Electric energy declaration strategy optimization method, device, program product and storage medium

Abstract

A method, device, program product, and storage medium for optimizing energy consumption reporting strategies are disclosed, relating to the technical field of data processing. The method includes: acquiring physical constraint data and parameters of the energy storage system; generating a physical baseline based on the physical constraint data and energy storage system parameters; acquiring historical market data; generating market forecast data based on the historical market data; identifying price-sensitive periods based on the market forecast data; generating a comprehensive reporting curve based on the physical baseline, market forecast data, and price-sensitive periods; acquiring preset risk model parameters; calculating expected return and conditional risk value based on the comprehensive reporting curve and risk model parameters; adjusting the comprehensive reporting curve when the conditional risk value exceeds a preset risk tolerance threshold; calculating a target risk value until the target risk value does not exceed the risk tolerance threshold; and outputting the final reporting strategy. Implementing the technical solution provided in this application can reduce the loss of economic benefits from energy storage systems.

Description

Technical Field

[0001] This application relates to the field of data processing technology, specifically to a method, device, program product, and storage medium for optimizing an electricity energy reporting strategy. Background Technology

[0002] With the deepening of energy structure transformation and electricity market reform, energy storage systems, as an important player in the electricity market, are increasingly participating in spot market transactions. Due to their bidirectional charging and discharging regulation characteristics, energy storage systems offer significant flexibility in their bidding strategies within the electricity spot market.

[0003] To improve the profitability of energy storage systems in the electricity spot market, market participants typically develop trading strategies based on historical operating data. Currently, the mainstream strategies usually determine fixed bid volumes and prices based on price forecasts. This simple bidding method can generate some profit when market prices are relatively stable.

[0004] However, due to the frequent fluctuations in electricity spot market prices and the significant differences in price fluctuation characteristics at different times, the fixed-bid strategy is difficult to effectively cope with rapid changes in market prices, which can easily lead to losses in the economic benefits of energy storage systems. Summary of the Invention

[0005] This application provides a method, device, program product, and storage medium for optimizing electricity energy reporting strategies, which can reduce the loss of economic benefits of energy storage systems.

[0006] The first aspect of this application provides a method for optimizing an electricity energy reporting strategy, specifically including: Acquire physical constraint data and energy storage system parameters of the energy storage system, and generate a physical baseline based on the physical constraint data and energy storage system parameters; Acquire historical market data, generate market forecast data based on the historical market data, and identify price-sensitive periods based on the market forecast data; A comprehensive order curve is generated based on the physical baseline, the market forecast data, and the price-sensitive period. Obtain preset risk model parameters, and calculate expected return and conditional value of risk based on the comprehensive declaration curve and the risk model parameters; When the conditional risk value exceeds the preset risk tolerance threshold, the comprehensive declaration curve is adjusted, and the target risk value is calculated based on the adjusted comprehensive declaration curve until the target risk value does not exceed the risk tolerance threshold. The output includes the adjusted composite reporting curve, the physical baseline, the expected return value, and the target risk value, resulting in a final reporting strategy.

[0007] By adopting the above technical solution, firstly, a physical baseline is generated based on the physical constraint data and system parameters of the energy storage system to ensure that the application strategy meets the operational constraints of the energy storage system; secondly, price-sensitive periods are identified by analyzing historical market data, and a comprehensive application curve is generated by combining market forecast data and the physical baseline to achieve accurate response to market price fluctuations; thirdly, risk model parameters are introduced to calculate conditional value of risk, and the comprehensive application curve is dynamically adjusted to ensure that the target value of risk does not exceed the risk tolerance threshold, thereby effectively reducing the loss of economic benefits of the energy storage system.

[0008] Optionally, generating a physical baseline based on the physical constraint data and the energy storage system parameters includes: Extract load demand data, distributed power output data, and energy storage configuration data from the physical constraint data; The net physical demand baseline is calculated based on the load demand data and the distributed power generation output data, and the flexible regulation capacity is calculated based on the load demand data and the distributed power generation output data. A preliminary energy storage scheduling plan is generated based on the net physical demand baseline, the flexible adjustment capacity, and the energy storage configuration data. Extract feasible ranges for energy storage capacity and energy storage power from the parameters of the energy storage system; The preliminary energy storage scheduling plan is constrained and verified based on the feasible range of energy storage capacity and the feasible range of energy storage power to obtain the energy storage scheduling plan. The net physical demand baseline is corrected according to the energy storage scheduling plan to obtain the physical baseline.

[0009] By adopting the above technical solution, the net physical demand baseline and flexible regulation capacity are calculated by extracting load demand data, distributed power output data and energy storage configuration data. Combined with the energy storage capacity and power feasible range, a constraint-verified energy storage dispatch plan is generated, thereby ensuring that the physical baseline generation process fully considers the various constraints of actual operating conditions and improving the feasibility of energy storage systems participating in electricity spot market transactions.

[0010] Optionally, generating a composite reporting curve based on the physical baseline, the market forecast data, and the price-sensitive period includes: A basic reporting curve is generated based on the physical baseline and the market forecast data; During the high volatility period of the price-sensitive period, the declared electricity volume corresponding to each time point in the high volatility period is reduced according to the flexible adjustment capacity and the preset risk control coefficient. During the low volatility period of the price-sensitive period, the declared electricity volume corresponding to each time point in the low volatility period is increased according to the flexible adjustment capacity and the preset profit optimization coefficient, so as to obtain the initial flexible declaration curve. The initial flexible reporting curve is adjusted based on the market forecast data and the price-sensitive period to obtain the target flexible reporting curve; By combining the target flexible declaration curve and the basic declaration curve, a comprehensive declaration curve is obtained.

[0011] By adopting the above technical solution, a basic declaration curve is first generated based on the physical baseline and market forecast data. Then, according to the fluctuation characteristics of price-sensitive periods, the declared electricity volume is adjusted differently for high-fluctuation and low-fluctuation periods by combining the flexible adjustment capacity with risk control coefficients and profit optimization coefficients. The target flexible declaration curve is further optimized by market forecast data. Finally, a comprehensive declaration curve that takes into account risk management and profit improvement is generated, thereby realizing the energy storage system's accurate response and flexible adjustment to market price fluctuations.

[0012] Optionally, adjusting the initial flexible reporting curve based on the market forecast data and the price-sensitive period to obtain the target flexible reporting curve includes: Calculate the local price average and local price fluctuation range for the price-sensitive period based on the market forecast data; Calculate the upper limit and lower limit of price constraints based on the local price average, the local price fluctuation range, and the preset risk control coefficient; According to the preset power adjustment rules, the power declared during the price-sensitive period that exceeds the upper limit of the price constraint is reduced to the power declared corresponding to the upper limit of the price constraint, and the power declared below the lower limit of the price constraint is increased to the power declared corresponding to the lower limit of the price constraint, so as to obtain the target flexible declaration curve.

[0013] By adopting the above technical solution, the local price average and fluctuation range during price-sensitive periods are calculated. The upper and lower limits of price constraints are set in combination with the risk control coefficient. The initial flexible declaration curve is finely adjusted according to the preset power regulation rules. This allows the target flexible declaration curve to effectively control the trading risks caused by extreme price fluctuations while maintaining the flexibility to respond to market price changes, thereby improving the stability of energy storage systems participating in the electricity spot market.

[0014] Optionally, the step of adjusting the composite declaration curve based on the conditional risk value exceeding a preset risk tolerance threshold, and calculating the target risk value based on the adjusted composite declaration curve, includes: When the conditional risk value exceeds a preset risk tolerance threshold, a risk adjustment coefficient is calculated based on the deviation between the conditional risk value and the risk tolerance threshold. The declared electricity volume during price-sensitive periods in the comprehensive declaration curve is adjusted according to the risk adjustment coefficient to obtain the adjusted comprehensive declaration curve; The target risk value is recalculated based on the adjusted composite reporting curve and the risk model parameters.

[0015] By adopting the above technical solution, the risk adjustment coefficient is dynamically calculated based on the deviation between the conditional risk value and the risk tolerance threshold, and the declared electricity volume during price-sensitive periods is adjusted accordingly. This achieves adaptive optimization of the comprehensive declaration curve, thereby ensuring that the target risk value always meets the risk control requirements and effectively improving the risk management capability of the energy storage system participating in the electricity spot market transaction.

[0016] Optionally, adjusting the declared electricity volume during price-sensitive periods in the comprehensive declaration curve according to the risk adjustment coefficient to obtain the adjusted comprehensive declaration curve includes: Extract the declared electricity volume at each time point in the price-sensitive period from the comprehensive declaration curve; Calculate the electricity reduction value at each time point based on the risk adjustment coefficient and the declared electricity volume at each time point in the price-sensitive period; Subtract the corresponding electricity reduction value from the declared electricity volume at each time point during the price-sensitive period to obtain the target declared electricity volume at each time point during the price-sensitive period; The comprehensive declaration curve is adjusted by combining the target declared electricity volume at each time point during the price-sensitive period to obtain the adjusted comprehensive declaration curve.

