Electricity market collusion behavior identification method and related device

Abstract

The invention belongs to a clustering recognition method, and aims to solve the technical problems that an existing electricity market collusion behavior recognition method is insufficient in collusion behavior feature reflection, lacks the capability of deeply mining complex index features, is insufficient in training samples and is insufficient in abnormal collusion sample recognition capability. The invention provides an electricity market collusion behavior identification method and a related device. Firstly, data corresponding to discrimination indexes of electricity market collusion behaviors are acquired; wherein the discrimination indexes comprise an electricity price index, an electric quantity index and a quantity-price relation index, the electricity price index comprises a declaration price fluctuation mean value, and the quantity-price relation index comprises quotation curve similarity. Inputting data corresponding to the discrimination indexes into a collusion recognition model to obtain a collusion behavior recognition result; the input of the collusion recognition model is interaction feature data between the two market subjects. Interaction modes among market subjects in different clusters can be analyzed without relying on collusion label data.

Description

Technical Field

[0001] This application belongs to a clustering recognition method, and specifically relates to a method and related device for identifying collusive behaviors in the electricity market. Background Art

[0002] The identification of collusive behaviors in the electricity market mainly includes two steps: constructing discriminant indicators and an identification model. Existing technologies have constructed discriminant indicators from different perspectives, but there are problems such as difficult acquisition and insufficient reflection of collusive behavior characteristics. The identification model mainly relies on subjective or subjective-objective combined evaluation methods, lacking the ability to deeply mine the characteristics of complex indicators. With the development of artificial intelligence technology, methods based on machine learning and deep learning have gradually been applied to the research of identifying collusive behaviors in the electricity market, but there are still problems such as lack of training samples, susceptibility to label noise, and insufficient ability to identify abnormal collusive samples. Summary of the Invention

[0003] Aiming at the technical problems existing in the existing methods for identifying collusive behaviors in the electricity market, such as insufficient reflection of collusive behavior characteristics, lack of the ability to deeply mine the characteristics of complex indicators, insufficient training samples, and insufficient ability to identify abnormal collusive samples when using artificial intelligence technology for identification, this application provides a method and related device for identifying collusive behaviors in the electricity market.

[0004] To achieve the above object, this application is implemented by adopting the following technical solutions: In the first aspect, this application proposes a method for identifying collusive behaviors in the electricity market, including: Obtaining data corresponding to the discriminant indicators of collusive behaviors in the electricity market; among them, the discriminant indicators include electricity price indicators, electricity quantity indicators, and electricity quantity-price relationship indicators, the electricity price indicators include the average value of the declared price fluctuation, and the electricity quantity-price relationship indicators include the similarity of the bid curves; According to the data corresponding to the discriminant indicators, calculating the interaction feature data between two market entities and inputting it into the collusion recognition model to obtain the collusion behavior recognition result; among them, the collusion recognition model is based on the point sequence search clustering structure recognition algorithm and adopts a method for identifying collusive behaviors in the electricity market based on the interaction and density clustering of two market entities.

[0005] In the second aspect, this application proposes a system for identifying collusive behaviors in the electricity market, including: A data module for obtaining data corresponding to the discriminant indicators of collusive behaviors in the electricity market; among them, the discriminant indicators include electricity price indicators, electricity quantity indicators, and electricity quantity-price relationship indicators, the electricity price indicators include the average value of the declared price fluctuation, and the electricity quantity-price relationship indicators include the similarity of the bid curves; An identification module, configured to calculate interaction feature data between two market entities based on discriminant index corresponding data, and input the data into a collusion identification model to obtain a collusion behavior identification result; wherein, the collusion identification model is based on a point sequence search clustering structure identification algorithm and adopts a method for identifying electricity market collusion behavior based on the interaction and density clustering of two market entities.

[0006] In a third aspect, the present application provides an electronic device, including: a memory and one or more processors; the memory is coupled to the processor; wherein, computer program code is stored in the memory, and the computer program code includes computer instructions. When the computer instructions are executed by the processor, the electronic device executes the steps of the above-mentioned method for identifying electricity market collusion behavior.

[0007] In a fourth aspect, the present application provides a computer-readable storage medium, in which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned method for identifying electricity market collusion behavior are implemented.

[0008] Compared with the prior art, the present application has the following beneficial effects: The present application provides a method for identifying electricity market collusion behavior, which obtains discriminant index corresponding data of electricity market collusion behavior. The electricity price index further includes the average value of the declared price fluctuation, and the quantity-price relationship index further includes the similarity of the bid curves. Then, the discriminant index corresponding data is input into the collusion identification model to obtain a collusion behavior identification result. The input of the collusion identification model is the interaction feature data between two market entities. The collusion identification model is based on a point sequence search clustering structure identification algorithm and adopts a method for identifying electricity market collusion behavior based on the interaction and density clustering of two market entities. The present application innovatively proposes two new indicators, namely the average value of the declared price fluctuation and the similarity of the bid curves. Considering that it is difficult to obtain collusion labels, the present application constructs a method for identifying electricity market collusion behavior based on the interaction and density clustering of two market entities. This method does not directly predict whether a single market entity has the suspicion of collusion, but starts from the perspective of mining the interaction behavior characteristics of electricity market entities. It can not only effectively identify collusion sample pairs, but also analyze the interaction patterns between market entities in different clusters. The identification method of the present application can accurately identify electricity market collusion behavior without relying on collusion label data, which is beneficial to ensuring the safe and stable operation of the electricity market.

