Method and system for constructing multi-dimensional risk management maturity model

Abstract

The invention discloses a multi-dimensional risk management maturity model construction method and system, and the method comprises the steps: collecting monitoring data and risk management data of a preset power system, and carrying out the preprocessing of the monitoring data and the risk management data; performing risk identification on the monitoring data to obtain risk data, acquiring a risk type through the risk data by adopting a prior algorithm, and performing power prediction through the risk management data to obtain management and control data; performing dynamic causal matching on the management and control data and the risk type to obtain a matching degree, management data and fuzzy data, performing longitudinal comparison evaluation according to the historical data and the fuzzy data to obtain an optimization degree, and adding the fuzzy data of which the optimization degree is greater than an optimization threshold value into the management data; and constructing a maturity evaluation function according to comprehensive comparison of transverse and longitudinal maturity of the management data, and constructing a power risk management maturity model according to the maturity evaluation function.

Description

Technical Field

[0001] The present invention relates to the field of risk management, and in particular to a method and system for constructing a multi-dimensional risk management maturity model. Background Art

[0002] With the transformation of energy structures and the rapid development of new power systems, the risks facing power systems are becoming increasingly complex and dynamic. Traditional power system risk management relies primarily on static analysis of a single risk dimension, making it difficult to address the coupled effects of multi-source, heterogeneous risks. Existing risk management models are often based on linear regression of historical data or a single indicator system. They lack the ability to quantitatively analyze the dynamic correlations and causal relationships between multi-dimensional risks, resulting in delayed risk identification and insufficiently adaptable control measures.

[0003] At the technical level, the existing risk management framework has the following bottlenecks: First, the data fusion mechanism is imperfect, and monitoring data and risk management data have not yet formed a unified multi-dimensional feature extraction and standardized processing process, which restricts the efficiency of risk collaborative analysis; second, risk type identification mostly relies on expert experience or a single algorithm model, with limited ability to distinguish between "single risk" and "multi-risk coupling" scenarios, and lacks a dynamic classification mechanism based on a priori knowledge base; third, the matching of management and control strategies with risk types relies on a static rule base, which cannot adapt to the dynamic changes in the real-time operating status of the power system and lacks self-optimization capabilities for fuzzy data.

[0004] Existing maturity models often use fixed weight allocation and horizontal benchmarking, ignoring the evolution of longitudinal historical data and the dynamic optimization path of risk management measures. In addition, traditional causal reasoning methods have difficulty quantifying the nonlinear characteristics of risk transmission paths when dealing with multi-timescale risk events, resulting in insufficient accuracy and adaptability in the construction of maturity assessment functions. Therefore, it is urgent to construct a multi-dimensional risk management maturity model that integrates dynamic analysis of multi-source data, intelligent matching of risk types, and self-optimization and iteration of fuzzy data to address the shortcomings of existing methods in data fusion, dynamic causal association, and cross-cycle evaluation, and provide systematic and forward-looking decision-making support for risk prevention and control of new power systems. Summary of the Invention

[0005] The purpose of the present invention is to provide a method for constructing a multi-dimensional risk management maturity model.

[0006] To achieve the above object, the present invention is implemented according to the following technical solutions: The present invention comprises the following steps: Collect monitoring data and risk management data of a preset power system and pre-process the monitoring data and risk management data; the risk management data includes equipment failure risk management, fuel supply risk management, grid operation safety risk management, distributed resource aggregation risk management, and power supply shortage or excess risk management; the monitoring data includes data to be analyzed and historical data; Performing risk identification on the monitoring data to obtain risk data, using a priori algorithms to obtain risk types from the risk data, and performing power forecasting on the risk management data to obtain control data; the risk types include single risk types and multiple risk types; Performing dynamic causal matching on the control data and the risk type to obtain a matching degree, using the control data with a matching degree greater than a matching threshold as management data, and otherwise using the control data as fuzzy data, performing a longitudinal comparative evaluation based on the historical data and the fuzzy data to obtain an optimization degree, and adding the fuzzy data with an optimization degree greater than the optimization threshold to the management data; A maturity evaluation function is constructed based on a comprehensive horizontal and vertical maturity comparison of the management data, a power risk management maturity model is constructed based on the maturity evaluation function, and a target model is output.