[0017] By adopting the above technical solution, the declared electricity volume at each time point during the price-sensitive period is extracted, and the corresponding electricity volume reduction value is calculated based on the risk adjustment coefficient. This enables precise adjustment of the declared electricity volume during the price-sensitive period, allowing the adjusted comprehensive declaration curve to achieve effective risk control while maintaining the original declaration characteristics. This further improves the risk management accuracy of energy storage systems participating in electricity spot market transactions.

[0018] Optionally, after the output includes the adjusted composite reporting curve, the physical baseline, the expected return value, and the final reporting strategy based on the target value at risk, it also includes: Generate a time-segmented declaration instruction set based on the adjusted comprehensive declaration curve; Physical feasibility verification is performed based on the physical baseline and the time-segmented reporting instruction set. An evaluation report on the final application strategy is generated based on the feasibility verification results, the expected return value, and the target risk value.

[0019] By adopting the above technical solution, a time-segmented declaration instruction set is generated and physical feasibility is verified. Combined with the expected return value and target risk value, an evaluation report of the final declaration strategy is generated, realizing comprehensive monitoring and evaluation of the declaration strategy execution process, and ensuring the feasibility and reliability of energy storage systems participating in electricity spot market transactions.

[0020] In a second aspect, this application provides an energy reporting strategy optimization device, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program code, which includes computer instructions, and the one or more processors call the computer instructions to cause the energy reporting strategy optimization device to perform the method as described in the first aspect and any possible implementation thereof.

[0021] Thirdly, this application provides a computer program product containing instructions that, when the computer program product is run on an energy reporting strategy optimization device, causes the energy reporting strategy optimization device to perform the method described in the first aspect and any possible implementation thereof.

[0022] Fourthly, this application provides a computer-readable storage medium including instructions that, when executed on an energy reporting strategy optimization device, cause the energy reporting strategy optimization device to perform the method described in the first aspect and any possible implementation thereof. Attached Figure Description

[0023] Figure 1 This is a flowchart illustrating an energy reporting strategy optimization method provided in an embodiment of this application; Figure 2 This is a schematic diagram of a comprehensive application curve generation process provided in an embodiment of this application; Figure 3 This is an exemplary hardware structure diagram of an energy reporting strategy optimization device provided in an embodiment of this application. Detailed Implementation

[0024] To enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0025] In the description of the embodiments of this application, the words "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design that is described as "for example" or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design options. Rather, the use of the words "for example" or "for instance" is intended to present the relevant concepts in a specific manner.

[0026] In the description of the embodiments of this application, the term "multiple" means two or more. For example, multiple systems means two or more systems, and multiple screen terminals means two or more screen terminals. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. The terms "comprising," "including," "having," and variations thereof all mean "including but not limited to," unless otherwise specifically emphasized.

[0027] This application provides a method for optimizing an electricity energy reporting strategy, referencing... Figure 1 , Figure 1 This is a flowchart illustrating an energy reporting strategy optimization method provided in an embodiment of this application, including steps S101 to S106, as follows: S101: Obtain physical constraint data and energy storage system parameters, and generate a physical baseline based on the physical constraint data and energy storage system parameters.

[0028] Physical constraint data refers to the set of data on various physical limitations that the energy storage system needs to meet during operation, including load demand data, distributed power output data, and energy storage configuration data. For example, the load demand at a certain time period might be 500 kW, and the photovoltaic output might be 200 kW. Energy storage system parameters represent the system's own operating characteristics, including feasible ranges for energy storage capacity and power output, and charge / discharge efficiency. For example, the energy storage capacity range might be 0 to 1000 kWh, and the maximum charge / discharge power might be 500 kW. The physical baseline represents the benchmark operating curve after considering the physical constraints of the energy storage system, used to depict the power demand or supply status of the energy storage system under the conditions of meeting all constraints.

[0029] Specifically, the process begins by retrieving physical constraint data and energy storage system parameters from the system's operational database. The physical constraint data includes load demand for each time period, predicted output from distributed generation sources, and configuration information for the energy storage devices. The energy storage system parameters include upper and lower limits for energy storage capacity, upper and lower limits for charge / discharge power, and key parameters such as energy conversion efficiency. Then, based on the load demand data and distributed generation output data, the net physical demand (NPD) at each time point is calculated—the difference between load demand and distributed generation output. Next, a preliminary energy storage scheduling plan is generated based on the energy storage configuration data, taking into account the energy storage system's charge / discharge strategies. Subsequently, the feasible capacity and power ranges from the energy storage system parameters are used to constrain and validate the preliminary energy storage scheduling plan, ensuring that the energy storage state of charge and charge / discharge power at each time point are within feasible limits. Finally, the validated energy storage scheduling plan is used to adjust the net physical demand, resulting in a physical baseline that satisfies all physical constraints.

[0030] In some embodiments, the physical baseline can be generated in several ways. Optionally, an optimization model-based approach can be used. First, an optimization model aimed at minimizing operating costs is constructed. This model's constraints include energy storage capacity constraints, power constraints, and energy balance constraints. Then, physical constraint data and energy storage system parameters are input, and the optimization model is solved using a linear programming or mixed-integer programming solver. Finally, the physical baseline is generated based on the solution results. Optionally, a rule-based heuristic approach can be used. First, charging and discharging rules for the energy storage system are set, such as discharging during peak load periods and charging during off-peak load periods. Then, the charging and discharging power of the energy storage system is calculated periodically based on the physical constraint data and energy storage system parameters. During the calculation process, it is checked in real time whether the capacity and power constraints are met. If the constraints are violated, the charging and discharging power is adjusted. Finally, the physical baseline is generated based on the adjusted charging and discharging plan. It is understood that other methods can also be used to generate the physical baseline, such as statistical analysis methods based on historical operating data or simulation-based methods; these are not limited here.

[0031] S102: Obtain historical market data, generate market forecast data based on historical market data, and identify price-sensitive periods based on market forecast data.

[0032] Historical market data refers to transaction data from the electricity spot market over a past period, including time-series data such as historical transaction prices, transaction volumes, and market clearing results. Examples include market clearing prices every 15 minutes over the past three months and the declared electricity volumes of each market participant. Market forecast data represents future market operating conditions predicted based on historical data. This mainly includes price forecasts and price fluctuation range forecasts for various future periods, such as predicting the market clearing price and its confidence interval for each period within the next 24 hours. Price-sensitive periods refer to times when market prices fluctuate significantly or when price levels have a significant impact on bidding strategies, such as periods where price fluctuations exceed 30% of the average or when prices are at extremely high or low levels.

[0033] Specifically, the process begins by acquiring historical market data from electricity market trading platforms or databases. This data typically includes price and electricity volume information for multiple trading days, organized in a time-series format. Next, the historical market data undergoes preprocessing, including data cleaning, outlier detection, and missing value imputation, to ensure data quality meets forecasting requirements. Then, a suitable forecasting model is selected to analyze and learn from the historical market data. This model can be a time-series model, a machine learning model, or a deep learning model. By inputting historical prices and relevant influencing factors, it outputs predicted prices for future periods and the range of prediction errors, thus generating market forecast data. Subsequently, the market forecast data is analyzed, calculating indicators such as price volatility and relative price levels for each period. Price-sensitive periods are then identified based on pre-defined rules or thresholds. These rules can be based on a comprehensive judgment across multiple dimensions, including price volatility, absolute price level, or price change rate.

[0034] In some embodiments, market forecast data generation and price-sensitive period identification can be achieved through various methods. Optionally, a time-series analysis-based approach is employed. First, historical market price data undergoes stationarity testing and differencing. Then, an autoregressive moving average model or a seasonal model is established. A forecast model is obtained through parameter estimation and model fitting. Finally, this model is used to predict prices for future periods and calculate the forecast interval. Price-sensitive periods are identified based on the width of the forecast interval and the price level. Optionally, a machine learning-based approach is used. First, characteristic variables from historical market data are extracted, including time features, price statistical features, and load features. Then, a model such as a random forest or gradient boosting tree is trained for price forecasting. The predicted values ​​output by the model and feature importance analysis are used to identify periods that significantly impact prices. Finally, a forecast uncertainty index is combined to determine price-sensitive periods. It is understood that other methods can also be used to achieve market forecasting and price-sensitive period identification, such as deep learning methods based on neural networks or rule-based methods based on expert experience; these are not limited here.

