New energy power transaction control method, system, device and medium

Abstract

This application provides a method, system, device, and medium for controlling new energy power trading, belonging to the field of new energy power trading technology. The method includes: acquiring historical power trading data, current predicted power values, and day-ahead electricity prices; determining the distribution characteristics of historical power deviations and historical electricity price deviations based on the historical power trading data; generating Monte Carlo scenarios related to actual power generation and actual electricity prices based on the distribution characteristics, predicted power values, and day-ahead electricity prices, obtaining a scenario set; based on the expected return calculation formula, and constrained by the scenario set and preset constraints, solving for the maximum expected return based on the predicted power values ​​and day-ahead electricity prices, obtaining a target decision coefficient; the expected return calculation formula and preset constraints include relevant data items or conditions related to accuracy penalties; determining and outputting the target declared power volume based on the target decision coefficient and predicted power values. This application aims to improve the expected return of new energy power trading and reduce penalty risks.

Description

Technical Field

[0001] This application relates to the field of new energy power trading technology, and in particular to a new energy power trading control method, system, device and medium. Background Technology

[0002] In related technologies, the revenue from spot trading of renewable energy electricity follows the formula: Revenue = (Actual Generation - Day-ahead Bid-Winning Volume) × (Actual Electricity Price - Day-ahead Electricity Price). The difference between the actual generation and the day-ahead bid-winning volume directly affects the revenue or loss. In addition, the size of the difference also affects the accuracy index (ACC) of the power grid assessment, which is associated with the risk of penalties. Therefore, even if the difference is positive, an excessively large difference may lead to the ACC exceeding the limit, thus offsetting the trading revenue.

[0003] To improve spot trading returns and reduce ACC exceedances, new energy power generation companies can multiply their projected power generation by an adjustment factor when reporting their power generation before the reporting date. Currently, the strategy for determining the adjustment factor generally only considers the relationship between quantity difference and returns. In practice, if the adjustment factor is set too small, it is difficult to significantly improve spot trading returns. On the other hand, if the adjustment factor is set too large, it may lead to ACC exceedances and trigger penalties, affecting the final trading returns.

[0004] In summary, the technical problems existing in the relevant technologies need to be improved. Summary of the Invention

[0005] The main objective of this application is to propose a new energy power trading control method, system, device, and medium, which aims to improve the expected returns of new energy power trading and reduce the risk of penalties.

[0006] To achieve the above objectives, one aspect of this application proposes a new energy power trading control method, the method comprising: Obtain historical electricity trading data, as well as current forecasted electricity volume and day-ahead electricity price; The distribution characteristics of historical electricity volume deviation and historical electricity price deviation are determined based on the historical electricity trading data. Based on the distribution characteristics, the predicted electricity value, and the day-ahead electricity price sampling, Monte Carlo scenarios related to actual electricity generation and actual electricity price are generated to obtain a scenario set; Based on the expected return calculation formula, and with the scenario set and preset constraints as constraints, the maximum expected return is solved according to the predicted electricity value and the day-ahead electricity price to obtain the target decision coefficient. The expected return calculation formula and the preset constraints include relevant data items or conditions related to accuracy penalties. The target declared electricity volume is determined and output based on the target decision coefficient and the predicted electricity volume value.

[0007] In some embodiments, the step of generating Monte Carlo scenarios related to actual power generation and actual electricity price based on the distribution characteristics, the predicted power value, and the day-ahead electricity price sampling, and obtaining a scenario set, includes: The actual power generation is restored based on the predicted power value and the power deviation that meets the distribution characteristics. The actual electricity price is restored based on the day-ahead electricity price and the price deviation that meets the distribution characteristics. A preset number of simulation scenarios are sampled and generated. Each simulation scenario includes several consecutive time periods. The preset number of simulated scenarios are combined to form the scenario set.

[0008] In some embodiments, the step of calculating the maximum expected return based on the expected return formula, using the scenario set and preset constraints as constraints, and solving for the target decision coefficient based on the predicted electricity value and the day-ahead electricity price, includes: Define decision coefficient variables corresponding to the time period; Based on the expected return calculation formula, the predicted electricity value and the day-ahead electricity price are input. With the preset constraints, the actual electricity generation and the actual electricity price simulated by the scenario set as constraints, and with the maximum expected return as the objective, the decision coefficient variables are solved by a stochastic programming solver using nonlinear programming or sequential quadratic programming to obtain the target decision coefficient.

[0009] In some embodiments, the preset constraints include a first condition, a second condition, and a third condition. The step of calculating the maximum expected return based on the expected return formula, using the scenario set and the preset constraints as constraints, and solving for the target decision coefficient based on the predicted electricity value and the day-ahead electricity price, includes: Define decision coefficient variables corresponding to the time period; Based on the expected return calculation formula, the predicted electricity value and the day-ahead electricity price are input. Constrained by the first condition, the second condition, the third condition, and the actual electricity generation and the actual electricity price simulated in the scenario set, the decision coefficient variable is solved with the goal of maximizing the expected return to obtain the target decision coefficient. The first condition is that the day-ahead declared electricity is less than or equal to the installed capacity, and the day-ahead declared electricity is the product of the decision coefficient variable and the predicted electricity value. The second condition is that the decision coefficient variable is greater than or equal to zero. The third condition is that the absolute value of the electricity accuracy is less than or equal to the accuracy threshold, and the accuracy penalty is related to the electricity accuracy.

[0010] In some embodiments, the process of sampling to generate a preset number of simulated scenarios further includes: When the restored actual power generation is greater than the installed capacity, or the actual power generation is less than zero, or the actual electricity price is less than zero, the corresponding simulation scenario is removed.