[0007] Furthermore, the method for performing risk identification on the monitoring data to obtain risk data includes: A decision tree algorithm is used to construct a decision tree based on the equipment's operating parameters and maintenance records, and the equipment failure risk is identified through the decision tree's scoring rules. A time series analysis algorithm is used to model the fuel consumption data, inventory data, and supply cycle. By analyzing the trend, seasonality, and cyclical characteristics of historical data, the fuel demand and supply situation are predicted. When the supply situation is lower than the fuel demand, it is determined to be a fuel supply risk. An association rule mining algorithm is used to follow the association rules between parameters in the power grid operation data, and when the association rules are not met, it is determined to be a power grid operation safety risk. Based on the fuzzy comprehensive evaluation algorithm, fuzzy quantification is performed based on stability and environmental factors, and a fuzzy evaluation matrix is established to evaluate the distributed resource aggregation risk in combination with objective weights. When the evaluation value is greater than the threshold, it is determined to be a distributed resource aggregation risk. A Monte Carlo simulation algorithm is used to simulate power supply and demand, and the probability distribution of power supply and demand is obtained through random sampling and simulation calculations. When the power distribution is higher than the threshold, it is determined to be a power supply shortage or surplus risk.

[0008] Furthermore, the method of performing dynamic causal matching on the control data and the risk type to obtain a matching degree includes: Sort the control data by time, divide the sorted control data into time windows, obtain control variables based on the control data, and obtain risk variables and risk factors based on risk types; Construct a causal graph, using the control variables and risk variables that are added or eliminated as the time window slides as nodes of the causal tree, and the causal relationships between nodes as edges of the causal graph; Weighted bootstrap resampling was used for the control data of sparse control variables, and a prior conditional independence test was performed on continuous risk factors and a chi-square test was performed on discrete multiple risk factors to obtain the cumulative statistics optimized for the conditional independence test, the regression coefficient matrix and the residual covariance of the structural vector autoregression model; Directly determine non-instantaneous causal relationships through temporal rules, and obtain instantaneous causal relationships by testing the relationship between control variables in the same time window through the structural vector autoregression model; Calculate single risk matching: , The exponential decay of the lag w is , the maximum lag period is , the single risk matching degree is , the standard deviation of the causal influence coefficient is , the single risk variable at time t is , the risk factor at time tw is , risk factors For a single risk variable The causal influence coefficient is , the dynamic adjustment weight at time t is , the forgetting factor is ; Perform principal component analysis and dimensionality reduction on multiple risk types to obtain principal components and calculate the multi-risk matching degree: , The ath principal component is , the number of principal components is , the variance contribution rate of the ath principal component is , the predictor variables are , predictor variables Principal component The Granger causality test result is , the multi-risk matching degree is ; Calculate the rolling mean and standard deviation based on the matching degree and set the adaptive threshold. The expression is: , The control threshold convergence speed coefficient is , the rolling mean is , the standard deviation is , the current time is t, and the adaptive threshold is ; When the matching degree is lower than the adaptive threshold, the nodes are dynamically added or reduced, and the conditional independence test is updated until all management and control data and risk types are traversed and the matching degree is output.

[0009] Furthermore, the method for obtaining the degree of optimization by performing longitudinal comparative evaluation based on the historical data and the fuzzy data includes: Fuzzy data is classified according to monitoring type, and fuzzy data far from the classification center is divided using a Gaussian mixture model to obtain classified data; monitoring types include environmental parameters, operating parameters, economic factors, and equipment status; Align historical data and classified data according to timestamps, and calculate the comprehensive optimization degree based on objective weighting: , The comprehensive optimization degree of the b-th risk management is The upper limit of monitoring time is The monitoring start time is The monitoring deadline is , the response time of the b-th risk management is , the xth classification data of the zth classification is , categorical data The value at time t is , the value of the xth historical data at time t is , the number of categories is , the xth weight coefficient is .

[0010] Furthermore, the method of constructing a maturity evaluation function based on the comprehensive horizontal and vertical maturity comparison of the management data includes: Obtain risk management data from different areas of other power systems as horizontal comparison data, use management data from the same power learning system at different time points as vertical comparison data, and normalize the horizontal comparison data; Exponential smoothing method was used to calculate the trend of longitudinal control data: ; The smoothing coefficient is , the trend value is h, and the trend value at time t-1 is , the longitudinal control data at time t is ; According to the horizontal comparison data, the horizontal maturity is evaluated to obtain the horizontal maturity, which is expressed as: , The horizontal maturity is , the number of horizontal control data is , the i-th horizontal control data is , the reference value of the i-th horizontal comparison data is , the response time of the i-th horizontal comparison data is ; Based on the longitudinal control data and change trends, longitudinal maturity assessment is performed to obtain the longitudinal maturity, which is expressed as: , The vertical maturity is , the number of longitudinal control data is , the upper limit of longitudinal observation time is , the longitudinal control data at time t is , the reference value of the longitudinal control data at time t is , the changing trend of the vth longitudinal control data at time t is , the response time of the vth longitudinal control data is , the reference response time of the vth longitudinal control data is ; The maturity evaluation function is constructed based on horizontal maturity and vertical maturity, and the expression is: , The comprehensive optimization degree of the b-th risk management is , the effectiveness of the b-th risk management strategy is , the number of risk management is M, and the optimization item is , the horizontal weight is , the vertical weight is , the optimization weight is , the mapping function is , the maturity evaluation function of the b-th risk management is , the vertical maturity of the b-th risk management is , the horizontal maturity of the b-th risk management is .

[0011] Furthermore, a method for constructing a power risk management maturity model based on the maturity assessment function includes: Multi-dimensional evaluation indicators are selected through management data, and the entropy weight method is used to obtain the weights of the evaluation indicators; the evaluation indicators include equipment performance indicators, power grid operation indicators, economic indicators, environmental protection indicators and user satisfaction indicators; The objective function of the power risk management maturity model is constructed as follows: , The objective function of the b-th risk management is , the maturity evaluation function of the jth evaluation indicator of the bth risk management is , the jth evaluation index of the bth risk management is , the loss function is , the number of evaluation indicators is D; The maturity level is divided according to the objective function. When the objective function score is less than 0.219, the power system is managed without risk; when the objective function score is greater than 0.219 and less than 0.417, the power system risk management capability is level four; when the objective function score is greater than 0.417 and less than 0.609, the power system risk management capability is level three; when the objective function score is greater than 0.609 and less than 0.794, the power system risk management capability is level two; when the objective function score is greater than 0.794, the power system risk management capability is level one.

[0012] The second aspect is a system for constructing a multi-dimensional risk management maturity model, including: Data acquisition module: used to collect monitoring data and risk management data of the preset power system and pre-process the monitoring data and risk management data; the risk management data includes equipment failure risk management, fuel supply risk management, grid operation safety risk management, distributed resource aggregation risk management, and power supply shortage or excess risk management; the monitoring data includes data to be analyzed and historical data; Risk type identification module: performs risk identification on the monitoring data to obtain risk data, uses a priori algorithms to obtain risk types from the risk data, and performs power forecasting on the risk management data to obtain control data; the risk types include single risk types and multiple risk types; Prediction and matching module: used to perform power prediction based on the risk management data to obtain control data, perform dynamic causal matching on the control data and the risk type to obtain a matching degree, and use the control data with a matching degree greater than a matching threshold as management data, otherwise as fuzzy data; Comparison and evaluation module: Performs dynamic causal matching on the control data and the risk type to obtain a matching degree, uses the control data with a matching degree greater than a matching threshold as management data, and uses the control data with a matching degree greater than a matching threshold as fuzzy data. A longitudinal comparison and evaluation is performed based on the historical data and the fuzzy data to obtain an optimization degree, and the fuzzy data with an optimization degree greater than the optimization threshold is added to the management data; Modeling optimization module: constructing a maturity evaluation function based on a comprehensive horizontal and vertical maturity comparison of the management data, building a power risk management maturity model based on the maturity evaluation function, and outputting a target model.

[0013] The beneficial effects of the present invention are: The present invention is a method and system for constructing a multi-dimensional risk management maturity model. Compared with the prior art, the present invention has the following technical effects: The present invention can improve the accuracy of the construction of the risk management maturity model through preprocessing, risk identification, acquisition of risk type, power forecasting, dynamic causal matching, longitudinal comparative evaluation, construction of maturity assessment function and model construction steps, thereby improving the accuracy of the construction of the risk management maturity model, optimizing the construction of the risk management maturity model, greatly saving resources, improving work efficiency, and realizing the scientific construction of the risk management maturity model. It can perform dynamic causal matching and construct maturity assessment function on the construction of the risk management maturity model in real time, which is of great significance to the construction of the risk management maturity model, can adapt to the construction of risk management maturity models of different standards and the construction requirements of different risk management maturity models, and has a certain universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 This is a flowchart of the steps of a method for constructing a multi-dimensional risk management maturity model of the present invention. DETAILED DESCRIPTION

[0015] The present invention will be further described below through specific examples. The illustrative examples and descriptions of the present invention are used to explain the present invention but are not intended to limit the present invention.

[0016] The present invention provides a method and system for constructing a multi-dimensional risk management maturity model, comprising the following steps: like Figure 1 As shown, in this embodiment, the following steps are included: Collect monitoring data and risk management data of a preset power system and pre-process the monitoring data and risk management data; the risk management data includes equipment failure risk management, fuel supply risk management, grid operation safety risk management, distributed resource aggregation risk management, and power supply shortage or excess risk management; the monitoring data includes data to be analyzed and historical data; In actual evaluations, the data to be analyzed includes transformer operating temperature, line power transmission value, generator speed, production raw material consumption data, production raw material inventory data, production raw material supply cycle information, voltage, current, power factor, voltage stability, light intensity, wind speed, power generation, and power consumption; historical data includes historical operating conditions, maintenance records, historical production raw material consumption, production raw material inventory, production raw material supply status, historical operating data, and historical data on distributed resources and power supply and demand; A power system is taken as the research object, the period from May 2021 to May 2024 is used as historical data, and the period from June 2024 is used as the data to be analyzed. The risk management mainly focuses on the generator speed, light intensity, and wind speed. Performing risk identification on the monitoring data to obtain risk data, using a priori algorithms to obtain risk types from the risk data, and performing power forecasting on the risk management data to obtain control data; the risk types include single risk types and multiple risk types; In actual evaluations, the control data include transformer operating temperature, line power transmission value, generator speed, voltage stability, sunlight intensity, and wind speed; Performing dynamic causal matching on the control data and the risk type to obtain a matching degree, using the control data with a matching degree greater than a matching threshold as management data, and otherwise using the control data as fuzzy data, performing a longitudinal comparative evaluation based on the historical data and the fuzzy data to obtain an optimization degree, and adding the fuzzy data with an optimization degree greater than the optimization threshold to the management data; A maturity evaluation function is constructed based on a comprehensive horizontal and vertical maturity comparison of the management data, a power risk management maturity model is constructed based on the maturity evaluation function, and a target model is output.

[0017] In this embodiment, the method for performing risk identification on the monitoring data to obtain risk data includes: A decision tree algorithm is used to construct a decision tree based on the equipment's operating parameters and maintenance records, and the equipment failure risk is identified through the decision tree's scoring rules. A time series analysis algorithm is used to model the fuel consumption data, inventory data, and supply cycle. By analyzing the trend, seasonality, and cyclical characteristics of historical data, the fuel demand and supply situation are predicted. When the supply situation is lower than the fuel demand, it is determined to be a fuel supply risk. An association rule mining algorithm is used to follow the association rules between parameters in the power grid operation data, and when the association rules are not met, it is determined to be a power grid operation safety risk. Based on the fuzzy comprehensive evaluation algorithm, fuzzy quantification is performed based on stability and environmental factors, and a fuzzy evaluation matrix is established to evaluate the distributed resource aggregation risk in combination with objective weights. When the evaluation value is greater than the threshold, it is determined to be a distributed resource aggregation risk. A Monte Carlo simulation algorithm is used to simulate power supply and demand, and the probability distribution of power supply and demand is obtained through random sampling and simulation calculations. When the power distribution is higher than the threshold, it is determined to be a power supply shortage or surplus risk.

