Electric power spot market risk prevention and control method and system considering market subject behaviors

Abstract

The invention relates to the technical field of electric power systems, in particular to an electric power spot market risk prevention and control method and system considering market subject behaviors. Acquiring operation data of generating capacity, electricity demand, market price and power grid state of the electric power spot market; on the basis of the acquired operation data, a coupling degree evaluation index and a stability evaluation index are introduced to carry out prediction and anomaly detection on a market trend, and influence factors of connection of a large-scale generator set and a small-scale power grid are particularly concerned; analyzing a market subject behavior pattern through transaction frequency, price volatility and market participation degree characteristic quantitative indexes, and identifying market manipulation and violation operation risks; market dynamics are monitored in real time, a risk threshold value is set, and an alarm is triggered when a risk index exceeds a set standard; early warning information of different levels is automatically sent out according to the risk degree, and corresponding countermeasures and suggestions are provided; and a supervision mechanism is helped to make a quick response through a visual interface.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems, and in particular to a method and system for preventing and controlling risks in a power spot market taking into account the behaviors of market entities. Background Art

[0002] With the deepening of the market-oriented reform of the power industry, the power spot market has become an important platform for resource allocation. The market is highly complex and dynamic, and the behavior patterns of market players (such as power generation companies and large electricity users) have an important impact on the stability and fairness of the market. In this context, how to effectively identify and prevent market operation risks has become a key issue that needs to be solved urgently.

[0003] At present, traditional risk prevention and control methods mainly rely on manual monitoring and simple data analysis, which has problems such as low efficiency and slow response. Especially in the special situation of large-scale power generation units connected to relatively small-scale power grids (i.e. "large generators and small grids"), existing risk identification methods are often unable to timely discover and respond to potential market risks. At the same time, due to the lack of in-depth analysis and prediction capabilities of market subject behavior patterns, risk prevention and control measures are not targeted and effective enough.

[0004] In addition, the existing market supervision system generally has problems such as incomplete data collection, single analysis methods, and lagging early warning mechanisms. When dealing with complex market subject behavior data, traditional systems have difficulty in achieving multi-dimensional real-time monitoring and intelligent early warning, and cannot meet the high requirements of the modern electricity spot market for risk prevention and control. Especially when market prices fluctuate violently and trading behaviors are abnormally frequent, the existing system is difficult to quickly make accurate judgments and respond in a timely manner, which seriously affects the safe and stable operation of the market. Summary of the invention

[0005] In view of the problems existing in the prior art, the present invention is proposed.

[0006] Therefore, the problem to be solved by the present invention is how to solve the problems commonly existing in the existing market supervision system, such as incomplete data collection, single analysis method, and lagging early warning mechanism.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, an embodiment of the present invention provides a method for risk prevention and control in a power spot market taking into account the behavior of market entities, which includes obtaining operational data of power generation, power demand, market price, and power grid status in a power spot market;

[0009] Based on the acquired operational data, forecast market trends and detect anomalies, with a particular focus on factors affecting the connection of large-scale power generating units to small-scale power grids;

[0010] Analyze the behavior patterns of market entities and identify risk behaviors that may involve market manipulation and illegal operations;

[0011] Monitor market dynamics in real time, set risk thresholds, and trigger an alarm when the monitored risk indicators exceed the set standards;

[0012] Automatically send early warning messages at different levels according to the risk level and propose corresponding countermeasure suggestions;

[0013] Help regulatory agencies make quick responses through a visual interface and optimize the efficiency of market supervision.

[0014] As a preferred embodiment of the power spot market risk prevention and control method considering the behavior of market entities according to the present invention, when predicting market trends and detecting anomalies, by introducing a coupling degree evaluation index and a stability evaluation index to enhance the adaptability to the characteristics of "large generators and small grids", wherein: the coupling degree evaluation index is used to measure the correlation strength between the generator set and the grid state;

[0015] The stability evaluation index includes volatility and maximum drawdown, which are used to quantify the degree of fluctuation of market prices or power generation.

[0016] As a preferred embodiment of the power spot market risk prevention and control method considering the behavior of market entities according to the present invention, when analyzing the behavior patterns of market entities, it is quantified through the following behavioral characteristics: trading frequency, which represents the number of transactions completed by market entities within a specific time window; price volatility, which measures the standard deviation of market prices; market participation, which represents the proportion of the trading volume of market entities within a specific time period to the total trading volume; abnormal trading behavior index, which is used to mark whether abnormal trading behavior is detected.

[0017] As a preferred embodiment of the power spot market risk prevention and control method considering the behavior of market entities according to the present invention, the calculated risk indicators of the monitoring adopt weight coefficients and satisfy: the weight coefficients include power generation weight coefficient, electricity demand weight coefficient, market price weight coefficient, and grid state weight coefficient; the sum of all weight coefficients is equal to 1, and each coefficient can be dynamically adjusted according to the actual situation.

[0018] As a preferred embodiment of the power spot market risk prevention and control method considering the behavior of market entities according to the present invention, the automatically sending early warning signals at different levels according to the risk level includes: when the risk level is greater than 100%, triggering a first-level early warning; when the risk level is between 80% and 100%, triggering a second-level early warning; when the risk level is between 50% and 80%, triggering a third-level early warning.

[0019] As a preferred solution of the power spot market risk prevention and control method considering the behavior of market entities in the present invention, wherein: the provided visual interface supports multi-dimensional data analysis, including: a geographical distribution map showing the spatial distribution of market entities; a time series chart demonstrating the changing trends of various indicators; and a correlation matrix diagram analyzing the mutual influences among different market elements.

[0020] As a preferred solution of the power spot market risk prevention and control method considering the behavior of market entities in the present invention, wherein: the following steps are further included: automatically executing preset security policies to suspend the trading permissions of specific market entities and restrict certain types of transactions;

[0021] Taking emergency measures in extreme cases to prevent the further spread of risks; and real-time updating and optimizing the warning thresholds to improve the accuracy of warnings.

[0022] In a second aspect, an embodiment of the present invention provides a power spot market risk prevention and control system considering the behavior of market entities, which includes a data acquisition module that acquires operation data of power generation, electricity demand, market price, and grid status in the power spot market;

[0023] A trend prediction module that predicts market trends and detects anomalies based on the acquired operation data, with particular attention to the influencing factors of large-scale generating units connected to small-scale power grids;

[0024] An identification module that analyzes the behavior patterns of market entities and identifies risk behaviors that may involve market manipulation and illegal operations;

[0025] A monitoring module that monitors market dynamics in real time, sets risk thresholds, and triggers an alarm when the monitored risk indicators exceed the set standards;

[0026] A prediction module that automatically issues warning messages at different levels according to the risk levels and proposes corresponding countermeasure suggestions;

[0027] A result output module that helps regulatory agencies make quick responses through a visual interface and optimizes the efficiency of market supervision.

[0028] In a third aspect, an embodiment of the present invention provides a computer device, including a memory and a processor, wherein: when the computer program instructions are executed by the processor, the steps of the power spot market risk prevention and control method considering the behavior of market entities as described in the first aspect of the present invention are implemented.

[0029] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored, wherein: when the computer program instructions are executed by the processor, the steps of the power spot market risk prevention and control method considering the behavior of market entities as described in the first aspect of the present invention are implemented.

[0030] The beneficial effects of the present invention are as follows: By establishing a multi-dimensional data collection mechanism and a coupling degree evaluation system, the present invention not only solves the problem of incomplete data collection in traditional systems, but also realizes the accurate identification of the characteristics of "large machines and small networks", significantly improving the accuracy of risk monitoring. By introducing quantitative indicators of the behavioral characteristics of market players, an analysis system including dimensions such as trading frequency and price volatility is established, effectively realizing the timely identification of market manipulation and illegal behaviors. By designing a calculation method for risk indicators with dynamic weights and a three-level early warning mechanism, combined with an automatically executed security strategy, the system is equipped with the ability of hierarchical early warning and automatic intervention for risks, improving the timeliness of risk prevention and control.

[0031] In addition, through the multi-dimensional analysis function of the visualization interface, combined with various display methods such as geographical distribution maps and time series charts, it helps supervisors quickly grasp the market dynamics and improves the supervision efficiency. Overall, the present invention constructs an intelligent and automated market risk prevention and control system, providing reliable technical support for ensuring the safe and stable operation of the electricity spot market. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0033] Figure 1 Flowchart of a risk prevention and control method for an electricity spot market considering the behaviors of market players;

[0034] Figure 2 Computer equipment diagram of a risk prevention and control method for an electricity spot market considering the behaviors of market players. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the following will make a detailed description of the specific embodiments of the present invention in conjunction with the drawings of the specification.

[0036] In the following description, many specific details are set forth in order to fully understand the present invention. However, the present invention can also be implemented in other ways different from those described herein. Those skilled in the art can make similar extensions without departing from the connotation of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0037] Second, the "one embodiment" or "embodiment" referred to herein means a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The appearances of "in one embodiment" in different places in this specification do not all refer to the same embodiment, nor are they separate or selectively exclusive embodiments from other embodiments.

[0038] Embodiment 1

[0039] Referring to Figures 1 to 2 , which is the first embodiment of the present invention. This embodiment provides a method for preventing and controlling power spot market risks considering the behaviors of market entities, including:

[0040] S100: Obtain the operation data of power generation, power consumption demand, market price, and grid status in the power spot market;

[0041] In the embodiments of the present application, the operation data includes the following four types of data: power generation data, power consumption demand data, market price data, and grid status data. The power generation data mainly includes information such as the real-time output of each generator set, the operating status of the unit, and the start-stop plan. The power consumption demand data mainly includes information such as the load forecast value, the actual power consumption load, and the load characteristics. The market price data mainly includes information such as the real-time electricity price, the day-ahead price forecast, and the historical transaction price. The grid status data mainly includes information such as line power flow, node voltage, and frequency quality.

[0042] In an optional embodiment, the acquisition of operation data can be achieved through different systems and different collection frequencies. For example, the power generation data can be collected every 5 minutes through the SCADA system to record the change of the unit output in real time; the power consumption demand data can be collected every 15 minutes through the smart meter system to master the change of the power consumption load; the market price data can be obtained in real time through the trading system to timely reflect the market fluctuations; the grid status data can be updated every 1 minute according to the dispatching system to monitor the operation status of the power grid.

[0043] In another optional embodiment, in addition to the above four types of basic operation data, other types of supplementary data can be added according to actual supervision requirements. For example, market entity credit rating data can be added, including information such as historical default records and financial status; environmental impact data can also be added to record environmental protection indicators such as carbon emissions and pollutant emissions; equipment health status data can also be added to monitor operation parameters such as equipment failure rate and maintenance records. These supplementary data can strengthen the control of market risks from different dimensions.

[0044] Exemplarily, in the specific implementation process of a regional power grid, the system is configured with 100 power generation data collection points with a sampling period of 5 minutes; at the same time, 1000 smart meters are deployed to collect electricity demand with a collection frequency of 15 minutes; in addition, the price data of 3 power trading centers are accessed to achieve real-time updates; and grid status monitoring devices are set at 50 key nodes with a monitoring frequency of 1 minute. Through this multi-point and multi-frequency data collection scheme, the system can obtain comprehensive and timely market operation data.

[0045] It should be noted that the multi-source heterogeneous data collection scheme adopted in this application not only ensures the comprehensiveness of the data, but also guarantees the reliability of the data through a multiple verification mechanism. The system will conduct source authentication on the collected data to ensure that the data comes from legal collection devices; at the same time, it will conduct data verification to check whether the data meets the preset rationality requirements; for the detected abnormal data, the system will mark it and initiate the corresponding processing process; in addition, the key data will be backed up in real time to prevent data loss. Through these measures, a high-quality data foundation is provided for subsequent risk analysis.

[0046] S200: Based on the obtained operation data, predict the market trend and detect anomalies, with particular attention to the influencing factors of large generator sets connected to small-scale power grids;

[0047] In the embodiment of this application, the prediction and anomaly detection of the market trend mainly consider the "large machine and small grid" characteristic. "Large machine and small grid" refers to the possible system stability problems when large generator sets are connected to small-scale power grids. When a large-capacity generator set is connected to a relatively small power grid, due to the large ratio of the single-unit capacity of the generator set to the system capacity, it will have a significant impact on the stability of the power grid.

[0048] In an alternative embodiment, the system uses the Gradient Boosting Tree (GBT) model for market trend prediction. The prediction process is divided into the following stages: First, input multi-dimensional data such as preprocessed power generation, electricity demand, market price, and grid status into the model; second, the model predicts the future market trend by analyzing the historical change laws of these data; finally, combine the current market state to dynamically adjust the prediction results. This prediction method can capture the non-linear characteristics of market changes and improve the prediction accuracy.

[0049] In another alternative embodiment, the system designs a special anomaly detection mechanism, which mainly includes three levels: one is the outlier detection based on statistics, which identifies abnormal points by calculating the dispersion degree of the data; the second is the rule detection based on expert experience, which judges abnormal situations according to the preset business rules; the third is the pattern detection based on machine learning, which identifies potential risks by learning historical abnormal patterns. This mechanism can timely detect abnormal behaviors in market operation.

[0050] Exemplarily, in a certain power market, a generating unit with a capacity of 600 MW is connected to a regional power grid with a total load of only 2000 MW. By collecting the output data of the unit, the power grid frequency data, and the market price data, the system analyzes and finds that when the output of the unit exceeds 300 MW, the power grid frequency fluctuation increases significantly, and the market price also shows abnormal fluctuations. Based on these data, the system can predict the possible market risks in advance.

[0051] It should be noted that the system's attention to the characteristics of "large generator in a small grid" is mainly reflected in three aspects: First, an association analysis model between the output of the generating unit and the power grid stability is established to monitor the mutual influence between the two in real time; second, targeted warning thresholds are set to give timely warnings when the impact of the unit output on the power grid exceeds the safe range; finally, an adaptive adjustment mechanism is developed, which can give reasonable suggestions for the unit output according to the actual bearing capacity of the power grid. These measures together constitute a complete risk prevention and control system for "large generator in a small grid".

[0052] S201: When predicting the market trend and detecting anomalies, by introducing the coupling degree evaluation index and the stability evaluation index to enhance the adaptability to the characteristics of "large generator in a small grid", where: the coupling degree evaluation index is used to measure the association strength between the generating unit and the power grid state;

[0053] The stability evaluation index includes the volatility rate and the maximum drawdown, which are used to quantify the fluctuation degree of the market price or the power generation.

[0054] S300: Analyze the behavior patterns of market players and identify the risk behaviors of possible market manipulation and illegal operations;

[0055] In the embodiment of the present application, the analysis of the market player behavior patterns mainly focuses on the trading behavior characteristics of market participants such as power generation enterprises and electricity sales companies. By comprehensively analyzing the data in multiple dimensions such as their quotation strategies, trading volume changes, and trading time distributions, the possible market manipulation and illegal behaviors are identified. The market manipulation behaviors mainly include malicious quotation, false trading, collusion and bid rigging, etc., while the illegal operations include trading beyond the limit, false information disclosure, etc.

[0056] In an optional embodiment, the system establishes a market player portrait model, which includes the following core indicators: the trading frequency indicator, which is used to measure the trading times and rhythms of market players within a unit time; the price deviation indicator, which is used to evaluate the deviation degree of the quotation from the market average price; the trading scale indicator, which is used to monitor the comparison of the single transaction volume with the historical average value; the time concentration indicator, which is used to analyze the distribution characteristics of the trading time. Through the combined analysis of these indicators, the behavior characteristics of market players can be effectively depicted.

[0057] In another optional embodiment, the system adopts an abnormal behavior recognition method that combines rules and machine learning. The rule part includes a market manipulation feature library summarized based on expert experience, such as continuous high-price quotes, sudden sharp increase in trading volume, etc.; the machine learning part uses a deep learning model to automatically learn abnormal patterns in historical data to identify new types of market manipulation methods. This dual recognition mechanism greatly improves the discovery rate of risk behaviors.

[0058] Exemplarily, the system monitors a power generation enterprise in a regional power market that continuously submits quotes significantly higher than the market average price during peak hours, and the output of its generating units is far lower than the rated capacity. Through behavioral pattern analysis, the system discovers that the enterprise attempts to influence the market price by controlling the output, and this behavior has obvious market manipulation characteristics. The system issues a warning signal in a timely manner to prevent abnormal fluctuations in the market price.

[0059] It should be noted that when analyzing the behavioral patterns of market entities, attention should be paid not only to the abnormal behaviors of individual entities but also to the associated behaviors among multiple entities. By constructing a market entity relationship network and analyzing features such as the trading correlation and price correlation among entities, the system can discover complex risk behaviors such as market collusion in a timely manner. At the same time, the system also establishes a dynamic evaluation mechanism to dynamically adjust the risk level of market entities according to their historical behavior records, realizing continuous supervision of the behaviors of market entities.

[0060] S301: When analyzing the behavioral patterns of market entities, the following behavioral characteristics are quantified: trading frequency, which represents the number of transactions completed by a market entity within a specific time window; price volatility, which measures the standard deviation of the market price; market participation rate, which represents the proportion of the trading volume of a market entity within a specific time period to the total trading volume; abnormal trading behavior index, which is used to mark whether abnormal trading behavior is detected.

[0061] S400: Monitor market dynamics in real time, set risk thresholds, and trigger an alarm when the monitored risk indicators exceed the set standards;

[0062] In the embodiment of the present application, market dynamics monitoring is a real-time and continuous process, including dynamic tracking of key indicators such as power generation, electricity demand, market price, and grid status. The system establishes a complete early warning trigger mechanism by setting a hierarchical risk threshold system. The setting of risk thresholds is based on historical data analysis, expert experience, and actual market conditions, and is dynamically adjusted according to the characteristics of different time periods and different regions.

[0063] In an optional embodiment, the risk threshold system is divided into four dimensions according to the index type: Generation capacity dimension: monitoring indicators such as the change rate of unit output and the degree of deviation from the planned value; Power consumption demand dimension: tracking indicators such as the deviation of load forecast and the implementation rate of demand response; Market price dimension: paying attention to indicators such as price volatility and the deviation degree of transaction price; Power grid status dimension: monitoring indicators such as the degree of network congestion and frequency deviation.

[0064] In another optional embodiment, the system adopts an adaptive threshold adjustment mechanism. This mechanism dynamically updates the threshold according to the following factors:

[0065] Seasonal factors: such as the peak electricity consumption period in summer; Period characteristics: such as the peak and valley periods of load in the morning and evening; Special events: such as major holidays; Historical experience: such as data in the same period of previous years; Market feedback: such as the evaluation of recent warning effects.

[0066] Exemplarily, during the intraday operation of a certain power market, the system simultaneously monitors the following abnormal situations: The output of a large unit drops suddenly by 30%; The regional electricity price rises by 50% within 10 minutes; The degree of blockage of the main transmission channel reaches 85%; At this time, since multiple indicators exceed the preset threshold simultaneously, the system immediately triggers the highest-level warning signal.

[0067] It should be noted that the risk monitoring system also needs to consider the correlation between indicators. For example, when there is a high correlation between the change in the output of the generating unit and the electricity price fluctuation, even if a single indicator does not exceed the threshold, the system may still trigger a warning. This multi-dimensional and correlated monitoring mechanism can more comprehensively evaluate the market risk status and improve the accuracy and timeliness of warnings.

[0068] S401: The calculation of the monitored risk indicators uses weight coefficients, and it satisfies: The weight coefficients include the generation capacity weight coefficient, the power consumption demand weight coefficient, the market price weight coefficient, and the power grid status weight coefficient; The sum of all weight coefficients is equal to 1, and each coefficient can be dynamically adjusted according to the actual situation.

[0069] S402: Automatically sending warning signals at different levels according to the risk level includes: When the risk level is greater than 100%, triggering a first-level warning; When the risk level is between 80% and 100%, triggering a second-level warning; When the risk level is between 50% and 80%, triggering a third-level warning.

[0070] S500: Automatically sending warning information at different levels according to the risk level, and putting forward corresponding suggestions for countermeasures;

[0071] In the embodiments of the present application, the system classifies early warnings into three levels according to the calculation result of the risk level L = R / T × 100%, where R is the current risk index value and T is the preset risk threshold. The early warning levels are classified as: level 1 early warning (L > 100%), level 2 early warning (80% < L ≤ 100%), and level 3 early warning (50% < L ≤ 80%). Different levels of early warnings correspond to different disposal processes and countermeasures.

[0072] In an alternative embodiment, the objects and contents of the level 3 early warning information are set as follows:

[0073] Level 1 early warning: Sending objects: person in charge of the market supervision department, power grid dispatching center, relevant market entities; Information content: specific risk type, risk degree, influence scope, recommended measures; Disposal requirements: The emergency plan must be activated within 30 minutes.

[0074] Level 2 early warning: Sending objects: person in charge of the market operation department, relevant market entities; Information content: abnormal situation of risk indicators, possible impacts, preventive suggestions; Disposal requirements: Complete risk assessment and intervention within 2 hours.

[0075] Level 3 early warning: Sending objects: market analysts, relevant market entities; Information content: risk warnings, monitoring focuses, matters needing attention; Disposal requirements: Complete risk tracking and analysis within 24 hours.

[0076] Exemplarily, when the system monitors that the electricity price in a certain area has increased by 80% within half an hour, a level 2 early warning is triggered. The system automatically sends an early warning message to the market operation department, including the time, location, and influence scope of the abnormal price fluctuation, and recommends intervening by increasing the power supply in this area and activating the demand-side response, etc. The operation department takes corresponding measures accordingly and successfully stabilizes the market price.

[0077] It should be noted that the early warning mechanism of the system not only includes risk identification and information sending, but also includes a complete early warning effect evaluation and feedback mechanism. By recording the accuracy, timeliness, and disposal effect of each early warning, the system can continuously optimize the early warning rules and threshold settings to improve the accuracy of early warnings. At the same time, the system also establishes a hierarchical push mechanism for early warning information to ensure that information can be delivered to relevant responsible persons in a timely manner to achieve rapid response and disposal.

[0078] S501: Provide a visual interface to support multi-dimensional data analysis, including: geographical distribution map, showing the spatial distribution of market entities; time series chart, demonstrating the change trends of various indicators; correlation matrix chart, analyzing the mutual influences between different market elements.

[0079] S600: Help the regulatory agency make a rapid response through the visual interface and optimize the market supervision efficiency.

[0080] In the embodiments of the present application, the visualization interface adopts a modular design, mainly including functional modules such as market overview, risk monitoring, early warning management, and decision support. Through multi-dimensional data display and interactive operations, the system helps supervisors intuitively understand the market situation, quickly identify potential risks, and make timely responses.

[0081] In an alternative embodiment, the visualization interface includes the following core functional areas: Market situation map: Displays the real-time operating status of the regional power grid; Marks the locations of key monitored market entities; Shows the power flow conditions of key transmission channels; Updates the price heat map in real time.

[0082] Data analysis dashboard: Displays the real-time values and trend charts of key indicators; Provides multi-dimensional data filtering and comparison functions; Supports the generation and export of customized reports; Displays the detailed information of abnormal data.

[0083] Early warning information center: Displays the list of current active early warning information; Provides progress tracking of early warning processing; Records historical early warnings and processing results; Supports the dynamic configuration of early warning rules.

[0084] Exemplarily, when the system detects abnormal price fluctuations in a certain area, the visualization interface will automatically focus on that area and display key information such as price change trends, relevant market entity information, and potential impact ranges. Supervisors can quickly view the disposal methods of historical similar cases through the interface and use scenario analysis tools to evaluate the effects of different intervention measures, so as to quickly formulate the optimal disposal plan.

[0085] It should be noted that the visualization interface design of the system follows the principles of "usability" and "practicality". On the one hand, through intuitive graphical displays and convenient operation methods, the usage threshold for supervisors is reduced; on the other hand, by providing rich analysis tools and decision support functions, the needs of actual supervision work are met. At the same time, the system also supports mobile access, enabling supervisors to grasp market dynamics at any time and achieve rapid response.

[0086] S601: It further includes the following steps: Automatically execute preset security policies, suspend the trading permissions of specific market entities, and restrict certain types of transactions;

[0087] Take emergency measures in extreme cases to prevent the further spread of risks; Update and optimize the early warning threshold in real time to improve the accuracy of early warnings.

[0088] Furthermore, this embodiment also provides a risk prevention and control system for the electricity spot market considering the behavior of market entities, including,

[0089] A data acquisition module that acquires the operation data of power generation, electricity demand, market price, and grid status in the electricity spot market;

[0090] A trend prediction module that predicts market trends and detects anomalies based on the acquired operation data, with special attention to the influencing factors of large generator sets connected to small-scale power grids;

[0091] An identification module that analyzes the behavior patterns of market players and identifies risk behaviors that may involve market manipulation and illegal operations;

[0092] A monitoring module that monitors market dynamics in real time, sets risk thresholds, and triggers an alarm when the monitored risk indicators exceed the set standards;

[0093] A prediction module that automatically issues early warning messages at different levels according to the risk levels and proposes corresponding countermeasure suggestions;

[0094] A result output module that helps regulatory agencies make quick responses through a visual interface and optimizes the efficiency of market supervision.

[0095] In summary, by collecting multi-dimensional operation data such as power generation, electricity demand, market price, and grid status in the electricity spot market in real time, a complete data collection system has been established, overcoming the problem of incomplete data collection in traditional systems, enhancing the data foundation for risk monitoring, and achieving a comprehensive perception of the market operation status.

[0096] By introducing coupling degree evaluation indicators and stability evaluation indicators, the adaptability to the characteristics of "large machines with small grids" has been particularly enhanced: the coupling degree evaluation indicator realizes the precise quantification of the correlation strength between generator sets and grid status; the stability evaluation indicator realizes the three-dimensional monitoring of market fluctuations through volatility and maximum drawdown; thus solving the technical problem that traditional methods are difficult to handle the scenario of large units connected to small grids.

[0097] By establishing a quantitative system for the behavior characteristics of market players, including dimensions such as trading frequency, price volatility, market participation, and abnormal trading behavior indicators, a systematic analysis of the behavior patterns of market players has been realized, enabling the timely identification of market manipulation and illegal operation behaviors and effectively preventing market risks.

[0098] By designing a calculation method for risk indicators with dynamic weights, the risk monitoring is made more flexible: a dynamic adjustment mechanism for weight coefficients is adopted; a multi-dimensional threshold system is established; thus improving the accuracy and adaptability of risk prevention and control.

[0099] By establishing a three-level early warning mechanism and combining it with an automatically executed security strategy: realizing hierarchical early warning of risks; supporting automatic intervention in emergency situations; having the ability to optimize the early warning threshold in real time; significantly enhancing the timeliness and effectiveness of market risk prevention and control.

[0100] Multi-dimensional data analysis function through a visual interface: provides a geographical distribution map to intuitively display the spatial distribution; uses time series charts to track the change trend; reveals the element associations through a correlation matrix diagram; greatly improves the decision-making efficiency of supervisors.

[0101] Generally speaking, through systematic technological innovation, the present invention constructs an intelligent and automated market risk prevention and control system, which not only solves the problems of incomplete data collection, single analysis means, and lagging warning mechanism existing in the prior art, but also realizes the accurate identification and rapid disposal of market risks through a number of innovative technical solutions, providing strong technical support for ensuring the safe and stable operation of the electricity spot market.

[0102] The present invention realizes the intelligent identification and prevention and control of the operation risks of the electricity spot market by integrating advanced data analysis and machine learning technologies, significantly improves the stability and fairness of the market, and at the same time provides scientific decision-making support for regulatory agencies, promoting the optimal allocation of electric power resources and the healthy development of the market.

[0103] Embodiment 2

[0104] Refer to Figure 1 - Figure 2 , which is the second embodiment of the present invention. This embodiment provides a method for preventing and controlling the risks of the electricity spot market considering the behaviors of market players. In order to verify the beneficial effects of the present invention, scientific demonstrations are carried out through economic benefit calculations and simulation experiments.

[0105] Data collection module: collects data such as power generation P gen , power consumption demand P load , market price C, grid status S, etc. from multiple data sources (such as power trading centers, power generation enterprise management systems, smart meters, grid dispatching centers, etc.).

[0106] Regular data acquisition: obtains the latest data from each data source through the API interface every hour to ensure the timeliness of the data.

[0107] Data cleaning: uses statistical methods to remove outliers (such as abnormal power generation or power consumption data under extreme weather conditions) and fill in missing values (such as linear interpolation or mean filling).

[0108] Data standardization: unifies the data format and unit, converts all time series data into a unified timestamp format, and converts data with different units into standard units (such as megawatt-hour MWh).

[0109] Analysis and prediction module: based on the collected data, uses the Gradient Boosting Tree (GBT) model for market trend prediction and anomaly detection, especially paying attention to the characteristics of "large machines and small grids".

[0110] Data Input: Input the preprocessed data into the GBT model, including features such as historical power generation, electricity demand, market price, grid status, etc.

[0111] Model Training: Use historical data to train the GBT model. The specific formula is as follows:

[0112] F m (x) = F m-1 (x) + γ m h m (x)

[0113] Where, F m (x) is the model prediction after the m-th iteration; F m-1 (x) is the model prediction after the (m - 1)-th iteration; γ m is the learning rate, which controls the amplitude of each update to prevent overfitting. It is usually a positive number less than 1; h m (x) is the weak learner added in this round (usually a decision tree), representing the output of the newly added weak learner to the input feature x at the m-th iteration.

[0114] The prediction output is:

[0115] Generate market trend prediction results and identify abnormal trading behaviors.

[0116] Special considerations for the "large machine, small grid" characteristic are:

[0117] Introduce the coupling degree evaluation index C couple and the stability evaluation indexes V and MDD to enhance the adaptability to the "large machine, small grid" characteristic. To measure the correlation strength between the generator set and the grid status, the coupling degree evaluation index uses the following formula:

[0118]

[0119] Where, Corr(P gen,i , S i ) is the correlation coefficient or mutual information, which is used to measure the correlation between the output power P gen,i of the i-th generator set and the grid S i at the corresponding position; n is the number of generator sets.

[0120] Quantify the fluctuation degree of time series data such as market price or power generation. The volatility uses the following formula:

[0121]

[0122] Where, N is the length of the time series, that is, the number of observation points; P(t) is the market price or power generation at time t. is the time average of the market price or the power generation volume,

[0123] The calculation formula is:

[0124]

[0125] MDD = max t∈[0,N] (max s≤t P(s) - P(t))

[0126] where MDD is the Maximum Drawdown, quantifying the maximum decline of the market price or the power generation volume; t is the current time point; s ≤ t are all time points before time t; P(s) is the market price or the power generation volume at time s; P(t) is the market price or the power generation volume at time t.

[0127] The behavior evaluation module analyzes the behavior patterns of market entities and identifies potential risk behaviors such as market manipulation and illegal operations.

[0128] Behavior feature extraction: The following behavior features are extracted as:

[0129]

[0130] F is the trading frequency, representing the number of transactions completed by a market entity within a specific time window; the total number of transactions is the quantity of all transactions conducted by the market entity within the specified time window; the time window length is the length of the time period used to calculate the trading frequency, such as one day, one week, or one month.

[0131]

[0132] σ P is the price volatility, measuring the standard deviation of the market price and reflecting the intensity of price changes; N is the length of the time series, i.e., the number of observation points; P(t): the market price at time t; the time average of the market price,

[0133] The calculation formula is:

[0134]

[0135] E is the market participation degree, representing the proportion of the trading volume of a market entity within a specific time period to the total trading volume;

[0136]

[0137] Qi(t) is the trading volume of market entity i at time t; Qtotal(t) is the total trading volume of the market at time t; is the cumulative trading volume of market entity i within the entire time window; is the cumulative total trading volume of the market within the entire time window.

[0138] Used to mark whether abnormal trading behavior is detected. The formula for the abnormal trading behavior indicator is:

[0139]

[0140] x is the observed behavior characteristic value (such as the amount of a single transaction, trading frequency, etc.); μ is the historical mean of this behavior characteristic; σ is the historical standard deviation of this behavior characteristic; k is the set threshold coefficient, usually a positive number greater than 1, used to define the boundary of abnormal behavior.

[0141] Comprehensive risk assessment model:

[0142] Construct a comprehensive risk scoring model: Score i = w1F + w2σ P + w3E + w4A + …

[0143] Score i The behavior score of the i-th market entity.

[0144] w is the weight corresponding to each behavior characteristic. These weights reflect the importance of each characteristic to risk assessment and satisfy ∑w = 1.

[0145] F is the trading frequency; σ P is the price volatility; E is the market participation; A is the abnormal trading behavior indicator; … are other behavior characteristics that may affect risk assessment.

[0146] Risk monitoring module

[0147] Monitor market dynamics in real time, set the risk threshold T, and trigger an alarm when the monitored risk indicator R exceeds the set standard.

[0148] Real-time data processing: Continuously receive and process real-time data from the data acquisition module to ensure data

[0149] Risk indicator calculation: Calculate the risk indicator R according to the weight coefficients α, β, γ, δ:

[0150] R = αP gen + βP load + γC + δ

[0151] R is the risk indicator, comprehensively measuring the impact degree of each key parameter in the electricity spot market on the overall risk. α, β, γ, δ are weight coefficients, reflecting the impact degree of each parameter on the risk, and can be adjusted according to the specific situation of the Hainan power system. α is the weight coefficient of the power generation P gen The weight coefficient of the electricity demand P loadWeight coefficient. γ: Weight coefficient of market price C. δ is the weight coefficient of grid state S. P gen is the power generation, representing the total power generation of market entities within a certain period, usually measured in megawatt-hours (MWh). P load is the electricity demand, representing the total electricity consumption of market entities within a certain period, usually measured in megawatt-hours (MWh). C is the market price, representing the real-time electricity price or average electricity price in the electricity spot market, usually measured in yuan per megawatt-hour (￥ / MWh). S is the grid state, which can be a comprehensive index of various grid operation parameters such as voltage, current, frequency, etc., used to evaluate the stability and health status of the grid. The weight coefficients α, β, γ, δ satisfy α + β + γ + δ = 1, ensuring that the sum of all weight coefficients is equal to 1, so that the risk index R is a weighted average and can reflect the relative contribution of each parameter to the overall risk.

[0152] Threshold comparison: Compare the calculated risk index R with the preset threshold T to determine whether it exceeds the warning line.

[0153] Alarm trigger: When R > T, immediately trigger an alarm to notify the relevant regulatory agencies to take corresponding measures.

[0154] Intelligent early warning module

[0155] Send early warning information at different levels according to the risk level L and put forward corresponding suggestions for countermeasures.

[0156] Risk level calculation:

[0157] Calculate the risk level L based on the risk index R and the threshold T:

[0158]

[0159] L represents the ratio of the current market risk to the set threshold, presented in percentage; R is the risk index, comprehensively measuring the impact degree of each key parameter in the electricity spot market on the overall risk; T is the risk threshold, the preset risk warning line, used to judge whether to trigger an early warning signal.

[0160] Early warning level determination:

[0161] When L > 100%, trigger a first-level early warning: indicating that the current market risk has significantly exceeded the preset threshold T and urgent measures need to be taken immediately for intervention.

[0162] When 80% < L ≤ 100%, trigger a second-level early warning: indicating that the market risk is close to but has not exceeded the preset threshold T, and it is recommended to pay close attention and prepare corresponding countermeasures.

[0163] When 50% < L ≤ 80%, a third-level warning is triggered: indicating that the market risk is at a medium level, reminding market participants to pay attention to the market change trend, and adjusting strategies in a timely manner to avoid possible risks.

[0164] When L ≤ 50%, no warning is triggered: indicating that the current market risk is relatively low and does not reach the standard for triggering a warning.

[0165] Decision Support Module

[0166] Provide a visual interface to help regulatory agencies make quick responses, optimize market supervision rules, and improve supervision efficiency.

[0167] Display the market operation conditions through various forms such as geographical distribution maps, time series charts, and correlation matrix charts, making complex data and evaluation results more intuitive and understandable. Combining the data analysis results, provide decision support to help regulatory agencies optimize market rules and strategies to ensure the stability and fairness of the market.

[0168] Embodiment 3

[0169] This embodiment also provides a computer device, applicable to a situation of a power spot market risk prevention and control method considering the behavior of market entities, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement a forced oscillation detection and positioning method for a distribution network as proposed in the above embodiment.

[0170] This embodiment also provides a storage medium, on which a computer program is stored, and when the program is executed by a processor, it implements a forced oscillation detection and positioning method for a distribution network as proposed in the above embodiment.

[0171] The computer device can be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through Wi-Fi, a carrier network, NFC (Near Field Communication), or other technologies. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad set on the computer device housing, or an external keyboard, touchpad, or mouse, etc.

[0172] If a function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs.

[0173] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a predefined sequence list of executable instructions for implementing logical functions. It can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or in combination with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.

[0174] More specific examples (non-exhaustive list) of computer-readable media include the following: electrical connection parts with one or more wirings (electronic devices), portable computer disk cartridges (magnetic devices), random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memories), optical fiber devices, and portable compact disc read-only memories (CDROM). Additionally, a computer-readable medium can even be paper or other suitable media on which a program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or otherwise processing it as appropriate, and then storing it in a computer memory.

[0175] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0176] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A method for preventing and controlling risks in the electricity spot market considering the behaviors of market players, characterized in that: Including obtaining operation data of power generation, electricity demand, market price, and grid status in the electricity spot market; Based on the obtained operation data, predicting market trends and detecting anomalies, with particular attention to the influencing factors of large generating units connected to small-scale power grids; Analyzing the behavior patterns of market players to identify potential risk behaviors of market manipulation and illegal operations; Real-time monitoring of market dynamics, setting risk thresholds, and triggering an alarm when the monitored risk indicators exceed the set standards; Automatically sending early warning messages at different levels according to the risk level and proposing corresponding countermeasure suggestions; Helping regulatory agencies make quick responses through a visual interface to optimize the efficiency of market supervision.

2. The risk prevention and control method for the electricity spot market considering the behaviors of market entities according to claim 1, wherein: When predicting market trends and detecting anomalies, by introducing a coupling degree evaluation index and a stability evaluation index to enhance the adaptability to the characteristics of "large machines and small grids", where: the coupling degree evaluation index is used to measure the correlation strength between the generating unit and the grid status; The stability evaluation index includes volatility and maximum drawdown, which are used to quantify the fluctuation degree of market price or power generation.

3. The risk prevention and control method for the electricity spot market considering the behavior of market entities according to claim 2, characterized in that: When analyzing the behavior patterns of market players, it is quantified through the following behavioral characteristics: trading frequency, which represents the number of transactions completed by market players within a specific time window; price volatility, which measures the standard deviation of market price; Market participation rate, which represents the proportion of the trading volume of market players within a specific time period to the total trading volume; Anomaly trading behavior index, which is used to mark whether an anomaly trading behavior is detected.

4. The method for preventing and controlling risks in the electricity spot market considering the behavior of market players as described in claim 3, characterized in that: The calculated risk indicators for monitoring adopt weight coefficients, and satisfy: the weight coefficients include a power generation weight coefficient, an electricity demand weight coefficient, a market price weight coefficient, and a grid status weight coefficient; the sum of all weight coefficients is equal to 1, and each coefficient can be dynamically adjusted according to the actual situation.

5. The method for preventing and controlling power spot market risks considering the behaviors of market entities according to claim 4, wherein: Automatically sending early warning signals at different levels according to the risk level includes: when the risk level is greater than 100%, triggering a first-level early warning; when the risk level is between 80% and 100%, triggering a second-level early warning; when the risk level is between 50% and 80%, triggering a third-level early warning.

6. The method for preventing and controlling risks in the electricity spot market considering the behavior of market players as claimed in claim 5, wherein: The provided visual interface supports multi-dimensional data analysis, including: a geographical distribution map, which shows the spatial distribution of market players; a time series chart, which displays the change trends of various indicators; a correlation matrix chart, which analyzes the mutual influence between different market elements.

7. The method for preventing and controlling risks in the electricity spot market considering the behavior of market players as claimed in claim 6, wherein: It also includes the following steps: Automatically executing preset security policies, suspending the trading permissions of specific market players, and restricting certain types of transactions; Taking emergency measures in extreme cases to prevent the further spread of risks; Real-time updating and optimizing the early warning threshold to improve the accuracy of early warnings.

8. A risk prevention and control system for the electricity spot market considering the behavior of market entities, based on the risk prevention and control method for the electricity spot market considering the behavior of market entities according to any one of claims 1 to 7, characterized in that: It also includes a data acquisition module that obtains operation data of power generation, electricity demand, market price, and grid status in the electricity spot market; A trend prediction module that predicts market trends and detects anomalies based on the obtained operation data, with particular attention to the influencing factors of large generating units connected to small-scale power grids; An identification module that analyzes the behavior patterns of market players to identify potential risk behaviors of market manipulation and illegal operations; Monitoring module, which monitors market dynamics in real time, sets risk thresholds, and triggers an alarm when the monitored risk indicators exceed the set standards; Prediction module, which automatically sends early warning messages at different levels according to the risk levels and proposes corresponding suggestions for countermeasures; Result output module, which helps the regulatory agency to make a quick response through a visual interface and optimize the efficiency of market supervision.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the power spot market risk prevention and control method considering the behavior of market entities according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the power spot market risk prevention and control method considering the behavior of market entities according to any one of claims 1 to 7.

Images