[0009] The present application also provides an electricity market collusion behavior identification system, an electronic device and a computer-readable storage medium, which have all the advantages of the above-mentioned method for identifying electricity market collusion behavior. Description of the Drawings

[0010] To more clearly illustrate the technical solutions of the embodiments of the present application, the accompanying drawings required for the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present application and should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other relevant drawings can be obtained based on these drawings.

[0011] Figure 1 It is a schematic diagram of a method for identifying collusive behavior in the electricity market of the present application; Figure 2 It is a schematic diagram of the ratio of the area difference of the bid curves in the embodiments of the present application; Figure 3 It is a schematic diagram of the similarity of the bid curves in the embodiments of the present application; Figure 4 It is a schematic diagram of an example of constructing paired features in the embodiments of the present application; Figure 5 It is a schematic diagram of the core concept of the clustering algorithm in the embodiments of the present application; Figure 6 It is a distribution diagram of the declared electricity price and declared electricity quantity of all segments of the experimental data in the embodiments of the present application; Figure 7 It is a reachability distance graph obtained by using the clustering algorithm in the embodiments of the present application; Figure 8 In the embodiments of the present application It is a schematic diagram of the clustering result at this time; Figure 9 It is a schematic diagram of a system for identifying collusive behavior in the electricity market of the present application. Detailed implementation manners

[0012] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. Usually, the components of the embodiments of the present application described and illustrated in the drawings here can be arranged and designed in various different configurations.

[0013] Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application to be protected, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0014] It should be noted that similar reference numerals and letters refer to similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0015] The methods for identifying collusive behaviors in the electricity market mainly consist of two core steps: First, construct discriminant indicators for collusive behaviors in the electricity market to quantify relevant influencing factors; Second, based on the corresponding data of these discriminant indicators, construct an identification model for collusive behaviors to reveal potential collusive behaviors.

[0016] The existing technologies have constructed discriminant indicators from different perspectives. For example, select market power risk warning indicators based on the three dimensions of market structure, market behavior, and market performance. Or, construct an identification and evaluation index system for violation behaviors covering the entire process before, during, and after transactions. And construct monitoring indicators from the two major dimensions of the overall market situation and the behaviors of market players. The index systems constructed by such research are relatively systematic and comprehensive. However, these studies mainly start from the perspective of individual market player members and fail to fully reflect the interaction relationships among market players. Therefore, it is difficult to capture the characteristics of collusive behaviors. In addition, due to factors such as confidentiality, it is difficult to obtain relevant index data (such as marginal cost, economic profit, etc.), which limits the feasibility of such index systems in actual application scenarios. And the quotation data, as the core data for market players to participate in electricity transactions, has relatively convenient acquisition channels. By mining the relationship of quotation data among multiple market players, it is possible to reveal whether there are collusive behaviors during the bidding process. Therefore, based on parallel pricing behaviors, the existing technologies have proposed the declaration information similarity index or introduced the index of the ratio of the difference area of the quotation curves to extract the quotation connection between any two market players. Although certain progress has been made in the design of the index system based on quotation data, there are still certain deficiencies in reflecting the relationship of quotation data, such as failing to fully reflect the fluctuation relationship and the quantity-price relationship of quotations.

[0017] For the above-mentioned constructed discriminant index system, in the existing technologies, warning threshold values are set for each discriminant indicator through the expert evaluation method, and a comprehensive index is constructed in combination with the weighted linear model to warn of market power risks. There are also those who use the fuzzy comprehensive evaluation method to calculate the warning index scores of market players under different violation trading behaviors. There are also those who use the grey comprehensive evaluation method to conduct three-stage evaluations of the market power behaviors of electricity selling companies, namely pre-event prevention, in-event monitoring, and post-event analysis. The identification models established by the above-mentioned research mainly rely on subjective or subjective-objective combined evaluation methods for judgment, lacking in-depth mining of the characteristics of complex indicators, which will affect the objectivity and accuracy of identification.

[0018] With the continuous progress of artificial intelligence technology, compared with statistical methods, methods based on machine learning and deep learning have significant advantages in processing complex feature data and are gradually applied to the research on the identification of collusive behaviors in the electricity market. The identification of collusive behaviors essentially belongs to a binary classification problem. Some studies use supervised classification algorithms such as the Naive Bayes classifier, Isolation Forest, ensemble learning, and support vector machine to predict the probability of abnormal behaviors. However, due to the small number of sample data with collusive labels, it is difficult to obtain, and there may also be collusive behaviors that have not been identified by humans. Therefore, the method based on the supervised classification algorithm lacks training samples, resulting in poor training and identification effects. There is also a proposed identification model based on semi-supervised support vector machines. First, use the labeled samples to train the support vector machine model and label the unlabeled samples. Then, merge the labeled samples with the original samples and train again to optimize the model. There are also methods that use the K-means clustering algorithm (an unsupervised learning algorithm) to perform preliminary pseudo-label assignment on the unlabeled samples and further use the cost-sensitive transductive support vector machine for identification. Such semi-supervised methods are easily affected by label noise, resulting in deteriorated identification results. In addition, there is also an unsupervised variational autoencoder Gaussian mixture model proposed by combining the idea of anomaly detection, which can maximize the retention of the original data information but has insufficient ability to identify abnormal collusive samples. These methods are all difficult to reveal the interactive bidding behaviors among market participants.

