Power market risk management method and device based on fuzzy logic, computer equipment, readable storage medium and program product

Abstract

The invention relates to an electricity market risk management method and device based on fuzzy logic, computer equipment, a readable storage medium and a program product. According to the method, a normalized weight and a preliminary risk assessment result of electricity price data can be determined through an electricity market price risk management model constructed based on an isolation forest and an analytic hierarchy process; under the condition that the preliminary risk assessment result is that the risk exists, according to the electricity price data and the normalized weight, and based on an electricity market price risk estimation model, a corrected risk assessment result capable of specifically measuring the electricity market price risk can be obtained; after the electricity price mode is identified based on the electricity price data, the electricity price risk assessment result under the electricity price mode can be finally determined based on the corrected risk assessment result and the electricity price mode.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power market risk, and particularly relates to a power market risk management method and device based on fuzzy logic, computer equipment, computer readable storage medium and computer program product. BACKGROUND

[0002] With the development of global power market, power risk management has become an important part of ensuring the stable operation of the power system. In the existing power market, various types of power transactions and power transaction methods are becoming more and more complex, which makes the uncertainty of the power market greater and greater. This increases the volatility of the power market price and the risk of interference. Price fluctuations are an important risk source affecting the economic benefits of power enterprises and users. Unstable electricity prices not only may bring significant operational risks to the power grid company's proxy power purchase business, but also will affect the power cost of power users.

[0003] In the traditional technology, the method and model for power market risk management based on fuzzy logic have been relatively mature, but the reliability is low in the processing of time volatility. SUMMARY

[0004] Therefore, it is necessary to provide a power market risk management method, device, computer equipment, computer readable storage medium and computer program product based on fuzzy logic with high reliability to solve the above technical problems.

[0005] In a first aspect, the present application provides a power market risk management method based on fuzzy logic, comprising:

[0006] Collecting electricity price data of the power market;

[0007] According to the electricity price data, and based on a preset power market price risk management model, determining the normalized weight of the electricity price data and a preliminary risk assessment result; wherein the power market price risk management model is a model constructed based on isolated forest and analytic hierarchy process;

[0008] In the case that the preliminary risk assessment result is that there is a risk, according to the electricity price data and the normalized weight, and based on a preset power market price risk estimation model, determining a corrected risk assessment result; wherein the power market price risk estimation model is a model optimized based on a preset fuzzy algorithm, and the preset fuzzy algorithm is a fuzzy algorithm optimized based on a cloud model;

[0009] According to the electricity price data, identifying the electricity price mode;

[0010] According to the corrected risk assessment result and the electricity price mode, determining the electricity price risk assessment result under the electricity price mode.

[0011] In one of the embodiments, the step of determining the corrected risk assessment result according to the electricity price data and the normalized weight and based on the preset electricity market price risk estimation model comprises:

[0012] determining a predicted electricity price according to the electricity price data and the normalized weight and based on the electricity market price risk estimation model;

[0013] determining a predicted electricity price fluctuation range according to the predicted electricity price and the historical electricity price;

[0014] determining the corrected risk assessment result according to the predicted electricity price fluctuation range, the predicted electricity price fluctuation range being positively correlated with the risk level of the corrected risk assessment result.

[0015] In one of the embodiments, the step of determining the predicted electricity price according to the electricity price data and the normalized weight and based on the electricity market price risk estimation model comprises:

[0016] initializing the electricity price data and the fuzzy clustering center;

[0017] determining the distance between each electricity price data and the fuzzy clustering center based on a distance formula;

[0018] updating the membership matrix according to the distance;

[0019] determining the membership degree according to the membership matrix;

[0020] determining the predicted electricity price according to the membership degree, the fuzzy clustering center, the normalized weight and the following formula:

[0021]

[0022] wherein, the predicted electricity price, u ij the membership degree, c j the fuzzy clustering center, ω i the normalized weight.

[0023] In one of the embodiments, after the step of updating the membership matrix according to the distance, and before the step of determining the membership degree according to the membership matrix, the method further comprises:

[0024] obtaining a change value of the membership matrix;

[0025] in the case that the change value is greater than or equal to a first preset value, updating the fuzzy clustering center and the iteration number, and entering the step of determining the distance between each electricity price data and the fuzzy clustering center based on the distance formula, until the change value is less than the first preset value.

[0026] In one of the embodiments, the step of determining the normalized weight of the electricity price data and the preliminary risk assessment result based on the electricity price data and the preset electricity market price risk management model comprises:

[0027] determining abnormal data according to the electricity price data and the isolation forest;

[0028] extracting a plurality of price fluctuation features based on the abnormal data;

[0029] determining the weighted result and the normalized weight of the price fluctuation features according to the weight of each price fluctuation feature and based on the analytic hierarchy process;

[0030] determining the preliminary risk assessment result according to the weight and the weighted result.