[0018] In this embodiment, the method for performing dynamic causal matching on the control data and the risk type to obtain a matching degree includes: Sort the control data by time, divide the sorted control data into time windows, obtain control variables based on the control data, and obtain risk variables and risk factors based on risk types; Construct a causal graph, using the control variables and risk variables that are added or eliminated as the time window slides as nodes of the causal tree, and the causal relationships between nodes as edges of the causal graph; Weighted bootstrap resampling was used for the control data of sparse control variables, and a prior conditional independence test was performed on continuous risk factors and a chi-square test was performed on discrete multiple risk factors to obtain the cumulative statistics optimized for the conditional independence test, the regression coefficient matrix and the residual covariance of the structural vector autoregression model; Directly determine non-instantaneous causal relationships through temporal rules, and obtain instantaneous causal relationships by testing the relationship between control variables in the same time window through the structural vector autoregression model; Calculate single risk matching: , The exponential decay of the lag w is , the maximum lag period is , the single risk matching degree is , the standard deviation of the causal influence coefficient is , the single risk variable at time t is , the risk factor at time tw is , risk factors For a single risk variable The causal influence coefficient is , the dynamic adjustment weight at time t is , the forgetting factor is ; Perform principal component analysis and dimensionality reduction on multiple risk types to obtain principal components and calculate the multi-risk matching degree: , The ath principal component is , the number of principal components is , the variance contribution rate of the ath principal component is , the predictor variables are , predictor variables Principal component The Granger causality test result is , the multi-risk matching degree is ; Calculate the rolling mean and standard deviation based on the matching degree and set the adaptive threshold. The expression is: , The control threshold convergence speed coefficient is , the rolling mean is , the standard deviation is , the current time is t, and the adaptive threshold is ; When the matching degree is lower than the adaptive threshold, the nodes are dynamically added or removed, and the conditional independence test is updated until all control data and risk types are traversed and the matching degree is output; In the actual evaluation, the forgetting factor is 0.297, the maximum lag period is 5, and the matching degrees of the transformer operating temperature, line power transmission value, generator speed, voltage stability, light intensity, and wind speed are 0.671, 0.594, 0.307, 0.761, 0.293, and 0.458, respectively.

[0019] In this embodiment, the method for obtaining the degree of optimization by performing longitudinal comparative evaluation based on the historical data and the fuzzy data includes: Fuzzy data is classified according to monitoring type, and fuzzy data far from the classification center is divided using a Gaussian mixture model to obtain classified data; monitoring types include environmental parameters, operating parameters, economic factors, and equipment status; Align historical data and classified data according to timestamps, and calculate the comprehensive optimization degree based on objective weighting: , The comprehensive optimization degree of the b-th risk management is The upper limit of monitoring time is The monitoring start time is The monitoring deadline is , the response time of the b-th risk management is , the xth classification data of the zth classification is , categorical data The value at time t is , the value of the xth historical data at time t is , the number of categories is , the xth weight coefficient is ; In the actual evaluation, the optimization degree is 0.247.

[0020] In this embodiment, the method for constructing a maturity evaluation function based on a comprehensive comparison of the horizontal and vertical maturity of the management data includes: Obtain risk management data from different areas of other power systems as horizontal comparison data, use management data from the same power learning system at different time points as vertical comparison data, and normalize the horizontal comparison data; Exponential smoothing method was used to calculate the trend of longitudinal control data: ; The smoothing coefficient is , the trend value is h, and the trend value at time t-1 is , the longitudinal control data at time t is ; According to the horizontal comparison data, the horizontal maturity is evaluated to obtain the horizontal maturity, which is expressed as: , The horizontal maturity is , the number of horizontal control data is , the i-th horizontal control data is , the reference value of the i-th horizontal comparison data is , the response time of the i-th horizontal comparison data is ; Based on the longitudinal control data and change trends, longitudinal maturity assessment is performed to obtain the longitudinal maturity, which is expressed as: , The vertical maturity is , the number of longitudinal control data is , the upper limit of longitudinal observation time is , the longitudinal control data at time t is , the reference value of the longitudinal control data at time t is , the changing trend of the vth longitudinal control data at time t is , the response time of the vth longitudinal control data is , the reference response time of the vth longitudinal control data is ; The maturity evaluation function is constructed based on horizontal maturity and vertical maturity, and the expression is: , The comprehensive optimization degree of the b-th risk management is , the effectiveness of the b-th risk management strategy is , the number of risk management is M, and the optimization item is , the horizontal weight is , the vertical weight is , the optimization weight is , the mapping function is , the maturity evaluation function of the b-th risk management is , the vertical maturity of the b-th risk management is , the horizontal maturity of the b-th risk management is .