[0019] Based on the above situation, the present application proposes a method and related device for identifying collusive behaviors in the electricity market. The following will make a detailed description of the present application in combination with embodiments and drawings.

[0020] As Figure 1 shown, it is a schematic flowchart of a method for identifying collusive behaviors in the electricity market of the present application, which may include: S101, obtain the corresponding data of the discriminant indicators for collusive behaviors in the electricity market; wherein, the discriminant indicators include electricity price indicators, electricity quantity indicators, and quantity-price relationship indicators. The electricity price indicators include the average value of the declared price fluctuations, and the quantity-price relationship indicators include the similarity of the bidding curves.

[0021] This application constructs a discriminant index system from three dimensions: electricity price, electricity quantity, and the relationship between quantity and price, covering the direct manifestations and potential correlations of market behaviors. Among them, the electricity price index includes indicators such as the average value of the declared price fluctuation, which is used to capture the abnormal stability or synergy of the market participants' quotations. The electricity quantity index can involve the deviation between the declared electricity quantity and the cleared electricity quantity, the concentration of electricity quantity allocation, etc., reflecting the abuse of market power or the manipulation of supply and demand. The quantity-price relationship index can measure the consistency of the quotation strategies of different market participants through the similarity of the quotation curves, revealing potential coordination behaviors. The acquisition of the data corresponding to these discriminant indicators can be obtained through market declaration data (such as quotation curves, declared electricity quantities), transaction clearing results, historical transaction records, etc. In practical applications, the data corresponding to the obtained discriminant indicators can also be preprocessed, for example, standardized processing, missing value filling, outlier detection, etc.

[0022] S102. According to the data corresponding to the discriminant indicators, calculate the interaction feature data between two market participants and input it into the collusion identification model to obtain the collusion behavior identification result. Among them, the collusion identification model is based on the point-order search clustering structure recognition algorithm and adopts a method for identifying electricity market collusion behaviors based on the interaction and density clustering of two market participants.

[0023] It should be noted that the interaction feature data between two market participants can include the quotation synchronization coefficient, strategy response delay, joint market power index, etc. Input the interaction feature data into the collusion identification model and use a method for identifying electricity market collusion behaviors based on the interaction and density clustering of two market participants for identification. Among them, the principle of the method for identifying electricity market collusion behaviors based on the interaction and density clustering of two market participants is that in the high-dimensional feature space, a candidate clustering center sequence is generated through local density search. Points with a density higher than the neighborhood threshold can be preferentially selected as the initial centers to avoid the sensitivity of random initialization. Then, based on the density reachability of the core points, the clustering is extended to automatically discover clusters of arbitrary shapes. The output decision of the collusion identification model can be to output the confidence level of the collusion behavior (usually between 0 and 1) based on density clustering and pattern matching degree. The threshold setting can combine the regulatory tolerance and Bayesian decision theory to determine the optimal classification threshold.

[0024] The following further details the method for identifying electricity market collusion behaviors of this application through some specific embodiments: 1. Regarding the improved collusion behavior discriminant index system.

[0025] Collusive behavior in the electricity market refers to the illegal act of two or more market entity members colluding on quotes and other means to raise prices, thereby maximizing the interests of the colluding market entities. When the electricity market shows a supply surplus, the colluding market entity members often obtain profits through parallel quotes. In the stage of relatively balanced supply and demand, the colluding market entity members create artificial local supply and demand tensions through abnormal or extreme quotes, inducing abnormal fluctuations in the market clearing price. This strategic quoting behavior is mainly reflected in the bidding data, so it is necessary to design a discriminant index system to reflect the interactive quoting behavior.

[0026] In the existing technology, the designed discriminant index system for collusive behavior usually has two strongly correlated indicators, namely the average value of the declared price safety degree and the average value of the relative ratio of the declared price, which may lead to a high dependence of the recognition model on such features and affect the accuracy of the recognition method. Based on the three-stage quoting method, this application constructs a discriminant index system for collusion around the quoting and volume data, optimizes the relative ratio of quotes index on the basis of the existing index system, and adds two new indicators: the average value of the declared price fluctuation and the similarity of the quoting curves.

[0027] As shown in Table 1, taking two market entities as the recognition objects, the constructed discriminant index system covers three dimensions: electricity price, electricity volume, and the relationship between volume and price.

[0028] Table 1 Discriminant Index System for Collusive Behavior

[0029] In some embodiments of this application, the meanings and calculation methods of each discriminant index are as follows: Set to represent the declared price, to represent the declared electricity volume, to represent the quoting stage, to represent the number of market entities.

[0030] (1) Declaration price consistency.

[0031] The declaration price consistency index measures the degree of correlation between the quotes of two market entities. The lower the corresponding data value of this index, the more consistent the quotes of the two market entities are, and the closer the adjustment range in each quoting stage is. Market entity and market entity The declaration price consistency The calculation formula is: .

[0032] Among them, is the price declared by market entity in the th stage of quoting, For market entities in the price declared in the in the average of the prices declared by all market entities in the

[0033] In the average of the prices declared by all market entities in the The calculation method is as follows: .

[0034] Among them, is the price declared by market entity in the

[0035] (2) Average of declared price fluctuations.

[0036] In market collusion behavior, there may be a performance of first reporting a low price to ensure market share and then reporting a high price to obtain higher profits. In response to this behavior, this application innovatively proposes an average index of declared price fluctuations to reflect the fluctuation situation between each market entity and market entity. The average of declared price fluctuations between market entity .

[0037] Among them, is the weighted average price of market entity , is the weighted average price of market entity , and the weight is the declared electricity quantity. The weighted average price of market entity is calculated as follows: .

[0038] Among them, is the electricity quantity declared by market entity in the

[0039] (3) Average of declared price safety levels.

[0040] The average of declared price safety levels is used to evaluate the deviation degree between the average quotes of two market entities and the historical marginal price. The higher the corresponding data value of this discrimination index, the greater the possibility that these two market entities jointly report higher prices. The average of declared price safety levels The calculation formula is: .

[0041] Among them, represents the expected value of the historical market marginal price.

[0042] (4) Comparison of declared prices.

[0043] The comparison of declared prices is used to measure the relative level of price declarations between two enterprises. The closer the average quotes of the two market players are, the closer the corresponding data of the comparison of declared prices is to 1, indicating that there may be a collusive behavior of jointly pushing up prices. Market player and market player 's comparison of declared prices The calculation formula is: .

[0044] (5) Consistency of declared electricity quantities.

[0045] The consistency of declared electricity quantities is a measure of the correlation of declared electricity quantities between two market players. The lower the value of this indicator, the closer the declared electricity quantities of the two market players are, and the more consistent the changes in their differences from the market average quote are. Market player and market player 's consistency of declared electricity quantities The calculation formula is: .

[0046] Among them, is the electricity quantity declared by market player in the th segment of quotes, is the electricity quantity declared by market player in the th segment of quotes, is the average value of the electricity quantities declared by all market players in the th segment of quotes.

[0047] The average value of the electricity quantities declared by all market players in the th segment of quotes is calculated as: .

[0048] Among them, is the electricity quantity declared by market player in the th segment of quotes.

[0049] (6) Ratio of the area difference of the quote curves.

[0050] The ratio of the difference area of the quotation curves refers to the ratio of the difference area formed by the quotation curves of two market entities on the three-stage quotation curve. As Figure 2 shown, it is a schematic diagram of the ratio of the difference area of the quotation curves. This indicator can reveal the differences in the shape and distribution of the quotation curves. The lower the ratio of the difference area of the quotation curves, the more similar the quantity-price relationship of the quotations of the two market entities, thus suggesting a greater possibility of collusion between them. Market entity and market entity The ratio of the difference area of the quotation curves is calculated as follows: .

[0051] Among them, is the quotation curve function of market entity , is the quotation curve function of market entity , is the minimum total power generation of market entity and market entity , is calculated as follows: .

[0052] (7) Similarity of quotation curves.

[0053] The calculation boundary of the ratio of the difference area of the quotation curves is set as the minimum power generation, which cannot fully reveal the differences in the quantity-price relationship of the third segment. Considering that the quotation curve is a curve composed of three pairs of declared quantities and declared prices , among which, is the declared quantity, is the declared price. This application innovatively introduces a discrimination index for the similarity of quotation curves. As Figure 3 shown, it is a schematic diagram of the similarity of quotation curves. By calculating the Euclidean distance between points on the quotation curve, the position differences of points on the quotation curve can be quantified. The similarity of the quotation curves of market entity and market entity is calculated as follows: .

[0054] Among them, is the electricity quantity declared by market entity in the th segment of the quotation, is the electricity quantity declared by market entity in the th segment of the quotation.

[0055] 2. Collusion Identification Algorithm (Collusion Identification Model) Based on Point-Order Search Clustering Structure Identification Algorithm

[0056] (1) Feature Construction Method

[0057] Collusive behavior in the electricity market usually involves complex interactions between two or more market players. If only the characteristics of a single market player are focused on, it will be difficult to comprehensively reveal the intricate interaction relationships between market players. Therefore, this application takes the interaction feature data between two market players as the input of the collusion identification algorithm, aiming to more accurately capture and analyze the behavior patterns between market players. Specifically, assuming there are market players, the corresponding eigenvalue is calculated according to the seven key interaction indicators in the collusion discrimination index system constructed in this application. By calculating the corresponding data values of the discrimination indicators between every two market players, samples can be generated. Each sample depicts the interaction characteristics between a pair of market players, thus being able to more accurately reflect the behavior relationship and potential collusive behavior characteristics between market players. As Figure 4 shown, it is a schematic diagram of the construction example of paired interaction features

[0058] (2) Principle of Point-Order Search Clustering Structure Identification Algorithm Clustering algorithms belong to unsupervised machine learning algorithms, mainly divided into partition clustering, hierarchical clustering, density clustering, etc. In the identification of collusive behavior in the electricity market, using the point-order search clustering structure identification algorithm has advantages compared with other clustering methods. First, the characteristics of collusive behavior in the electricity market are complex and changeable, and the clusters formed in the feature space often show irregular shapes. The density-based clustering method can break through the limitations of traditional partition clustering algorithms. By deeply analyzing the density connectivity of data points, it can accurately identify clusters of any shape, thus more effectively capturing the potential patterns and feature associations of collusive behavior. Second, the collusive behavior in the electricity market is essentially an abnormal behavior, and the density-based clustering method has a strong ability to identify outliers. It can accurately identify outliers as low-density regions and exclude them from normal clusters, thus ensuring the reliability of the clustering results. In addition, other clustering methods may have problems such as low computational efficiency and insufficient result stability when processing data. In contrast, the density-based clustering method is relatively better in terms of computational efficiency and is not affected by the order of data input, and can provide more stable and reliable clustering results. This application uses an algorithm based on the interaction and density clustering of two market players, which is improved on the basis of the traditional density clustering algorithm, reducing the influence of the selection of input parameters on the clustering results.

[0059] Let the sample set be , and each sample contains the seven discrimination index features in the collusion discrimination index system: 。

[0060] Among them, is the th sample, to are the first to seventh discriminant index features in the th sample discriminant index system.

[0061] Given the neighborhood radius and the minimum number of clustering data points , the samples in the sample set are sorted in an orderly manner so that similar samples are adjacent in the orderly arrangement. According to the orderly arrangement, a decision graph can be generated, and then the clustering results based on any neighborhood radius can be obtained from the decision graph.

[0062] The above algorithm involves three core concepts, as Figure 5 shown, which is a schematic diagram of the above core concepts: 1) Core object: For a certain sample , if the circle within the neighborhood radius of contains at least samples, then this sample is defined as a core object. The mathematical expression of the core object is: .

[0063] Among them, is the number of samples contained in the circle within the neighborhood radius of sample with as the neighborhood radius.

[0064] 2) Core distance: It is the minimum neighborhood radius required for sample to become a core object. Let be the th nearest neighbor node within the neighborhood radius of sample , and the mathematical formula for the core distance is expressed as: .

[0065] Among them, is the core distance of sample , is undefined, is otherwise, represents and the Euclidean distance between them.

[0066] 3) Reachability distance: It represents the distance from sample to sample The distance reflects the clustering situation of the samples. The mathematical formula for the reachability distance is expressed as: .

[0067] Among them, is and 's reachability distance, is 's core distance, is and the Euclidean distance between them.

[0068] It should be noted that Figure 5 in which rd represents the reachability distance, co represents the core object, and cd represents the core distance.

[0069] Based on the above three core concepts, the core steps are as follows: 1) Initialization.

[0070] Initialize three empty queues: the core object queue , the queue of unprocessed neighbor points and the ordered queue (i.e., the final output queue) .

[0071] 2) Identify core objects.

[0072] Traverse all samples in the sample set. For each sample, calculate the number of samples within its neighborhood radius . Mark all core objects that meet the requirements as unprocessed and put them into the core object queue , and calculate the core distance.

[0073] 3) Process core objects.

[0074] Check whether the core object queue is empty. If it is empty, the algorithm ends. Otherwise, take an unprocessed core object from and put it into the ordered queue , and mark it as processed. Calculate the reachability distances between all unprocessed samples within the neighborhood of the core object and the core object, and put them into the queue of unprocessed neighbor points in ascending order of the reachability distance.

[0075] 4) Process neighbor points.

[0076] Take an unprocessed sample with the smallest reachability distance from the queue of unprocessed neighbor points , and put into the ordered queue and mark it as processed. If is the core object, then neighborhood Add all unprocessed samples in the to the queue of unprocessed neighbor points and calculate the reachability distance of each sample in the queue of unprocessed neighbor points compared to If there is a smaller reachability distance, update it. Repeat step 4) until the queue of unprocessed neighbor points

[0077] 3. Collusion behavior identification.

[0078] Based on the improved collusion discrimination index system of this application and the above algorithm, this application constructs a method for identifying electricity market collusion behavior based on the interaction and density clustering of two home field entities, and the specific steps are as follows: (1) Set the input data as the three-section bid volume and price quotation datasets of market entities, where , , is the first-section price quotation of market entity , is the first-section bid volume of market entity , is the second-section price quotation of market entity , is the second-section bid volume of market entity , is the third-section price quotation of market entity , is the third-section bid volume of market entity .

[0079] (2) Calculate the interaction feature data between any two market entities to obtain the sample set , where the number of samples .

[0080] (3) Normalize the interaction feature data to convert it into a standard normal distribution with zero mean and unit variance. The Z-score normalization method is used, that is, normalization is achieved by subtracting the mean of each interaction feature data and dividing it by its standard deviation.

[0081] (4) Analyze the normal distribution of the interaction feature data, including its central tendency, dispersion degree, and skewness.

[0082] (5) Given , , a clustering algorithm using a clustering algorithm based on a point-order search clustering structure identification algorithm is used to cluster the sample set to generate a reachable distance graph.