[0031] In one of the embodiments, after the step of determining the weighted result and the normalized weight according to the weight of each price fluctuation feature and based on the analytic hierarchy process, and before the step of determining the preliminary risk assessment result according to the weight and the weighted result, the method further comprises:

[0032] establishing a judgment matrix according to the index scoring method;

[0033] determining the maximum eigenvalue of the judgment matrix according to the judgment matrix;

[0034] determining the consistency index according to the maximum eigenvalue and the order of the judgment matrix;

[0035] determining the consistency ratio according to the consistency index and a random consistency index, wherein the random consistency index is determined according to the order of the judgment matrix and a preset retrieval table;

[0036] in the case where the consistency ratio is greater than or equal to a preset value, re-entering the step of extracting a plurality of price fluctuation features based on the abnormal data until the consistency ratio is less than the preset value.

[0037] In a second aspect, the present application also provides an electricity market risk management device based on fuzzy logic, comprising:

[0038] a collection module for collecting electricity price data of an electricity market;

[0039] a first data determination module for determining the normalized weight of the electricity price data and the preliminary risk assessment result based on the electricity price data and a preset electricity market price risk management model; wherein the electricity market price risk management model is a model constructed based on the isolation forest and the analytic hierarchy process;

[0040] The second data determining module is configured to, when the preliminary risk assessment result is that there is risk, determine a revised risk assessment result according to the electricity price data and the normalized weight and based on a preset electricity market price risk estimation model; the electricity market price risk estimation model is a model optimized based on a preset fuzzy algorithm from an electricity market price risk management model; and the preset fuzzy algorithm is a fuzzy algorithm optimized based on a cloud model.

[0041] The electricity price mode identifying module is configured to identify an electricity price mode according to the electricity price data.

[0042] The electricity price risk assessment module is configured to determine an electricity price risk assessment result under the electricity price mode according to the revised risk assessment result and the electricity price mode.

[0043] In a third aspect, the present application further provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements any step of the above-mentioned electricity market risk management method based on fuzzy logic when executing the computer program.

[0044] In a fourth aspect, the present application further provides a computer readable storage medium having a computer program stored thereon, wherein the computer program implements any step of the above-mentioned electricity market risk management method based on fuzzy logic when executed by a processor.

[0045] In a fifth aspect, the present application further provides a computer program product comprising a computer program, wherein the computer program implements any step of the above-mentioned electricity market risk management method based on fuzzy logic when executed by a processor.

[0046] The power market risk management method, device, computer equipment, computer readable storage medium and computer program product based on fuzzy logic can determine the normalized weight of the electricity price data and the preliminary risk assessment result through the power market price risk management model constructed based on the isolated forest and the analytic hierarchy process; in the case that the preliminary risk assessment result is that there is risk, the correction risk assessment result capable of specifically measuring the size of the power market price risk can be obtained according to the electricity price data and the normalized weight and based on the power market price risk estimation model; after the electricity price mode is identified based on the electricity price data, the electricity price risk assessment result under the electricity price mode can be finally determined based on the correction risk assessment result and the electricity price mode. Unlike the traditional method, the power market risk management method based on fuzzy logic effectively identifies and quantifies the power market price risk, links theory with practice, improves the accuracy and reliability of risk assessment in the case of high uncertainty (the electricity price data exist time fluctuations), and emphasizes the importance of adaptive strategies (identifying the corresponding electricity price mode based on the electricity price data, and determining the electricity price risk assessment result under the electricity price mode based on the correction risk assessment result and the electricity price mode), so as to lay a foundation for solving the complexity of the modern power market by combining electricity price data analysis and real-time monitoring of the power market in the future. BRIEF DESCRIPTION OF DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other related drawings can be obtained by those skilled in the art without creative labor.

[0048] Figure 1 The application environment diagram of the power market risk management method based on fuzzy logic in an embodiment;

[0049] Figure 2 The flowchart of the power market risk management method based on fuzzy logic in an embodiment;

[0050] Figure 3 The structure block diagram of the power market risk management device based on fuzzy logic in an embodiment;

[0051] Figure 4 The internal structure diagram of the computer equipment in an embodiment. DETAILED DESCRIPTION

[0052] In order to make the purposes, technical solutions and advantages of the present application clearer, further detailed description will be given below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and should not be used to limit the present application.

[0053] The power market risk management method based on fuzzy logic provided by the embodiments of the present application can be applied to the application environment as shown in Figure 1 . The terminal 102 communicates with the server 104 through the network. The data storage system can store the power market price risk management model, the power market price risk estimation model and other data to be processed preset by the server 104. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The server 104 collects the electricity price data of the power market, determines the corresponding normalized weight and preliminary risk assessment result of the electricity price data according to the electricity price data and based on the preset power market price risk management model, determines the correction risk assessment result corresponding to the preliminary risk assessment result according to the electricity price data and the normalized weight and based on the preset power market price risk estimation model in the case that the preliminary risk assessment result is risky, determines the electricity price risk assessment result in the electricity price mode according to the correction risk assessment result and the electricity price mode. The server 104 can send the electricity price risk assessment result to the terminal 102 for the user to view. The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, unmanned aerial vehicles, low-altitude flying vehicles, Internet of Things devices and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle device, a projection device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, smart glasses, etc. The server 104 can be a stand-alone physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0054] In an exemplary embodiment, as shown in Figure 2 , a power market risk management method based on fuzzy logic is provided. Taking the server 104 in Figure 1 as an example, the method includes the following steps:

[0055] S202, collecting electricity price data of the power market.