[0011] In some embodiments, determining the distribution characteristics of historical electricity volume deviation and historical electricity price deviation based on the historical electricity trading data includes: The historical electricity volume deviation and the historical electricity price deviation are determined based on the historical electricity trading data. A first candidate distribution is determined based on the statistical characteristics of the historical electricity consumption deviation, and a second candidate distribution is determined based on the statistical characteristics of the historical electricity price deviation. The distribution parameters of the first candidate distribution and the second candidate distribution are estimated respectively, and the goodness of fit is checked according to the distribution parameters respectively to determine the optimal first distribution type in the first candidate distribution and the optimal second distribution type in the second candidate distribution. The distribution features include the first distribution type and the second distribution type. Calculate the Pearson correlation coefficient and Spearman correlation coefficient between the historical electricity consumption deviation and the historical electricity price deviation, and based on the Pearson correlation coefficient and the Spearman correlation coefficient, determine the joint distribution characteristics of the historical electricity consumption deviation and the historical electricity price deviation through a connection function. The distribution characteristics also include the joint distribution characteristics.

[0012] In some embodiments, after determining and outputting the target declared electricity based on the target decision coefficient and the predicted electricity value, the method further includes: Output the expected return, electricity accuracy compliance rate, penalty risk value, and risk-reward ratio obtained from the maximum expected return solution.

[0013] To achieve the above objectives, another aspect of this application proposes a new energy power trading control system, the system comprising: The data collection module is used to acquire historical electricity trading data, as well as current predicted electricity values ​​and day-ahead electricity prices; The statistical analysis module is used to determine the distribution characteristics of historical electricity volume deviation and historical electricity price deviation based on the historical electricity trading data. The scenario analysis module is used to generate Monte Carlo scenarios related to actual power generation and actual electricity price based on the distribution characteristics, the predicted power value and the day-ahead electricity price, and obtain a scenario set; The prediction module is used to calculate the maximum expected revenue based on the expected revenue calculation formula, with the scenario set and preset constraints as constraints, according to the predicted electricity value and the day-ahead electricity price, to obtain the target decision coefficient. The expected revenue calculation formula and the preset constraints include relevant data items or conditions related to accuracy penalties. The output module is used to determine and output the target declared electricity based on the target decision coefficient and the predicted electricity value.

[0014] To achieve the above objectives, another aspect of this application provides a computer device including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-described method.

[0015] To achieve the above objectives, another aspect of the embodiments of this application proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0016] The embodiments of this application include at least the following beneficial effects: This application provides a new energy power trading control method, system, device, and medium. This scheme obtains historical power trading data, current predicted power value, and day-ahead electricity price. Based on the analysis of historical power trading data, it determines the distribution characteristics of historical power deviation and historical electricity price deviation. Based on these distribution characteristics, it generates a Monte Carlo scenario by sampling the predicted power value and day-ahead electricity price. The Monte Carlo scenario simulates the actual power generation and actual electricity price. Then, based on the current predicted power value and day-ahead electricity price, it solves for the maximum expected return by combining the expected return calculation formula with preset constraints and the scenario set of the Monte Carlo scenario, and obtains the target decision coefficient. Thus, it determines and outputs the target declared power based on the target decision coefficient and the predicted power value. Compared to the adjustment coefficient, which is difficult to guarantee ACC compliance and thus incurs penalties, this application's solution incorporates accuracy penalties as one of the constraints in the process of solving for the maximum expected return. Then, the target decision coefficient is solved, allowing the target decision coefficient to take into account the impact of accuracy penalties caused by electricity accuracy on expected return. Thus, under the premise that the predicted electricity value itself is uncertain, the target decision coefficient of this solution provides a target declared electricity volume that minimizes accuracy penalties, thereby increasing the expected return of new power supply electricity trading and reducing penalty risks, balancing the risks and benefits. Attached Figure Description

[0017] Figure 1 This is a flowchart of a new energy power trading control method provided in an embodiment of this application; Figure 2 yes Figure 1 Flowchart of step S102; Figure 3 yes Figure 1 Flowchart of step S103; Figure 4 yes Figure 1 A flowchart of an embodiment of step S104; Figure 5 yes Figure 1 A flowchart of another embodiment of step S104; Figure 6 This is a schematic diagram of the structure of the new energy power trading control system provided in the embodiments of this application; Figure 7 This is a schematic diagram of the hardware structure of the computer device provided in the embodiments of this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0019] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0020] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0022] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.

[0023] 1) The day-ahead winning bid volume refers to the volume of electricity declared and won by the power generator in the day-ahead market. Its unit is generally MWh. It is determined by the product of the predicted volume value and the adjustment coefficient (which is also equivalent to the decision coefficient of this application). It is the most important parameter decided by the power generator and affects the transaction revenue.

[0024] 2) Actual power generation refers to the actual amount of electricity generated by a new energy power plant in the real-time market. Its unit is generally MWh. However, it is subject to fluctuations due to factors such as weather (such as irradiance and wind speed) and equipment status. Therefore, there is an unavoidable deviation from the predicted power generation value before the transaction. The adjustment coefficient is used to make up for this deviation as much as possible through decision-making.

[0025] 3) Day-ahead electricity price refers to the winning bid price in the day-ahead market, which is determined before the start of the transaction and is a known fixed parameter in revenue calculation.

[0026] 4) Actual electricity price refers to the settlement price in the real-time market. It is affected by supply and demand factors such as grid load, renewable energy generation and fuel prices, and will fluctuate with the day-ahead electricity price known before the transaction.

[0027] In related technologies, the revenue from spot trading of renewable energy electricity follows the formula: Revenue = (Actual Generation - Day-ahead Bid-Winning Volume) × (Actual Electricity Price - Day-ahead Electricity Price). The difference between the actual generation and the day-ahead bid-winning volume directly affects the revenue or loss. In addition, the size of the difference also affects the accuracy index (ACC) of the power grid assessment, which is associated with the risk of penalties. Therefore, even if the difference is positive, an excessively large difference may lead to the ACC exceeding the limit, thus offsetting the trading revenue.

[0028] To improve spot trading returns and reduce ACC exceedances, new energy power generation companies can multiply their projected power generation by an adjustment factor when reporting their power generation before the reporting date. Currently, the strategy for determining the adjustment factor generally only considers the relationship between quantity difference and returns, with a typical adjustment factor range of 0.8 to 1.2. In practice, if the adjustment factor is set too small, it is difficult to significantly improve spot trading returns, while if the adjustment factor is set too large, it may lead to ACC exceedances and trigger penalties, affecting the final trading returns.

[0029] In view of this, this application provides a new energy power trading control method, system, device, and medium. This scheme obtains historical power trading data, current predicted power value, and day-ahead electricity price. Based on the analysis of historical power trading data, it determines the distribution characteristics of historical power deviation and historical electricity price deviation. Based on these distribution characteristics, it generates a Monte Carlo scenario by sampling the predicted power value and day-ahead electricity price. The Monte Carlo scenario simulates the actual power generation and actual electricity price. Then, based on the current predicted power value and day-ahead electricity price, it solves for the maximum expected return by combining the expected return calculation formula with preset constraints and the scenario set of the Monte Carlo scenario, obtaining the target decision coefficient. Finally, it determines and outputs the target declared power based on the target decision coefficient and the predicted power value. Compared to the adjustment coefficient, which is difficult to guarantee ACC compliance and thus incurs penalties, this application's solution incorporates accuracy penalties as one of the constraints in the process of solving for the maximum expected return. Then, the target decision coefficient is solved, allowing the target decision coefficient to take into account the impact of accuracy penalties caused by electricity accuracy on expected return. Thus, under the premise that the predicted electricity value itself is uncertain, the target decision coefficient of this solution provides a target declared electricity volume that minimizes accuracy penalties, thereby increasing the expected return of new power supply electricity trading and reducing penalty risks, balancing the risks and benefits.

[0030] The new energy power trading control method provided in this application relates to the field of new energy power trading technology. The new energy power trading control method provided in this application can be applied to a terminal, a server, or software running on a terminal or server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, smart speaker, smartwatch, or vehicle terminal, but is not limited to these. The server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The server can also be a node server in a blockchain network. The software can be an application implementing the new energy power trading control method, but is not limited to the above forms.

[0031] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0032] Figure 1 This is an optional flowchart of the new energy power trading control method provided in the embodiments of this application. Figure 1 The method may include, but is not limited to, steps S101 to S105.

[0033] Step S101: Obtain historical electricity trading data, as well as the current predicted electricity value and day-ahead electricity price; This application proposes to combine historical electricity trading data and analyze it from a statistical perspective to determine the regular relationship between actual electricity generation, day-ahead winning bid electricity (i.e., predicted electricity value and adjustment coefficient), actual electricity price and day-ahead electricity price. Based on this regular relationship, the application calculates the most suitable target decision coefficient as the adjustment coefficient using the current predicted electricity value and day-ahead electricity price.

[0034] Therefore, historical electricity trading data is first obtained, specifically data within the target time period, which can be set to the most recent year or the most recent six months. This historical electricity trading data includes statistics on historical predicted electricity volume, historical actual electricity generation, historical day-ahead electricity price, historical real-time electricity price, and historical day-ahead winning bid volume. Each data point has a specific time-based granularity, such as 15 minutes or 1 hour. This granularity facilitates analysis of specific time periods in subsequent steps, improving the accuracy of pattern summarization.

[0035] On the other hand, the projected electricity volume and day-ahead electricity price required for the current transaction are also obtained. It should be noted that the ultimate goal of this application is to determine a suitable target decision coefficient, i.e., an adjustment coefficient. This target decision coefficient is used to multiply the projected electricity volume to determine the appropriate target declared electricity volume. The day-ahead electricity price is a known parameter and cannot be used for decision-making. The projected electricity volume is obtained through predictions from other schemes and is also considered a known parameter in this application, and similarly does not constitute a decision for this application. In addition, the projected electricity volume is inherently uncertain because it is obtained through prediction, which is also a limitation of other schemes. This application designs an optimal trading scheme that balances risk and return based on this uncertainty.

[0036] Step S102: Determine the distribution characteristics of historical electricity volume deviation and historical electricity price deviation based on historical electricity trading data; In some embodiments, before conducting specific data analysis, the historical electricity trading data is first cleaned to remove abnormal data.

[0037] The analysis of historical electricity trading data starts with historical electricity deviation and historical electricity price deviation. It statistically analyzes the distribution characteristics of historical electricity deviation and historical electricity price deviation in each time period from a time direction, so as to support the reconstruction of its data trend based on the distribution characteristics in subsequent steps.

[0038] refer to Figure 2 In some embodiments, step S102 includes: Step S201: Determine the historical electricity volume deviation and historical electricity price deviation based on historical electricity trading data; Step S202: Determine the first candidate distribution based on the statistical characteristics of historical electricity consumption deviation, and determine the second candidate distribution based on the statistical characteristics of historical electricity price deviation; Step S203: Estimate the distribution parameters of the first candidate distribution and the second candidate distribution respectively, and perform goodness-of-fit verification based on the distribution parameters to determine the optimal first distribution type among the first candidate distributions and the optimal second distribution type among the second candidate distributions. The distribution features include the first distribution type and the second distribution type. Step S204: Calculate the Pearson correlation coefficient and Spearman correlation coefficient of historical electricity consumption deviation and historical electricity price deviation, and based on the Pearson correlation coefficient and Spearman correlation coefficient, determine the joint distribution characteristics of historical electricity consumption deviation and historical electricity price deviation through the connection function. The distribution characteristics also include joint distribution characteristics.

[0039] Specifically, historical power generation deviation is determined based on the difference between historical actual power generation and historical predicted power generation for each historical period, and historical electricity price deviation is determined based on the difference between historical real-time electricity price and historical day-ahead electricity price. Then, statistical analysis is performed on the historical power generation deviation and historical electricity price deviation for each historical period to analyze their possible distribution types, which are defined as the first candidate distribution and the second candidate distribution, respectively. The statistical analysis can examine the kurtosis, skewness, and tail probability of the data. If the deviation exhibits heavy tail characteristics, i.e., a high probability of extreme values, it may be a t-distribution or a skewed t-distribution. If the deviation is a proportion of the [0,1] interval, it may be a Beta distribution. If the deviation is approximately symmetrically distributed, it may be a normal distribution. The aforementioned t-distribution, Beta distribution, and normal distribution are the possible distribution types.

[0040] Then, the distribution parameters of each possible distribution type in the candidate distributions are estimated. Estimation methods can include maximum likelihood estimation or Bayesian estimation. For example, for the t-distribution, its distribution parameters include degrees of freedom, mean, and standard deviation; for the Beta distribution, its distribution parameters include α and β parameters. Based on the estimated distribution parameters, a goodness-of-fit test is performed. Specifically, the Akaike information criterion (AIC) and / or the Kolmogorov-Smirnov test (KS) can be used to evaluate the fit of different distributions. The distribution type with the smallest fitting error and / or the highest statistical significance is selected, thereby determining the first distribution type of historical electricity deviation and the second distribution type of historical electricity price deviation.

[0041] The first and second distribution types are used to describe the individual data patterns of historical electricity consumption deviation and historical electricity price deviation, respectively. However, this scheme needs to further describe the correlation between historical electricity consumption deviation and historical electricity price deviation. Therefore, the Pearson correlation coefficient (PCCs) and Spearman's rank correlation coefficient are calculated for historical electricity consumption deviation and historical electricity price deviation. Both coefficients can be used to measure the correlation between the two variables. Then, based on the Pearson and Spearman correlation coefficients, the joint distribution pattern of historical electricity consumption deviation and historical electricity price deviation is analyzed through a copula function (such as Gaussian Copula or Clayton Copula), determining the influence relationship between the two variables and obtaining the joint distribution characteristics. In this way, the first distribution type of historical electricity consumption deviation, the second distribution type of historical electricity price deviation, and the joint distribution characteristics of historical electricity consumption deviation and historical electricity price deviation are obtained, totaling three distribution characteristics.

[0042] By specifically analyzing the distribution characteristics related to historical power deviation and historical electricity price deviation, this study supports the analysis of data patterns among historical predicted power, historical actual power generation, historical day-ahead electricity price, and historical predicted real-time electricity price, thereby improving the accuracy of the maximum expected return solution.

[0043] Step S103: Based on the distribution characteristics, predicted electricity values ​​and day-ahead electricity prices, sample Monte Carlo scenarios related to actual electricity generation and actual electricity prices are generated to obtain a scenario set; The Monte Carlo method is a numerical computation method based on random sampling. It probabilistically models the uncertainties in a system, generates a large number of random samples to simulate various possible scenarios, and then performs statistical analysis on the sampling results to ultimately approximate the true probabilistic characteristics of the system. In this embodiment, based on the current predicted electricity volume and day-ahead electricity price, combined with the electricity volume deviation and price deviation that satisfy the above distribution characteristics, the actual electricity volume and actual electricity price are treated as uncertainties. The simulated scenario is reconstructed through a Monte Carlo simulation to support the solution of the expected revenue calculation formula in subsequent steps.

[0044] refer to Figure 3 In some embodiments, step S103 includes: Step S301: Reconstruct the actual power generation based on the predicted power value and the power deviation that meets the distribution characteristics; reconstruct the actual electricity price based on the day-ahead electricity price and the price deviation that meets the distribution characteristics; and sample to generate a preset number of simulation scenarios, each of which includes several consecutive time periods. Step S302: The preset number of simulated scene groups are combined into a scene set.

[0045] Specifically, a preset number of simulated scenarios are generated by sampling. The preset number falls within a certain range, such as 1,000 to 5,000. The preset number needs to ensure that the fluctuation range of expected returns and risk losses is less than or equal to a preset range (e.g., 5%) when the number is increased. The generated scenarios are defined as the simulated scenarios. Each simulated scenario simulates several consecutive time periods. For example, a simulated scenario is a whole day, including 24 time periods divided into hours. All simulated scenarios are combined to form the scenario set.

[0046] On the other hand, the simulated scenario corresponds to electricity trading data. Based on the current predicted electricity value and the day-ahead electricity price, and combined with the distribution characteristic analysis of electricity deviation and price deviation from the above embodiments, the sum of the predicted electricity value and the electricity deviation is calculated to reconstruct the actual electricity generation. The sum of the day-ahead electricity price and the price deviation is then calculated to reconstruct the actual electricity price. Specifically, the electricity deviation must satisfy a first distribution type, the price deviation must satisfy a second distribution type, and the electricity deviation and price deviation must also satisfy a joint distribution characteristic.

