indicator system.

[0038] (2) Determination of indicator weights: Invite experts to evaluate the indicators from four dimensions (market impact, volatility, independence and sensitivity).

[0039] (3) Constructing Hesitant Fuzzy Language Set: The Hesitant Fuzzy Language Set (HFLS) is used for expert scoring to quantify the impact of each indicator on the regulatory level.

[0040] (4) Building a cloud model: The cloud model is used to convert the hesitant fuzzy language set scores into a processable probability distribution, thus achieving the fusion of qualitative and quantitative data.

[0041] (5) Provincial electricity spot market regulatory grading: The scoring results of the secondary indicators are mapped to the regulatory level, and the regulatory levels of the primary indicators are weighted and summarized to ultimately form the overall regulatory level of the provincial electricity spot market.

[0042] The step (1) specifically includes the following steps: (1a) Based on the five first-level dimensions of market structure, participant behavior, operating mechanism, transparency and system security, the second-level indicators were determined through literature review and expert interviews.

[0043] (1b) Invite experts to evaluate the necessity of each indicator and provide feedback to ensure the scientificity and comprehensiveness of the system.

[0044] The step (2) specifically includes the following steps: (2a) Invite experts to evaluate the indicators based on four principles (market impact, volatility, independence and sensitivity). A judgment matrix is ​​constructed by pairwise comparison, covering both primary and secondary indicators.

[0045] (2b) Each row of the judgment matrix is ​​normalized using formula (1), and the average value of each row is calculated using formula (2) as the initial weight vector.

[0046] (1) (2) (2c) Calculate the consistency ratio (CR) to ensure the consistency of the expert evaluation. CR is calculated using formula (3). When the CR value is less than 0.1, the matrix is ​​considered consistent.

[0047] (3) After ensuring consistency, the weights were aggregated and normalized to ensure that the sum of the weights was 1. Experts reviewed the results and made multiple iterative adjustments to ensure the scientificity and practicality of the weight distribution.

[0048] The step (3) specifically includes the following steps: (3a) Five fuzzy language levels are defined: “S0: low”, “S1: lower”, “S2: medium”, “S3: higher” and “S4: high”, and a fuzzy numerical range is assigned to each level to standardize the scale of indicator scoring.

[0049] (3b) Invite experts to select one or more fuzzy language levels for scoring based on their understanding of the relevance of the secondary indicators in market risk. The selected language levels are combined with the corresponding feasibility values ​​to form the hesitant fuzzy language set ,in is a set of language levels, is the set of hesitation values.

[0050] (3c) The language levels and feasibility scores selected by experts are converted into fuzzy numerical values ​​to enable comparison of all scoring results on a unified scale.

[0051] (3d) The experts’ scoring results and feasibility values ​​are summarized to form a comprehensive hesitant fuzzy language set for each secondary indicator, and a consistency check is performed to ensure the rationality of the scoring and minimize the bias.

[0052] (3e) After completing the aggregation and consistency processing, construct the final hesitant fuzzy language set for each secondary indicator, laying the foundation for the subsequent regulatory level classification.

[0053] The step (4) specifically includes the following steps: (4a) Calculate the expected value, entropy and super entropy of each secondary indicator according to formulas (4)-(6).

[0054] (4) (5) (6) (4b) Based on the expectation, entropy and super entropy of each secondary indicator, a series of cloud drops are generated to represent the distribution status of the indicator under different expert scores.

[0055] (4c) The generated cloud droplet values ​​are fitted with a normal distribution to form the final distribution curve of the cloud model, and the distribution curves of each indicator are hierarchically mapped to the standard cloud map of each regulatory level.

[0056] The step (5) specifically includes the following steps: (5a) Based on the results of the cloud model, the scores of the secondary indicators are mapped to a predefined regulatory level range, including five levels: low, medium, higher, high and very high.

[0057] (5b) Using the weighted method, the grading results of the secondary indicators under each primary indicator are weighted and summarized to generate a comprehensive supervision level for the primary indicator.

[0058] (5c) The weighted sum of the comprehensive regulatory levels of the first-level indicators is used to obtain the overall regulatory level of the provincial power spot market, which is used to clarify the regulatory needs of the market.

[0059] (5d) By analyzing the distribution of regulatory levels, we can identify the risk characteristics in the provincial electricity spot market and provide data support for the formulation of tailored regulatory strategies.

[0060] Any matters not described in the present invention are applicable to the prior art.