[0056] S204, determine a normalization weight and a preliminary risk assessment result of the electricity price data according to the electricity price data and based on a preset electricity market price risk management model; wherein the electricity market price risk management model is a model constructed based on an isolation forest and an analytic hierarchy process.

[0057] S206, in a case where the preliminary risk assessment result is that there is a risk, determine a corrected risk assessment result according to the electricity price data and the normalization weight and based on a preset electricity market price risk estimation model; wherein the electricity market price risk estimation model is a model optimized based on a preset fuzzy algorithm from the electricity market price risk management model; and the preset fuzzy algorithm is a fuzzy algorithm optimized based on a cloud model.

[0058] After the preset fuzzy algorithm is optimized and improved based on the cloud model, an optimized fuzzy algorithm is obtained, and then the preset electricity market price risk management model is optimized based on the optimized fuzzy algorithm to obtain the preset electricity market price risk estimation model. The preset fuzzy algorithm can be a fuzzy C-means (FCM) algorithm. The cloud model can represent a process from a qualitative concept to a quantitative representation (forward cloud generator) and also represent a process from a quantitative representation to a qualitative concept (reverse cloud generator). The cloud model can better represent the fuzziness of data points in cloud droplets, so that the model can be enhanced after being optimized based on the cloud model to compensate for some deficiencies of the fuzzy C-means algorithm in fuzzy logic.

[0059] S208, identify an electricity price pattern according to the electricity price data.

[0060] S210, determine an electricity price risk assessment result in the electricity price pattern according to the corrected risk assessment result and the electricity price pattern.

[0061] According to the electricity price data and based on the preset electricity market price risk management model, a preliminary risk assessment result indicating that there is a risk and a preliminary risk assessment result indicating that there is no risk can be determined. Thus, in a case where the preliminary risk assessment result is that there is a risk, the next operation is performed; and in a case where the preliminary risk assessment result is that there is no risk, the execution of the electricity market risk management method based on fuzzy logic can be directly ended to reduce the waste of computing resources.

[0062] The electricity price mode includes a peak period mode, a flat period mode and a valley period mode. The peak period refers to a time period in which the power load is relatively high and the electricity demand is strong in a day. At this time, the power supply pressure of the power system is relatively large. In order to guide users to reasonably use electricity and relieve the situation of tight power supply, the electricity price in the peak period is relatively high. The flat period is a time period in which the power load is relatively stable, neither belonging to the peak period nor the valley period in a day. The flat electricity price is usually between the peak electricity price and the valley electricity price. The flat electricity price is mainly set to more reasonably reflect the power cost and supply and demand relationship. The valley period refers to a time period in which the power load is relatively low and the electricity demand is relatively small. At this time, the power generation capacity of the power system is relatively surplus. In order to encourage users to use electricity in the time period and improve the utilization efficiency of power resources, the valley electricity price is relatively low. Generally, the peak period, the flat period and the valley period are different in different regions and different seasons. Therefore, the current electricity price mode can be determined according to the electricity price data.

[0063] Specifically, the electricity price data can be adjusted according to the real-time supply and demand of the power market. Therefore, real-time electricity price data can be obtained to accurately identify the electricity price mode.

[0064] The correction risk assessment result is a specific value for measuring the size of the price risk of the power market. The price risk of the power market in the same electricity price data is different in different electricity price modes. For example, in the peak period mode, the corresponding correction risk assessment result is relatively high due to the strong electricity demand. Correspondingly, in the valley period mode, the corresponding correction risk assessment result is relatively low due to the small electricity demand. The flat period mode is between the peak period mode and the valley period mode, and therefore the corresponding correction risk assessment result is also at a medium level. Thus, the electricity price risk assessment result in the electricity price mode can be determined based on the correction risk assessment result and the electricity price mode.

[0065] In the above fuzzy logic-based power market risk management method, the power market price risk management model constructed based on the isolation forest and the analytic hierarchy process can determine the normalized weight of the price data and the preliminary risk assessment result. In the case where the preliminary risk assessment result indicates that there is a risk, the correction risk assessment result that can specifically measure the size of the power market price risk can be obtained according to the price data and the normalized weight and based on the power market price risk estimation model. After the price pattern is identified based on the price data, the price risk assessment result under the price pattern can be finally determined based on the correction risk assessment result and the price pattern. Unlike traditional methods, the fuzzy logic-based power market risk management method effectively identifies and quantifies the power market price risk, links theory with practice, improves the accuracy and reliability of risk assessment in the case of high uncertainty (time fluctuations in price data), and emphasizes the importance of adaptive strategies (identifying the corresponding price pattern based on price data, determining the price risk assessment result under the price pattern based on the correction risk assessment result and the price pattern), laying a foundation for solving the complexity of modern power markets by combining price data analysis and real-time monitoring of power markets in the future.