[0021] In this embodiment, the method for constructing a power risk management maturity model based on the maturity assessment function includes: Multi-dimensional evaluation indicators are selected through management data, and the entropy weight method is used to obtain the weights of the evaluation indicators; the evaluation indicators include equipment performance indicators, power grid operation indicators, economic indicators, environmental protection indicators and user satisfaction indicators; The objective function of the power risk management maturity model is constructed as follows: , The objective function of the b-th risk management is , the maturity evaluation function of the jth evaluation indicator of the bth risk management is , the jth evaluation index of the bth risk management is , the loss function is , the number of evaluation indicators is D; The maturity level is divided according to the objective function. When the objective function score is less than 0.219, the power system is managed without risk. When the objective function score is greater than 0.219 and less than 0.417, the power system risk management capability is at level 4. When the objective function score is greater than 0.417 and less than 0.609, the power system risk management capability is at level 3. When the objective function score is greater than 0.609 and less than 0.794, the power system risk management capability is at level 2. When the objective function score is greater than 0.794, the power system risk management capability is at level 1. In actual evaluations, equipment performance indicators include equipment failure rate, maintenance cycle, and reliability; grid operation indicators include power supply stability, load fluctuation, and response time; economic indicators include production costs, operating costs, and power losses; environmental protection indicators include carbon emission levels and the proportion of renewable energy; and user satisfaction indicators include customer complaint rate and service response time.

[0022] The second aspect is a system for constructing a multi-dimensional risk management maturity model, including: Data acquisition module: used to collect monitoring data and risk management data of the preset power system and pre-process the monitoring data and risk management data; the risk management data includes equipment failure risk management, fuel supply risk management, grid operation safety risk management, distributed resource aggregation risk management, and power supply shortage or excess risk management; the monitoring data includes data to be analyzed and historical data; Risk type identification module: performs risk identification on the monitoring data to obtain risk data, uses a priori algorithms to obtain risk types from the risk data, and performs power forecasting on the risk management data to obtain control data; the risk types include single risk types and multiple risk types; Prediction and matching module: used to perform power prediction based on the risk management data to obtain control data, perform dynamic causal matching on the control data and the risk type to obtain a matching degree, and use the control data with a matching degree greater than a matching threshold as management data, otherwise as fuzzy data; Comparison and evaluation module: Performs dynamic causal matching on the control data and the risk type to obtain a matching degree, uses the control data with a matching degree greater than a matching threshold as management data, and uses the control data with a matching degree greater than a matching threshold as fuzzy data. A longitudinal comparison and evaluation is performed based on the historical data and the fuzzy data to obtain an optimization degree, and the fuzzy data with an optimization degree greater than the optimization threshold is added to the management data; Modeling optimization module: constructing a maturity evaluation function based on a comprehensive horizontal and vertical maturity comparison of the management data, building a power risk management maturity model based on the maturity evaluation function, and outputting a target model.

[0023] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for constructing a multi-dimensional risk management maturity model, characterized in that: The following steps are involved: Collecting monitoring data and risk management data of a preset power system, and preprocessing the monitoring data and the risk management data; The risk management data includes equipment failure risk management, fuel supply risk management, power grid operation safety risk management, distributed resource aggregation risk management, and power supply shortage or excess risk management; the monitoring data includes data to be analyzed and historical data; Performing risk identification on the monitoring data to obtain risk data, using a priori algorithms to obtain risk types through the risk data, and performing power forecasting through the risk management data to obtain control data; The risk types include single risk types and multiple risk types; Performing dynamic causal matching on the control data and the risk type to obtain a matching degree, using the control data with a matching degree greater than a matching threshold as management data, and otherwise using the control data as fuzzy data, performing a longitudinal comparative evaluation based on the historical data and the fuzzy data to obtain an optimization degree, and adding the fuzzy data with an optimization degree greater than the optimization threshold to the management data; A maturity evaluation function is constructed based on a comprehensive horizontal and vertical maturity comparison of the management data, a power risk management maturity model is constructed based on the maturity evaluation function, and a target model is output.