[0035] S103: Generate a composite reporting curve based on physical baselines, market forecast data, and price-sensitive periods.

[0036] The composite declaration curve represents the combined curve of the electricity volume and price declared by the energy storage system to the electricity market at various points in time. This curve comprehensively considers physical operating constraints, market price forecasts, and price fluctuation characteristics, including the declared electricity volume and corresponding declared price at each time point. For example, the declared electricity volume for a certain period is 300 kilowatts, and the declared price is 0.5 yuan per kilowatt-hour. The composite declaration curve is the core decision-making basis for the energy storage system to participate in market transactions. It must not only meet the constraints of the physical baseline but also be dynamically adjusted according to market forecast data and the characteristics of price-sensitive periods.

[0037] Specifically, firstly, the adjustable power range of the energy storage system at each time point is determined based on a physical baseline. This range is limited by energy storage capacity and power constraints. Then, a basic declaration curve is generated by combining price forecasts from market forecast data. This basic declaration curve is typically initially set according to the principle of increasing discharge declarations during high-price periods and increasing charging declarations during low-price periods. Next, differentiated processing is applied to identified price-sensitive periods. For high-fluctuation periods within price-sensitive periods, the declared power is reduced based on the flexible adjustment capacity and a preset risk control coefficient to mitigate the uncertainty risk caused by price fluctuations. For low-fluctuation periods within price-sensitive periods, the declared power is increased based on the flexible adjustment capacity and a preset profit optimization coefficient to fully utilize profit opportunities during stable price periods. Subsequently, the local price average and local price fluctuation amplitude of price-sensitive periods are calculated. Based on these statistical characteristics and risk control coefficients, upper and lower price constraint limits are set, and the declaration curve is finely adjusted according to preset power adjustment rules. Finally, the flexible declaration curve adjusted by risk control is integrated with the basic declaration curve to obtain a comprehensive declaration curve.

[0038] In some embodiments, the comprehensive declaration curve can be generated in several ways. Optionally, a hierarchical optimization method is adopted. First, in the first layer of optimization, a basic declaration curve is solved based on the physical baseline and market forecast data. The objective function is to maximize the expected return, and the constraints are physical constraints and market rule constraints. Then, in the second layer of optimization, risk adjustment is performed for price-sensitive periods. A risk penalty term is introduced, and the declared electricity volume is adjusted according to price fluctuation characteristics. Finally, the results of the two layers of optimization are merged to obtain the comprehensive declaration curve. Optionally, a scenario-based analysis method is adopted. First, multiple price scenarios are generated based on market forecast data. Each scenario corresponds to a possible price trend. Then, the optimal declaration curve is calculated for each price scenario. Next, the declaration curves under each scenario are weighted and averaged. The weights are determined by the probability of scenario occurrence and the importance of price-sensitive periods. Finally, a comprehensive declaration curve considering multiple scenarios is obtained. It is understood that other methods can also be used to generate the comprehensive declaration curve, such as dynamic decision-making methods based on reinforcement learning or intelligent adjustment methods based on fuzzy control. This is not limited here.

[0039] like Figure 2 As shown, Figure 2 This diagram illustrates the generation process of a comprehensive declaration curve provided in this application embodiment. Using declared electricity volume as the horizontal axis and declared price as the vertical axis, the diagram showcases the optimization and evolution of the declaration strategy through four curves of different line types. The bottom solid line represents the basic declaration curve, directly generated from physical baselines and market forecast data, exhibiting a basic pattern of increasing price as electricity volume increases. After identifying price-sensitive periods, the system reduces declared electricity volume during periods of high volatility based on flexible adjustment capacity and risk control coefficients to mitigate risk, and increases declared electricity volume during periods of low volatility based on profit optimization coefficients to seize profit opportunities, forming an initial flexible declaration curve represented by a dashed line. The system then calculates the local price average and volatility during price-sensitive periods, setting two horizontal dashed lines (upper and lower limits) for price constraints as marked in the diagram. Electricity volume exceeding the upper limit in the initial flexible declaration curve is reduced, while electricity volume below the lower limit is increased, generating a target flexible declaration curve represented by a dashed line. Finally, the target flexible declaration curve is merged with the basic declaration curve according to preset weights to obtain a comprehensive declaration curve marked with a thick solid line. This curve takes into account physical constraints, market opportunity capture, and risk boundary control, achieving a multi-dimensional optimized declaration strategy.

[0040] S104: Obtain the preset risk model parameters, and calculate the expected return value and conditional risk value based on the comprehensive declaration curve and the risk model parameters.

[0041] Risk model parameters refer to various parameters required in the model used to quantify market transaction risk, including confidence level, number of scenarios, and price fluctuation distribution parameters. For example, the confidence level is set at 95%, and the number of scenarios is 1000. Expected return value represents the expected return of the energy storage system after participating in market transactions according to the comprehensive reporting curve. It is usually obtained by probability-weighted summation of returns under multiple price scenarios; for example, the expected return value is 10,000 yuan. Conditional value of risk represents the expected maximum loss that may be suffered when the market price fluctuates adversely at a given confidence level. This indicator comprehensively considers the degree of loss under extremely adverse scenarios; for example, the conditional value of risk is 2000 yuan at a 95% confidence level.

[0042] Specifically, the process begins by acquiring pre-defined risk model parameters. These parameters are typically pre-set and stored in the system configuration file based on historical market data statistical characteristics and risk management requirements. Then, based on the composite bid curve and market forecast data, multiple market price scenarios are constructed. Each scenario represents a possible price realization path. Scenario generation can be achieved through Monte Carlo simulation or a scenario tree method based on historical data. Next, for each price scenario, the payout value is calculated based on the bid volume in the composite bid curve and the price within the scenario. The payout value calculation considers the relationship between the bid volume and the market clearing volume, as well as the actual transaction price. Subsequently, the payout values ​​under all scenarios are weighted and averaged according to the probability of occurrence of each scenario to obtain the expected payout value. For the calculation of conditional value of risk, a quantile is first determined based on the confidence level. For example, a 95% confidence level corresponds to a 5% worst-case scenario. Then, all scenarios with payout values ​​below this quantile are selected, and the average loss of payout values ​​under these unfavorable scenarios is calculated. This average loss is the conditional value of risk.

[0043] In some embodiments, the expected return and conditional value of risk can be calculated in various ways. Optionally, a Monte Carlo simulation-based method is used. First, a large number of price scenarios are randomly generated based on the price volatility distribution parameters in the risk model parameters. Each scenario contains the realized price values ​​for each future time period. Then, the return is calculated for each scenario based on the composite reporting curve. The expected return is obtained by averaging the returns of all scenarios, and the conditional value of risk is obtained by calculating the conditional expectation of the returns of scenarios below the confidence level quantile. Optionally, a historical scenario backtesting method is used. First, several representative price time series are extracted from historical market data as scenario samples. Then, the composite reporting curve is applied to these historical scenarios to calculate the actual return under each historical scenario. The expected return is obtained by statistically analyzing the historical scenario returns, and the conditional value of risk is obtained by identifying several of the most unfavorable historical scenarios and calculating their average loss. It is understood that other methods can also be used to calculate risk indicators, such as analytical calculation methods based on parametric risk models or extreme scenario analysis methods based on stress testing; these are not limited here.

[0044] S105: When the conditional risk value exceeds the preset risk tolerance threshold, the composite declaration curve is adjusted, and the target risk value is calculated based on the adjusted composite declaration curve until the target risk value does not exceed the risk tolerance threshold.

[0045] The risk tolerance threshold refers to the maximum risk loss limit that market participants can accept. This threshold is pre-set based on the risk appetite and financial capacity of the energy storage system operator. For example, a risk tolerance threshold of 1,500 yuan means that the maximum acceptable conditional risk value does not exceed 1,500 yuan. The target risk value represents the conditional risk value corresponding to the adjusted composite declaration curve. This value needs to meet the requirement of not exceeding the risk tolerance threshold. The target risk value is gradually reduced to an acceptable range through iterative adjustments to the composite declaration curve.