[0066] In an exemplary embodiment, the step of determining the correction risk assessment result according to the price data and the normalized weight and based on the preset power market price risk estimation model comprises:

[0067] According to the price data and the normalized weight, and based on the power market price risk estimation model, a predicted price is determined.

[0068] According to the predicted price and the historical price, a predicted price fluctuation range is determined.

[0069] The historical price is averaged to obtain a historical price average value. The predicted price is subtracted from the historical price average value to obtain a price difference value. The predicted price fluctuation range is obtained by dividing the price difference value by the historical price average value.

[0070] According to the predicted price fluctuation range, the correction risk assessment result is determined. The predicted price fluctuation range and the correction risk assessment result are positively correlated in terms of risk level.

[0071] The correction risk assessment result can be divided into multiple different price risk levels. For example, five price risk levels are divided, namely, extremely low risk, low risk, medium risk, high risk, and extremely high risk. When the price fluctuation range is less than 5%, the correction risk assessment result can be extremely low risk. When the price fluctuation range is greater than 20%, the correction risk assessment result can be extremely high risk.

[0072] In an embodiment, an emergency measure is determined according to the predicted price fluctuation range.

[0073] In the case of modifying the risk assessment result to be extremely low risk, since the electricity price has the least impact on the electricity market at this time, no emergency measures can be taken.

[0074] In the case of modifying the risk assessment result to be extremely high risk, since the electricity price has the greatest impact on the electricity market at this time, emergency intervention is needed.

[0075] In an exemplary embodiment, the step of determining the predicted electricity price according to the electricity price data and the normalized weights, and based on the electricity market price risk estimation model, comprises:

[0076] The electricity price data and the fuzzy clustering centers are initialized.

[0077] The step of initializing the electricity price data can also be performed after the step of collecting the electricity price data of the electricity market, and before the step of determining the normalized weights and the preliminary risk assessment result of the electricity price data according to the electricity price data, and based on the preset electricity market price risk management model, to ensure that the isolation forest can correctly select samples from the data set (all the collected electricity price data) in the process of constructing the isolation tree, and these samples can effectively isolate outliers in the subsequent splitting process. Specifically, the initialization step includes randomly selecting a certain number of samples from the data set as initial sampling points, which will be used to construct nodes of the isolation tree. In this way, the isolation forest can randomly sample the data without preserving the original data distribution, thereby improving the accuracy of outlier detection.

[0078] Based on the distance formula, the distance between each electricity price data and the fuzzy clustering center is determined.

[0079] According to the distance, the membership matrix is updated.

[0080] According to the membership matrix, the membership degree is determined.

[0081] According to the membership degree, the fuzzy clustering center, the normalized weight, and the following formula, the predicted electricity price is determined:

[0082]

[0083] wherein, is the predicted electricity price, u ij is the membership degree, c j is the fuzzy clustering center, ω j is the normalized weight.

[0084] The determination step of the predicted electricity price formula is as follows:

[0085] Assuming x iis a data point (electricity price data) in the electricity market, and the cloud drop formation process in the cloud model thereof is represented by the following equation:

[0086]

[0087] wherein E i represents the cloud drop of x i , μ i represents the expected value of the data point, and σ i represents the standard deviation of the data point.

[0088] The update of the membership degree of the cloud model and the fuzzy clustering center is represented by the following equation:

[0089]

[0090] wherein it is assumed that N is the number of data points, u ij represents the membership degree of the data point x i to the fuzzy clustering center, m is a fuzzy factor (usually m>1), d ij represents the distance, and k is an index variable for traversing all clustering centers. In the FCM algorithm, the membership degree of the data point x j to each fuzzy clustering center needs to consider the distance of the point to all fuzzy clustering centers (numbered as k=1, 2, …, c).

[0091] d ij can be determined by the following equation:

[0092]

[0093] wherein μ j represents the jth fuzzy clustering center, and σ j represents the actual deviation of the data point.

[0094] Based on the above formula, the predicted electricity price formula can be determined:

[0095]

[0096] In an exemplary embodiment, after the step of updating the membership degree matrix according to the distance, and before the step of determining the membership degree according to the membership degree matrix, the above method further comprises:

[0097] obtaining the change value of the membership degree matrix.

[0098] In the case where the change value is greater than or equal to a first preset value, the fuzzy clustering center and the iteration number are updated, and the step of determining the distance between each electricity price data and the fuzzy clustering center based on the distance formula is entered, until the change value is less than the first preset value.