2. The method for constructing a multi-dimensional risk management maturity model according to claim 1, characterized in that: The method for performing risk identification on the monitoring data to obtain risk data includes: A decision tree algorithm is used to construct a decision tree based on the equipment's operating parameters and maintenance records, and the equipment failure risk is identified through the decision tree's scoring rules. A time series analysis algorithm is used to model the fuel consumption data, inventory data, and supply cycle. By analyzing the trend, seasonality, and cyclical characteristics of historical data, the fuel demand and supply situation are predicted. When the supply situation is lower than the fuel demand, it is determined to be a fuel supply risk. An association rule mining algorithm is used to follow the association rules between parameters in the power grid operation data, and when the association rules are not met, it is determined to be a power grid operation safety risk. Based on the fuzzy comprehensive evaluation algorithm, fuzzy quantification is performed based on stability and environmental factors, and a fuzzy evaluation matrix is established to evaluate the distributed resource aggregation risk in combination with objective weights. When the evaluation value is greater than the threshold, it is determined to be a distributed resource aggregation risk. A Monte Carlo simulation algorithm is used to simulate power supply and demand, and the probability distribution of power supply and demand is obtained through random sampling and simulation calculations. When the power distribution is higher than the threshold, it is determined to be a power supply shortage or surplus risk.

3. The method for constructing a multi-dimensional risk management maturity model according to claim 1, characterized in that: The method for performing dynamic causal matching on the control data and the risk type to obtain a matching degree includes: Sort the control data by time, divide the sorted control data into time windows, obtain control variables based on the control data, and obtain risk variables and risk factors based on risk types; Construct a causal graph, using the control variables and risk variables that are added or eliminated as the time window slides as nodes of the causal tree, and the causal relationships between nodes as edges of the causal graph; Weighted bootstrap resampling was used for the control data of sparse control variables, and a prior conditional independence test was performed on continuous risk factors and a chi-square test was performed on discrete multiple risk factors to obtain the cumulative statistics optimized for the conditional independence test, the regression coefficient matrix and the residual covariance of the structural vector autoregression model; Directly determine non-instantaneous causal relationships through temporal rules, and obtain instantaneous causal relationships by testing the relationship between control variables in the same time window through the structural vector autoregression model; Calculate single risk matching: ， The exponential decay of the lag w is , the maximum lag period is , the single risk matching degree is , the standard deviation of the causal influence coefficient is , the single risk variable at time t is , the risk factor at time tw is , risk factors For a single risk variable The causal influence coefficient is , the dynamic adjustment weight at time t is , the forgetting factor is ; Perform principal component analysis and dimensionality reduction on multiple risk types to obtain principal components and calculate the multi-risk matching degree: ， The ath principal component is , the number of principal components is , the variance contribution rate of the ath principal component is , the predictor variables are , predictor variables Principal component The Granger causality test result is , the multi-risk matching degree is ; Calculate the rolling mean and standard deviation based on the matching degree and set the adaptive threshold. The expression is: ， The control threshold convergence speed coefficient is , the rolling mean is , the standard deviation is , the current time is t, and the adaptive threshold is ; When the matching degree is lower than the adaptive threshold, the nodes are dynamically added or reduced, and the conditional independence test is updated until all management and control data and risk types are traversed and the matching degree is output.

4. The method for constructing a multi-dimensional risk management maturity model according to claim 1, characterized in that: The method for obtaining the degree of optimization by performing longitudinal comparative evaluation based on the historical data and the fuzzy data includes: Fuzzy data is classified according to monitoring type, and fuzzy data far from the classification center is divided using a Gaussian mixture model to obtain classified data; monitoring types include environmental parameters, operating parameters, economic factors, and equipment status; Align historical data and classified data according to timestamps, and calculate the comprehensive optimization degree based on objective weighting: ， The comprehensive optimization degree of the b-th risk management is The upper limit of monitoring time is The monitoring start time is The monitoring deadline is , the response time of the b-th risk management is , the xth classification data of the zth classification is , categorical data The value at time t is , the value of the xth historical data at time t is , the number of categories is , the xth weight coefficient is .

5. The method for constructing a multi-dimensional risk management maturity model according to claim 1, characterized in that: The method for constructing a maturity evaluation function based on a comprehensive comparison of the horizontal and vertical maturity of the management data includes: Obtain risk management data from different areas of other power systems as horizontal comparison data, use management data from the same power learning system at different time points as vertical comparison data, and normalize the horizontal comparison data; Exponential smoothing method was used to calculate the trend of longitudinal control data: ； The smoothing coefficient is , the trend value is h, and the trend value at time t-1 is , the longitudinal control data at time t is ; According to the horizontal comparison data, the horizontal maturity is evaluated to obtain the horizontal maturity, which is expressed as: ， The horizontal maturity is , the number of horizontal control data is , the i-th horizontal control data is , the reference value of the i-th horizontal comparison data is , the response time of the i-th horizontal comparison data is ; Based on the longitudinal control data and change trends, longitudinal maturity assessment is performed to obtain the longitudinal maturity, which is expressed as: ， The vertical maturity is , the number of longitudinal control data is , the upper limit of longitudinal observation time is , the longitudinal control data at time t is , the reference value of the longitudinal control data at time t is , the changing trend of the vth longitudinal control data at time t is , the response time of the vth longitudinal control data is , the reference response time of the vth longitudinal control data is ; The maturity evaluation function is constructed based on horizontal maturity and vertical maturity, and the expression is: ， The comprehensive optimization degree of the b-th risk management is , the effectiveness of the b-th risk management strategy is , the number of risk management is M, and the optimization item is , the horizontal weight is , the vertical weight is , the optimization weight is , the mapping function is , the maturity evaluation function of the b-th risk management is , the vertical maturity of the b-th risk management is , the horizontal maturity of the b-th risk management is .

6. The method for constructing a multi-dimensional risk management maturity model according to claim 1, characterized in that: The method for constructing a power risk management maturity model according to the maturity assessment function includes: Multi-dimensional evaluation indicators are selected through management data, and the entropy weight method is used to obtain the weights of the evaluation indicators; the evaluation indicators include equipment performance indicators, power grid operation indicators, economic indicators, environmental protection indicators and user satisfaction indicators; The objective function of the power risk management maturity model is constructed as follows: ， The objective function of the b-th risk management is , the maturity evaluation function of the jth evaluation indicator of the bth risk management is , the jth evaluation index of the bth risk management is , the loss function is , the number of evaluation indicators is D; The maturity level is divided according to the objective function. When the objective function score is less than 0.219, the power system is managed without risk; when the objective function score is greater than 0.219 and less than 0.417, the power system risk management capability is level four; when the objective function score is greater than 0.417 and less than 0.609, the power system risk management capability is level three; when the objective function score is greater than 0.609 and less than 0.794, the power system risk management capability is level two; when the objective function score is greater than 0.794, the power system risk management capability is level one.

7. A system for constructing a multi-dimensional risk management maturity model, used to execute the method according to any one of claims 1 to 6, characterized in that: include: Data acquisition module: used to collect monitoring data and risk management data of a preset power system, and pre-process the monitoring data and the risk management data; The risk management data includes equipment failure risk management, fuel supply risk management, power grid operation safety risk management, distributed resource aggregation risk management, and power supply shortage or excess risk management; the monitoring data includes data to be analyzed and historical data; Risk type identification module: performs risk identification on the monitoring data to obtain risk data, uses a priori algorithms to obtain risk types from the risk data, and performs power forecasting on the risk management data to obtain control data; The risk types include single risk types and multiple risk types; Prediction and matching module: used to perform power prediction based on the risk management data to obtain control data, perform dynamic causal matching on the control data and the risk type to obtain a matching degree, and use the control data with a matching degree greater than a matching threshold as management data, otherwise as fuzzy data; Comparison and evaluation module: Performs dynamic causal matching on the control data and the risk type to obtain a matching degree, uses the control data with a matching degree greater than a matching threshold as management data, and uses the control data with a matching degree greater than a matching threshold as fuzzy data. A longitudinal comparison and evaluation is performed based on the historical data and the fuzzy data to obtain an optimization degree, and the fuzzy data with an optimization degree greater than the optimization threshold is added to the management data; Modeling optimization module: constructing a maturity evaluation function based on a comprehensive horizontal and vertical maturity comparison of the management data, building a power risk management maturity model based on the maturity evaluation function, and outputting a target model.

Images