[0047] This restoration operation enables the reconstruction of actual power generation and actual electricity price that conform to historical data patterns in simulated scenarios spanning continuous time periods. Furthermore, in simulated scenarios with a preset number of groups, it can reconstruct various possible values ​​and probability distributions of actual power generation and actual electricity price for different days based on the distribution characteristics of power generation and price deviations. While fully reflecting the possible value range, it can also reflect the confidence interval, thereby supporting subsequent steps to solve for the maximum expected return through the Monte Carlo scenario.

[0048] In step S301 of some embodiments, the process of sampling to generate a preset number of simulated scenarios further includes: When the actual generated electricity is greater than the installed capacity, or the actual generated electricity is less than zero, or the actual electricity price is less than zero, the corresponding simulation scenario is removed.

[0049] Although the predicted electricity volume and day-ahead electricity price conform to physical or market laws, and their distribution characteristics also conform to the laws of data development, the sum of the predicted electricity volume and the electricity volume deviation, as well as the sum of the day-ahead electricity price and the electricity price deviation, may still be affected by various interference factors, leading to the calculation of actual electricity volume or actual electricity price that does not conform to physical or market laws.

[0050] Therefore, during the generation of the simulation scenario, the reconstructed actual power generation and actual electricity price are simultaneously verified to determine whether the actual power generation is greater than or equal to zero and less than or equal to the installed capacity, and whether the actual electricity price is greater than or equal to zero. If any of the following conditions is met: actual power generation is greater than the installed capacity, actual power generation is less than zero, or actual electricity price is less than zero, the simulation scenario is judged as abnormal and discarded to prevent interference with subsequent steps in calculating the maximum expected return, thereby improving the accuracy of expected return and target decision coefficients.

[0051] Step S104: Based on the expected return calculation formula, with the scenario set and preset constraints as constraints, the maximum expected return is solved according to the predicted electricity value and the day-ahead electricity price to obtain the target decision coefficient. The expected return calculation formula and preset constraints include relevant data items or conditions related to accuracy penalties. Specifically, the adjustment coefficients to be calculated are defined as decision coefficient variables. These decision coefficient variables also need to correspond to the time periods of each simulation scenario, enabling the electricity reporting strategy to flexibly adapt to changes in actual electricity generation at different times of the day. Based on this, the expected return calculation formula for electricity trading is set, referring to the following formula (1): (1) in, To maximize expected return, N is a preset quantity, and T is the number of time periods divided in each scenario. This is the actual amount of electricity generated. For decision coefficient variables, To predict the power consumption value, This is the actual electricity price. The current day electricity price, For battery accuracy, The relevant function for accuracy penalties. Therefore, Equivalent to the electricity volume reported in the previous day, This is equivalent to the power consumption deviation during the corresponding time period. This is equivalent to the electricity price deviation for the corresponding time period.

[0052] Based on the expected return calculation formula, the current predicted electricity value and day-ahead electricity price can be substituted into the formula. With the constraints of the preset conditions, the accuracy penalty in the calculation formula, and the data patterns of actual power generation and actual electricity price reflected by the scenario set, the decision coefficient variable that can obtain the maximum expected return can be solved and determined as the target decision coefficient.

[0053] Among them, the accuracy penalty in the expected return calculation formula It is a factor related to battery accuracy. The relevant functions. The calculation method for electricity accuracy is ACC = (Daily Bid Winnings - Actual Generation) / Actual Generation. Therefore, electricity accuracy can be calculated based on the decision coefficient variables, predicted electricity values, and actual generation. Furthermore, since the Monte Carlo scenario set represents various possibilities for actual generation, various possibilities regarding electricity accuracy can also be included in the solution process. On the other hand, functions... The functional form is related to the rules of local power grids and needs to be determined according to local penalty rules, thereby determining the accuracy penalty based on the accuracy of electricity consumption. By setting the accuracy penalty as a data item and adding it to the expected return calculation formula, it can be used as one of the constraints in the subsequent solution process. This allows the solution to take into account the impact of the accuracy penalty caused by electricity consumption accuracy on the expected return, thereby reducing the penalty risk.

[0054] refer to Figure 4 In step S104 of some embodiments, based on the expected return calculation formula, and with the scenario set and preset constraints as constraints, the maximum expected return is solved according to the predicted electricity value and the day-ahead electricity price to obtain the target decision coefficient, including: Step S401: Define the decision coefficient variables corresponding to the time period; Step S402: Based on the expected return calculation formula, input the predicted electricity value and the day-ahead electricity price. With preset constraints and the actual electricity generation and actual electricity price simulated in the scenario set as constraints, and with the maximum expected return as the objective, use a stochastic programming solver to solve the decision coefficient variables using nonlinear programming or sequential quadratic programming to obtain the target decision coefficients.

[0055] The solution method can be a stochastic programming solver. Based on the characteristics of the expected return calculation formula and the preset constraints, nonlinear programming or sequential quadratic programming can be used for the solution.

[0056] In the solution process, the relationships between expected revenue, actual power generation, decision coefficient variables, predicted power value, actual electricity price, day-ahead electricity price, and accuracy penalty are based on the expected revenue calculation formula; the accuracy penalty is calculated using a function. Based on the accuracy of electricity generation; the predicted electricity generation value and the day-ahead electricity price are the current input values; the actual electricity generation and the actual electricity price are constrained by a set of scenarios, and the range and confidence interval of the actual electricity generation and the actual electricity price are determined according to the constraints of the scenario values; combining the above factors, the corresponding decision coefficient variables are solved with the goal of maximizing expected return, and the solved corresponding decision coefficient variables are defined as the target decision coefficients. Since the decision coefficient variables correspond to each time period, the target decision coefficients for a whole day are represented as a vector such as X=[x1,x2,...,x_T].

[0057] By solving for the target decision coefficient, a scenario is simulated by combining the statistical characteristics of historical data. Considering the constraint of accuracy penalty, the adjustment coefficient that can meet the maximum expected return is analyzed based on the current predicted power volume and the day-ahead electricity price. This supports the determination of the target declared power volume and improves the expected return of new power source power trading.

[0058] refer to Figure 5 In step S104 of some embodiments, based on the expected return calculation formula, and with the scenario set and preset constraints as constraints, the maximum expected return is solved according to the predicted electricity value and the day-ahead electricity price to obtain the target decision coefficient, including: Step S501: Define the decision coefficient variables corresponding to the time period; Step S502: Based on the expected return calculation formula, input the predicted electricity value and the day-ahead electricity price. Using the first condition, the second condition, the third condition, and the actual power generation and actual electricity price simulated in the scenario set as constraints, and with the maximum expected return as the objective, solve the decision coefficient variable to obtain the target decision coefficient. Among them, the first condition is that the day-ahead declared electricity is less than or equal to the installed capacity, and the day-ahead declared electricity is the product of the decision coefficient variable and the predicted electricity value; the second condition is that the decision coefficient variable is greater than or equal to zero; the third condition is that the absolute value of the electricity accuracy is less than or equal to the accuracy threshold, and the accuracy penalty is related to the electricity accuracy.

[0059] In the solution process of the above embodiments, preset constraints are involved. Optionally, the preset constraints include a first condition, a second condition, and a third condition.

[0060] The first condition restricts the calculated daily reported electricity volume during the solution process to be less than or equal to the installed capacity, to avoid the final target reported electricity volume exceeding the maximum output, thereby avoiding unachievable results. The second condition restricts the decision coefficient variable to be greater than or equal to zero, because a negative adjustment coefficient has no practical transaction significance. The third condition is that the absolute value of the electricity volume accuracy is less than or equal to the accuracy threshold, which is used to ensure that the electricity volume accuracy meets local requirements. This accuracy threshold is set according to local power grid rules.

[0061] By setting the first, second, and third conditions, the solution to the target decision coefficient can take into account the constraints of the actual probability of achievement and the accuracy penalty, thereby making the target decision coefficient conform to the actual needs and realizing the solution of this application.

[0062] Step S105: Determine and output the target declared electricity volume based on the target decision coefficient and the predicted electricity volume value.

[0063] After the target decision coefficient is calculated, the target declared electricity volume can be determined by multiplying the target decision coefficient and the predicted electricity volume, and the target declared electricity volume can be output to guide users to declare electricity volume in the day-ahead market according to the target declared electricity volume.

[0064] In some embodiments, after step S105, the method further includes: Output the expected return, electricity accuracy compliance rate, penalty risk value, and risk-reward ratio obtained from the maximum expected return solution.

[0065] In addition to the target decision coefficient and the target declared electricity volume, the various data involved in the solution process in step S104 can also be recorded and calculated to obtain the expected return, electricity volume accuracy compliance rate, penalty risk value and risk-reward ratio corresponding to the target decision coefficient, and output these data so that users can fully understand the benefits and risks that the target declared electricity volume can bring.

[0066] Steps S101 to S105 of this application embodiment involve incorporating accuracy penalties as one of the constraints in the process of solving for the maximum expected return, and then solving for the target decision coefficient. This allows the target decision coefficient to take into account the impact of accuracy penalties caused by electricity accuracy on the expected return. Thus, under the premise that the predicted electricity value itself is uncertain, the target decision coefficient of this scheme provides a target declared electricity volume that minimizes accuracy penalties, thereby increasing the expected return of new power supply electricity trading and reducing penalty risks, balancing the risks and returns.

[0067] The following is a detailed description and explanation of the solutions in the embodiments of the present invention, using specific application examples: This application provides a new energy power trading control method, which can be applied to the field of new energy power trading.

[0068] Obtain historical electricity trading data, including historical forecasted electricity volume and historical day-ahead electricity price, as well as obtain the forecasted electricity volume and day-ahead electricity price for the current electricity trading.

[0069] Historical electricity volume deviation and historical electricity price deviation are determined based on historical electricity trading data. A first candidate distribution is determined based on the statistical characteristics of historical electricity volume deviation, and a second candidate distribution is determined based on the statistical characteristics of historical electricity price deviation. Then, the distribution parameters of the first and second candidate distributions are estimated respectively, and goodness-of-fit checks are performed based on the distribution parameters to determine the optimal first distribution type among the first candidate distributions and the optimal second distribution type among the second candidate distributions. The Pearson correlation coefficient and Spearman correlation coefficient of historical electricity volume deviation and historical electricity price deviation are calculated, and based on the Pearson and Spearman correlation coefficients, the joint distribution characteristics of historical electricity volume deviation and historical electricity price deviation are determined through a connection function.

[0070] Based on the predicted electricity volume, day-ahead electricity price, first distribution type, second distribution type, and joint distribution characteristics, the actual electricity generation is reconstructed according to the deviation between the predicted electricity volume and the electricity volume satisfying the first distribution type, and the actual electricity price is reconstructed according to the deviation between the day-ahead electricity price and the price satisfying the second distribution type. Simultaneously, the electricity volume deviation and the price deviation also satisfy the joint distribution characteristics. A preset number of simulation scenarios are sampled and generated, each scenario including several consecutive time periods. These preset number of simulation scenarios are combined into a scenario set. Furthermore, if the reconstructed actual electricity generation is greater than the installed capacity, or the actual electricity generation is less than zero, or the actual electricity price is less than zero, the corresponding simulation scenario is discarded.

[0071] Define decision coefficient variables corresponding to time periods and determine the expected return calculation formula, which includes relevant data items for accuracy penalties. Input the predicted electricity volume and day-ahead electricity price according to the expected return calculation formula. Use the first, second, and third conditions as one constraint, and the actual electricity generation and actual electricity price simulated in the scenario set as another constraint. Through a stochastic programming solver, nonlinear programming or sequential quadratic programming is used to solve for the decision coefficient variables with the objective of maximizing the expected return, obtaining the target decision coefficients. Specifically, the first condition is that the day-ahead declared electricity volume is less than or equal to the installed capacity, and the day-ahead declared electricity volume is the product of the decision coefficient variable and the predicted electricity volume value; the second condition is that the decision coefficient variable is greater than or equal to zero; and the third condition is that the absolute value of the electricity volume accuracy is less than or equal to the accuracy threshold.

[0072] Then, based on the target decision coefficient and the predicted electricity value, the target declared electricity volume is determined and output. The expected return, electricity volume accuracy compliance rate, penalty risk value, and risk-reward ratio, which are also obtained from the maximum expected return solution, are also output.

[0073] This application embodiment incorporates accuracy penalties as one of the constraints in the process of solving for the maximum expected return, and then solves for the target decision coefficient. This allows the target decision coefficient to take into account the impact of accuracy penalties caused by electricity accuracy on the expected return, thereby providing a target declared electricity volume that minimizes accuracy penalties, improving the expected return of new power supply electricity trading and reducing penalty risks.

[0074] Please see Figure 6 This application also provides a new energy power trading control system that can implement the above method. The system includes: The data collection module is used to acquire historical electricity trading data, as well as current predicted electricity values ​​and day-ahead electricity prices; The statistical analysis module is used to determine the distribution characteristics of historical electricity volume deviation and historical electricity price deviation based on historical electricity trading data; The scenario analysis module is used to generate Monte Carlo scenarios related to actual power generation and actual electricity price based on distribution characteristics, predicted power values ​​and day-ahead electricity prices, and obtain a scenario set. The prediction module is used to solve for the maximum expected revenue based on the expected revenue calculation formula, with the scenario set and preset constraints as constraints, according to the predicted electricity value and the day-ahead electricity price, to obtain the target decision coefficient. The expected revenue calculation formula and preset constraints include relevant data items or conditions related to accuracy penalties. The output module is used to determine and output the target declared electricity volume based on the target decision coefficient and the predicted electricity volume.

[0075] It is understood that the content of the above method embodiments is applicable to this system embodiment. The specific functions implemented in this system embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0076] This application also provides a computer device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method. This computer device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0077] It is understood that the content of the above method embodiments is applicable to the present device embodiments. The specific functions implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0078] Please see Figure 7 , Figure 7 The hardware structure of a computer device according to another embodiment is illustrated. The computer device includes: The processor 701 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 702 can be implemented as a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 702 can store the operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 702 and is called and executed by the processor 701 using the methods described in the embodiments of this application. The input / output interface 703 is used to implement information input and output; The communication interface 704 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 705 transmits information between various components of the device (e.g., processor 701, memory 702, input / output interface 703, and communication interface 704); The processor 701, memory 702, input / output interface 703, and communication interface 704 are connected to each other within the device via bus 705.

[0079] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0080] It is understood that the content of the above method embodiments is applicable to this storage medium embodiment. The specific functions implemented in this storage medium embodiment are the same as those in the above method embodiments, and the beneficial effects achieved are also the same as those achieved in the above method embodiments.

[0081] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0082] The new energy power trading control method, system, device, and medium provided in this application embodiment acquire historical power trading data, current predicted power value, and day-ahead electricity price. Based on the analysis of historical power trading data, the distribution characteristics of historical power deviation and historical electricity price deviation are determined. Based on these distribution characteristics, a Monte Carlo scenario is generated by sampling the predicted power value and day-ahead electricity price. The Monte Carlo scenario simulates the actual power generation and actual electricity price. Then, based on the current predicted power value and day-ahead electricity price, the maximum expected return is solved by combining the expected return calculation formula with preset constraints and the scenario set of the Monte Carlo scenario, obtaining the target decision coefficient. Finally, the target declared power is determined and output based on the target decision coefficient and the predicted power value. Compared to the adjustment coefficient, which is difficult to guarantee ACC compliance and thus incurs penalties, this application's solution incorporates accuracy penalties as one of the constraints in the process of solving for the maximum expected return. Then, the target decision coefficient is solved, allowing the target decision coefficient to take into account the impact of accuracy penalties caused by electricity accuracy on expected return. Thus, under the premise that the predicted electricity value itself is uncertain, the target decision coefficient of this solution provides a target declared electricity volume that minimizes accuracy penalties, thereby increasing the expected return of new power supply electricity trading and reducing penalty risks, balancing the risks and benefits.

[0083] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0084] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0085] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0086] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0087] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0088] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0089] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0090] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0091] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0092] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0093] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for controlling the trading of new energy electricity, characterized in that, The method includes the following steps: Obtain historical electricity trading data, as well as current forecasted electricity volume and day-ahead electricity price; The distribution characteristics of historical electricity volume deviation and historical electricity price deviation are determined based on the historical electricity trading data. Based on the distribution characteristics, the predicted electricity value, and the day-ahead electricity price sampling, Monte Carlo scenarios related to actual electricity generation and actual electricity price are generated to obtain a scenario set; Based on the expected return calculation formula, and with the scenario set and preset constraints as constraints, the maximum expected return is solved according to the predicted electricity value and the day-ahead electricity price to obtain the target decision coefficient. The expected return calculation formula and the preset constraints include relevant data items or conditions related to accuracy penalties. The target declared electricity volume is determined and output based on the target decision coefficient and the predicted electricity volume value.

2. The method according to claim 1, characterized in that, The process of generating Monte Carlo scenarios related to actual power generation and actual electricity price based on the distribution characteristics, the predicted power consumption value, and the day-ahead electricity price sampling yields a scenario set, including: The actual power generation is restored based on the predicted power value and the power deviation that meets the distribution characteristics. The actual electricity price is restored based on the day-ahead electricity price and the price deviation that meets the distribution characteristics. A preset number of simulation scenarios are sampled and generated. Each simulation scenario includes several consecutive time periods. The preset number of simulated scenarios are combined to form the scenario set.

3. The method according to claim 2, characterized in that, The method based on the expected return calculation formula, using the scenario set and preset constraints as constraints, solves for the maximum expected return based on the predicted electricity value and the day-ahead electricity price to obtain the target decision coefficient, including: Define decision coefficient variables corresponding to the time period; Based on the expected return calculation formula, the predicted electricity value and the day-ahead electricity price are input. With the preset constraints, the actual electricity generation and the actual electricity price simulated by the scenario set as constraints, and with the maximum expected return as the objective, the decision coefficient variables are solved by a stochastic programming solver using nonlinear programming or sequential quadratic programming to obtain the target decision coefficient.

4. The method according to claim 2, characterized in that, The preset constraints include a first condition, a second condition, and a third condition. The step of calculating the maximum expected return based on the expected return formula, using the scenario set and the preset constraints as constraints, and solving for the target decision coefficient based on the predicted electricity volume and the day-ahead electricity price, includes: Define decision coefficient variables corresponding to the time period; Based on the expected return calculation formula, the predicted electricity value and the day-ahead electricity price are input. Constrained by the first condition, the second condition, the third condition, and the actual electricity generation and the actual electricity price simulated in the scenario set, the decision coefficient variable is solved with the goal of maximizing the expected return to obtain the target decision coefficient. The first condition is that the day-ahead declared electricity is less than or equal to the installed capacity, and the day-ahead declared electricity is the product of the decision coefficient variable and the predicted electricity value. The second condition is that the decision coefficient variable is greater than or equal to zero. The third condition is that the absolute value of the electricity accuracy is less than or equal to the accuracy threshold, and the accuracy penalty is related to the electricity accuracy.

5. The method according to claim 2, characterized in that, The process of generating a preset number of simulated scenarios through sampling also includes: When the restored actual power generation is greater than the installed capacity, or the actual power generation is less than zero, or the actual electricity price is less than zero, the corresponding simulation scenario is removed.

6. The method according to any one of claims 1 to 5, characterized in that, The step of determining the distribution characteristics of historical electricity volume deviation and historical electricity price deviation based on the historical electricity trading data includes: The historical electricity volume deviation and the historical electricity price deviation are determined based on the historical electricity trading data. A first candidate distribution is determined based on the statistical characteristics of the historical electricity consumption deviation, and a second candidate distribution is determined based on the statistical characteristics of the historical electricity price deviation. The distribution parameters of the first candidate distribution and the second candidate distribution are estimated respectively, and the goodness of fit is checked according to the distribution parameters respectively to determine the optimal first distribution type in the first candidate distribution and the optimal second distribution type in the second candidate distribution. The distribution features include the first distribution type and the second distribution type. Calculate the Pearson correlation coefficient and Spearman correlation coefficient between the historical electricity consumption deviation and the historical electricity price deviation, and based on the Pearson correlation coefficient and the Spearman correlation coefficient, determine the joint distribution characteristics of the historical electricity consumption deviation and the historical electricity price deviation through a connection function. The distribution characteristics also include the joint distribution characteristics.

7. The method according to any one of claims 1 to 5, characterized in that, After determining and outputting the target declared electricity volume based on the target decision coefficient and the predicted electricity volume value, the method further includes: Output the expected return, electricity accuracy compliance rate, penalty risk value, and risk-reward ratio obtained from the maximum expected return solution.

8. A new energy power trading control system, characterized in that, The system includes: The data collection module is used to acquire historical electricity trading data, as well as current predicted electricity values ​​and day-ahead electricity prices; The statistical analysis module is used to determine the distribution characteristics of historical electricity volume deviation and historical electricity price deviation based on the historical electricity trading data. The scenario analysis module is used to generate Monte Carlo scenarios related to actual power generation and actual electricity price based on the distribution characteristics, the predicted power value and the day-ahead electricity price, and obtain a scenario set; The prediction module is used to calculate the maximum expected revenue based on the expected revenue calculation formula, with the scenario set and preset constraints as constraints, according to the predicted electricity value and the day-ahead electricity price, to obtain the target decision coefficient. The expected revenue calculation formula and the preset constraints include relevant data items or conditions related to accuracy penalties. The output module is used to determine and output the target declared electricity based on the target decision coefficient and the predicted electricity value.

9. A computer device, characterized in that, The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images