A power market transaction optimization decision system for microgrid assets

Abstract

The application is a kind of micro-grid asset power market transaction optimization decision system, belonging to the technical field of power market transaction and financial risk management;The system obtains market electricity price, planned power, financial data and extreme weather risk event signals in real time;The risk quantification module quantifies potential market opportunity income and planned deviation penalty cost based on this, and constructs a risk factor reflecting the comprehensive financial risk level;The strategy decision and weight generation module dynamically generates the weight coefficients of income and deviation penalty through a nonlinear mapping function according to the financial risk, and constructs a real-time optimization objective function with the goal of maximizing risk-adjusted income. Finally, the system solves the function to determine the optimal transaction decision;The application quantifies complex market financial risks into dynamic decision-making basis, enabling the transaction strategy to adaptively adjust between avoiding financial losses and pursuing arbitrage opportunities.

Description

Technical Field

[0001] This invention relates to the field of electricity market trading and financial risk management technology, specifically to an optimized decision-making system for electricity market trading of microgrid assets. Background Technology

[0002] In the context of electricity market transactions, microgrid operators, as market participants, directly influence their economic gains and risk exposure in various transactions such as the spot market and ancillary services market through their dispatch decisions.

[0003] In existing technologies, scheduling strategies are usually based on fixed financial objective functions, such as simply pursuing cost minimization or profit maximization. Such static financial models cannot effectively cope with the complex financial risks constituted by real-time market price fluctuations and sudden events. It is difficult to make a dynamic and quantitative trade-off between avoiding high deviation penalties and capturing instantaneous market arbitrage opportunities. As a result, their market trading strategies are either too conservative and miss out on profits, or face significant economic losses due to insufficient risk assessment.

[0004] Therefore, how to construct a scheduling method that can quantify comprehensive risks in real time and dynamically adjust and optimize objectives, thereby improving the economy and robustness of microgrid operation in a complex and ever-changing market environment, is a key technical problem that urgently needs to be solved. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides an optimized decision-making system for electricity market transactions of microgrid assets. Specifically, the technical solution of this invention includes:

[0006] The data acquisition module is used to acquire financial data and risk event signals related to electricity market transactions in real time. The financial data includes at least real-time market price signals and day-ahead planned power curves. The risk event signals include at least regional extreme weather event warning signals.

[0007] The risk quantification module is used to quantify potential market opportunity returns and potential planning deviation penalty costs based on real-time market price signals. The risk quantification module is also used to combine regional extreme weather event warning signals with real-time market price signals to construct risk factors that reflect the overall level of financial risk.

[0008] The strategy decision-making module is used to calculate the trading strategy preference index based on potential market opportunity returns, potential plan deviation penalty costs, and comprehensive risk factors.

[0009] The weight generation module is used to dynamically generate return weight coefficients and deviation penalty weight coefficients based on the trading strategy preference index through a preset non-linear mapping function.

[0010] The objective construction module is used to construct a real-time optimization objective function based on the return weighting coefficient and the deviation penalty weighting coefficient, with the goal of maximizing risk-adjusted return.

[0011] An optimization solution module is used to solve the real-time optimization objective function to determine a set of optimal electricity market trading strategies, which include at least a bid curve or regulation power for market bidding.

[0012] Preferably, the risk quantification module constructs risk factors that reflect the overall level of financial risk, including:

[0013] Based on regional extreme weather event warning signals, determine the external shock amplification term;

[0014] The standard coefficient of variation is determined based on the mean and standard deviation of real-time market price signals within a preset sliding time window.

[0015] The standard coefficient of variation is used to describe the endogenous relative volatility of market prices.

[0016] The comprehensive risk factor is determined by multiplying the external shock amplification term by the standard coefficient of variation.

[0017] Preferably, the strategy decision module calculates the trading strategy tendency index, including:

[0018] The expected net income is determined based on the difference between the potential market opportunity gains and the potential planning deviation penalty costs.

[0019] The total economic size is determined by the sum of potential market opportunity gains and potential planning deviation penalty costs.

[0020] Multiplying the total economic size by the comprehensive risk factor yields the risk-adjusted total economic size.

[0021] The trading strategy preference index is obtained by calculating the ratio of expected net return to the risk-adjusted total economic size.