[0099] The convergence of the algorithm for determining the membership degree can be determined according to the change value of the membership matrix. Specifically, if the change value of the membership matrix is very small, it means that the clustering membership relationship almost does not change any more, and it can be considered that the algorithm for determining the membership degree has converged. More specifically, if the difference between the new membership matrix and the old membership matrix (i.e. the change value of the membership matrix) is less than a first preset value, it converges; otherwise, it does not converge. Therefore, by comparing the change value of the membership matrix with the first preset value, the convergence can be determined. If the convergence is not achieved, the fuzzy clustering center and the iteration number are updated and returned to continue calculating the change value of the membership matrix until the change value is less than the first preset value. If the convergence condition is reached, the final fuzzy clustering center and the membership matrix are directly output, and the membership degree is determined according to the membership matrix, and then the step is ended.

[0100] In an exemplary embodiment, the step of determining the normalized weight of the electricity price data and the preliminary risk assessment result according to the electricity price data and based on the preset electricity market price risk management model comprises:

[0101] According to the electricity price data and the isolation forest, the abnormal data is determined.

[0102] The isolation forest is an unsupervised learning algorithm, and the efficiency and independence of the isolation forest in abnormal data detection are good. Compared with other anomaly detection methods, the isolation forest can more effectively process high-dimensional data and has higher sensitivity to abnormal values, making it suitable for identifying anomalies in power market price fluctuations. Therefore, the isolation forest has an advantage in processing complex and uncertain data in the power market.

[0103] Specifically, the isolation forest constructs a decision tree by randomly selecting features and splitting points, and the decision tree uses the path length of the data points in the tree to determine whether the data points are abnormal values, and the path length c(n) is as follows:

[0104]

[0105] Wherein, n represents the number of data points (electricity price data), and H(n-1) is the (n-1)th harmonic number.

[0106] The determination of the abnormal score is as follows:

[0107]

[0108] Wherein, x represents the data point (electricity price data) to be detected, h(x) represents the path length of x on the tree, E(h(x)) is the abnormal electricity price, and s(x, n) represents the abnormal score of x. Specifically, if s(x, n) is equal to 1, x is an abnormal value; if s(x, n) is equal to 0, x is a normal point (normal value).

[0109] In the risk identification of abnormal electricity price, the abnormal electricity price is represented by the following equation:

[0110]

[0111] wherein T represents the number of decision trees in the isolated forest, h i (x) represents the path length of x in the i-th decision tree.

[0112] Based on the abnormal data, a plurality of price fluctuation features are extracted.

[0113] The price fluctuation features can be at least one of the electricity price risk indicators in the electricity price risk indicator system. The electricity price risk indicator system has five indicators, namely electricity price, price difference, electricity price fluctuation, electricity price rationality and electricity price correlation. Among them, the electricity price includes four types, namely the highest electricity price, the lowest electricity price, the median electricity price and the average electricity price. The price difference includes short-term price difference, medium-term price difference and long-term price difference. The electricity price fluctuation includes the low valley change rate, the daily change rate and the peak valley change rate. The electricity price rationality includes the electricity price upper limit ratio, the electricity price lower limit ratio and the cost deviation. The electricity price correlation includes the correlation coefficient of electricity price and supply-demand ratio, electricity price and production cost, and electricity price and new energy output.

[0114] According to the weight of each price fluctuation feature, and based on the analytic hierarchy process, the weighted result and the normalized weight of the price fluctuation feature are determined. The weight distribution of each price fluctuation feature is the key part of the analytic hierarchy process, which determines the weight of each electricity price risk indicator and objectively distinguishes the electricity price risk indicators.

[0115] According to the weights and the weighted results, the preliminary risk assessment result is determined.

[0116] Specifically, first, an index set (including at least one of the electricity price risk indicators in the electricity price risk indicator system) is established to clearly indicate the various indicators to be evaluated. Then, a judgment matrix is established by expert scoring and index scoring method to reflect the relative importance of each indicator. The index scoring method is a method of comparing each indicator in the same level with each other to determine their relative importance. Finally, by comprehensively calculating the weight of each candidate target (price fluctuation feature), the importance ranking of each candidate target can be obtained, that is, the weights are determined, and the weighted result and the normalized weight of the price fluctuation feature are determined based on the weights.

[0117] It is known that the isolation forest algorithm is used for anomaly detection to label outliers in historical data that indicate abnormal risk conditions, i.e. to label outliers in the collected electricity price data. Subsequently, the analytic hierarchy process builds a comparison by evaluating the importance of various criteria (each criterion in the determined set of criteria) to prioritize these identified risks, and this double method improves the accuracy of risk identification and provides information for the decision-making process, ensuring that stakeholders can effectively reduce significant risks in the electricity market.

[0118] In an exemplary embodiment, after the step of determining the weighted results and the normalized weights according to the weights of each price fluctuation feature and based on the analytic hierarchy process, and before the step of determining the preliminary risk assessment results according to each weight and the weighted results, the above method further comprises:

[0119] According to the criterion scoring method, a judgment matrix is established.

[0120] According to the judgment matrix, the maximum eigenvalue of the judgment matrix is determined.

[0121] According to the maximum eigenvalue and the order of the judgment matrix, a consistency index is determined.

