Multi-market transaction prediction method for virtual power plant

Abstract

The embodiment of the invention relates to the field of data processing, in particular to a multi-market transaction prediction method and system for a virtual power plant. The method comprises the steps of obtaining first predicted output data based on historical electricity prices, user load data and time-of-use electricity prices before a transaction, obtaining a first preset total energy demand through correction of a load fuzzy response model, and generating a day-ahead market bidding strategy and a first bidding electricity price; and on the same day of the transaction, acquiring second predicted output data based on the real-time data, receiving the first bidding result, correcting the first bidding result to obtain a second preset total energy demand, and generating a real-time market bidding strategy and a second bidding electricity price. And after the second bidding result is received, dynamically adjusting the real-time preset total energy demand, optimizing the power scheduling and charging and discharging strategy of the energy storage system, and balancing the energy reserve after the transaction. According to the method, the bounded rationality problem of the controllable load in the demand response process is solved, the user demand response result and the DER are effectively combined, and a solution is provided for the VPP to participate in the bidding plan of multiple types of power markets.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of data processing, and in particular to a multi-market transaction prediction method and system for a virtual power plant. Background Art

[0002] In recent years, distributed power sources have developed rapidly. Their reliability, economy, flexibility and environmental protection characteristics have made renewable energy such as wind power and photovoltaics increasingly popular. However, the output of these distributed power sources is random and uncontrollable, which poses a challenge to the safe and stable operation of the power system. Virtual power plant (VPP) technology can effectively deal with these problems. By aggregating distributed energy resources (DER), energy storage equipment (such as batteries and electric vehicles) and controllable loads, and using energy management systems (EMS) for coordinated optimization, it can not only smooth out the output fluctuations of wind power and photovoltaics, but also help improve the reliability and flexibility of the power system, thereby maximizing economic benefits.

[0003] Among the related technologies, VPP has been widely used in auxiliary services such as the day-ahead market, real-time market, forward contract market and reserve market. In addition, VPP improves system flexibility and creates additional revenue by participating in multiple markets, demand response (DR) schemes and aggregated energy storage. Compared with traditional energy storage, electric vehicles are relatively easy to be included in the power market for charging and discharging management because they are idle most of the time. In the operation of EMS, through information exchange with electric vehicle owners, information such as the grid connection and off-grid time, driving distance, etc. of each electric vehicle can be obtained, so as to formulate corresponding charging and discharging strategies to ensure that the driving needs of electric vehicles are met. This orderly management method enables idle electric vehicles to actively participate in the power market, support peak and frequency regulation, and form synergy with wind and photovoltaic power generation.

[0004] As another important component of VPP, controllable loads usually participate in the power system through demand response. In related technologies, the research on distribution network optimization dispatch modeling can be divided into four categories: first, establishing a demand price elasticity matrix to reflect the user's sensitivity to electricity prices, but unable to explain its rationality; second, maximizing the utility function, assuming that users are completely rational, but the actual situation is often not the case; third, using questionnaires to collect user preferences, but this method is time-consuming and not accurate enough; fourth, the prediction method based on deep learning, its "black box" characteristics lead to a lack of credibility and explainability, making it difficult to support EMS decision-making. It is necessary to develop a segmented incentive demand response (SIBDR) strategy for commercial and residential users based on the power consumption characteristics of different users, while for industrial users, an IBDR strategy with transferable load management and a PBDR strategy are adopted.

[0005] In summary, it is urgent to propose a new technical solution to solve the problem of limited rationality of controllable loads in the demand response process, and to achieve an effective combination of user demand response results and DER, and to propose solutions for VPPs to participate in bidding plans for multiple electricity markets. Summary of the invention

[0006] In view of the technical problems existing in the prior art, the embodiments of the present application provide a multi-market transaction prediction method and system for a virtual power plant, which are used to solve the limited rationality problem of controllable loads in the demand response process, and to achieve an effective combination of user demand response results and DER, and to propose solutions for VPP's bidding plan for participating in multiple types of electricity markets.

[0007] In a first aspect, an embodiment of the present application provides a multi-market transaction prediction method and system for a virtual power plant, the method comprising:

[0008] Before participating in multi-market transactions, obtain the first predicted output data of the preset energy in each time period based on historical electricity price data, user load historical data, and time-of-use electricity price information;

[0009] Correcting the first predicted output data by using a load fuzzy response mechanism model to obtain a first preset total energy demand in each time period;

[0010] Generate a day-ahead market bidding strategy and corresponding first bidding electricity price information based on the first preset total energy demand;

[0011] On the day of participating in multi-market transactions, obtain the second predicted output data of the preset energy in each time period based on the real-time electricity price data, user load real-time data, and time-of-use electricity price information;

[0012] After receiving the first bidding result matching the day-ahead market bidding strategy and the first bidding electricity price information, based on the first bidding result, the second predicted output data, and the user load real-time data, the second predicted output data is corrected through a load fuzzy response mechanism model to obtain a second preset total energy demand in each time period;

[0013] Based on the second preset total energy demand and the collected user real-time load response data, generate a real-time market bidding strategy and corresponding second bidding electricity price information;

[0014] After receiving the real-time market bidding strategy and the second bidding result matching the second bidding electricity price information, dynamically adjusting the corresponding real-time preset total energy demand in the current period through the load fuzzy response mechanism model;

[0015] Based on the real-time preset total energy demand, the power dispatch strategy and the charging and discharging strategy of the energy storage system are optimized to balance the energy reserves after multi-market transactions.

[0016] In a second aspect, an embodiment of the present application provides a multi-market transaction prediction system for a virtual power plant, the system comprising the following units, wherein:

[0017] The day-ahead transaction prediction unit is configured to obtain first predicted output data of a preset energy source in each time period according to historical electricity price data, user load historical data, and time-of-use electricity price information before participating in multi-market transactions; correct the first predicted output data through a load fuzzy response mechanism model to obtain a first preset energy total demand in each time period; generate a day-ahead market bidding strategy and corresponding first bidding electricity price information based on the first preset energy total demand;

[0018] The real-time transaction prediction unit is configured to obtain, on the day of participating in multi-market transactions, second predicted output data of the preset energy in each time period according to real-time electricity price data, user load real-time data, and time-of-use electricity price information; after receiving the first bidding result matching the day-ahead market bidding strategy and the first bidding electricity price information, based on the first bidding result, the second predicted output data, and the user load real-time data, correct the second predicted output data through the load fuzzy response mechanism model to obtain the second preset energy total demand in each time period; based on the second preset energy total demand and the collected user real-time load response data, generate a real-time market bidding strategy and corresponding second bidding electricity price information;

[0019] The balancing adjustment unit is configured to dynamically adjust the corresponding real-time preset total energy demand in the current period through the load fuzzy response mechanism model after receiving the second bidding result matching the real-time market bidding strategy and the second bidding electricity price information; based on the real-time preset total energy demand, optimize the power dispatching strategy and charging and discharging strategy of the energy storage system to balance the energy reserves after multi-market transactions.

[0020] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising:

[0021] at least one processor, memory, and input-output unit;

[0022] Wherein, the memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the multi-market transaction prediction method of the virtual power plant of the first aspect.

[0023] In a fourth aspect, a computer-readable storage medium is provided, which includes instructions, which, when executed on a computer, enable the computer to execute the multi-market transaction prediction method for a virtual power plant of the first aspect.

[0024] The beneficial effect of the embodiment of the present application is: a multi-market transaction prediction method and system for a virtual power plant is provided. In this technical solution, before participating in multi-market transactions, the first predicted output data of the preset energy in each time period is obtained according to the historical electricity price data, the user load historical data, and the time-of-use electricity price information. The first predicted output data is corrected by the load fuzzy response mechanism model to obtain the first preset energy total demand in each time period. The day-ahead market bidding strategy and the corresponding first bidding electricity price information are generated based on the first preset energy total demand. Furthermore, on the day of participating in multi-market transactions, the second predicted output data of the preset energy in each time period is obtained according to the real-time electricity price data, the user load real-time data, and the time-of-use electricity price information. After receiving the first bidding result matching the day-ahead market bidding strategy and the first bidding electricity price information, the second predicted output data is corrected by the load fuzzy response mechanism model based on the first bidding result, the second predicted output data, and the user load real-time data, to obtain the second preset energy total demand in each time period. Based on the second preset energy total demand and the collected user real-time load response data, the real-time market bidding strategy and the corresponding second bidding electricity price information are generated. After receiving the second bidding result that matches the real-time market bidding strategy and the second bidding electricity price information, the corresponding real-time preset total energy demand in the current period is dynamically adjusted through the load fuzzy response mechanism model. Finally, based on the real-time preset total energy demand, the power scheduling strategy and charging and discharging strategy of the energy storage system are optimized to balance the energy reserves after multi-market transactions. This technical solution can solve the limited rationality problem of controllable loads in the demand response process, and realize the effective combination of user demand response results and DER, and propose solutions for VPP's bidding plan to participate in multiple types of electricity markets. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a flow chart of a multi-market transaction prediction method for a virtual power plant according to an embodiment of the present application;

[0026] Figures 2 to 8 It is a schematic diagram of the principle of a multi-market transaction prediction method for a virtual power plant in an embodiment of the present application;

[0027] Fig. 9 This is a structural diagram of a multi-market transaction prediction system for a virtual power plant according to an embodiment of the present application;

[0028] Fig.10 is a schematic diagram of the structure of an electronic device according to an embodiment of the present application;

[0029] Fig.11 It is a structural schematic diagram of a medium device according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0031] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0032] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be interpreted as being more preferred or more advantageous than other embodiments. In order to enable any technician in the field to implement and use the embodiments of the present application, the following description is given. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the embodiments of the present application can also be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details that make the description of the embodiments of the present application obscure. Therefore, the embodiments of the present application are not intended to be limited to the embodiments shown, but are consistent with the widest range of principles and features disclosed in the present application.

[0033] Among the related technologies, virtual power plant (VPP) technology has been widely used in auxiliary services such as the day-ahead market, real-time market, forward contract market and reserve market. By aggregating distributed energy resources, energy storage equipment and controllable loads, it can improve the flexibility of the power system and create additional revenue. Electric vehicles are easy to be included in the power market for charging and discharging management because they are idle most of the time. In the energy management system (EMS), information can be exchanged with electric vehicle owners to obtain information such as the grid connection and off-grid time, driving distance and other information of each vehicle, so as to formulate charging and discharging strategies to meet the driving needs of electric vehicles, provide support for peak and frequency regulation, and form synergy with wind and photovoltaic power generation.

[0034] At present, the research on distribution network optimization dispatch modeling is mainly divided into four categories. The first is based on the demand price elasticity matrix, while the second assumes that users are completely rational to maximize utility, which is inconsistent with the actual situation. The third method collects user preferences through questionnaires, but it is inefficient and inaccurate. Finally, although the prediction method based on deep learning improves the prediction accuracy, it lacks interpretability and is difficult to use for EMS decision-making. Therefore, it is necessary to develop suitable demand response strategies based on the power consumption characteristics of different users, such as segmented incentive demand response (SIBDR) and transferable load management (IBDR).

[0035] Further analysis shows that there are at least the following reasons for the above problems: First, although the current price-based demand response (PBDR) model can reflect the user's sensitivity to electricity prices, it lacks a deep understanding of user behavior and cannot explain the rationality of user decisions. Second, in many models based on utility functions, it is assumed that users are completely rational, which is inconsistent with the actual situation, resulting in the optimization results being unable to reflect the needs and behaviors of real users. Third, the method of obtaining user preferences through questionnaires is time-consuming and prone to inaccuracies, making it difficult to promote in practical applications. Fourth, although the prediction model based on deep learning can improve the prediction accuracy, due to its "black box" characteristics, it lacks interpretability, which makes it difficult for these models to provide reliable support for energy management system (EMS) decision-making. Fifth, although there are segmented incentive demand response (SIBDR), transferable load management (IBDR) and price-based demand response (PBDR) strategies for commercial, residential and industrial users, the design of these strategies often does not fully consider the social attributes and limited rationality of various types of users, which increases the complexity of optimization scheduling.

[0036] It is urgent to propose a completely new technical solution to solve at least one of the above technical problems.

[0037] The embodiment of the present application provides a multi-market transaction prediction method and system for a virtual power plant. In this technical solution, before participating in multi-market transactions, the first predicted output data of the preset energy in each time period is obtained according to the historical electricity price data, the user load historical data, and the time-of-use electricity price information. The first predicted output data is corrected by the load fuzzy response mechanism model to obtain the first preset energy total demand in each time period. The day-ahead market bidding strategy and the corresponding first bidding electricity price information are generated based on the first preset energy total demand. Furthermore, on the day of participating in multi-market transactions, the second predicted output data of the preset energy in each time period is obtained according to the real-time electricity price data, the user load real-time data, and the time-of-use electricity price information. After receiving the first bidding result matching the day-ahead market bidding strategy and the first bidding electricity price information, the second predicted output data is corrected by the load fuzzy response mechanism model based on the first bidding result, the second predicted output data, and the user load real-time data, to obtain the second preset energy total demand in each time period. Based on the second preset energy total demand and the collected user real-time load response data, the real-time market bidding strategy and the corresponding second bidding electricity price information are generated. After receiving the second bidding result matching the real-time market bidding strategy and the second bidding electricity price information, the corresponding real-time preset total energy demand in the current period is dynamically adjusted through the load fuzzy response mechanism model. Finally, based on the real-time preset total energy demand, the power dispatch strategy and charging and discharging strategy of the energy storage system are optimized to balance the energy reserves after multi-market transactions.

[0038] From a technical point of view, limited rationality means that the behavior of users in the process of demand response is not completely rational and may be affected by many factors, such as cognitive ability, information asymmetry, psychological factors, etc. To overcome these problems, in the embodiment of the present application, the predicted output data process can be corrected. Specifically, collecting and processing historical data, such as historical electricity price data, user load historical data, and time-of-use electricity price information, is the basis for prediction. Through these data, the load change law of users at different electricity prices and time periods can be understood. Based on historical data and user behavior patterns, machine learning or time series analysis methods are used to predict the output data of preset energy in each time period to obtain the first predicted output data. The load fuzzy response mechanism model can use Logistic regression or other prediction models to simulate user load transfer and response behavior, correct the first predicted output data, and obtain a more accurate first preset energy total demand. Then, a multi-market bidding strategy is generated. Specifically, the day-ahead market bidding strategy (DAM) formulates the day-ahead market bidding strategy and the corresponding bidding electricity price information based on the revised first preset energy total demand. In this way, the DAM bidding is generated and submitted to obtain the first bidding result. The real-time market bidding strategy (RTM) is to obtain the second predicted output data based on the real-time electricity price data, user load real-time data and time-of-use electricity price information on the day of the transaction. Combined with the previous first bidding results, the load fuzzy response mechanism model is used to revise again to obtain the second preset total energy demand in each time period. Based on the second preset total energy demand and user real-time load response data, the real-time market bidding strategy and the corresponding bidding electricity price information are generated to conduct RTM bidding.

[0039] In addition, in order to cope with limited rationality strategies, logistic models or other adaptive models are used to capture user behavior patterns and predict their load responses at different electricity prices and time periods. Through model parameter training, not only can the accuracy of load response prediction be improved, but also the weights can be continuously adjusted to cope with changes in user behavior. In actual operation, the model is constantly modified and iterated using real-time data. For example, according to the second predicted output data and real-time load response data, the model parameters are dynamically adjusted to make the prediction closer to reality.

[0040] At the same time, the energy storage system (ESS) strategy is also adjusted and optimized. Based on the real-time market bidding results and the second preset total energy demand in the current period, the power dispatch and charging and discharging strategies of the ESS are formulated. Through the strategy of discharging the energy storage system during peak hours and charging during off-peak hours, the power supply and demand are balanced, and the use and benefits of the energy storage system are optimized. Combined with the fluctuations of real-time load and market prices, the demand in the current period is dynamically adjusted through the load fuzzy response mechanism model, so that supply and demand are balanced in each time period.

[0041] Of course, we also combine the transaction characteristics of the multilateral market, integrate the bidding results of DAM and RTM and the actual response of users, comprehensively analyze the bidding strategies in multiple markets, and optimize the overall economic benefits. By constantly adjusting the model and strategy, we ensure that the bidding plan remains efficient and flexible in different markets.

[0042] In summary, this technical solution uses historical and real-time data to predict and correct through the load fuzzy response mechanism model to ensure accurate prediction and real-time adjustment. The user load response behavior is analyzed through the Logistic model, and the model is gradually corrected and optimized taking into account the limited rationality of the user. Based on the characteristics of different markets, accurate bidding strategies are formulated and dynamically adjusted to ensure that economic benefits are maximized in multi-market transactions. Through the reasonable scheduling of the energy storage system, the supply and demand relationship is further balanced, and the overall reliability and economy of the system are improved. Through the above technical solutions, VPP can effectively deal with the limited rationality of users in the demand response process, and realize the effective combination of user demand response results and DER output. This not only improves the accuracy of the prediction, but also optimizes the bidding strategy in multi-market transactions.

[0043] The multi-market transaction prediction scheme of the virtual power plant provided in the embodiment of the present application can also be executed by an electronic device, which can be a server, a server cluster, or a cloud server. The electronic device can also be a terminal device such as a mobile phone, a computer, a tablet computer, a wearable device, or a dedicated device (such as a dedicated terminal device with a multi-market transaction prediction system for a virtual power plant). These electronic devices can also be equipped with the chips introduced in the above embodiments. Alternatively, these electronic devices can also be installed with a service program for executing a multi-market transaction prediction scheme for a virtual power plant.

[0044] Figure 1 A flowchart of a multi-market transaction prediction method for a virtual power plant provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method comprises the following steps:

[0045] 101. Before participating in multi-market transactions, obtain the first predicted output data of the preset energy in each time period based on historical electricity price data, user load historical data, and time-of-use electricity price information;

[0046] 102, correcting the first predicted output data through a load fuzzy response mechanism model to obtain a first preset total energy demand in each time period;

[0047] 103. Generate a day-ahead market bidding strategy and corresponding first bidding electricity price information based on the first preset total energy demand;

[0048] 104. On the day of participating in multi-market transactions, obtain the second predicted output data of the preset energy in each time period according to the real-time electricity price data, the real-time user load data, and the time-of-use electricity price information;

[0049] 105, after receiving the first bidding result matching the day-ahead market bidding strategy and the first bidding electricity price information, based on the first bidding result, the second predicted output data, and the user load real-time data, the second predicted output data is corrected through a load fuzzy response mechanism model to obtain a second preset total energy demand in each time period;

[0050] 106. Generate a real-time market bidding strategy and corresponding second bidding electricity price information based on the second preset total energy demand and the collected real-time user load response data;

[0051] 107, after receiving the second bidding result matched with the real-time market bidding strategy and the second bidding electricity price information, dynamically adjusting the corresponding real-time preset total energy demand in the current period through the load fuzzy response mechanism model;

[0052] 108. Based on the real-time preset total energy demand, optimize the power dispatch strategy and the charging and discharging strategy of the energy storage system to balance the energy reserves after multi-market transactions.

[0053] In the embodiment of the present application, the distributed resources aggregated by the VPP are as follows: micro gas turbine (MG), wind turbine (WT), photovoltaic station (PV), energy storage system (ESS), EVs and household loads (HL). Among them, HL includes fixed load, transferable load and interruptible load, and uses 1-norm and ∞-norm to constrain the uncertainty set of electricity price with incomplete probability distribution.

[0054] In this embodiment, the virtual power plant (VPP) aggregates multiple distributed energy resources to optimize power dispatch and bidding strategies. The micro gas turbine (MG) has the ability to start and stop quickly, and is used to provide stable power output, especially as a backup power source when renewable energy fluctuates greatly. The wind turbine (WT) uses wind energy to generate electricity. The uncertainty of wind speed makes its output volatile, which is suitable for use in combination with other stable power sources. Photovoltaic units (PV) use solar energy to generate electricity, which is greatly affected by weather and light intensity and has daytime peak power generation characteristics. The energy storage system (ESS) is used to store excess electricity, which can release electricity when electricity demand peaks or prices are high, balance electricity supply and demand, and provide flexible dispatch capabilities. Electric vehicles (EVs) are not only mobile loads, but also energy storage devices that feed electricity back to the grid and participate in demand response. Household loads (HL) include three types of loads: fixed loads, that is, the basic electricity demand that users cannot change on a daily basis. Transferable loads, loads that can be scheduled in different time periods, such as washing machines or charging equipment. Interruptible loads, loads that can be temporarily interrupted when electricity is tight or electricity prices are high, such as air conditioners and other equipment.

[0055] In the above steps 101 to 108, first, before participating in multi-market transactions, it is necessary to obtain the first predicted output data of the preset energy in each time period based on the historical electricity price data, the user load historical data and the time-of-use electricity price information. The purpose of this step is to make a preliminary prediction of the preset energy based on the historical data to obtain the preliminary output data of each time period. These historical data include historical electricity price curves, user electricity consumption records and future electricity price plans. By using time series analysis, regression models or machine learning models (such as LSTM, ARIMA, etc.), the output of the preset energy in different time periods can be predicted to obtain the first predicted output data of each time period. Next, the first predicted output data is corrected by the load fuzzy response mechanism model to take into account the user's load response behavior, so that the predicted data is more accurate. The load fuzzy response mechanism model can use the Logistic regression model to simulate the user's load response behavior under different electricity prices, thereby correcting the first predicted output data and obtaining a more realistic total energy demand in each time period, that is, the first preset total energy demand.

[0056] Then, based on the revised total demand for the first preset energy, a day-ahead market bidding strategy and the corresponding first bidding electricity price information are generated. To this end, it is necessary to determine the electricity demand for each time period, calculate a reasonable bidding amount and the corresponding electricity price, and generate a day-ahead market bidding plan, including expected electricity purchase and sales amounts and corresponding quotations. On the day of the transaction, it is necessary to obtain the second predicted output data of the preset energy in each time period based on the real-time electricity price data, the real-time data of the user load, and the time-of-use electricity price information. This step is to update the forecast based on the latest real-time data to reflect the actual situation of the day. Similarly, by using the above-mentioned forecasting model, the output data of each time period can be re-forecasted to obtain the second predicted output data updated on the day.

[0057] Next, combined with the bidding results of the day-ahead market, the output data of each time period of the day is further corrected through the load fuzzy response mechanism model to obtain the second preset total energy demand for each time period. To this end, it is necessary to combine the actual transaction volume and electricity price (first bidding result) of the day-ahead market, and consider the user's real-time load data to correct the second predicted output data, so as to obtain a more accurate second preset total energy demand for the day. Based on the second preset total energy demand and the user's real-time load response data, it is necessary to generate a real-time market bidding strategy and the corresponding second bidding electricity price information. This step is to bid in the real-time market to maximize revenue or reduce costs. By calculating the bidding volume and quotation of the real-time market, the bidding strategy and the second bidding electricity price information of the real-time market can be formulated. After receiving the second bidding result matching the real-time market bidding strategy and the second bidding electricity price information, the real-time preset total energy demand of the current time period is dynamically adjusted through the load fuzzy response mechanism model. This step dynamically adjusts and corrects the total demand of the current time period in real time according to the transaction results of the real-time market to accurately reflect the actual supply and demand situation.

[0058] Finally, based on the adjusted real-time preset total energy demand, the dispatch strategy and charging and discharging strategy of the energy storage system are optimized to balance the energy reserves after multi-market transactions. To this end, it is necessary to formulate and optimize the power dispatch strategy of the energy storage system, including the discharge strategy during peak load periods and the charging strategy during low load periods, so as to balance the energy reserves and ensure the stability and economy of the system.

[0059] Through the systematic process of the above steps, virtual power plants can effectively participate in multi-market transactions, solve various challenges, achieve optimal integration of demand response and energy resources, and maximize economic benefits and grid stability.

[0060] In an embodiment of the present application, before participating in the multi-power market bidding, the virtual power plant (VPP) needs to consider the response effect of the customers it serves to the time-of-use electricity price, and make effective adjustments based on the actual response behavior of the users. According to research on consumer psychology, changes in electricity prices will have a complex impact on users' demand responses: electricity price differences that are too large or too small, as well as the smoothness of the responsiveness curve when electricity prices change, will affect users' response behavior. Under the electricity price incentive mechanism, users participate in the response on a voluntary basis, so their behavior has significant randomness. Specifically, the user's actual demand response curve will be between the optimistic response prediction curve and the pessimistic response prediction curve, and will exhibit certain fuzzy properties. This fuzzy property reflects the user's demand adjustment behavior that cannot be fully predicted when facing changes in electricity prices.

[0061] In order to more accurately predict and adjust the output data of the preset energy, VPP needs to adopt a load fuzzy response mechanism model. This model comprehensively considers the possible behavior of users under different electricity price conditions, weights the optimistic and pessimistic response prediction values, and forms a real response prediction value between the two. In this way, the virtual power plant can formulate bidding strategies more flexibly and accurately in a changing market environment to meet actual electricity demand while maximizing economic benefits.

[0062] In the embodiment of the present application, the load fuzzy response mechanism model refers to guiding users to transfer loads based on their fuzzy response behavior to time-of-use electricity prices, thereby optimizing the bidding strategy of virtual power plants (VPPs). This model takes into account the psychological reaction of users to electricity price changes and their uncertainty, and models and analyzes them through fuzzy logic.

[0063] Optionally, the load fuzzy response mechanism model is constructed based on a logistic algorithm. Specifically, the embodiment of the present application uses a load fuzzy response mechanism model based on logistic to guide users to transfer loads according to time-of-use electricity prices, as a bidding basis for VPPs to participate in market transaction bidding strategy predictions.

[0064] Among them, the stages of the load fuzzy response mechanism model are divided into: dead zone, response zone, and saturation zone. Different stages have different response characteristics and calculation methods. Further optionally, the user response behavior in the dead zone is determined by the average of the optimistic and pessimistic response predictions. This means that the model takes into account the possible responses of users in extreme cases (optimistic and pessimistic), and takes the average value to reflect the random response behavior of users when the electricity price difference is small. The electricity price difference is small, the user is not sensitive to changes in electricity prices, and the response behavior has greater randomness. In this area, since the electricity price difference is not enough to motivate users to significantly change their electricity consumption behavior, the user response is low. Further optionally, the user response behavior in the response zone is calculated by taking the optimistic response membership as the probability constraint of the demand response mechanism and using a biased semi-trapezoidal membership function. The optimistic response membership reflects the probability that the user responds to the optimistic estimate under the electricity price difference. The user response is calculated using a biased semi-trapezoidal membership function. As the electricity price difference increases, users become sensitive to changes in electricity prices and their response enthusiasm increases. The user's response behavior tends to be more optimistic, that is, they are more willing to reduce electricity consumption during peak electricity prices and increase electricity consumption during valley hours. Further optionally, the user's response behavior in the saturated area is determined based on the maximum value of the load transfer rate. When the price difference reaches a certain level, the user's responsiveness to changes in electricity prices reaches saturation, and no matter how large the price difference is, it will not significantly increase the user's responsiveness. