Risk assessment system based on electricity transaction market

Abstract

The invention relates to the technical field of electric power system risk assessment, and discloses a risk assessment system based on an electric power transaction market, which realizes real-time acquisition and dynamic processing of electric power transaction price data through a price data real-time acquisition module in combination with a real-time deviation analysis module, calculates a price deviation value in real time and captures related influence factors, thereby realizing risk assessment of the electric power transaction market. The dynamic parameter adjustment module can establish a correlation model, automatically trigger parameter adjustment when real-time factor fluctuation exceeds a threshold value, and realize automatic updating of computational logic by combining scene adaptation and emergency adjustment subunits, so as to ensure that a price deviation value accurately reflects an actual risk; the risk assessment module combines dynamic parameters to construct a model, calculates risk indexes and divides grades, the risk early warning module generates early warning information in time, and the risk conduction analysis and pressure test unit provides comprehensive risk pre-judgment, assists market subjects to scientifically make plans, and maintains the stability of the power transaction market.

Description

Technical Field

[0001] The present invention relates to the technical field of power system risk assessment, and in particular to a risk assessment system based on a power trading market. Background Art

[0002] The risk assessment system integrates market data (such as electricity price fluctuations and supply and demand changes), transaction data (such as contract terms and performance records), and external factors (such as policy adjustments and extreme weather events). It then uses quantitative models and artificial intelligence algorithms to identify risk points such as price fluctuations, credit defaults, and abuse of market power. The system monitors market dynamics in real time, provides early warnings of abnormal transactions, and assesses the probability of risk losses in different scenarios. This system provides decision-making support for market players such as power generators and electricity retailers, assists regulators in maintaining market order, and enhances the stability and security of electricity trading.

[0003] However, in the current electricity trading market, price deviation values ​​are affected by real-time factors such as supply and demand fluctuations, changes in renewable energy output, and changes in load demand, showing high-frequency and diverse dynamic change characteristics. Existing technologies rely on fixed historical data and preset model parameters during the evaluation process. For example, announcement numbers CN111612289B and CN117151882B have neither established real-time collection and dynamic calibration channels for price deviation values ​​nor lacked a mechanism to automatically update the price deviation calculation logic according to real-time market fluctuations. As a result, when the market price formation rules change due to real-time factors, the price deviation values ​​calculated based on fixed parameters cannot accurately reflect the price deviation risks in actual transactions. Summary of the Invention

[0004] The technical problem to be solved by the present invention is that the existing technology has the disadvantage that the price deviation value calculated based on fixed parameters cannot accurately reflect the price deviation risk in actual transactions. For this reason, we propose a risk assessment system based on the electricity trading market.

[0005] In order to achieve the above-mentioned purpose, the present application adopts the following technical solutions: a risk assessment system based on the electricity trading market, including a real-time price data acquisition module, which is used to: collect electricity trading price data in real time based on the Internet of Things and the market trading interface, pre-process the collected original price data, and store the processed data in a real-time database; a real-time deviation analysis module, which is used to: dynamically process the price data in the real-time database based on the streaming computing framework, construct a real-time price deviation calculation model, calculate the deviation value between the transaction price and the market benchmark price in real time, extract the dynamic characteristics of the deviation value, and capture the real-time factors affecting the deviation value; a dynamic parameter adjustment ... Based on the analysis results of the real-time deviation analysis module, a correlation model between price deviation calculation parameters and real-time influencing factors is established. When the fluctuation of real-time factors exceeds the preset threshold, the parameter adjustment mechanism is automatically triggered to dynamically update the price deviation calculation coefficient, benchmark price calibration factor and floating interval parameters; the risk assessment module is used to: construct a risk assessment model based on the real-time parameters output by the dynamic parameter adjustment module and the dynamic characteristics of the price deviation value, calculate the risk index corresponding to the price deviation, divide the risk level, and generate a real-time risk assessment report; the risk warning module is used to: monitor the risk index output by the risk assessment module in real time, and automatically generate warning information when the risk level exceeds the preset warning threshold.

[0006] The real-time deviation analysis module includes a real-time deviation value calculation unit, which is used to calculate the price deviation value per unit time in real time based on the sliding window algorithm, construct a deviation value time series, and calculate the instantaneous fluctuation amplitude, cumulative deviation amount and deviation change rate of the deviation value; the price deviation value is obtained by the following formula: ,in, : Sliding window time length; : New energy is output in real time at all times; : New energy benchmark output; : Real-time transaction prices at all times; : Market benchmark price at that moment; : Real-time supply-demand ratio at all times; an influencing factor capture unit, used to: collect real-time factor data affecting price deviation through a multi-source data interface, the real-time factors include real-time supply-demand ratio, real-time output of new energy, transmission channel load, and temporary policy control signals, normalize various factors, and construct a feature set associated with factors and deviations; a dynamic feature extraction unit, used to: use a time series feature extraction algorithm to perform feature mining on the time series of price deviation values, extract the periodic characteristics, mutation point characteristics, and trend characteristics of the deviation values, and combine the feature set associated with factors and deviations to generate a dynamic feature vector of the deviation.

[0007] Furthermore, the real-time deviation analysis module also includes: a deviation attribution analysis unit, which is used to: when the price deviation value exceeds the preset normal range, analyze the contribution of each real-time factor to the deviation value based on the feature importance evaluation algorithm, locate the dominant influencing factors, generate a deviation attribution report, and clarify the influence weight and action mechanism of each factor; a data quality verification unit, which is used to: monitor the integrity and timeliness of the collected price data and influencing factor data in real time, and when the data missing rate or delay time exceeds the threshold, start the data completion mechanism, and perform data repair based on historical similar time period data and trend prediction models to ensure the accuracy of the analysis results.

[0008] Furthermore, the dynamic parameter adjustment module includes: a parameter association modeling unit, which is used to: construct a mapping relationship model between price deviation calculation parameters and real-time influencing factors based on historical data, use a machine learning algorithm to train parameter adjustment rules, determine the optimal parameter configuration under different factor combinations, and form a parameter adjustment knowledge base; an automatic triggering unit, which is used to: compare real-time influencing factor data with a preset threshold in real time, and when the fluctuation amplitude of a single factor exceeds the threshold or the comprehensive fluctuation index of multiple factors reaches the trigger condition, automatically activate the parameter adjustment process and send an adjustment instruction to the parameter updating unit; a parameter updating unit, which is used to: dynamically correct the base price coefficient, deviation weight factor and abnormality judgment threshold in the price deviation calculation model according to the optimal parameter configuration output by the parameter association modeling unit and combined with the real-time deviation characteristics, record the parameter adjustment time, adjustment amplitude and triggering reason, and generate a parameter adjustment log.

[0009] Furthermore, the parameter updating unit includes a real-time parameter calibration subunit, which is used to perform minute-level calibration on the initially determined optimal parameter configuration based on the deviation dynamic characteristics and influencing factor data output by the real-time deviation analysis module, and correct the parameter adjustment amplitude through real-time data feedback; the calibration formula is: ,in, : Parameter value after calibration at all times, : Preliminary optimal parameter configuration, Adjustment coefficient, : The dynamic characteristic value of the moment deviation, : feedback attenuation factor, : Comprehensive value of influencing factors at all times; dynamic characteristic value of deviation Exceeding the threshold When the second correction is started: ,in, : Secondary correction coefficient : symbolic function; the scenario adaptation subunit is used to identify the current operating scenarios of the power trading market, including spot trading periods, futures delivery periods, and policy regulation periods. Based on the differences in price formation mechanisms in different scenarios, it calls the parameter adjustment templates for the corresponding scenarios and dynamically matches the calculation logic of the benchmark price coefficient; the parameter constraint verification subunit is used to set the upper and lower limits of parameter adjustment and the adjustment frequency threshold. During the parameter update process, it verifies in real time whether the parameters exceed the reasonable range. When the single adjustment range exceeds the preset threshold, it activates the step-by-step adjustment mechanism and implements the parameter update in stages to avoid the fluctuation of risk assessment results due to sudden parameter changes; the adjustment trajectory tracking subunit is used to record the specific values, triggering factors, associated deviation characteristics and corresponding risk assessment results of each parameter update, build a parameter adjustment trajectory database, identify the rules and potential optimization points of parameter adjustment through time series analysis, and provide iterative training data for the parameter association modeling unit; the emergency adjustment trigger subunit is used to monitor extreme values ​​in real-time influencing factors. When extreme values ​​occur, it skips the regular parameter adjustment process and directly calls the preset emergency parameter configuration. At the same time, it sends an expedited evaluation request to the adjustment effect evaluation unit to ensure the validity of parameters under extreme market conditions.

[0010] Furthermore, the dynamic parameter adjustment module also includes: an adjustment effect evaluation unit, which is used to: after the parameter adjustment, evaluate the parameter adjustment effect by comparing the price deviation calculation accuracy and risk assessment fit before and after the adjustment; when the effect does not meet expectations, start the secondary adjustment mechanism and optimize the parameter association model based on the feedback results; a parameter backup and backtracking unit, which is used to: back up the configuration before each parameter adjustment, support backtracking to the historical parameter status according to the time point or risk assessment results, and quickly restore to the optimal parameter configuration when the system is abnormal.

[0011] Furthermore, the risk assessment module includes: a risk index calculation unit, which is used to: construct a risk index calculation formula based on the price deviation value after dynamic parameter adjustment, combined with the deviation duration, fluctuation frequency and cumulative deviation amount, and calculate the real-time risk index, wherein the risk index is nonlinearly correlated with the deviation characteristics; a risk level classification unit, which is used to: classify multiple risk levels according to the size of the risk index and the risk tolerance of market entities, including low risk, medium risk, high risk, and extreme risk, and clarify the trigger conditions and impact levels corresponding to each level of risk; an assessment model optimization unit, which is used to: regularly optimize the weight configuration of the risk assessment model based on historical risk events and assessment results, using a reinforcement learning algorithm to improve the model's ability to identify extreme price deviation events and reduce assessment lag.

[0012] Furthermore, the risk assessment module also includes: a risk transmission analysis unit, which is used to analyze the transmission path of price deviation risk to other market links, evaluate the potential impact on subsequent trading periods, related regional markets and upstream and downstream entities, and generate a risk transmission map; a stress testing unit, which is used to stress test the current risk assessment model based on historical extreme price deviation data and simulation scenarios, verify the stability and assessment accuracy of the model under extreme market conditions, and output a test report and model optimization suggestions.

[0013] The technical effects and advantages of the present invention are as follows: the present invention collects electricity transaction price data in real time based on the Internet of Things and market transaction interface through a real-time price data acquisition module, and combines the real-time deviation analysis module to use a streaming computing framework and a sliding window algorithm to dynamically process data, calculate price deviation values ​​in real time, and capture real-time influencing factors such as the supply-demand ratio and the output of new energy sources, so that market entities can grasp the dynamic characteristics of price deviations in real time, accurately identify the price deviation risks in current transactions, provide real-time data support for adjusting trading strategies, reduce the risk of decision-making errors caused by information lags, and improve operational stability. The present invention establishes an association model between price deviation calculation parameters and real-time influencing factors through a dynamic parameter adjustment module, automatically triggers parameter adjustment when the real-time factor fluctuation exceeds a threshold, combines a scenario adaptation subunit to match calculation logic for different transaction scenarios, and an emergency adjustment trigger subunit to deal with extreme market conditions, thereby realizing the automatic update of price deviation calculation logic with real-time market fluctuations, ensuring that when market prices form regular changes, the calculated price deviation value can still accurately reflect the actual risk, helping market entities effectively avoid risk misjudgment caused by parameter solidification, and improving the flexibility of risk response. The present invention constructs a risk assessment model through the risk assessment module combined with the deviation value and dynamic characteristics after dynamic parameter adjustment, calculates the risk index and divides it into levels, and cooperates with the risk warning module to automatically generate warning information when the risk exceeds the limit, so that market entities can clearly grasp the risk level and trigger conditions and take prevention and control measures in time; at the same time, the risk transmission analysis unit and the stress testing unit evaluate the risk transmission path and the model stability under extreme scenarios, providing market entities with comprehensive risk prediction, helping them to scientifically formulate trading plans and maintain the stable operation of the power trading market. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The disclosure of the present invention is illustrated with reference to the accompanying drawings. It should be understood that the drawings are for illustrative purposes only and are not intended to limit the scope of protection of the present invention. In the drawings, the same reference numerals are used to refer to the same components: Figure 1 It is a module schematic diagram of the present invention. DETAILED DESCRIPTION

[0015] It is easy to understand that according to the technical solution of the present invention, without changing the essential spirit of the present invention, a person skilled in the art can propose a variety of interchangeable structural modes and implementation modes. Therefore, the following specific embodiments and drawings are only exemplary descriptions of the technical solution of the present invention and should not be regarded as the entire invention or as a limitation or restriction of the technical solution of the present invention.

[0016] The present invention discloses a risk assessment system based on the power trading market, which aims to achieve accurate assessment and timely warning of power trading market risks by collecting power trading price data in real time, dynamically analyzing price deviations, and adjusting assessment parameters, thereby providing decision-making support for market entities and ensuring the stable operation of the power trading market.

[0017] See also Figure 1 The system includes a real-time price data acquisition module, which is the entry point for system data and is responsible for providing high-quality basic data for subsequent analysis. Its specific workflow is as follows: Intelligent monitoring terminals deployed based on IoT technology and market trading interfaces connected to the power trading platform collect real-time power trading price data, including transaction prices, listing prices, and settlement prices for each trading period. The collection frequency is dynamically adjusted based on market trading activity, with data collected in seconds during peak trading periods and in minutes during off-peak periods to ensure data timeliness.

[0018] The collected raw price data is preprocessed. This includes: data cleaning to remove significant outliers; format standardization to convert data from different sources and formats into a unified format with millisecond-level timestamp accuracy; and data deduplication to remove duplicate records by comparing timestamps and prices. The processed data is stored in a real-time database that supports high-concurrency writes and fast queries of time-series data, meeting the system's requirements for real-time data storage.

[0019] The system also includes a real-time deviation analysis module: the real-time deviation analysis module performs dynamic processing and feature mining based on the pre-processed data provided by the real-time price data acquisition module to provide key analysis results for risk assessment.

[0020] The real-time deviation analysis module includes the following: (1) Real-time Deviation Calculation Unit: This unit calculates the price deviation within a unit of time in real time based on a sliding window algorithm. The size of the sliding window can be dynamically configured based on the trading cycle. The unit calculates the deviation between the transaction price within the window and the market benchmark price in real time. The market benchmark price can be the average transaction price for the same period of the day or a reference benchmark price published by the regulatory authorities.

[0021] Construct a time series of deviation values, and calculate the instantaneous fluctuation amplitude, cumulative deviation, and deviation change rate of the deviation value through time series analysis; the price deviation value is obtained using the following formula: ,in, : Sliding window time length; : New energy is output in real time at all times; : New energy benchmark output; : Real-time transaction prices at all times; : Market benchmark price at that moment; : Real-time supply and demand ratio at all times.

[0022] (2) Influencing Factor Capture Unit: This unit collects real-time data on factors influencing price deviations through a multi-source data interface. The real-time supply-demand ratio is derived from real-time load and power generation data from the power dispatch center; real-time renewable energy output data is derived from the real-time monitoring systems of wind and photovoltaic power plants; transmission channel load data is derived from the grid operation monitoring platform; and temporary policy control signals are derived from the regulatory agency's information release system. Each factor is normalized, converting factor data of varying magnitudes and units to the [0, 1] range to eliminate dimensionality. Based on this normalized factor data, a feature set of factor-deviation correlations is constructed, containing the real-time correlation between each factor and the price deviation value.

[0023] (3) Dynamic Feature Extraction Unit: This unit uses a time series feature extraction algorithm, such as wavelet transform or LSTM, to extract the periodicity, mutation point, and trend characteristics of the price deviation values. The extracted deviation features are then combined with a set of factor-related deviation-related features to generate a deviation dynamic feature vector. This vector encompasses the dynamic characteristics of the deviation value itself and the correlation information of the influencing factors, providing multi-dimensional feature support for subsequent parameter adjustments and risk assessments.

[0024] (IV) Deviation Attribution Analysis Unit: When the price deviation exceeds the preset normal range, deviation attribution analysis is initiated. Based on the feature importance assessment algorithm, the contribution of each real-time factor to the deviation is analyzed and a significance score is calculated for each factor. A higher score indicates a greater impact on the current deviation. The dominant influencing factors are identified based on the significance score, and a deviation attribution report is generated. The report clearly defines the impact weight and mechanism of each factor, providing a basis for market participants to understand the causes of the deviation.

[0025] (5) Data Quality Verification Unit: Real-time monitoring of the integrity and timeliness of collected price data and influencing factor data. Integrity is measured by the data missing rate, and timeliness is measured by data delay. When the data missing rate exceeds 5% or the delay exceeds 30 seconds, the data completion mechanism is activated. Data repair is performed based on historical data from similar time periods and trend prediction models.

[0026] In this embodiment, the application of the sliding window algorithm enables real-time calculation of price deviations, dynamically capturing price fluctuation characteristics; the collection and normalization of multi-source influencing factors ensures the comprehensiveness and comparability of factor analysis; the time series feature extraction and fusion technology enhances the richness of deviation features; the deviation attribution analysis unit helps market entities accurately locate the causes of deviations; and the data quality verification unit ensures the reliability of the analyzed data, avoiding distortion of analysis results due to data problems. The system also includes a dynamic parameter adjustment module: based on the analysis results of the real-time deviation analysis module, the dynamic parameter adjustment module achieves dynamic optimization of price deviation calculation parameters, ensuring that the risk assessment model adapts to market changes.

[0027] The dynamic parameter adjustment module includes the following: (1) Parameter Association Modeling Unit: This unit constructs a mapping model between price deviation calculation parameters and real-time influencing factors based on historical data. Machine learning algorithms (such as gradient boosting and neural networks) are used to train parameter adjustment rules. The input is normalized influencing factor data, and the output is the optimal price deviation calculation parameters. Through training with extensive historical data, the optimal parameter configurations for different factor combinations are determined, forming a parameter adjustment knowledge base.

[0028] (2) Automatic Trigger Unit: This unit compares real-time influencing factor data with preset thresholds. These thresholds include single-factor thresholds and multi-factor combined volatility index thresholds. When the fluctuation range of a single factor exceeds a threshold or the multi-factor combined volatility index reaches 0.6, the parameter adjustment process is automatically activated, sending adjustment instructions to the parameter update unit to ensure that parameters respond promptly to market changes.

[0029] (3) Parameter Update Unit: The parameter update unit includes a real-time parameter calibration subunit, a scene adaptation subunit, a parameter constraint verification subunit, an adjustment trajectory tracking subunit, and an emergency adjustment trigger subunit. The real-time parameter calibration subunit performs minute-level calibration on the optimal parameter configuration output by the parameter association modeling unit based on the deviation dynamic characteristics and influencing factor data output by the real-time deviation analysis module. The calibration formula is: ,in, : Parameter value after calibration at all times, : Preliminary optimal parameter configuration, Adjustment coefficient, : The dynamic characteristic value of the moment deviation, : feedback attenuation factor, : Comprehensive value of influencing factors at all times; dynamic characteristic value of deviation Exceeding the threshold When the second correction is started: ,in, : Secondary correction coefficient : Symbolic function. Parameter adjustment ranges are adjusted using real-time data feedback to ensure that parameters closely align with current market conditions. The scenario adaptation subunit identifies the current operating scenarios of the power trading market, including spot trading periods, futures delivery periods, and policy regulation periods. Based on the differences in price formation mechanisms across different scenarios, parameter adjustment templates are applied to the corresponding scenarios. For example, a more sensitive benchmark price coefficient calculation logic is used during spot trading periods, while policy factors are weighted more heavily in the parameters during policy regulation periods. The parameter constraint verification subunit sets upper and lower limits for parameter adjustments and adjustment frequency thresholds. During the parameter update process, parameters are verified in real time to ensure they remain within reasonable ranges. When a single adjustment exceeds a preset threshold, a step-by-step adjustment mechanism is initiated, implementing parameter updates in two or three stages to avoid volatility in risk assessment results caused by sudden parameter changes. The adjustment trajectory tracking subunit records the specific values, triggering factors, associated deviation characteristics, and corresponding risk assessment results of each parameter update, building a parameter adjustment trajectory database. Time series analysis identifies patterns in parameter adjustments and potential optimization points, providing iterative training data for the parameter association modeling unit to continuously optimize the parameter adjustment model. The emergency adjustment trigger subunit monitors extreme values ​​in real-time influencing factors. When extreme values ​​appear, the regular parameter adjustment process is skipped and the preset emergency parameter configuration is directly called. At the same time, an expedited evaluation request is sent to the adjustment effect evaluation unit to ensure the validity of parameters under extreme market conditions and quickly respond to market risks.

[0030] (IV) Adjustment Effect Evaluation Unit: After parameter adjustments are made, the effectiveness of the parameter adjustments will be evaluated by comparing the accuracy of price deviation calculations and the degree of risk assessment fit before and after the adjustments. If the results do not meet expectations, a secondary adjustment mechanism will be activated to optimize the parameter association model based on the feedback results, and the parameter configuration will be regenerated and updated.

[0031] (5) Parameter Backup and Rollback Unit: Backs up the configuration before each parameter adjustment, including the specific parameter values, adjustment time, and other information. This allows rollback to historical parameter states based on time points or risk assessment results. In the event of a system anomaly, the system can quickly restore to the optimal parameter configuration, ensuring stable system operation.

[0032] In this embodiment, the parameter association modeling unit realizes the intelligent association between parameters and influencing factors through machine learning algorithms, thereby improving the scientific nature of parameter adjustment; the automatic triggering unit ensures the timeliness of parameter adjustment, avoiding parameter lag after market changes; the multiple sub-units of the parameter update unit work together to realize accurate calibration of parameters, scenario adaptation, risk control and trajectory tracking, thereby improving the reliability of parameter adjustment; the adjustment effect evaluation unit and the parameter backup and backtracking unit provide closed-loop optimization and security guarantees for parameter adjustment, ensuring that the parameters are always in the optimal state.

[0033] The system also includes a risk assessment module: Based on the real-time parameters output by the dynamic parameter adjustment module, the risk assessment module completes risk index calculation, grading and model optimization, providing a basis for risk warning. The risk assessment module includes the following contents: (1) Risk Index Calculation Unit: Based on the price deviation value after dynamic parameter adjustment, combined with the deviation duration, fluctuation frequency, and cumulative deviation, a risk index calculation formula is constructed. The risk index is nonlinearly correlated with the deviation characteristics. When characteristics such as the deviation value and duration exceed a certain threshold, the risk index will increase exponentially, highlighting a high-risk state. The calculated real-time risk index serves as the core indicator for measuring market risk.

[0034] (II) Risk Level Classification Unit: Based on the risk index and the risk tolerance of market entities, multiple risk levels are established, including low risk (risk index < 30), medium risk (risk index 30 ≤ < 60), high risk (risk index 60 ≤ < 80), and extreme risk (risk index ≥ 80). The trigger conditions and impact levels for each level of risk are clearly defined. For example, low risk corresponds to a small, short-lived deviation, with a negligible impact on market entities; extreme risk corresponds to a large, long-lasting deviation, potentially leading to market disruption. Furthermore, customized risk level thresholds are tailored to the risk tolerance of different market entities to enhance the targeted nature of risk assessments.

[0035] (3) Assessment Model Optimization Unit: We regularly optimize the weighting of the risk assessment model using reinforcement learning algorithms based on historical risk events and assessment results. By continuously learning the correlation between risk characteristics in historical data and actual risk events, we adjust the weighting factors in the risk index calculation formula, improve the model's ability to identify extreme price deviation events, and reduce assessment lags.

[0036] (IV) Risk Transmission Analysis Unit: Analyzes the transmission path of price deviation risk to other market links, assesses the potential impact on subsequent trading periods, related regional markets, and upstream and downstream entities, generates a risk transmission map, and intuitively displays the risk diffusion path and impact range.

[0037] (V) Stress Testing Unit: Based on historical extreme price deviation data and simulated scenarios, this unit stress tests the current risk assessment model. This unit verifies the model's stability and assessment accuracy under extreme market conditions and produces a test report and recommendations for model optimization.

[0038] In this embodiment, the risk index calculation unit constructs a risk index through multi-dimensional deviation characteristics, thereby realizing a quantitative assessment of market risk; the risk level classification unit combines the differences between market entities to improve the practicality of risk assessment; the assessment model optimization unit continuously optimizes the model through reinforcement learning to ensure that the assessment capability keeps pace with the times; the risk transmission analysis unit helps market entities predict the scope of risk diffusion and take countermeasures in advance; the stress testing unit ensures the reliability of the model under extreme market conditions and improves the robustness of the system.

[0039] The system also includes a risk warning module: This module monitors risk assessment results in real time and promptly delivers warning information to market participants, enabling early detection and resolution of risks. The specific workflow is as follows: The risk assessment module outputs risk indices and risk levels, automatically generating warning information when the risk level exceeds the preset warning threshold. Warning information includes the risk type, scope of impact, and recommended measures. Push notification channels are selected based on the market participants' pre-set contact information to ensure prompt delivery of warning information. For high and extreme risks, push notifications are delivered simultaneously through multiple channels, and a delivery confirmation mechanism is implemented to ensure timely receipt by relevant parties.

[0040] In this embodiment, the risk warning module achieves rapid transmission of risk information through real-time monitoring and multi-channel push notifications, helping market players take timely countermeasures and reduce risk losses. The detailed content of the warning information provides market players with clear action guidelines, improving the effectiveness of risk response.

[0041] The system also includes a data storage module: the data storage module is responsible for the storage and management of various types of system data, ensuring the security, integrity and accessibility of the data. The data storage module includes the following contents: (1) Time series data storage unit: Configure a distributed time series database to store real-time price data, deviation value series, and risk index partitioned by time dimension.

[0042] (2) Associated data storage unit: stores parameter adjustment records, influencing factor data, and risk assessment report related information, and uses a relational database to establish the association relationship between data.

[0043] (3) Data Lifecycle Management Unit: Set storage periods for different types of data based on data importance and time characteristics. Automatically clean up expired and redundant data and archive important historical data to ensure data storage efficiency and reduce storage costs.

[0044] (4) Data Encryption Unit: This unit encrypts stored sensitive information, using a field-level encryption mechanism that encrypts only sensitive fields and leaves non-sensitive fields unencrypted. This ensures data security while improving data processing efficiency. Furthermore, data transmission is encrypted to prevent information leakage during transmission.

[0045] (5) Access Control Unit: Implement a role-based access control strategy to assign different data access permissions to different market entities. For example, regulatory agencies can access all data, while power sales companies can only access price data and risk assessment results relevant to them. Log data query and export operations, including the operator, time, and content of the operation, and conduct regular permission audits to ensure data access compliance and prevent data misuse.

[0046] In this embodiment, the application of a distributed time series database ensures efficient storage and access to massive time series data; the associative data storage unit realizes the associative management of various types of data, improving the convenience of data query; the data lifecycle management unit optimizes the allocation of storage resources and reduces storage costs; the data encryption unit and access control unit ensure data security and access compliance from a technical perspective, protecting the privacy and data rights of market entities.

[0047] The system also includes a system adaptation module: The system adaptation module is responsible for monitoring the system operating status, optimizing resource allocation, and ensuring that the system operates efficiently under different loads. The system adaptation module includes the following: (1) Performance Monitoring Unit: This unit monitors the operating indicators of each system module in real time, including parameter adjustment time, risk assessment calculation time, CPU utilization, memory usage, network transmission rate, etc. It also generates system performance reports regularly, analyzes the changing trends of each indicator, and identifies potential performance bottlenecks.

[0048] (2) Dynamic Resource Allocation Unit: Based on the performance monitoring unit's monitoring results, the system automatically adjusts resource allocation strategies when resource consumption in a particular module is excessive. Through containerization technology, the CPU and memory quotas of each module are dynamically adjusted, prioritizing the resource needs of the real-time data collection, deviation calculation, and risk assessment modules, ensuring that core functions are not affected by resource constraints.

[0049] (3) Adaptive Optimization Unit: Analyzes the correlation between system operating indicators and market trading activity, and establishes a resource demand forecasting model. This automatically pre-emptively expands system processing capacity during peak trading periods and reduces resource usage during off-peak periods (such as the early morning hours). This enables dynamic scheduling of system resources, improves resource utilization, and reduces operating costs.

[0050] In this embodiment, the performance monitoring unit provides data basis for system optimization; the resource dynamic allocation unit ensures the stable operation of the core module and avoids resource bottlenecks affecting system functions; the adaptive optimization unit achieves efficient utilization of system resources through prediction and dynamic adjustment, and improves the adaptability and economy of the system under different loads.

[0051] In summary, the present invention achieves real-time assessment and early warning of power trading market risks through the collaborative work of various modules. The real-time price data acquisition module provides high-quality basic data, the real-time deviation analysis module deeply explores the characteristics and influencing factors of price deviations, the dynamic parameter adjustment module ensures that assessment parameters adapt to market changes, the risk assessment module quantifies and categorizes risks, the risk early warning module promptly transmits risk information, the data storage module ensures data security and management, and the system adaptation module optimizes system performance. This system can provide market participants with accurate risk information and decision-making support, promoting the stable, efficient, and fair operation of the power trading market.

[0052] The technical scope of the present invention is not limited to the contents of the above description. Those skilled in the art can make various deformations and modifications to the above embodiments without departing from the technical idea of ​​the present invention, and these deformations and modifications should all fall within the protection scope of the present invention.

Claims

1. A risk assessment system based on the power trading market, characterized in that: It includes a price data real-time acquisition module, which is used to: collect power transaction price data in real time based on the Internet of Things and market transaction interface, pre-process the collected raw price data, and store the processed data in a real-time database; The real-time deviation analysis module is used to: dynamically process price data in the real-time database based on the streaming computing framework, build a real-time price deviation calculation model, calculate the deviation value between the transaction price and the market benchmark price in real time, extract the dynamic characteristics of the deviation value, and capture the real-time factors that affect the deviation value; the dynamic parameter adjustment module is used to: establish an association model between price deviation calculation parameters and real-time influencing factors based on the analysis results of the real-time deviation analysis module, and automatically trigger the parameter adjustment mechanism when the real-time factor fluctuation exceeds the preset threshold, and dynamically update the price deviation calculation coefficient, benchmark price calibration factor and floating interval parameter; the risk assessment module is used to: build a risk assessment model based on the real-time parameters output by the dynamic parameter adjustment module and the dynamic characteristics of the price deviation value, calculate the risk index corresponding to the price deviation, divide the risk level, and generate a real-time risk assessment report; The risk warning module is used to: monitor the risk index output by the risk assessment module in real time, and automatically generate warning information when the risk level exceeds the preset warning threshold.

2. The risk assessment system based on the power trading market according to claim 1 is characterized in that: The real-time deviation analysis module includes a real-time deviation value calculation unit, which is used to calculate the price deviation value per unit time in real time based on the sliding window algorithm, construct a deviation value time series, and calculate the instantaneous fluctuation amplitude, cumulative deviation amount and deviation change rate of the deviation value; the price deviation value is obtained by the following formula: ,in, : Sliding window time length; : New energy is output in real time at all times; : New energy benchmark output; : Real-time transaction prices at all times; : Market benchmark price at that moment; : Real-time supply-demand ratio at all times; an influencing factor capture unit, used to: collect real-time factor data affecting price deviation through a multi-source data interface, the real-time factors include real-time supply-demand ratio, real-time output of new energy, transmission channel load, and temporary policy control signals, normalize various factors, and construct a feature set associated with factors and deviations; a dynamic feature extraction unit, used to: use a time series feature extraction algorithm to perform feature mining on the time series of price deviation values, extract the periodic characteristics, mutation point characteristics, and trend characteristics of the deviation values, and combine the feature set associated with factors and deviations to generate a dynamic feature vector of the deviation.

3. The risk assessment system based on the power trading market according to claim 2 is characterized in that: The real-time deviation analysis module also includes: a deviation attribution analysis unit, which is used to: when the price deviation value exceeds the preset normal range, analyze the contribution of each real-time factor to the deviation value based on the feature importance evaluation algorithm, locate the dominant influencing factors, generate a deviation attribution report, and clarify the influence weight and action mechanism of each factor; a data quality verification unit, which is used to: monitor the integrity and timeliness of the collected price data and influencing factor data in real time, and when the data missing rate or delay time exceeds the threshold, start the data completion mechanism, and repair the data based on historical similar time period data and trend prediction model to ensure the accuracy of the analysis results.

4. The risk assessment system based on the power trading market according to claim 1 is characterized in that: The dynamic parameter adjustment module includes: a parameter association modeling unit, which is used to: construct a mapping relationship model between price deviation calculation parameters and real-time influencing factors based on historical data, use a machine learning algorithm to train parameter adjustment rules, determine the optimal parameter configuration under different factor combinations, and form a parameter adjustment knowledge base; an automatic triggering unit, which is used to: compare real-time influencing factor data with a preset threshold in real time, and when the fluctuation amplitude of a single factor exceeds the threshold or the comprehensive fluctuation index of multiple factors reaches the trigger condition, automatically activate the parameter adjustment process and send an adjustment instruction to the parameter updating unit; a parameter updating unit, which is used to: dynamically correct the base price coefficient, deviation weight factor and abnormality judgment threshold in the price deviation calculation model according to the optimal parameter configuration output by the parameter association modeling unit and in combination with the real-time deviation characteristics, record the parameter adjustment time, adjustment amplitude and triggering reason, and generate a parameter adjustment log.

5. The risk assessment system based on the power trading market according to claim 4 is characterized in that: The parameter updating unit includes a real-time parameter calibration subunit, which is used to perform minute-level calibration on the initially determined optimal parameter configuration based on the deviation dynamic characteristics and influencing factor data output by the real-time deviation analysis module, and to correct the parameter adjustment amplitude through real-time data feedback; the calibration formula is: ,in, : Parameter value after calibration at all times, : Preliminary optimal parameter configuration, : adjustment coefficient, : The dynamic characteristic value of the moment deviation, : feedback attenuation factor, : Comprehensive value of influencing factors at all times; dynamic characteristic value of deviation Exceeding the threshold When the second correction is started: ,in, : Secondary correction coefficient : symbolic function; the scenario adaptation subunit is used to identify the current operating scenarios of the power trading market, including spot trading periods, futures delivery periods, and policy regulation periods. Based on the differences in price formation mechanisms in different scenarios, it calls the parameter adjustment templates for the corresponding scenarios and dynamically matches the calculation logic of the benchmark price coefficient; the parameter constraint verification subunit is used to set the upper and lower limits of parameter adjustment and the adjustment frequency threshold. During the parameter update process, it verifies in real time whether the parameters exceed the reasonable range. When the single adjustment range exceeds the preset threshold, it activates the step-by-step adjustment mechanism and implements the parameter update in stages to avoid the fluctuation of risk assessment results due to sudden parameter changes; the adjustment trajectory tracking subunit is used to record the specific values, triggering factors, associated deviation characteristics and corresponding risk assessment results of each parameter update, build a parameter adjustment trajectory database, identify the rules and potential optimization points of parameter adjustment through time series analysis, and provide iterative training data for the parameter association modeling unit; the emergency adjustment trigger subunit is used to monitor extreme values ​​in real-time influencing factors. When extreme values ​​occur, it skips the regular parameter adjustment process and directly calls the preset emergency parameter configuration. At the same time, it sends an expedited evaluation request to the adjustment effect evaluation unit to ensure the validity of parameters under extreme market conditions.

6. The risk assessment system based on the power trading market according to claim 4 is characterized in that: The dynamic parameter adjustment module also includes: an adjustment effect evaluation unit, which is used to: after the parameter adjustment, evaluate the parameter adjustment effect by comparing the price deviation calculation accuracy and risk assessment fit before and after the adjustment. When the effect does not meet expectations, a secondary adjustment mechanism is initiated to optimize the parameter association model based on the feedback results; a parameter backup and backtracking unit, which is used to: back up the configuration before each parameter adjustment, support backtracking to the historical parameter status according to the time point or risk assessment results, and quickly restore to the optimal parameter configuration when the system is abnormal.

7. The risk assessment system based on the power trading market according to claim 1 is characterized in that: The risk assessment module includes: a risk index calculation unit, which is used to: construct a risk index calculation formula based on the price deviation value after dynamic parameter adjustment, combined with the deviation duration, fluctuation frequency and cumulative deviation amount, and calculate the real-time risk index, wherein the risk index and the deviation characteristics are nonlinearly correlated; a risk level classification unit, which is used to: classify multiple risk levels according to the size of the risk index and the risk tolerance of market entities, including low risk, medium risk, high risk, and extreme risk, and clarify the trigger conditions and impact levels corresponding to each level of risk; an assessment model optimization unit, which is used to: regularly optimize the weight configuration of the risk assessment model based on historical risk events and assessment results using a reinforcement learning algorithm, improve the model's ability to identify extreme price deviation events, and reduce assessment lags.

8. The risk assessment system based on the power trading market according to claim 6, characterized in that: The risk assessment module also includes: a risk transmission analysis unit, which is used to analyze the transmission path of price deviation risk to other market links, evaluate the potential impact on subsequent trading periods, related regional markets and upstream and downstream entities, and generate a risk transmission map; a stress testing unit, which is used to stress test the current risk assessment model based on historical extreme price deviation data and simulation scenarios, verify the stability and assessment accuracy of the model under extreme market conditions, and output a test report and model optimization suggestions.

9. The risk assessment system based on the power trading market according to claim 1, characterized in that: It also includes a data storage module, which includes: a time series data storage unit, which is used to: configure a distributed time series database, store real-time price data, deviation value sequences and risk indexes by time dimension partitions, support high-concurrency writing and low-latency queries, and optimize data compression algorithms to reduce storage occupancy; an associated data storage unit, which is used to: store parameter adjustment records, influencing factor data and risk assessment report related information, establish index associations with time series data, and support multi-dimensional queries by events, parameters and risk levels; a data lifecycle management unit, which is used to: set storage periods for different types of data based on data importance and time characteristics, automatically clean up expired redundant data, and archive important historical data to ensure data storage efficiency.

10. The risk assessment system based on the power trading market according to claim 1, characterized in that: It also includes a system adaptive module, which includes: a performance monitoring unit, which is used to: monitor the operating indicators of each module of the system in real time, record the time consumed by parameter adjustment and the time consumed by risk assessment calculation, and generate a system performance report; a dynamic resource allocation unit, which is used to: based on the monitoring results of the performance monitoring unit, when the resource consumption of a certain module is too high, automatically adjust the system resource allocation strategy to give priority to the resource requirements of the real-time data collection, deviation calculation and risk assessment modules; an adaptive optimization unit, which is used to: analyze the correlation between the system operating indicators and the market trading activity, establish a resource demand prediction model, automatically expand the system processing capacity in advance during peak trading periods, and reduce resource usage during low periods to achieve efficient system operation.

Images