[0122] According to the consistency index and a random consistency index, a consistency ratio is determined; wherein the random consistency index is determined according to the order of the judgment matrix and a preset retrieval table.

[0123] In the case where the consistency ratio is greater than or equal to a preset value, re-entering the step of "extracting a plurality of price fluctuation features based on abnormal data" until the consistency ratio is less than the preset value.

[0124] Specifically, the judgment matrix A ij is represented by the following equation:

[0125]

[0126] where i and j are both criteria participating in comparison, and criterion i and criterion j represent different criteria participating in comparison (comparison in the criterion scoring method); A ij is the importance degree of criterion i relative to criterion j, generally between 1 and 9. A ij The larger, the more important the comparison between criterion i and criterion j. If A ij is 1, the importance of the two criteria is equal.

[0127] The calculation of the consistency test is represented by the following equation:

[0128]

[0129] wherein CR represents a consistency ratio, and z represents the order of the judgment matrix. CI represents a consistency index, and RI represents a random consistency index. λ max represents the maximum eigenvalue of the judgment matrix. When CR < 0.1, the judgment matrix is considered to have satisfactory consistency. When CR≥0.1, the consistency of the judgment matrix is crossed, and needs to be adjusted again, that is, to re-enter the step of “extracting multiple price fluctuation features based on abnormal data”, until the consistency ratio is less than the preset value.

[0130] The normalized matrix of the judgment matrix (A=a×b) and the normalized weight ω i as shown in the following equation:

[0131]

[0132] wherein a ij represents the normalized element of the judgment matrix.

[0133] In one embodiment, after the step of collecting the electricity price data of the electricity market, before the step of determining the normalized weight of the electricity price data and the preliminary risk assessment result according to the electricity price data and based on the preset electricity market price risk management model, the above method further comprises:

[0134] Pretreating the electricity price data.

[0135] Processing and converting the cleaned data for subsequent analysis and use.

[0136] wherein the pretreatment includes subtracting the mean value of each data point (electricity price data) of each feature, and then dividing by the standard deviation of the feature, so that the data distribution of each feature has a zero mean and a unit variance.

[0137] In addition, in the case of random missing values, mean filling or median filling can also be used for processing to reduce data bias.

[0138] It should be understood that although each step in the flowchart involved in the above-described embodiments is shown in sequence according to the arrow, the steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other orders. Moreover, at least some of the steps in the flowchart involved in the above-described embodiments can include multiple steps or multiple stages, which are not necessarily executed at the same time but can be executed at different times, and the execution of the steps or stages is not necessarily sequential but can be performed alternately or alternately with at least some of the other steps or steps or stages in other steps. It can be understood that the steps in different embodiments can be freely combined as needed, and various non-contradictory schemes formed by the combination are within the scope of protection of the present application.

[0139] Based on the same inventive concept, the embodiments of the present application also provide a fuzzy logic-based power market risk management device for implementing the above-mentioned fuzzy logic-based power market risk management method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more fuzzy logic-based power market risk management device embodiments provided below can refer to the limitations of the fuzzy logic-based power market risk management method described above, and will not be repeated here.

[0140] In one exemplary embodiment, as shown in Figure 3 A fuzzy logic-based power market risk management device 300 is provided, comprising: an acquisition module 302, a first data determination module 304, a second data determination module 306, a price pattern recognition module 308, and a price risk assessment module 310, wherein:

[0141] The acquisition module 302 is configured to acquire price data of a power market.

[0142] The first data determination module 304 is configured to determine a normalized weight of the price data and a preliminary risk assessment result based on a preset power market price risk management model according to the price data; wherein the power market price risk management model is a model constructed based on an isolated forest and an analytic hierarchy process.

[0143] The second data determination module 306 is configured to determine a corrected risk assessment result based on a preset power market price risk estimation model according to the price data and the normalized weight when the preliminary risk assessment result indicates that there is a risk; wherein the power market price risk estimation model is a model optimized based on a preset fuzzy algorithm based on the power market price risk management model; and the preset fuzzy algorithm is a fuzzy algorithm optimized based on a cloud model.

[0144] The electricity price pattern recognition module 308 is configured to recognize an electricity price pattern according to the electricity price data.

[0145] The electricity price risk assessment module 310 is configured to determine an electricity price risk assessment result under the electricity price pattern according to the corrected risk assessment result and the electricity price pattern.

[0146] In an exemplary embodiment, the second data determination module 306 comprises a predicted electricity price determination module, an electricity price fluctuation amplitude prediction module and a corrected risk assessment result determination module.

[0147] The predicted electricity price determination module is configured to determine a predicted electricity price according to the electricity price data and the normalized weight and based on an electricity market price risk estimation model.

[0148] The electricity price fluctuation amplitude prediction module is configured to determine a predicted electricity price fluctuation amplitude according to the predicted electricity price and the historical electricity price.

[0149] The corrected risk assessment result determination module is configured to determine a corrected risk assessment result according to the predicted electricity price fluctuation amplitude, the predicted electricity price fluctuation amplitude and the corrected risk assessment result being in a positive correlation in terms of risk level.

[0150] In an exemplary embodiment, the predicted electricity price determination module comprises an initialization module, a distance determination module, an update module, a membership degree determination module and an operation module.

[0151] The initialization module is configured to initialize the electricity price data and the fuzzy clustering center.

[0152] The distance determination module is configured to determine the distance between each electricity price data and the fuzzy clustering center based on a distance formula.

[0153] The update module is configured to update the membership degree matrix according to the distance.

[0154] The membership degree determination module is configured to determine the membership degree according to the membership degree matrix.

[0155] The operation module is configured to determine the predicted electricity price according to the membership degree, the fuzzy clustering center, the normalized weight and the following formula.

[0156]

[0157] wherein, is the predicted electricity price, u ij is the membership degree, c j is the fuzzy clustering center, ω i is the normalized weight.

[0158] In an exemplary embodiment, the fuzzy logic-based electricity market risk management device 300 further comprises a change value acquisition module and an iteration module.

[0159] The change value obtaining module is configured to obtain a change value of the membership matrix.

[0160] The iteration module is configured to update the fuzzy clustering center and the iteration number when the change value is greater than or equal to a first preset value, and enter the step of determining the distance between each electricity price data and the fuzzy clustering center based on the distance formula until the change value is less than the first preset value.

[0161] In an exemplary embodiment, the first data determining module 304 comprises an abnormal data determining module, a feature extraction module and a first data determining sub-module.

[0162] The abnormal data determining module is configured to determine abnormal data according to the electricity price data and the isolated forest.

[0163] The feature extraction module is configured to extract a plurality of price fluctuation features based on the abnormal data.

[0164] The first data determining sub-module is configured to determine a weighted result of the price fluctuation features and a normalized weight based on the analytic hierarchy process according to the weight of each price fluctuation feature.

[0165] The preliminary risk assessment result is determined according to each weight and the weighted result.

[0166] In an exemplary embodiment, the fuzzy logic-based electricity market risk management device 300 further comprises a matrix establishing module, a maximum eigenvalue determining module, a consistency index determining module, a consistency ratio determining module and a comparison module.

[0167] The matrix establishing module is configured to establish a judgment matrix according to an index scoring method.

[0168] The maximum eigenvalue determining module is configured to determine a maximum eigenvalue of the judgment matrix according to the judgment matrix.

[0169] The consistency index determining module is configured to determine a consistency index according to the maximum eigenvalue and the order of the judgment matrix.

[0170] The consistency ratio determining module is configured to determine a consistency ratio according to the consistency index and a random consistency index, wherein the random consistency index is determined according to the order of the judgment matrix and a preset search table.

[0171] The comparison module is configured to re-enter the step of extracting a plurality of price fluctuation features based on abnormal data when the consistency ratio is greater than or equal to a preset value until the consistency ratio is less than the preset value.

[0172] The various modules in the power market risk management device based on fuzzy logic can be implemented by software, hardware, and combinations thereof, in whole or in part. The various modules can be embedded in or independent of a processor in a computer device in hardware form, or stored in a memory in a computer device in software form, so as to be called and executed by a processor to perform the operations corresponding to the various modules.

[0173] In an exemplary embodiment, a computer device, which can be a server, is provided, and an internal structure diagram of the computer device can be as shown in Figure 4 The computer device includes a processor, a memory, an input / output interface (I / O), and a communication interface. The processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is configured 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 running the operating system and the computer program in the non-volatile storage medium. The database of the computer device is configured to store a preset power market price risk management model, a preset power market price risk estimation model, and historical price data. The input / output interface of the computer device is configured to exchange information between the processor and external devices. The communication interface of the computer device is configured to communicate with external terminals through network connection. The computer program is executed by the processor to implement a power market risk management method based on fuzzy logic.

[0174] Those skilled in the art can understand that Figure 4 The structure shown in the above

[0175] In an exemplary embodiment, a computer device is provided, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the steps of any method of the power market risk management method based on fuzzy logic.

[0176] In an exemplary embodiment, a computer readable storage medium is provided, which stores a computer program. The computer program is executed by a processor to implement the steps of any method of the power market risk management method based on fuzzy logic.

[0177] In one embodiment, a computer program product is provided, comprising a computer program which, when executed by a processor, implements the steps of any of the above-mentioned fuzzy logic based power market risk management method.

[0178] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to a memory, database or other medium used in the embodiments provided in the present application can include at least one of a non-volatile memory and a volatile memory. The non-volatile memory can include a read-only memory (ROM), a magnetic tape, a floppy disk, a flash memory, an optical memory, a high-density embedded non-volatile memory, a resistive random access memory (ReRAM), a magnetoresistive random access memory (MRAM), a ferroelectric random access memory (FRAM), a phase change memory (PCM), a graphene memory, etc. The volatile memory can include a random access memory (RAM) or an external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as a static random access memory (SRAM) or a dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0179] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not contradict, they should be considered as falling within the scope of the present application.