Claims

1. A method for monitoring and evaluating the electricity spot market based on a hesitant intuitionistic fuzzy cloud model, characterized in that: The following steps are involved: (1) Establish a comprehensive regulatory indicator system; (2) Determination of indicator weights: Invite experts to evaluate the indicators from four dimensions: market impact, volatility, independence, and sensitivity; (3) Constructing a hesitant fuzzy language set: Using a hesitant fuzzy language set for expert scoring, we can quantify the impact of each indicator on the regulatory level. (4) Building a cloud model: The cloud model is used to convert the hesitant fuzzy language set scores into a processable probability distribution, thus achieving the fusion of qualitative and quantitative data. (5) Provincial electricity spot market regulatory grading: The scoring results of the secondary indicators are mapped to the regulatory level, and the regulatory levels of the primary indicators are weighted and summarized to ultimately form the overall regulatory level of the provincial electricity spot market.

2. The power spot market monitoring and evaluation method based on the hesitant intuitionistic fuzzy cloud model according to claim 1 is characterized in that: The step (1) comprises the following steps: (1a) Based on the five first-level dimensions of market structure, participant behavior, operating mechanism, transparency, and system security, the second-level indicators were determined through literature review and expert interviews; (1b) Invite experts to evaluate the necessity of each indicator and provide feedback to ensure the scientificity and comprehensiveness of the system.

3. The power spot market monitoring and evaluation method based on the hesitant intuitionistic fuzzy cloud model according to claim 1 is characterized in that: The step (2) comprises the following steps: (2a) Invite experts to evaluate the indicators from four aspects: market impact, volatility, independence and sensitivity, and construct a judgment matrix through pairwise comparison, covering both primary and secondary indicators; (2b) Each row of the judgment matrix is ​​normalized using formula (1), and the average value of each row is calculated using formula (2) as the initial weight vector; (1) (2) (2c) Calculate the consistency ratio to ensure the consistency of the expert evaluation. The CR is calculated using formula (3). When the CR value is less than 0.1, the matrix is ​​considered to be consistent. (3) After ensuring consistency, the weights were aggregated and normalized to ensure that the total weight was 1; experts reviewed the results and made multiple iterative adjustments to ensure the scientificity and practicality of the weight distribution.

4. The power spot market monitoring and evaluation method based on the hesitant intuitionistic fuzzy cloud model according to claim 1 is characterized in that: The step (3) specifically comprises the following steps: (3a) Define five fuzzy language levels: "S0: low", "S1: lower", "S2: medium", "S3: higher" and "S4: high", and assign a fuzzy numerical range to each level to standardize the scale of indicator scoring; (3b) Invite experts to select one or more fuzzy language levels for scoring based on their understanding of the relevance of the secondary indicators in market risk; the selected language levels are combined with the corresponding feasibility values ​​to form a hesitant fuzzy language set ,in is a set of language levels, is the set of hesitation values; (3c) Convert the language levels and feasibility scores selected by experts into fuzzy numerical values ​​to enable comparison of all scoring results on a unified scale; (3d) Summarize the experts’ scoring results and feasibility values ​​to form a comprehensive hesitant fuzzy language set for each secondary indicator, and perform consistency checks to ensure the rationality of the scoring and minimize bias; (3e) After completing the aggregation and consistency processing, construct the final hesitant fuzzy language set for each secondary indicator, laying the foundation for the subsequent regulatory level classification.

5. The power spot market monitoring and evaluation method based on the hesitant intuitionistic fuzzy cloud model according to claim 1 is characterized by: The step (4) specifically comprises the following steps: (4a) Calculate the expected value, entropy and super entropy of each secondary indicator according to formulas (4)-(6): (4) (5) (6) (4b) According to the expectation, entropy and super entropy of each secondary indicator, a series of cloud drops are generated to represent the distribution state of the indicator under different expert scores; (4c) The generated cloud droplet values ​​are fitted with a normal distribution to form the final distribution curve of the cloud model, and the distribution curves of each indicator are hierarchically mapped to the standard cloud map of each regulatory level.

6. The power spot market monitoring and evaluation method based on the hesitant intuitionistic fuzzy cloud model according to claim 1 is characterized by: The step (5) specifically comprises the following steps: (5a) Based on the results of the cloud model, the scores of the secondary indicators are mapped to a predefined regulatory level range, including five levels: low, medium, high, high and very high; (5b) Using a weighted method, the results of the secondary indicators under each primary indicator are weighted and summarized to generate a comprehensive regulatory grade for the primary indicator; (5c) The weighted sum of the comprehensive regulatory levels of the first-level indicators is used to obtain the overall regulatory level of the provincial power spot market, which is used to clarify the regulatory needs of the market; (5d) By analyzing the distribution of regulatory levels, we can identify the risk characteristics in the provincial electricity spot market and provide data support for the formulation of tailored regulatory strategies.

Images