[0022] Preferably, the weight generation module uses the logistic function as a nonlinear mapping function to map the trading strategy tendency index to a preset interval to generate a return weight coefficient and a deviation penalty weight coefficient; wherein the sum of the return weight coefficient and the deviation penalty weight coefficient is always 1.

[0023] Preferably, the target construction module constructs a real-time optimization objective function aimed at maximizing risk-adjusted return, including:

[0024] The weighted market return is obtained by multiplying the return weighting coefficient by the expected actual market return generated after the scheduling action is performed.

[0025] The weighted deviation penalty is obtained by multiplying the deviation penalty weighting coefficient by the expected actual deviation penalty generated after the scheduling action is executed.

[0026] To maximize the difference between the weighted market return and the weighted bias penalty, a real-time optimization objective function is constructed with the goal of maximizing the risk-adjusted return.

[0027] Preferably, the risk prediction module is used to call a pre-trained probability prediction model for any candidate scheduling action and output the probability density function of the actual planned deviation in electricity volume caused by the action.

[0028] Preferably, the risk prediction module is further used for:

[0029] Based on the probability density function and the preset nonlinear penalty function, the expected deviation penalty cost corresponding to the candidate scheduling action is determined by integral operation, and the expected deviation penalty cost is used as the expected actual deviation penalty.

[0030] The nonlinear penalty function is used to describe the relationship between penalty cost and deviation power.

[0031] Preferably, the scheduling mode decision module is used to compare the trading strategy tendency index with the preset conservative mode threshold and aggressive mode threshold, and select the current scheduling mode from conservative mode, balanced mode and aggressive mode.

[0032] Preferably, the specific operations of the scheduling mode decision module include:

[0033] When the trading strategy tendency index is less than the conservative mode threshold, the conservative mode is triggered, and the return weight coefficient is set to zero, while the deviation penalty weight coefficient is set to one.

[0034] When the trading strategy tendency index exceeds the aggressive mode threshold, aggressive mode is triggered, and the profit weight coefficient is set to one, while the deviation penalty weight coefficient is set to zero.

[0035] In response to the trading strategy tendency index falling between the conservative mode threshold and the aggressive mode threshold, an equilibrium mode is triggered, and the return weight coefficient and deviation penalty weight coefficient generated by the weight generation module are used.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] 1. This system integrates electricity market price fluctuations and external shock events into a comprehensive financial risk assessment framework, achieving dynamic and comprehensive quantification of market transaction risks. Compared with traditional dispatching methods that rely solely on a single technical or economic indicator, this system can more accurately assess financial risks in complex market environments, providing a basis for decision-making in formulating scientific trading strategies.

[0038] 2. This system can dynamically adjust the emphasis on market returns and deviation penalties in trading strategies based on quantified financial risks; by generating a trading strategy preference index to weigh potential returns and risk costs in real time, the trading strategy can adaptively and smoothly adjust between aggressive profit-seeking and conservative risk-averse, overcoming the problem of rigid trading decision models in existing technologies that cannot adapt to market dynamics.

[0039] 3. This system introduces three trading modes—conservative, balanced, and aggressive—and automatically switches between them based on a trading strategy preference index, making the macro strategy for microgrids participating in market trading clearer and more intelligent. When market opportunities are great and financial risks are low, the system can switch to aggressive mode to maximize trading returns; while when financial risks are high, it automatically switches to conservative mode to focus on avoiding penalties and hedging risks.

[0040] 4. This system constructs a real-time optimization objective function with maximizing risk-adjusted financial returns as its core, and can more accurately quantify potential deviation penalties by introducing a probabilistic prediction model. This refined financial modeling and solution mechanism ensures that the final output decision instructions can effectively improve the overall economic benefits and financial stability of market participants in a volatile market environment while meeting the requirements of power grid compliance. Attached Figure Description

[0041] The present invention will be further explained below with reference to the accompanying drawings and embodiments:

[0042] Figure 1 This is a structural diagram of the system of the present invention. Detailed Implementation

[0043] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0044] Example 1:

[0045] Please see Figure 1 A decision-making system for optimizing electricity market transactions of microgrid assets, comprising:

[0046] The data acquisition module is used to acquire financial data and risk event signals related to electricity market transactions in real time. The financial data includes at least real-time market price signals and day-ahead planned power curves. The risk event signals include at least regional extreme weather event warning signals.

[0047] The risk quantification module is used to quantify potential market opportunity returns and potential planning deviation penalty costs based on real-time market price signals. The risk quantification module is also used to combine regional extreme weather event warning signals with real-time market price signals to construct risk factors that reflect the overall level of financial risk.

[0048] The strategy decision-making module is used to calculate the trading strategy preference index based on potential market opportunity returns, potential plan deviation penalty costs, and comprehensive risk factors.

[0049] The weight generation module is used to dynamically generate return weight coefficients and deviation penalty weight coefficients based on the trading strategy preference index through a preset non-linear mapping function.

[0050] The objective construction module is used to construct a real-time optimization objective function based on the return weighting coefficient and the deviation penalty weighting coefficient, with the goal of maximizing risk-adjusted return.

[0051] An optimization solution module is used to solve the real-time optimization objective function to determine a set of optimal electricity market trading strategies, which include at least a bid curve or regulation power for market bidding.

[0052] This invention provides a power market transaction optimization decision-making system for microgrid assets; the system includes a closed-loop, adaptive scheduling decision-making process, specifically implemented by the collaborative work of the following modules:

[0053] The data acquisition module aims to provide real-time, multi-dimensional data input for subsequent risk quantification and strategy decision-making, serving as the perception foundation for the entire optimization and scheduling system. In this system, a data preprocessing and verification module follows the data acquisition module to identify and process abnormal market price signals, ensuring the rationality of the data input to the risk quantification module. Furthermore, the weight generation module processes the calculated comprehensive risk factors... and trading strategy preference index Reasonable upper and lower limits are set to prevent saturation or sudden changes in weighting coefficients due to extreme inputs, ensuring a smooth transition in decision-making. In this embodiment, the module uses standard industrial communication protocol interfaces, such as Modbus / TCP, OPC-UA, or DNP3, to achieve concurrent, high-frequency acquisition of multiple data sources. The module acquires real-time price signals from multiple markets in which the microgrid participates, mainly including real-time electricity prices in the energy market. Service prices in the ancillary services market And carbon prices in the carbon trading market This module receives dispatch time intervals from the upper-level power grid dispatch center. Planned power curves for day-ahead resolution This module subscribes to and receives regional extreme weather event warning signals through an external information interface. This interface can be implemented based on a RESTful API, and the received data is typically in JSON format. This signal is defined as an extreme weather warning level factor. This variable is used to quantify the severity of major external disturbances; its basic form can be simplified to a binary state, for example... This indicates that the warning has been activated. This represents the normal state, while in the refined model, different values ​​can be taken to correspond to different warning levels. The source is the official warning information issued by authoritative meteorological departments or power grid operators.

[0054] The risk quantification module aims to transform abstract market and environmental risks into calculable and comparable mathematical indicators. In this embodiment, based on real-time market price signals acquired by the data acquisition module, this module proactively quantifies the potential benefits and costs of speculative scheduling by the microgrid in the next scheduling cycle. Specifically, it calculates potential market opportunity gains. Penalty costs for potential plan deviations Potential market opportunity gains This refers to the maximum theoretical benefit a microgrid could obtain by using all of its current adjustable power to participate in the ancillary services market, without considering penalty risks; potential planning deviation penalty costs. This refers to the theoretical penalty cost that a microgrid might incur if it performs the aforementioned maximum power regulation action, due to deviation from the day-ahead plan;

[0055] Among them, the current total adjustable power It is the maximum responsive power calculated in real time based on the current operating status of each controllable unit within the microgrid;

[0056] In this embodiment, and The calculation formula can be specifically defined as follows:

[0057]

[0058]

[0059] in, The current service prices in the assisted services market, For scheduling time intervals, The penalty function related to the deviation in electricity consumption is defined by the power grid; the risk quantification module is also used to construct a comprehensive risk factor by combining regional extreme weather event warning signals with real-time market price signals. The purpose of this factor is to quantify the impact of external emergencies and the market's endogenous price volatility in a unified manner.

[0060] The core purpose of the strategy decision-making module is to generate a macro-level decision-making instruction that can guide subsequent weight allocation based on the return, cost, and risk indicators output by the risk quantification module. In this embodiment, the module calculates a trading strategy preference index. To achieve this function; the trading strategy favors indexes. It refers to a dimensionless indicator used to measure the expected net return per unit of risk-adjusted economic size; its function is to determine the appropriateness of speculative allocation at present, thereby deciding whether the allocation strategy should be more aggressive or conservative.

[0061] The weight generation module aims to generate the trading strategy preference index output by the strategy decision module. This is transformed into precise mathematical weights for constructing a specific optimization objective function; in this embodiment, the module dynamically generates the revenue weight coefficients through a preset nonlinear mapping function. And deviation penalty weight coefficient ;

[0062] The objective construction module aims to construct a real-time optimization objective function that reflects the current risk preference, based on the weight coefficients dynamically generated by the weight generation module. This module is based on and The value of is adjusted and optimized in real time to adjust the emphasis on market returns and deviation penalties in the objective, thus constructing a dynamic objective with the maximization of risk-adjusted comprehensive returns as the core.

[0063] The optimization solution module aims to solve the real-time optimization objective function constructed by the objective function construction module to determine the optimal electricity market trading strategy within the current scheduling cycle. In this embodiment, the module employs a numerical optimization algorithm, given the objective function... The specific form may be nonlinear. In this embodiment, efficient nonlinear programming solvers such as sequential quadratic programming or interior-point methods can be used to find the optimal solution; the adjustment power of each controllable unit in the microgrid is used as the decision variable. Under the premise of satisfying power grid security constraints, solve for... The maximum value is obtained to arrive at the optimal electricity market trading strategy. The optimal electricity market trading strategy This is the final output of the system, specifically a set of optimal business decision data to support bidding activities in the electricity market; for further explanation, the trading strategy... This should include at least a bid curve or regulated electricity volume used for market bidding. For example, this electricity market trading strategy. The determined optimal regulation power value and the corresponding price (i.e., the point on the bid curve) can be packaged into a standardized data format for automatic generation and submission to the higher-level electricity market trading platform for corresponding ancillary service bids or clearing power declarations in the real-time energy market. The function of this system terminates at generating this business strategy data, rather than executing physical power control.

[0064] Compared to existing technologies, this invention can perceive multi-dimensional risks such as market price fluctuations and extreme weather impacts in real time, quantify them into dynamic decision-making criteria, and then reconstruct and optimize the objective function in real time. This enables the microgrid's scheduling strategy to shift from a fixed cost minimization or revenue maximization model to a dynamic and smooth optimization model that balances risk avoidance and revenue pursuit. Thus, while ensuring grid compliance, this system primarily focuses on optimizing economic risks in the market environment. In specific engineering applications, the system's output commands also need to be verified by a verification module based on equipment operating status and safety constraints to address other operational risks such as equipment failures and significant load forecast deviations. This improves the overall economic efficiency and operational robustness of the microgrid in complex and volatile market environments.

[0065] Example 2:

[0066] The risk quantification module constructs risk factors that reflect the overall level of financial risk, including:

[0067] Based on regional extreme weather event warning signals, determine the external shock amplification term;

[0068] The standard coefficient of variation is determined based on the mean and standard deviation of real-time market price signals within a preset sliding time window.

[0069] The standard coefficient of variation is used to describe the endogenous relative volatility of market prices.

[0070] The comprehensive risk factor is determined by multiplying the external shock amplification term by the standard coefficient of variation.

[0071] This embodiment constructs a risk factor reflecting the overall financial risk level based on the risk quantification module of Embodiment 1. Further explanation of the specific implementation method; to quantify the impact of external extreme weather events and market endogenous volatility in a unified manner, this embodiment introduces a comprehensive risk factor. The calculation method is as follows:

[0072]

[0073] in, This is an extreme weather warning level factor, whose value corresponds to the officially issued weather warning level. For example, when there is no warning... During a blue alert When a yellow alert is issued Orange alert This allows for a more precise quantification of the severity of external shocks.

[0074] α is the weighting coefficient for the impact of extreme weather, used to quantify the amplification effect of external shocks on market volatility. It is a dimensionless positive real number; its source is determined through statistical analysis of historical calibration datasets. Specifically, the market price volatility amplification factor in the historical calibration dataset is defined as... It is calculated as the ratio of the standard deviation of market prices during a given extreme weather event to the standard deviation over a time window of equal length prior to the event. This is achieved by analyzing all similar extreme weather events in the dataset. Perform linear regression analysis on the values ​​or directly calculate the average value to calibrate the parameters. ;

[0075] The standard deviation of the overall market price over the past preset sliding time window is expressed in yuan / MWh and is calculated in real time by this module based on price data collected by the data acquisition module. The length of the sliding time window is preset to 1 hour. This length is chosen to balance the sensitivity to short-term high-frequency fluctuations in market prices with the stability of long-term trends. Through historical data analysis, a 1-hour window can better reflect the market risk characteristics in the upcoming scheduling cycle.

[0076] The average market price is the average price over a preset sliding time window, expressed in yuan / MWh, and is calculated in real-time by this module based on price data collected by the data acquisition module. The average market price is an equivalent price calculated by weighting the main market activities currently participated in by the microgrid, for example... The weighting coefficients we, wa, and wc are determined based on the microgrid's operation strategy and the proportion of trading volume in each market.

[0077] The calculation logic of this formula consists of two parts; the first is to determine the external shock amplification term based on the regional extreme weather event warning signal. Secondly, the standard coefficient of variation is determined based on the mean and standard deviation of real-time market price signals within a preset sliding time window. The standard coefficient of variation (SCV) is a statistical measure of standardized dispersion, used to describe the endogenous relative volatility of market prices. Finally, the comprehensive risk factor is determined by multiplying the external shock amplification term by the SCV. Through this design, It can not only reflect the market's own fluctuations, but also reasonably amplify the amplitude of the fluctuations when external shocks occur, so that subsequent decisions can predictively increase the weight of risk aversion.

[0078] Example 3:

[0079] The strategy decision module calculates a trading strategy preference index, including:

[0080] The expected net income is determined based on the difference between the potential market opportunity gains and the potential planning deviation penalty costs.

[0081] The total economic size is determined by the sum of potential market opportunity gains and potential planning deviation penalty costs.

[0082] Multiplying the total economic size by the comprehensive risk factor yields the risk-adjusted total economic size.

[0083] The trading strategy preference index is obtained by calculating the ratio of expected net return to the risk-adjusted total economic size.

[0084] This embodiment calculates the trading strategy tendency index using the strategy decision-making module of Embodiment 1. Further explanation of the specific implementation method; to establish a decision-making basis for dynamically balancing the pursuit of returns and the avoidance of risks, this embodiment introduces a trading strategy propensity index. The calculation method is as follows:

[0085]

[0086] in, The potential market opportunity return is expressed in yuan and is calculated by the risk quantification module based on real-time market prices.

[0087] The potential planning deviation penalty cost, in yuan, is estimated by the risk quantification module based on the power grid penalty rules.

[0088] The comprehensive risk factors are dimensionless and calculated by the risk quantification module; to prevent the denominator from being zero, a small positive constant is added during the calculation. The formula is revised to ;when When the value approaches 0, it means that the economic scale of the scheduling action is extremely small, at which point it can be... Defined as 0, indicating a neutral tendency;

[0089] The calculation logic of this index is based on: potential market opportunity returns. Penalty costs for potential plan deviations The difference determines the expected net income. Based on potential market opportunity gains Penalty costs for potential plan deviations The sum of these factors determines the total economic scale. Total economic scale refers to the total amount of funds involved in executing this dispatch action; combining total economic scale with comprehensive risk factors Multiply by each other to obtain the risk-adjusted total economic size. The trading strategy preference index is obtained by calculating the ratio of expected net return to the risk-adjusted total economic size. The physical meaning of this index is the net return that a unit of risk-adjusted economic size can generate.

[0090] Example 4:

[0091] The weight generation module uses the logistic function as a non-linear mapping function to map the trading strategy tendency index to a preset range to generate the return weight coefficient and the deviation penalty weight coefficient; wherein, the sum of the return weight coefficient and the deviation penalty weight coefficient is always 1.

[0092] This embodiment is a further explanation of the specific implementation of the weight generation module in Embodiment 1; in order to favor the trading strategy towards the index. The weights are smoothly and reasonably mapped to weight coefficients. In this embodiment, the logistic function is used as the nonlinear mapping function. The weight generation formula is as follows:

[0093]

[0094]

[0095] in, The trading strategy bias index is dimensionless and is calculated by the strategy decision module.

[0096] The return weighting coefficient represents the degree of importance attached to pursuing market returns in the optimization objective. It is a dimensionless variable with a value between 0 and 1.

[0097] The bias penalty weight coefficient represents the degree of importance attached to avoiding bias penalties in the optimization objective. It is a dimensionless variable with a value between 0 and 1.

[0098] k and η0 are adjustable parameters of the logistic function, both of which are dimensionless; Control the steepness of the curve. It represents the equilibrium point for decision-making; its origin is determined through backtesting and optimization of historical scheduling data; specifically, it involves defining a performance index to evaluate the effectiveness of historical scheduling. By solving the optimization problem Determine and The optimal value; for example, numerical optimization methods such as grid search or gradient ascent can be used to solve this optimization problem; this performance index It can be defined as the cumulative net return during the historical data backtesting period, or the risk-adjusted return, which is the ratio of total net return to return volatility.

[0099] The logic of this module is to shift the trading strategy towards the index. As input, the logistic function maps the result to the interval between 0 and 1 to generate the revenue weighting coefficients. Simultaneously, deviation penalty weight coefficients are generated. And ensure that the sum of the benefit weighting coefficient and the deviation penalty weighting coefficient is always 1.

[0100] Example 5:

[0101] The objective construction module constructs a real-time optimized objective function aimed at maximizing risk-adjusted return, including:

[0102] The weighted market return is obtained by multiplying the return weighting coefficient by the expected actual market return generated after the scheduling action is performed.

[0103] The weighted deviation penalty is obtained by multiplying the deviation penalty weighting coefficient by the expected actual deviation penalty generated after the scheduling action is executed.

[0104] To maximize the difference between the weighted market return and the weighted bias penalty, a real-time optimization objective function is constructed, aiming to maximize the risk-adjusted return. In this embodiment, the above function can be specifically defined as follows:

[0105] Expected Real Market Return Function Defined as the power regulation action performed by the microgrid Subsequently, revenue gained through participation in markets such as ancillary services, for example ,in To support service prices in the service market, To provide regulation power to the ancillary services market, The scheduling time interval;

[0106] Expected actual deviation penalty function Defined as the result of performing power regulation action And deviating from the planned power The resulting punishment; can be initially constructed as ,in It is to perform an action The actual total power after It is the penalty function specified by the power grid; where the actual total power It can be formed by the sum of the power of each unit in the microgrid, for example , here The load power at the current moment. The predicted output of renewable energy is represented by u, which represents the output of controllable units such as energy storage (discharge is positive).

[0107] To further improve the physical fidelity of the model, a cost term related to equipment losses can be introduced into the objective function; for example, for energy storage units, the charging and discharging operations can be included. The resulting cyclic aging costs Added to the penalty term, the corrected objective function is: Meanwhile, in the optimization solution, the upper and lower limits of power, ramp rate, and battery state of charge range of each unit must be treated as rigid constraints.

[0108] This embodiment further illustrates the specific implementation of the target construction module in Embodiment 1, which constructs a real-time optimization objective function aimed at maximizing risk-adjusted return. To construct an optimization objective that can adapt to current market risk, this embodiment designs the following real-time optimization objective function:

[0109]

[0110] in, These are decision variables, representing specific market transaction actions, such as the proposed bidding volume (in MW) or key parameters of the price curve;

[0111] These are the revenue weight coefficient and the deviation penalty weight coefficient calculated by the weight generation module, and are dimensionless.

[0112] Let be the expected actual market return function, representing the execution of scheduling actions. The expected actual market return, in yuan;

[0113] The expected actual deviation penalty function represents the scheduling action to be performed. Then, the expected actual deviation penalty, in yuan;

[0114] The logic behind constructing this objective function lies in: weighting the return coefficients... The expected actual market returns generated after executing the scheduling action Multiply by this to obtain the weighted market return; then apply the bias penalty weighting coefficient. Penalty for deviation from expected to actual after executing scheduling actions Multiplying these together yields the weighted bias penalty; with the goal of maximizing the difference between the weighted market return and the weighted bias penalty, a real-time optimization objective function is constructed to maximize the risk-adjusted return.

[0115] Example 6:

[0116] The risk prediction module is used to call a pre-trained probabilistic prediction model for any candidate scheduling action and output the probability density function of the actual planned power deviation caused by the action.

[0117] The risk prediction module is also used for:

[0118] Based on the probability density function and the preset nonlinear penalty function, the expected deviation penalty cost corresponding to the candidate scheduling action is determined by integral operation, and the expected deviation penalty cost is used as the expected actual deviation penalty.

[0119] The nonlinear penalty function is used to describe the relationship between penalty cost and deviation power.

[0120] This embodiment is a preferred implementation of the system in Embodiment 5, which adds a risk prediction module to penalize expected-to-actual deviations. To perform more refined quantification;

[0121] This system also includes a risk prediction module, the purpose of which is to introduce a probabilistic prediction model to assess the risk of each potential scheduling action in a more scientific way; for any candidate scheduling action... This module calls a pre-trained probabilistic prediction model and outputs the actual planned deviation in electricity consumption caused by the action. probability density function In this embodiment, the probabilistic prediction model uses a long short-term memory network based on deep learning. This network can effectively learn the dynamic features in time series data, thereby predicting the probability distribution of future deviation power based on the current system state and control commands.

[0122] To transform the uncertainty to be predicted into a definite cost item for optimization, this embodiment employs an expected value calculation method:

[0123]

[0124] in, The penalty cost for expected deviation, i.e., the cost of performing the action. The penalty cost under the corresponding mathematical expectation, in yuan;

[0125] This is the conditional probability density function, derived from the probabilistic prediction model within this module. This model is trained based on historical operational data and relevant features. Specifically, the input features of this model may include: candidate scheduling actions. Current load levels, renewable energy output forecasts, and market price signals. and comprehensive risk factors wait;

[0126] This is a non-linear penalty function used to describe the relationship between penalty cost and deviation electricity, and its source is the official penalty rules issued by the grid operator;

[0127] The logic of this module is based on the probability density function. With the preset nonlinear penalty function By performing integral calculations, the expected deviation penalty cost corresponding to the candidate scheduling action is determined. Penalty cost for deviation from expectation As defined in Example 5, the expected actual deviation penalty Through this step, the system completes a closed-loop decision-making process, from macro-level trend judgment to micro-level action optimization.

[0128] Example 7:

[0129] The scheduling mode decision module is used to compare the trading strategy preference index with the preset conservative mode threshold and aggressive mode threshold, and select the current scheduling mode from conservative mode, balanced mode and aggressive mode.

[0130] The specific operations of the scheduling mode decision module include:

[0131] When the trading strategy tendency index is less than the conservative mode threshold, the conservative mode is triggered, and the return weight coefficient is set to zero, while the deviation penalty weight coefficient is set to one.

[0132] When the trading strategy tendency index exceeds the aggressive mode threshold, aggressive mode is triggered, and the profit weight coefficient is set to one, while the deviation penalty weight coefficient is set to zero.

[0133] In response to the trading strategy tendency index falling between the conservative mode threshold and the aggressive mode threshold, an equilibrium mode is triggered, and the return weight coefficient and deviation penalty weight coefficient generated by the weight generation module are used.

[0134] This embodiment is a preferred control strategy implementation of the system in Embodiment 1. By adding a scheduling mode decision module, the system can switch to the optimal macro-operation mode in market environments with different risk levels.

[0135] This system also includes a scheduling mode decision module, which will determine the trading strategy's preference for the index. Compared with the preset conservative mode threshold and the threshold for aggressive mode A comparison is made between conservative, balanced, and aggressive modes to select the current scheduling mode; the conservative mode threshold is also considered. and aggressive mode threshold This refers to the critical value used to distinguish different scheduling modes; its setting logic is based on the operator's risk preference and is calibrated through backtesting of historical data; for example... It can be set as the value corresponding to the lower limit of the preset confidence interval for expected net speculative returns being less than zero. This value is used to ensure that speculative behavior has a very high probability of causing losses when entering conservative mode.

[0136] The specific operations of this scheduling mode decision module include:

[0137] Response to trading strategy preference index Less than the conservative mode threshold The system triggers conservative mode; in this mode, the module adjusts the profit weighting coefficient. Forced to zero, deviation penalty weighting coefficient Forced to set to 1; at this point, the real-time optimization objective function degenerates into ;

[0138] Response to trading strategy preference index Greater than the aggressive mode threshold The system triggers an aggressive mode; in this mode, the module adjusts the profit weighting coefficient. Forced to set to 1, deviation penalty weighting coefficient Forced to zero; at this point, the real-time optimization objective function degenerates into ;

[0139] Response to trading strategy preference index Between conservative mode threshold With the threshold of aggressive mode Between these points, the system triggers a balance mode; in this mode, the system uses a weight generation module based on... Dynamically generated profit weighting coefficients With deviation penalty weighting coefficient Using the complete real-time optimization objective function Solve the problem.

[0140] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A power market trading optimization decision-making system for microgrid assets, characterized in that, Applications in the electricity market for financial transaction decisions and risk management of microgrid assets include: The data acquisition module is used to acquire financial data and risk event signals related to electricity market transactions in real time. The financial data includes at least real-time market price signals and day-ahead planned power curves. The risk event signals include at least regional extreme weather event warning signals. The risk quantification module is used to quantify potential market opportunity returns and potential planning deviation penalty costs based on real-time market price signals. The risk quantification module is also used to combine regional extreme weather event warning signals with real-time market price signals to construct risk factors that reflect the overall level of financial risk. The strategy decision-making module is used to calculate the trading strategy preference index based on potential market opportunity returns, potential plan deviation penalty costs, and comprehensive risk factors. The weight generation module is used to dynamically generate return weight coefficients and deviation penalty weight coefficients based on the trading strategy preference index through a preset non-linear mapping function. The objective construction module is used to construct a real-time optimization objective function based on the return weighting coefficient and the deviation penalty weighting coefficient, with the goal of maximizing risk-adjusted return. An optimization solution module is used to solve the real-time optimization objective function to determine a set of optimal electricity market trading strategies, which include at least a bid curve or regulation power for market bidding. The risk quantification module constructs risk factors that reflect the overall level of financial risk, including: Based on regional extreme weather event warning signals, determine the external shock amplification term; The standard coefficient of variation is determined based on the mean and standard deviation of real-time market price signals within a preset sliding time window. The standard coefficient of variation is used to describe the endogenous relative volatility of market prices. The comprehensive risk factor is determined by multiplying the external shock amplification term by the standard coefficient of variation. The strategy decision module calculates the trading strategy preference index, including: The expected net income is determined based on the difference between the potential market opportunity gains and the potential planning deviation penalty costs. The total economic size is determined by the sum of potential market opportunity gains and potential planning deviation penalty costs. Multiplying the total economic size by the comprehensive risk factor yields the risk-adjusted total economic size. The trading strategy preference index is obtained by calculating the ratio of expected net return to the risk-adjusted total economic size. The weight generation module uses the logistic function as a non-linear mapping function to map the trading strategy tendency index to a preset range to generate a return weight coefficient and a deviation penalty weight coefficient; wherein, the sum of the return weight coefficient and the deviation penalty weight coefficient is always 1. The objective construction module constructs a real-time optimized objective function aimed at maximizing risk-adjusted return, including: The weighted market return is obtained by multiplying the return weighting coefficient by the expected actual market return generated after the scheduling action is performed. The weighted deviation penalty is obtained by multiplying the deviation penalty weighting coefficient by the expected actual deviation penalty generated after the scheduling action is executed. To maximize the difference between the weighted market return and the weighted bias penalty, a real-time optimization objective function is constructed with the goal of maximizing the risk-adjusted return.

2. The power market transaction optimization decision-making system for microgrid assets according to claim 1, characterized in that, Also includes: The risk prediction module is used to call a pre-trained probabilistic prediction model for any candidate scheduling action and output the probability density function of the actual planned power deviation caused by the action.

3. The power market transaction optimization decision-making system for microgrid assets according to claim 2, characterized in that, The risk prediction module is also used for: Based on the probability density function and the preset nonlinear penalty function, the expected deviation penalty cost corresponding to the candidate scheduling action is determined by integral operation, and the expected deviation penalty cost is used as the expected actual deviation penalty. The nonlinear penalty function is used to describe the relationship between penalty cost and deviation power.

4. The power market transaction optimization decision-making system for microgrid assets according to claim 1, characterized in that, Also includes: The scheduling mode decision module is used to compare the trading strategy preference index with the preset conservative mode threshold and aggressive mode threshold, and select the current scheduling mode from conservative mode, balanced mode and aggressive mode.

5. The power market transaction optimization decision-making system for microgrid assets according to claim 4, characterized in that, The specific operations of the scheduling mode decision module include: When the trading strategy tendency index is less than the conservative mode threshold, the conservative mode is triggered, and the return weight coefficient is set to zero, while the deviation penalty weight coefficient is set to one. When the trading strategy tendency index exceeds the aggressive mode threshold, aggressive mode is triggered, and the profit weight coefficient is set to one, while the deviation penalty weight coefficient is set to zero. In response to the trading strategy tendency index falling between the conservative mode threshold and the aggressive mode threshold, an equilibrium mode is triggered, and the return weight coefficient and deviation penalty weight coefficient generated by the weight generation module are used.

Images