[0180] The above-described embodiments are merely illustrative of several embodiments of the present application, which are described in more detail and in a specific manner, but should not be construed as limiting the scope of the patent of the present application. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A power market risk management method based on fuzzy logic, characterized in that, The method includes: Collect electricity price data from the electricity market; Based on the electricity price data and a pre-defined electricity market price risk management model, the normalized weights of the electricity price data and the preliminary risk assessment results are determined; wherein, the electricity market price risk management model is a model constructed based on the forest isolation method and the analytic hierarchy process. If the preliminary risk assessment indicates the existence of risk, a revised risk assessment result is determined based on the electricity price data and the normalized weights, and on a preset electricity market price risk estimation model; wherein, the electricity market price risk estimation model is the electricity market price risk management model based on a model optimized by a preset fuzzy algorithm; the preset fuzzy algorithm is a fuzzy algorithm optimized based on a cloud model; Identify the electricity pricing pattern based on the electricity price data; Based on the revised risk assessment results and the electricity pricing model, the electricity price risk assessment results under the electricity pricing model are determined.

2. The method according to claim 1, characterized in that, The step of determining the corrected risk assessment result based on the electricity price data and the normalized weights, and based on a preset electricity market price risk estimation model, includes: Based on the electricity price data and the normalized weights, and using the electricity market price risk estimation model, the predicted electricity price is determined. Based on the predicted electricity price and historical electricity prices, determine the predicted electricity price fluctuation range; Based on the predicted electricity price fluctuation range, the revised risk assessment result is determined, and the predicted electricity price fluctuation range is positively correlated with the level of risk of the revised risk assessment result.

3. The method according to claim 2, characterized in that, The step of determining the predicted electricity price based on the electricity price data and the normalized weights, and based on the electricity market price risk estimation model, includes: The electricity price data and fuzzy cluster centers are initialized; Based on the distance formula, the distance between each of the electricity price data and the fuzzy clustering center is determined; Update the membership matrix based on the distance; Determine the membership degree based on the membership degree matrix; The predicted electricity price is determined based on the membership degree, the fuzzy cluster center, the normalized weight, and the following formula: in, For the predicted electricity price, u ij Let c be the membership degree. j Let ω be the fuzzy cluster center. i The normalized weights are...

4. The method according to claim 3, characterized in that, After the step of updating the membership matrix based on the distance, and before the step of determining the membership degree based on the membership matrix, the method further includes: Obtain the change value of the membership matrix; If the change value is greater than or equal to a first preset value, the fuzzy cluster center and the number of iterations are updated, and the process proceeds to the step of "determining the distance between each of the electricity price data and the fuzzy cluster center based on the distance formula" until the change value is less than the first preset value.

5. The method according to claim 1, characterized in that, The step of determining the normalized weights and preliminary risk assessment results of the electricity price data based on the electricity price data and a preset electricity market price risk management model includes: Based on the electricity price data and the isolated forest, abnormal data was identified; Based on the aforementioned abnormal data, multiple price fluctuation features were extracted; Based on the weights of each price fluctuation feature and the analytic hierarchy process, the weighted result of the price fluctuation feature and the normalized weight are determined. The preliminary risk assessment result is determined based on the weights and the weighted result.

6. The method according to claim 5, characterized in that, After the step of determining the weighted result and the normalized weight based on the weights of each of the price fluctuation characteristics and the analytic hierarchy process, and before the step of determining the preliminary risk assessment result based on each of the weights and the weighted result, the method further includes: Establish a judgment matrix based on the indicator scoring method; Based on the judgment matrix, determine the largest eigenvalue of the judgment matrix; The consistency index is determined based on the largest eigenvalue and the order of the judgment matrix; The consistency ratio is determined based on the consistency index and the random consistency index; wherein the random consistency index is determined based on the order of the judgment matrix and the preset retrieval table. If the consistency ratio is greater than or equal to a preset value, the process re-enters the step of "extracting multiple price fluctuation features based on the abnormal data" until the consistency ratio is less than the preset value.

7. A power market risk management device based on fuzzy logic, characterized in that, The device includes: The data acquisition module is used to collect electricity price data from the electricity market. The first data determination module is used to determine the normalized weight and preliminary risk assessment results of the electricity price data based on the electricity price data and a preset electricity market price risk management model; wherein the electricity market price risk management model is a model constructed based on the forest isolation method and the analytic hierarchy process. The second data determination module is used to determine a revised risk assessment result based on the electricity price data and the normalized weight, and on a preset electricity market price risk estimation model, when the preliminary risk assessment result indicates the existence of risk; wherein the electricity market price risk estimation model is the electricity market price risk management model based on a model optimized by a preset fuzzy algorithm; the preset fuzzy algorithm is a fuzzy algorithm optimized based on a cloud model. The electricity price pattern recognition module is used to identify the electricity price pattern based on the electricity price data; The electricity price risk assessment module is used to determine the electricity price risk assessment result under the electricity price model based on the modified risk assessment result and the electricity price model.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images