[0046] Specifically, the calculated conditional risk value is first compared with a preset risk tolerance threshold to determine if it exceeds the threshold. If the conditional risk value does not exceed the threshold, no adjustment is needed, and the current comprehensive declaration curve meets the risk requirements. If the conditional risk value exceeds the threshold, the comprehensive declaration curve needs to be adjusted to reduce risk. The adjustment first calculates the deviation between the conditional risk value and the risk tolerance threshold, reflecting the degree of risk exceeding the limit. Then, a risk adjustment coefficient is calculated based on the deviation. The risk adjustment coefficient is positively correlated with the deviation; the larger the deviation, the larger the adjustment coefficient. The adjustment coefficient can be calculated using a linear or non-linear relationship. Next, the declared electricity volume during price-sensitive periods in the comprehensive declaration curve is adjusted according to the risk adjustment coefficient. Specifically, the declared electricity volume at each time point during the price-sensitive period is extracted, and the electricity reduction value at each time point is calculated based on the risk adjustment coefficient. The electricity reduction value is equal to the product of the original declared electricity volume and the risk adjustment coefficient. Then, the corresponding electricity reduction value is subtracted from the declared electricity volume at each time point to obtain the adjusted declared electricity volume. Finally, the adjusted declared electricity volume is updated in the comprehensive declaration curve to obtain the adjusted comprehensive declaration curve. Next, the target risk value is recalculated based on the adjusted composite reporting curve and risk model parameters, using the same method as the conditional risk value calculation in step S104. Finally, it is determined again whether the target risk value exceeds the risk tolerance threshold. If it still exceeds it, the above adjustment process is repeated until the target risk value does not exceed the risk tolerance threshold.

[0047] In some embodiments, risk adjustment of the comprehensive declaration curve can be achieved in several ways. Optionally, an iterative optimization method based on gradient descent can be used. First, an optimization problem is constructed with the target risk value as the optimization objective and the risk tolerance threshold as the constraint. Then, the gradient or sensitivity of the target risk value relative to the declared electricity volume in each time period is calculated. The declared electricity volume is adjusted according to the gradient direction and step size parameters. The target risk value is recalculated, and the constraint satisfaction is checked. This process is iteratively executed until the target risk value meets the constraint conditions. Optionally, a heuristic method based on piecewise adjustment can be used. First, several price-sensitive time periods that contribute the most to the conditional risk value are identified. These time periods are usually the periods with the most drastic price fluctuations or the largest declared electricity volume. Then, the declared electricity volume in these high-contribution time periods is adjusted first. After each adjustment, the target risk value is recalculated. If the target risk value still exceeds the threshold, the next highest contribution time period is adjusted, and the adjustment range is gradually expanded until the target risk value meets the requirements. It is understood that other methods can also be used to achieve risk adjustment, such as a fast convergence method based on binary search or a Pareto front search method based on multi-objective optimization; these are not limited here.

[0048] S106: Output the final reporting strategy, which includes the adjusted composite reporting curve, physical baseline, expected return value, and target risk value.

[0049] The final application strategy refers to the complete application plan after physical constraint verification, market forecast optimization, and risk control adjustment. This strategy includes multiple components such as the comprehensive application curve, physical baseline, expected return value, and target risk value, providing a decision-making basis for the energy storage system to participate in electricity market transactions. For example, the final application strategy includes information such as the application power curve for each period in the next 24 hours, physical operating baseline, expected return of 10,000 yuan, and target risk value of 1,200 yuan.

[0050] Specifically, after completing the risk adjustment of the composite reporting curve and ensuring that the target risk value meets the risk tolerance threshold, the system begins to generate the final reporting strategy. First, it integrates information such as the risk-adjusted composite reporting curve, the physical baseline on which the curve is based, the calculated expected return value, and the target risk value that meets risk constraints. Then, following the format and specifications required for electricity market reporting, this information is organized into a structured reporting strategy file or data package. This file typically includes time-related information, reported electricity volume and price information for each time period, physical baseline data, and risk-return indicators. Next, the generated final reporting strategy undergoes a completeness and consistency check to ensure that the relationship between the composite reporting curve and the physical baseline is reasonable, and that the calculations of the expected return value and the target risk value are accurate. Finally, the final reporting strategy is output through the system output interface. The output method can be in various forms, such as generating a report file, writing data to a database, transmitting data to the market reporting system via an interface, or displaying it on the user interface.

[0051] In some embodiments, the final declaration strategy can be output in several ways. Optionally, a report-based approach can be used. First, a declaration strategy document is created based on a predefined report template. This document includes text descriptions, data tables, and visualization charts. Then, the comprehensive declaration curve is displayed as a line graph, the physical baseline as a comparison curve, and the expected return and target value at risk as key indicators. Next, explanatory information and risk warnings about the strategy generation process are added. Finally, the complete report document is output and archived in PDF or HTML format. Optionally, a data interface-based approach can be used. First, the data in the final declaration strategy is converted to the format according to the interface specifications of the market trading system, typically using standard data formats such as JSON or XML. Then, a communication connection is established with the electricity market declaration platform, and the declaration strategy data is transmitted to the market system via API interface or message queue. Then, confirmation information or error messages returned by the market system are received, and the declaration status is recorded or anomalies are handled based on the feedback. It is understood that other methods can also be used to output the final declaration strategy, such as push notifications based on mobile applications or interactive output based on manual review; these are not limited here.

[0052] Based on the above embodiments, as an optional embodiment, S101: the step of generating a physical baseline based on physical constraint data and energy storage system parameters may specifically include the following steps: S201: Extract load demand data, distributed power output data, and energy storage configuration data from physical constraint data.

[0053] Load demand data refers to the electrical power consumed by electrical equipment in the power system at various points in time, organized in time series format. For example, the load power sequence for every 15 minutes from 0:00 to 24:00 on a certain day is [450 kW, 430 kW, ..., 520 kW]. Distributed power generation output data refers to the power generation data of distributed generation equipment at various points in time, including the output of renewable energy sources such as photovoltaic and wind power. For example, the output sequence of photovoltaic power from 8:00 to 18:00 is [50 kW, 120 kW, ..., 80 kW]. Energy storage configuration data refers to the technical parameters and configuration information of energy storage equipment, including the rated capacity, rated power, and initial state of charge of the energy storage system. For example, the energy storage capacity is 1000 kWh, the rated power is 500 kW, and the initial state of charge is 50%.

[0054] When extracting the above three types of data from physical constraint data, the process begins by accessing the physical constraint database or data file. Based on the data field identifiers, the data table or data segment containing the load demand data is located. The load power time series within the specified time range is read and stored as an array or list structure. Next, the data table containing the distributed power source output data is located. The output time series of each distributed power source is extracted according to power source type and time dimension. For multiple distributed power sources, the output data of each power source is extracted separately, and the power source type is labeled. Then, the parameter table containing the energy storage configuration data is located. Key parameters such as the rated capacity, rated power, charge / discharge efficiency, and initial state of charge of the energy storage system are extracted and organized into structured configuration data objects. After extraction, the extracted data undergoes an integrity check to confirm that the data timestamps are aligned, the numerical range is reasonable, and there are no missing or outlier values.

[0055] S202: Calculate the net physical demand baseline based on load demand data and distributed power generation output data, and calculate the flexible regulation capacity based on load demand data and distributed power generation output data.

[0056] The net physical demand baseline refers to the net load demand time series after deducting the output of distributed generation, reflecting the actual electricity demand that needs to be obtained from the grid or energy storage system at each point in time. Flexible regulation capacity refers to the adjustable power range of the energy storage system at each point in time under physical constraints, including upward and downward regulation capacity. For example, the upward regulation capacity might be 200 kW and the downward regulation capacity 150 kW at a certain time period.

[0057] When calculating the net physical demand baseline, the load demand data and distributed generation output data are iterated through each time point. For each time point t, the calculated net physical demand baseline value is equal to the load demand data value at time point t minus the distributed generation output data value at time point t, i.e., net physical demand baseline [t] = load demand [t] - distributed generation output [t]. The calculation results for all time points are then combined to form the net physical demand baseline time series. When calculating the flexible regulation capacity, the load fluctuation amplitude at each time point is first calculated. This is done by calculating the absolute value of the difference between the load demand data at time point t and the adjacent time points t-1 and t+1, and taking the maximum value as the load fluctuation amplitude at that time point. Then, the distributed generation output fluctuation amplitude is calculated, using the same method to calculate the maximum absolute value of the difference between the distributed generation output at time point t and the adjacent time points. Next, the upward adjustment capacity is calculated, which is equal to the sum of the load fluctuation amplitude and the output fluctuation amplitude of the distributed power source multiplied by the safety margin coefficient. The downward adjustment capacity is calculated in the same way. The safety margin coefficient is usually between 1.1 and 1.3 to ensure that the adjustment capacity has sufficient margin, thus obtaining the flexible adjustment capacity.

[0058] S203: Generate a preliminary energy storage scheduling plan based on the net physical demand baseline, flexible adjustment capacity, and energy storage configuration data.

[0059] The preliminary energy storage dispatch plan refers to the time series of charging and discharging power of the energy storage system determined based on the net physical demand baseline and flexible adjustment capacity. This plan has not yet been rigorously verified by the physical constraints of the energy storage system and includes the charging or discharging power of the energy storage system at each time point. For example, the charging power is -200 kW at one time period and the discharging power is 300 kW at another time period. Negative values ​​indicate charging and positive values ​​indicate discharging.

[0060] When generating a preliminary energy storage dispatch plan, the power surplus / deficit status at each time point is first identified based on the net physical demand baseline. A positive net physical demand baseline value indicates a power shortage, while a negative value indicates a power surplus. Then, the upper limit of the energy storage system's charging and discharging power is determined based on the rated power in the energy storage configuration data. For periods of power shortage, the energy storage system's discharging power is set to the sum of the net physical demand baseline value and the upward adjustment portion of the flexible regulation capacity, but not exceeding the rated power of the energy storage. For periods of power surplus, the energy storage system's charging power is set to the sum of the absolute value of the net physical demand baseline value and the downward adjustment portion of the flexible regulation capacity, but not exceeding the rated power of the energy storage. Next, based on the initial state of charge (SOC) in the energy storage configuration data, the energy storage charging and discharging amounts are accumulated point by point to calculate the SOC at each time point. The SOC increases during charging and decreases during discharging. The change in SOC is equal to the charging / discharging power multiplied by the time interval and then by the charging / discharging efficiency. Finally, the energy storage charging and discharging power at each time point is organized into a time series to form the preliminary energy storage dispatch plan.

[0061] S204: Extract feasible ranges for energy storage capacity and energy storage power from the energy storage system parameters; perform constraint verification on the preliminary energy storage scheduling plan based on the feasible ranges for energy storage capacity and energy storage power to obtain the energy storage scheduling plan; and revise the net physical demand baseline based on the energy storage scheduling plan to obtain the physical baseline.

[0062] The feasible range of energy storage capacity refers to the range of allowed state of charge (SOC) of the energy storage system, determined by a lower and upper capacity limit, such as a lower limit of 100 kWh and an upper limit of 900 kWh. The feasible range of energy storage power refers to the range of allowed charging and discharging power of the energy storage system, determined by an upper limit of charging power and an upper limit of discharging power, such as an upper limit of -500 kW and an upper limit of 500 kW. Constraint verification refers to the process of checking whether the preliminary energy storage dispatch plan meets the energy storage capacity and power constraints, and correcting any violations. The energy storage dispatch plan is the time series of energy storage charging and discharging power that meets all physical constraints after constraint verification and correction.

[0063] When extracting the feasible range of energy storage capacity from the energy storage system parameters, the maximum and minimum capacity values ​​are read. The maximum capacity value is typically equal to the rated energy storage capacity multiplied by the maximum allowable state of charge (SOC) percentage, and the minimum capacity value is equal to the rated energy storage capacity multiplied by the minimum allowable SOC percentage. When extracting the feasible range of energy storage power, the upper limits of charging and discharging power are read. During constraint verification, the system first iterates through each time point of the preliminary energy storage scheduling plan, calculates the SOC at each time point based on the charging and discharging power in the preliminary energy storage scheduling plan, and checks whether the SOC and charging / discharging power are within the feasible range of energy storage capacity and power. For time points that violate capacity constraints, the charging and discharging power at that time point and subsequent time points are adjusted to bring the SOC back to the feasible range. The adjustment method is to reduce the charging power or increase the discharging power when the SOC exceeds the capacity upper limit, and reduce the discharging power or increase the charging power when the SOC is below the capacity lower limit. For time points that violate power constraints, the charging and discharging power is directly limited to the feasible power range. After adjustments, an energy storage dispatch plan that satisfies all constraints is obtained. When correcting the net physical demand baseline based on the energy storage dispatch plan, for each time point, the corrected physical baseline value is calculated as the net physical demand baseline value minus the charging and discharging power in the energy storage dispatch plan. The corrected values ​​for all time points are then combined to form the physical baseline.

[0064] Based on the above embodiments, as an optional embodiment, S103: the step of generating a composite order curve based on physical baselines, market forecast data, and price-sensitive periods may specifically include the following steps: S301: Generate a basic reporting curve based on physical baselines and market forecast data.

[0065] Market forecast data refers to the time series of electricity price forecasts at various points in time in the electricity market, including price forecasts for the day-ahead market and the real-time market. For example, the hourly electricity price forecast series from 0:00 to 24:00 on a certain day might be [0.45 yuan / kWh, 0.42 yuan / kWh, ..., 0.58 yuan / kWh]. The basic bidding curve refers to the curve showing the correspondence between the declared electricity volume and the declared price at each point in time, generated based on the physical baseline and price forecasts. It reflects the initial market bidding strategy, for example, a declared electricity volume of 500 kWh and a declared price of 0.50 yuan / kWh for a certain period.

[0066] When generating the basic declaration curve, the physical baseline time series and market forecast data time series are first read to ensure alignment in time dimension. Then, each time point is iterated through. For each time point t, the physical baseline value is used as the basic declared electricity volume for that time point, and the predicted price in the market forecast data for that time point is used as the basic declared price, forming a declared electricity volume-price pair. Next, the declaration pairs for each time point are sorted according to the declared price pair, arranged from low to high, constructing a stepped declaration curve. For multiple time points at the same price level, their declared electricity volumes are accumulated and merged. Finally, the declared electricity volume-price pairs are organized into a curve data structure, with the horizontal axis representing the cumulative declared electricity volume and the vertical axis representing the corresponding declared price, forming the basic declaration curve.

[0067] S302: During periods of high volatility in price-sensitive periods, the declared electricity volume at each time point in the high volatility period is reduced based on the flexible adjustment capacity and the preset risk control coefficient. During periods of low volatility in price-sensitive periods, the declared electricity volume at each time point in the low volatility period is increased based on the flexible adjustment capacity and the preset profit optimization coefficient, thus obtaining the initial flexible declaration curve.

[0068] Price-sensitive periods refer to times when price fluctuations are significant or price levels exceed the normal range, identified by price standard deviation or price thresholds, such as periods where prices exceed the mean plus one standard deviation. High-volatility periods refer to price-sensitive periods where price volatility exceeds a preset volatility threshold, such as periods with price volatility greater than 20%. Low-volatility periods refer to price-sensitive periods where price volatility is below a preset volatility threshold, such as periods with price volatility less than 5%. The preset risk control coefficient is a parameter used to adjust the reduction in declared electricity volume, with a value ranging from 0 to 1, for example, 0.3. The preset profit optimization coefficient is a parameter used to adjust the increase in declared electricity volume, with a value ranging from 0 to 1, for example, 0.2.

[0069] First, price-sensitive periods are identified. Market forecast data is traversed, and the price mean and standard deviation are calculated. When the price at a certain point in time exceeds the mean plus the standard deviation or falls below the mean minus the standard deviation, that point in time is marked as a price-sensitive period. Then, within the price-sensitive periods, high-volatility and low-volatility periods are identified. Price volatility at each point in time is calculated. Volatility equals the absolute value of the difference between the price at that point and the price at the previous point in time, divided by the price at the previous point in time. When volatility exceeds a volatility threshold, it is marked as a high-volatility period; when volatility is below the volatility threshold, it is marked as a low-volatility period. For each point in a high-volatility period, the adjustment amount for the declared electricity volume is calculated as the downward adjustment capacity in the flexible adjustment capacity multiplied by a preset risk control coefficient. The declared electricity volume at that point in the basic declaration curve is subtracted by the adjustment amount, resulting in a reduction in declared electricity volume. For each point in a low-volatility period, the adjustment amount for the declared electricity volume is calculated as the upward adjustment capacity in the flexible adjustment capacity multiplied by a preset return optimization coefficient. The declared electricity volume at that point in the basic declaration curve is added by the adjustment amount, resulting in an increase in declared electricity volume. After adjustment, all declared electricity volume-price pairs at all points in time are reorganized into a curve form to obtain the initial flexible declaration curve.

[0070] S303: Adjust the initial flexible reporting curve based on market forecast data and price-sensitive periods to obtain the target flexible reporting curve; combine the target flexible reporting curve with the basic reporting curve to obtain the composite reporting curve.

[0071] The target flexible reporting curve refers to an optimized reporting strategy obtained by further adjusting the initial flexible reporting curve to be price-oriented. This curve is finely adjusted during price-sensitive periods, such as further increasing discharge reporting during high-price periods and further increasing charging reporting during low-price periods. The composite reporting curve refers to the final market reporting strategy obtained by merging the target flexible reporting curve and the basic reporting curve according to certain weights, taking into account both physical constraints and market opportunities. For example, the composite reporting curve may be the sum of 60% of the reporting volume of the basic reporting curve and 40% of the reporting volume of the target flexible reporting curve for a certain period.

[0072] When adjusting the initial flexible reporting curve, the process first iterates through each time point in the price-sensitive period, reading the price values ​​from the market forecast data. For periods where prices are higher than the average price, the physical baseline is determined to be positive or negative. If the physical baseline is positive, indicating a need to purchase electricity from the market, the reported electricity volume at that time point is reduced to decrease the cost of purchasing electricity at high prices. The reduction is equal to the current reported electricity volume multiplied by the price deviation, where the price deviation is equal to the price at that time point minus the average price, then divided by the average price. If the physical baseline is negative, indicating a need to sell electricity to the market, the reported electricity volume at that time point is increased to increase the revenue from selling electricity at high prices. The increase is equal to the current reported electricity volume multiplied by the price deviation. For periods where prices are lower than the average price, if the physical baseline is positive, the reported electricity volume is increased to take advantage of purchasing electricity at low prices; if the physical baseline is negative, the reported electricity volume is reduced to avoid selling electricity at low prices. After adjustment, the target flexible reporting curve is obtained. When combining the target flexible declaration curve and the basic declaration curve, a fusion weight is set, with the basic declaration curve weight being 0.6 and the target flexible declaration curve weight being 0.4. For each time point, the comprehensive declared electricity volume is calculated as the basic declaration curve electricity volume multiplied by 0.6 plus the target flexible declaration curve electricity volume multiplied by 0.4. The comprehensive declaration price is the weighted average of the declaration prices of the two curves. The comprehensive declared electricity volume-price pairs of all time points are organized into a comprehensive declaration curve.

[0073] Based on the above embodiments, as an optional embodiment, S303: the step of adjusting the initial flexible reporting curve based on market forecast data and price-sensitive periods to obtain the target flexible reporting curve may specifically include the following steps: S401: Calculate the local average price and local price fluctuation range during price-sensitive periods based on market forecast data; calculate the upper limit and lower limit of price constraints based on the local average price, local price fluctuation range, and preset risk control coefficient.

[0074] The local price mean refers to the arithmetic mean of prices at all points in time within a price-sensitive period, reflecting the central price level of that period. For example, if a price-sensitive period includes 10 points in time with a total price of 5.5 yuan / kWh, then the local price mean is 0.55 yuan / kWh. Local price volatility refers to the dispersion of price changes within a price-sensitive period, expressed as the price standard deviation, for example, a standard deviation of 0.08 yuan / kWh. The upper limit of the price constraint refers to the maximum allowed price for a bid, used to limit the risk of high-price bids. The lower limit of the price constraint refers to the minimum allowed price for a bid, used to limit the losses of low-price bids. The preset risk control coefficient is a parameter used to adjust the width of the price constraint range, with a value ranging from 0 to 3, for example, 1.5.

[0075] When calculating the local price mean, firstly, market forecast data for all time points within the price-sensitive period is extracted, these price values ​​are summed, and then divided by the total number of time points to obtain the local price mean. When calculating the local price volatility, for each time point within the price-sensitive period, the difference between that time point's price and the local price mean is calculated. All differences are squared and summed, then divided by the total number of time points minus 1. Finally, the square root of the result is taken to obtain the local price volatility, i.e., the price standard deviation. When calculating the upper limit of price constraints, the local price mean is added to the product of the local price volatility and a preset risk control coefficient; that is, the upper limit of price constraints equals the local price mean plus the local price volatility multiplied by the preset risk control coefficient. When calculating the lower limit of price constraints, the local price mean is subtracted from the product of the local price volatility and the preset risk control coefficient; that is, the lower limit of price constraints equals the local price mean minus the local price volatility multiplied by the preset risk control coefficient. When the calculation result is negative, the lower limit of price constraints is set to zero.

[0076] S402: According to the preset power adjustment rules, reduce the declared power volume that exceeds the price constraint upper limit during the price-sensitive period of the initial flexible declaration curve to the declared power volume corresponding to the price constraint upper limit, and increase the declared power volume that is lower than the price constraint lower limit to the declared power volume corresponding to the price constraint lower limit, so as to obtain the target flexible declaration curve.

[0077] Electricity adjustment rules are a set of rules defining how declared electricity volume is adjusted according to price constraints. These rules include reduction and increase rules, specifying the adjustment methods for electricity volume within different price ranges. The declared electricity volume corresponding to the upper price constraint limit refers to the declared electricity volume value when the price equals the upper price constraint limit in the initial flexible declaration curve. This is obtained by finding the horizontal axis corresponding to the upper price constraint limit on the declaration curve. For example, when the upper price constraint limit is 0.70 yuan / kWh, the corresponding declared electricity volume is 400 kWh. The declared electricity volume corresponding to the lower price constraint limit refers to the declared electricity volume value when the price equals the lower price constraint limit in the initial flexible declaration curve. For example, when the lower price constraint limit is 0.40 yuan / kWh, the corresponding declared electricity volume is 600 kWh.

[0078] The algorithm iterates through each reporting point on the initial flexible reporting curve during the price-sensitive period. For each reporting point, it reads the reported price and reported electricity volume. It then determines whether the reported price exceeds the upper price constraint limit. If the reported price exceeds the upper price constraint limit, it finds the position on the initial flexible reporting curve where the price equals the upper price constraint limit, calculates the reported electricity volume corresponding to that price level using linear interpolation, replaces the reported electricity volume of the current reporting point with that value, and corrects the reported price to the upper price constraint limit. Next, it determines whether the reported price is below the lower price constraint limit. If the reported price is below the lower price constraint limit, it finds the position on the initial flexible reporting curve where the price equals the lower price constraint limit, calculates the reported electricity volume corresponding to that price level using linear interpolation, replaces the reported electricity volume of the current reporting point with that value, and corrects the reported price to the lower price constraint limit. The linear interpolation calculation method is as follows: Let the prices of two adjacent reporting points be P1 and P2, and their corresponding electricity volumes be Q1 and Q2, respectively. The target price is P. Then, the corresponding electricity volume Q is equal to Q1 plus the difference between Q2 and Q1 multiplied by the difference between P and P1, and then divided by the difference between P2 and P1. All the adjusted declaration points are reorganized into a curve to obtain the target flexible declaration curve.

[0079] Based on the above embodiments, as an optional embodiment, S105: the step of adjusting the composite declaration curve according to the conditional risk value exceeding the preset risk tolerance threshold, and calculating the target risk value based on the adjusted composite declaration curve, may specifically include the following steps: S501: When the conditional risk value exceeds the preset risk tolerance threshold, a risk adjustment coefficient is calculated based on the deviation between the conditional risk value and the risk tolerance threshold.

[0080] Conditional Value at Risk (VaR) is the expected loss exceeding the risk value at a given confidence level. It measures risk exposure under extremely adverse conditions. For example, a VaR of 12,000 yuan at a 95% confidence level means an average loss of 12,000 yuan in the worst-case 5% scenario. The risk tolerance threshold is a preset maximum acceptable risk level, set according to risk preference; for example, a risk tolerance threshold of 8,000 yuan. The deviation value is the difference between the VaR and the risk tolerance threshold, used to quantify the degree of risk exceeding the limit; for example, a deviation value of 4,000 yuan. The risk adjustment factor is a coefficient used to adjust the declared electricity volume to reduce risk, ranging from 0 to 1, with a larger value indicating a larger adjustment.

[0081] First, the conditional risk value is compared with the risk tolerance threshold to determine if the conditional risk value exceeds the risk tolerance threshold. When the conditional risk value exceeds the risk tolerance threshold, the deviation value is calculated as the conditional risk value minus the risk tolerance threshold. Then, a risk adjustment factor is calculated based on the deviation value, which is equal to the deviation value divided by the conditional risk value. This calculation method ensures that the risk adjustment factor reflects the relative extent of risk exceeding the limit. An upper limit constraint is applied to the calculated risk adjustment factor; when the risk adjustment factor is greater than 1, it is set to 1 to ensure that the adjustment factor is within an effective range. A lower limit constraint is applied to the risk adjustment factor; when the risk adjustment factor is less than 0, it is set to 0. When the conditional risk value is less than or equal to the risk tolerance threshold, it indicates that the risk is within an acceptable range, and the risk adjustment factor is set to 0, with no risk adjustment performed.

[0082] S502: Adjust the declared electricity volume during price-sensitive periods in the comprehensive declaration curve according to the risk adjustment coefficient to obtain the adjusted comprehensive declaration curve.

[0083] The adjusted composite reporting curve is a risk-adjusted composite reporting curve. The reported electricity volume during price-sensitive periods has been reduced to lower risk exposure. For example, the reported electricity volume at a certain point in time has been adjusted from 500 kWh to 400 kWh.

[0084] Locate the bidding points corresponding to price-sensitive periods from the composite bidding curve, and iterate through these bidding points. For each bidding point within a price-sensitive period, read its current declared electricity value. Calculate the electricity adjustment amount for that bidding point based on the risk adjustment coefficient, which is calculated as the electricity adjustment amount equal to the current declared electricity multiplied by the risk adjustment coefficient. Calculate the adjusted declared electricity amount, which is equal to the current declared electricity amount minus the electricity adjustment amount; that is, the adjusted declared electricity amount equals the current declared electricity amount multiplied by 1 minus the risk adjustment coefficient. Update the declared electricity amount for that bidding point to the adjusted declared electricity amount, while keeping the declared price unchanged. For bidding points in non-price-sensitive periods, keep their declared electricity amount and declared price unchanged. Reorder all adjusted bidding points according to price from low to high, and update the cumulative declared electricity amount. For each price level, the cumulative declared electricity amount equals the sum of the declared electricity amounts corresponding to that price and all prices below it. Organize the updated bidding point sequence into a curve form to obtain the adjusted composite bidding curve.

[0085] S503: Recalculate the target risk value based on the adjusted composite reporting curve and risk model parameters.

[0086] Risk model parameters are a set of model parameters used to calculate the Value at Risk (VaR), including confidence level, price volatility, and electricity volatility, for example, a confidence level of 95% and a price volatility of 15%. The target VaR is the VaR recalculated using the adjusted composite reporting curve and is used to verify the effectiveness of risk adjustment.

[0087] Read the risk model parameters, including confidence level, volatility parameters from market forecast data, and historical price data. Extract the declared electricity volume and declared price for each time point from the adjusted composite declaration curve. For each time point, calculate the expected return based on the declared electricity volume and declared price; the expected return equals the declared electricity volume multiplied by the declared price. Calculate the distribution of realized price values ​​based on market forecast data and historical price data, and generate multiple price scenarios using Monte Carlo simulation, each scenario containing realized price values ​​for each time point. For each price scenario, calculate the actual return under that scenario; the actual return equals the sum of the declared electricity volume multiplied by the realized price values ​​for that scenario. Calculate the return deviation for each scenario; the return deviation equals the expected return minus the actual return. Sort all scenario return deviations from largest to smallest, and determine the quantile position of the Value at Risk (VaR) based on the confidence level; for example, at a 95% confidence level, the quantile position is the total number of scenarios multiplied by 5%. Extract the return deviation value corresponding to the quantile position; this value is the VaR. Calculate the conditional VaR, which equals the arithmetic mean of all return deviations greater than the VaR; use this conditional VaR as the target VaR.

[0088] Based on the above embodiments, as an optional embodiment, S502: the step of adjusting the declared electricity volume during the price-sensitive period in the comprehensive declaration curve according to the risk adjustment coefficient to obtain the adjusted comprehensive declaration curve may specifically include the following steps: S601: Extract the declared electricity volume at each time point during the price-sensitive period from the comprehensive declaration curve; calculate the electricity reduction value at each time point based on the risk adjustment coefficient and the declared electricity volume at each time point during the price-sensitive period.

[0089] The power reduction value is the amount of declared power that needs to be reduced at each point in time. It is used to reduce risk exposure during price-sensitive periods. For example, the power reduction value at a certain point in time is 100 kWh.

[0090] Access the data structure of the comprehensive declaration curve to locate the time range of price-sensitive periods. Iterate through each time point within the price-sensitive period. For each time point, find the corresponding declaration point in the comprehensive declaration curve, read the declared electricity value for that point, and store it in an array of time point indices. After extraction, obtain the declared electricity array for each time point within the price-sensitive period. Read the value of the risk adjustment coefficient. Iterate through each element in the declared electricity array. For each time point, calculate the electricity reduction value, calculated as the electricity reduction value equal to the declared electricity value multiplied by the risk adjustment coefficient. Store the calculated electricity reduction value in an array of electricity reduction values ​​corresponding to the declared electricity array, ensuring a one-to-one correspondence between array indices and time points. Verify the reasonableness of the electricity reduction value, checking if it is non-negative and does not exceed the corresponding declared electricity value. Correct any electricity reduction values ​​that do not meet the conditions: if the electricity reduction value is greater than the declared electricity value, set it as the declared electricity value; if the electricity reduction value is less than zero, set it to zero.

[0091] S602: Subtract the corresponding electricity reduction value from the declared electricity volume at each time point during the price-sensitive period to obtain the target declared electricity volume at each time point during the price-sensitive period; adjust the comprehensive declaration curve by combining the target declared electricity volume at each time point during the price-sensitive period to obtain the adjusted comprehensive declaration curve.

[0092] The target declared electricity volume is the declared electricity volume value at each time point after risk adjustment. This value is lower than the original declared electricity volume to reduce risk. For example, if the original declared electricity volume is 500 kWh and the electricity volume reduction value is 100 kWh, then the target declared electricity volume is 400 kWh.

[0093] Iterate through each time point in the price-sensitive period. For each time point, read the declared electricity volume and the corresponding electricity reduction value. Calculate the target declared electricity volume for that time point, which is equal to the declared electricity volume minus the electricity reduction value. Store the calculated target declared electricity volume in a target declared electricity volume array, with the array index corresponding to the time point. After completing the calculation for all time points, obtain the target declared electricity volume array for each time point in the price-sensitive period. Access the data structure of the comprehensive declaration curve and iterate through each declaration point within the price-sensitive period. For each declaration point, read the target declared electricity volume from the target declared electricity volume array according to its corresponding time point, update the declared electricity volume field of that declaration point to the target declared electricity volume, and keep the declared price field unchanged. For declaration points in non-price-sensitive periods, keep their declared electricity volume and declared price unchanged. Recalculate the cumulative declared electricity volume of the comprehensive declaration curve, starting from the declaration point with the lowest price, and accumulate the declared electricity volume of each declaration point, updating the cumulative declared electricity volume field of each declaration point. Verify the continuity and monotonicity of the adjusted comprehensive declaration curve, ensuring that the price in the curve increases monotonically with the cumulative declared electricity volume. Save the updated comprehensive declaration curve data to obtain the adjusted comprehensive declaration curve.

[0094] Based on the above embodiments, as an optional embodiment, S106: after the step of outputting the final declaration strategy including the adjusted comprehensive declaration curve, physical baseline, expected return value, and target risk value, the method further includes a step of generating a declaration strategy evaluation report, which may specifically include the following steps: S701: Generate time-segmented declaration instruction sets based on the adjusted comprehensive declaration curve; perform physical feasibility verification based on the physical baseline and the time-segmented declaration instruction sets.

[0095] The time-segmented declaration instruction set converts the comprehensive declaration curve into a set of specific declaration instructions for each time period. Each instruction includes information such as the time period identifier, the declared electricity volume, and the declared price. For example, the time period is 10:00-11:00, the declared electricity volume is 450 kWh, and the declared price is 0.52 yuan / kWh. Physical feasibility verification is the process of checking whether the declaration instructions meet physical constraints, including checking energy storage capacity constraints, power constraints, and power balance constraints.

[0096] Read the comprehensive declaration curve data and iterate through each declaration point in the curve. For each declaration point, read its corresponding time point, declared electricity volume, and declared price. Determine the corresponding time period based on the time point, and encapsulate the declared electricity volume and declared price into a declaration instruction object. The declaration instruction object contains a time period identifier field, a declared electricity volume field, and a declared price field. Add the generated declaration instruction objects to the time-segmented declaration instruction set, arranged in time period order. After completing the conversion of all declaration points, a complete time-segmented declaration instruction set is obtained. When performing physical feasibility verification, first read the physical baseline data to obtain the net physical demand value for each time period. Iterate through each declaration instruction in the time-segmented declaration instruction set. For each declaration instruction, read its declared electricity volume and compare the declared electricity volume with the physical baseline value for the corresponding time period. Calculate the deviation between the declared electricity volume and the physical baseline value; the deviation is equal to the absolute value of the declared electricity volume minus the physical baseline value. Read the energy storage system parameters, including the energy storage power limit and capacity limit. Determine whether the deviation of the declared electricity volume exceeds the energy storage power limit. If the deviation is greater than the energy storage power limit, mark the time period as a power constraint violation. Accumulate the reported electricity volume deviations for each time period and determine whether the cumulative deviation exceeds the energy storage capacity limit. If the cumulative deviation exceeds the energy storage capacity limit, it is marked as a capacity constraint violation. Summarize all constraint violation marks to generate a feasibility verification result.

[0097] S702: Generate an assessment report on the final application strategy based on the feasibility verification results, expected returns, and target risk value.

[0098] The feasibility verification result is the result of the physical feasibility verification, including information such as constraint satisfaction, time periods of constraint violation, and degree of violation. For example, the power constraint was violated in three time periods, with a maximum violation of 50 kilowatts. The expected revenue value is the expected revenue calculated based on the application strategy and price forecasts, for example, an expected daily revenue of 8,500 yuan. The evaluation report is a comprehensive assessment document of the final application strategy, including feasibility assessment, revenue assessment, risk assessment, and overall evaluation.

[0099] Read the feasibility verification results data, extract the number of time periods where constraints were violated, the types of violations (power constraint violation or capacity constraint violation), and the magnitude of violations in each time period. Calculate the constraint satisfaction rate, which is equal to the number of time periods where constraints were satisfied divided by the total number of time periods multiplied by 100%. Read the expected return value data, analyze the return distribution, calculate the return contribution of each time period, and identify high-return and low-return periods. Read the target risk value data, calculate the risk-return ratio, which is equal to the target risk value divided by the expected return value. Create an assessment report document structure, including a title, summary, detailed assessment, and conclusion. In the feasibility assessment section, record the constraint satisfaction rate, the list of time periods where constraints were violated, the statistics of violation magnitudes, and provide the feasibility assessment conclusion. In the return assessment section, record the expected return value, the distribution of return contributions in each time period, and the analysis of high-return periods, and provide the return assessment conclusion. In the risk assessment section, record the target risk value, the risk-return ratio, the analysis of risk-sensitive periods, and provide the risk assessment conclusion. The comprehensive evaluation section assesses feasibility, benefits, and risks, providing a final overall score for the application strategy. The score is calculated as follows: overall score = constraint fulfillment rate multiplied by 0.3 + normalized expected return value multiplied by 0.4 + risk score multiplied by 0.3. The risk score equals 1 minus the normalized risk-reward ratio. Evaluation recommendations are generated, including adjustment suggestions for constraint violations, improvement suggestions for benefit optimization, and preventative suggestions for risk control. All content is organized into a structured evaluation report document.

[0100] The following describes an exemplary device for optimizing an electricity reporting strategy, provided by an embodiment of this application. Figure 3 This is an exemplary hardware structure diagram of an energy reporting strategy optimization device provided in an embodiment of this application.

[0101] In some embodiments, the energy reporting strategy optimization device is a computer device or includes a computer device in the energy reporting strategy optimization device. The computer device includes a processor, memory, and a network interface connected via a system bus. The processor of the computer device provides computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database of the computer device stores data. The network interface of the computer device is used to communicate with other external terminals or servers via a network connection. In some embodiments, the network interface can be a wired network interface; in some embodiments, the network interface can also be a wireless network interface. When the computer program is executed by the processor, it implements the methods in the embodiments of this application.

[0102] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0103] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0104] As used in the above embodiments, depending on the context, the term "when..." can be interpreted as meaning "if...", "after...", "in response to determining...", or "in response to detecting...". Similarly, depending on the context, the phrase "when determining..." or "if (the stated condition or event) is interpreted as meaning "if determining...", "in response to determining...", "when (the stated condition or event) is detected", or "in response to detecting (the stated condition or event)".

[0105] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive), etc.

[0106] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for optimizing an electricity energy reporting strategy, characterized in that, The method includes: Acquire physical constraint data and energy storage system parameters of the energy storage system, and generate a physical baseline based on the physical constraint data and energy storage system parameters; Acquire historical market data, generate market forecast data based on the historical market data, and identify price-sensitive periods based on the market forecast data; A comprehensive order curve is generated based on the physical baseline, the market forecast data, and the price-sensitive period. Obtain preset risk model parameters, and calculate expected return and conditional value of risk based on the comprehensive declaration curve and the risk model parameters; When the conditional risk value exceeds the preset risk tolerance threshold, the comprehensive declaration curve is adjusted, and the target risk value is calculated based on the adjusted comprehensive declaration curve until the target risk value does not exceed the risk tolerance threshold. The output includes the adjusted composite reporting curve, the physical baseline, the expected return value, and the target risk value, resulting in a final reporting strategy.

2. The method for optimizing the electricity energy reporting strategy according to claim 1, characterized in that, The generation of a physical baseline based on the physical constraint data and the energy storage system parameters includes: Extract load demand data, distributed power output data, and energy storage configuration data from the physical constraint data; The net physical demand baseline is calculated based on the load demand data and the distributed power output data, and the flexible regulation capacity is calculated based on the load demand data and the distributed power output data. A preliminary energy storage scheduling plan is generated based on the net physical demand baseline, the flexible adjustment capacity, and the energy storage configuration data. Extract feasible ranges for energy storage capacity and energy storage power from the parameters of the energy storage system; The preliminary energy storage scheduling plan is constrained and verified based on the feasible range of energy storage capacity and the feasible range of energy storage power to obtain the energy storage scheduling plan. The net physical demand baseline is corrected according to the energy storage scheduling plan to obtain the physical baseline.

3. The method for optimizing the electricity energy reporting strategy according to claim 2, characterized in that, The generation of a comprehensive order curve based on the physical baseline, the market forecast data, and the price-sensitive period includes: A basic reporting curve is generated based on the physical baseline and the market forecast data; During the high volatility period of the price-sensitive period, the declared electricity volume corresponding to each time point in the high volatility period is reduced according to the flexible adjustment capacity and the preset risk control coefficient. During the low volatility period of the price-sensitive period, the declared electricity volume corresponding to each time point in the low volatility period is increased according to the flexible adjustment capacity and the preset profit optimization coefficient, so as to obtain the initial flexible declaration curve. The initial flexible reporting curve is adjusted based on the market forecast data and the price-sensitive period to obtain the target flexible reporting curve; By combining the target flexible declaration curve and the basic declaration curve, a comprehensive declaration curve is obtained.

4. The method for optimizing the electricity energy reporting strategy according to claim 3, characterized in that, The adjustment of the initial flexible reporting curve based on the market forecast data and the price-sensitive period to obtain the target flexible reporting curve includes: Calculate the local price average and local price fluctuation range for the price-sensitive period based on the market forecast data; Calculate the upper limit and lower limit of price constraints based on the local price average, the local price fluctuation range, and the preset risk control coefficient; According to the preset power adjustment rules, the power declared during the price-sensitive period that exceeds the upper limit of the price constraint is reduced to the power declared corresponding to the upper limit of the price constraint, and the power declared below the lower limit of the price constraint is increased to the power declared corresponding to the lower limit of the price constraint, so as to obtain the target flexible declaration curve.

5. The method for optimizing the electricity energy reporting strategy according to claim 1, characterized in that, The step of adjusting the composite declaration curve based on the conditional risk value exceeding a preset risk tolerance threshold, and calculating the target risk value based on the adjusted composite declaration curve, includes: When the conditional risk value exceeds a preset risk tolerance threshold, a risk adjustment coefficient is calculated based on the deviation between the conditional risk value and the risk tolerance threshold. The declared electricity volume during price-sensitive periods in the comprehensive declaration curve is adjusted according to the risk adjustment coefficient to obtain the adjusted comprehensive declaration curve; The target risk value is recalculated based on the adjusted composite reporting curve and the risk model parameters.

6. The method for optimizing the electricity energy reporting strategy according to claim 5, characterized in that, The step of adjusting the declared electricity volume during price-sensitive periods in the comprehensive declaration curve according to the risk adjustment coefficient to obtain the adjusted comprehensive declaration curve includes: Extract the declared electricity volume at each time point in the price-sensitive period from the comprehensive declaration curve; Calculate the electricity reduction value at each time point based on the risk adjustment coefficient and the declared electricity volume at each time point in the price-sensitive period; Subtract the corresponding electricity reduction value from the declared electricity volume at each time point during the price-sensitive period to obtain the target declared electricity volume at each time point during the price-sensitive period; The comprehensive declaration curve is adjusted by combining the target declared electricity volume at each time point during the price-sensitive period to obtain the adjusted comprehensive declaration curve.

7. The method for optimizing the electricity energy reporting strategy according to claim 1, characterized in that, The output, after including the adjusted composite reporting curve, the physical baseline, the expected return value, and the final reporting strategy based on the target value at risk, also includes: Generate a time-segmented declaration instruction set based on the adjusted comprehensive declaration curve; Physical feasibility verification is performed based on the physical baseline and the time-segmented reporting instruction set. An evaluation report on the final application strategy is generated based on the feasibility verification results, the expected return value, and the target risk value.

8. An energy reporting strategy optimization device, characterized in that, The energy reporting strategy optimization device includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to cause the energy reporting strategy optimization device to perform the method as described in any one of claims 1-7.

9. A computer program product containing instructions, characterized in that, When the computer program product is run on the energy reporting strategy optimization device, the energy reporting strategy optimization device performs the method as described in any one of claims 1-7.

10. A computer-readable storage medium comprising instructions, characterized in that, When the instruction is executed on the power energy reporting strategy optimization device, the power energy reporting strategy optimization device performs the method as described in any one of claims 1-7.

Images