[0083] (6) According to the reachable distance graph, select a suitable , and analyze the clustering results. The intra-cluster members pairs identified as abnormal classes are determined to be suspected of collusion, and the involved market entity members pairs are exported to form a list of suspected collusion.

[0084] (7) Start the collusion behavior identification program to monitor each pair of members in the list of suspected collusion. The monitoring content includes: detecting whether two market entities without an actual control relationship have the same trading declaration MAC (Media Access Control) address and IP (Internet Protocol) address; detecting whether two market entities without an actual control relationship declare using the same trading account; detecting whether there is data interaction on the information-based trading platforms of two market entities without an actual control relationship, etc. According to the further monitoring results, execute the corresponding market control procedures.

[0085] To verify the effectiveness of the method proposed in this application, the data in a monthly centralized bidding transaction data table of a certain province is used as experimental data, which includes three-section quotation data of 25 electricity selling companies (market entities) in total. Some of the original data are shown in Table 2. Among them, the collusion possibilities of the 1st and 10th electricity selling companies, and the 2nd, 3rd and 5th electricity selling companies are the highest, regarded as collusion pairs and are abnormal samples. It should be noted that in Table 2, the "id" column represents the serial number of the market entity.

[0086] Table 2 Partial transaction data table

[0087] As Figure 6 shown, it is the distribution diagram of the declared price and declared volume of all segments of the experimental data. It can be seen that the declared price is mainly distributed around 400 yuan / (MW·h) -1 nearby, while the declared volume is concentrated around 5000 MW. There are individual declared prices lower than 390 yuan / (MW·h) -1 , and individual declared volumes are higher than 150000 MW.

[0088] Based on the improved collusion discrimination index system, the characteristics of the collusion behavior discrimination indexes of 300 samples were calculated. The characteristics of the collusion behavior discrimination indexes of some samples are shown in Table 3. Among them, the first four samples belong to the collusion sample pairs. By comparing and analyzing each discrimination index, it can be found that the values of the first four samples on discrimination index 1 (declaration price consistency) and index 4 (relative quotation ratio) are significantly lower than those of other samples, indicating that the collusion sample pairs have different discrimination index characteristics from normal samples and may have a significant distance from normal samples in the sample space. Therefore, through the method of this application, these collusion sample pairs can be accurately identified as outliers, thus effectively distinguishing them from normal samples. It should be noted that in Table 3, index 1 is the declaration price consistency, index 2 is the average value of the declaration price fluctuation, index 3 is the average value of the declaration price safety degree, index 4 is the relative ratio of the declaration price, index 5 is the consistency of the declared electricity quantity, index 6 is the ratio of the difference area of the quotation curves, and index 7 is the similarity of the quotation curves.

[0089] Table 3 Characteristics of Some Discrimination Samples

[0090] The reachability distance graph obtained by using the point-order search clustering structure recognition algorithm is as Figure 7 shown, and the reachability distance of each sample is recorded in the reachability distance graph.

[0091] The silhouette coefficient and the DB (Davies-Bouldin) index are used to evaluate the point-order search clustering structure recognition algorithm of this application. Among them, the silhouette coefficient is used to quantify the closeness of a sample to other samples within the same cluster and the separation from the nearest neighbor cluster. Its value range is [-1, 1]. The larger the value, the better the clustering effect, with the samples within the cluster being close and the clusters being clearly separated. The DB index measures the clustering quality by calculating the ratio of the within-cluster compactness to the between-cluster separation. The smaller the value of this index, the more ideal the clustering result, with the data points within the cluster being closely aggregated and the between-cluster differentiation being high.

[0092] To verify the rationality of the selection, the clustering performance under different settings was tested. As shown in Table 4, as increases, the silhouette coefficient gradually increases, while the DB index generally shows a trend of first decreasing and then increasing. Therefore, combining the peak-valley changes of the reachability graph and the performance of the evaluation indexes, this application selects as the parameter input for the final clustering.

[0093] Table 4 Performance of the Clustering Algorithm under Different Settings

[0094] For the convenience of visualization, the present application can also use the principal component analysis dimensionality reduction method to perform dimensionality reduction processing on the samples. As Figure 8 shown, it shows the clustering results at that time. In the figure, cluster - 1 (purple points) represents outliers, and clusters 0 (blue), 1 (green), and 2 (yellow points) represent normal clusters.

[0095] The number of samples contained in each cluster and the average volume - price similarity within the cluster are shown in Table 5. Through analysis, it can be obtained that in cluster - 1 where the outliers are located, the quotation similarity of paired market - entity members is at the lowest level, and for cluster 0 containing the majority of samples, its similarity is the second. This shows that although different market entities may show a certain degree of similarity in their quotations due to key factors such as costs that affect volume and price, such similarity is not sufficient to classify them as abnormal clusters. The similarity value of cluster 1 is relatively large, indicating that there are obvious differences in the quotation behaviors of paired entity members within the cluster. The volume - quotation similarity value of cluster 2 is relatively large, indicating that there are relatively large differences in the volume quotations of paired entity members within the cluster. Further analysis shows that the collusive sample pairs (1,10), (2,5), (3,5) are correctly assigned to cluster - 1, and the collusive sample pair (2,3) is mis - assigned to cluster 0. Although there are 4 non - collusive samples in cluster - 1, this mis - clustering phenomenon can be corrected through subsequent monitoring procedures.

[0096] The above experimental analysis shows that the present application can identify most of the collusive samples. At the same time, through the method proposed in the present application, it is possible to deeply explore the interaction behavior characteristics between market entities for different pairs of market entities within different clusters, so as to discover potential illegal interaction and trading behaviors among power - market members.

[0097] Table 5 Sample situation within each cluster

[0098] To verify the effectiveness of the method proposed in the present application, the performance of multiple clustering methods was compared, including the KMeans method (K - means method) based on partition clustering, the method based on first PCA (Principal Component Analysis, principal component analysis) dimensionality reduction and then KMeans clustering, and the method based on first PCA dimensionality reduction and then conventional clustering. The silhouette coefficient and the DB index were used to evaluate different methods, and the results are shown in Table 6. Since the KMeans clustering method requires the number of clusters to be specified manually, for consistency, the number of clusters was set to 4. In addition, since the reach - distance graph changes after PCA dimensionality reduction, the . The experimental results show that the method adopted in this application has a higher silhouette coefficient and a lower DB index compared with other methods, that is, the data points within the clusters are closer and the separation degree of data points between clusters is larger, and the clustering effect is the best.

[0099] Table 6 Comparison of clustering effects of different methods

[0100] Compared with the supervised algorithms mentioned in the prior art, the method proposed in this application does not need to rely on labeled data and can directly mine potential interaction patterns and features from the unlabeled market entity quotation data. This method does not rely on a clear objective function to guide the learning process, thus having stronger flexibility and adaptability. It enables it to closely combine with the operating characteristics of the power market and has the potential to identify collusive patterns that have not been clearly defined.

[0101] The clustering method based on the characteristics of independent entities mainly focuses on clustering analysis of the quotation characteristics of a single entity. However, in the power market, different enterprises often generate similar quotations due to cost similarity, which easily leads to misclassifying a single entity participating in collusion as a normal sample, thus reducing the accuracy of collusive behavior identification. In contrast, the clustering method based on the interaction characteristics of entities starts from the perspective of the interaction behavior characteristics between entities and conducts clustering analysis on the interaction behavior of entity pairs. This method can capture the potential associations and abnormal interaction patterns between entities more comprehensively and deeply, thus more effectively realizing the accurate identification of collusive behaviors.

[0102] Aiming at the problems that the existing methods do not fully explore the characteristics of the quotation data of market entity interactions and the scarcity of collusive samples in the power market, this application improves the existing discriminant index system for power market collusive behaviors, and introduces three new key indicators around the quotation data, namely, the quotation ratio, the average value of the volatility of the declared price, and the similarity of the quotation curves. Based on the constructed discriminant index system, this application constructs a new collusive behavior identification model. This model can effectively identify abnormal collusive behavior clusters by dividing regions with different densities in the sample space into different clusters. The resulting list of suspected collusion can be provided to power market monitoring personnel for the next step of program identification, which helps to prevent and resolve market collusion risks.

[0103] As Figure 9 shown, it is a schematic diagram of a power market collusive behavior identification system, which may include: A data module for obtaining the data corresponding to the discriminant indicators of power market collusive behaviors; among them, the discriminant indicators include electricity price indicators, electricity quantity indicators, and electricity quantity-price relationship indicators, the electricity price indicators include the average value of the volatility of the declared price, and the electricity quantity-price relationship indicators include the similarity of the quotation curves; An identification module is configured to calculate interaction feature data between two market entities based on discriminant index corresponding data and input the data into a collusion identification model to obtain a collusion behavior identification result. The collusion identification model is based on a point order search clustering structure identification algorithm and adopts a method for identifying electricity market collusion behavior based on the interaction and density clustering of two market entities.

[0104] It should be noted that in several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For example, the division of each module is only a logical function division. In actual implementation, there may be other division methods. For example, multiple modules can be combined or integrated into another device, or some features can be ignored or not executed. The modules described as separate components may or may not be physically separated. The components shown as modules can be a physical unit or multiple physical units, that is, they can be located in one place or distributed to multiple different places. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] In addition, in each embodiment of the present invention, each module can be integrated in a processing unit, or each module can exist physically alone, or two or more modules can be integrated in a unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0106] This application embodiment also provides an electronic device, which may include one or more processors, a memory, and a communication interface.

[0107] Among them, the memory and the communication interface are coupled to the processor. For example, the memory and the communication interface can be coupled together through a bus.

[0108] Among them, the communication interface is used for data transmission with other devices. The memory stores computer program code. The computer program code includes computer instructions. When the computer instructions are executed by the processor, the electronic device executes the steps of the above method for identifying electricity market collusion behavior.

[0109] Among them, the processor can be a processor or a controller. For example, it can be a Central Processing Unit (CPU), a general-purpose processor, a Digital Signal Processor (DSP), an Application-Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It can implement or execute various exemplary logical blocks, modules, and circuits described in conjunction with the present disclosure. The processor can also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and so on. The processor can be used to support the electronic device in executing the method steps provided in the above embodiments.

[0110] Among them, the bus can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The above buses can be divided into an address bus, a data bus, a control bus, etc.

[0111] A computer-readable storage medium provided by an embodiment of the present application stores a computer program, and when the computer program is executed by a processor, it implements the steps of the above method for identifying collusive behavior in the electricity market.

[0112] The computer-readable storage medium involved in the present application includes a Random Access Memory (RAM), a memory, a Read-Only Memory (ROM), an Electrically Programmable ROM, an Electrically Erasable Programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium well-known in the technical field.

[0113] The above are only the preferred embodiments of the present application and are not used to limit the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the protection scope of the present application.

Claims

1. A method for identifying collusion in the electricity market, characterized in that: include: Obtaining data corresponding to the discrimination index of collusion in the electricity market; wherein the discrimination index includes an electricity price index, an electricity quantity index and a quantity-price relationship index, wherein the electricity price index includes a declared price fluctuation mean, and the quantity-price relationship index includes a quotation curve similarity; According to the corresponding data of the discrimination index, the interaction feature data between the two market players is calculated and input into the collusion identification model to obtain the collusion behavior identification result; among them, the collusion identification model is based on the point sequence search clustering structure recognition algorithm, and adopts the electricity market collusion behavior identification method based on the interaction and density clustering of two market players.

2. A method for identifying collusion in the power market according to claim 1, characterized in that: The electricity price index also includes the consistency of the declared price, the average value of the safety of the declared price and the relative comparison of the declared price; The electricity quantity index includes the consistency of reported electricity quantity; The quantity-price relationship indicator also includes the quotation curve difference area ratio.

3. A method for identifying collusion in the power market according to claim 2, characterized in that: The calculation formula for the consistency of the declared price is: in, For market players and market players Consistency of declared prices, For the The average price quoted by all market players in the quotation segment. For market players In the The price declared in the segment quotation, For market players In the The price declared in the segment quotation; The calculation formula for the average safety degree of the declared price is: in, For market players and market players The average safety of the declared price, is the expected value of the historical market marginal price, For market players The weighted average price of For market players The weighted average price of The calculation formula for the relative ratio of the declared price is: in, For market players and market players Compared with the declared price; The calculation formula for the reported power consistency includes: in, For market players and market players The consistency of reported power consumption, For the The average amount of electricity reported by all market players in the quotation segment. For market players In the The electricity quantity reported in the segment quotation, For market players In the The electricity quantity declared in the quotation for the segment.

4. A method for identifying collusion in the power market according to claim 2, characterized in that: The calculation formula of the quotation curve difference area ratio includes: in, For market players and market players The ratio of the difference area of ​​the quotation curve, For market players and market players The minimum total power generation capacity, For market players The quotation curve function, For market players The quotation curve function, For power generation.

5. A method for identifying collusion in the power market according to claim 1, characterized in that: The calculation formula for the average price fluctuation of the declared price is: in, For market players and market players The average price fluctuation of the declared price, For market players In the The price declared in the segment quotation, For market players The weighted average price of For market players In the The price declared in the segment quotation, For market players The weighted average price quote.

6. A method for identifying collusion in the power market according to claim 1, characterized in that: The calculation formula of the quotation curve similarity is: in, For market players and market players The similarity of the quotation curves, For market players In the The electricity quantity reported in the segment quotation, For market players In the The electricity quantity declared in the quotation for the segment.

7. A method for identifying collusion in the power market according to claim 1, characterized in that: The method for identifying collusion in the electricity market based on interaction between two market players and density clustering includes: Normalize the interaction feature data between two market players and convert them into standard normal distribution with zero mean and unit variance. Analyze the standard normal distribution of the interaction characteristic data between two market players one by one to obtain the normal distribution analysis results; Combined with the results of normal distribution analysis, given the core object neighborhood in the point-order search clustering structure recognition algorithm and the number of samples contained in the circle within the neighborhood radius, the sample set including the interaction feature data between multiple two market entities is clustered based on the point-order search clustering structure recognition algorithm to generate a reachable distance graph; According to the reachable distance graph, the core object neighborhood is selected, and the clustering results are analyzed to obtain the recognition results.

8. A system for identifying collusion in the electricity market, characterized in that: include: A data module, used to obtain data corresponding to the discrimination index of collusion in the power market; wherein the discrimination index includes an electricity price index, an electricity quantity index and a quantity-price relationship index, wherein the electricity price index includes a declared price fluctuation mean, and the quantity-price relationship index includes a quotation curve similarity; The identification module is used to calculate the interaction feature data between two market players according to the corresponding data of the discrimination index, and input it into the collusion identification model to obtain the collusion behavior identification result; wherein, the collusion identification model is based on the point sequence search clustering structure recognition algorithm, and adopts the electricity market collusion behavior identification method based on the interaction and density clustering of two market players.

9. An electronic device, characterized in that: include: A memory and one or more processors; the memory is coupled to the processor; wherein the memory stores computer program code, the computer program code includes computer instructions, and when the computer instructions are executed by the processor, the electronic device executes the steps of the method for identifying collusion in the electricity market as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method for identifying collusion in the electricity market as described in any one of claims 1 to 7.

Images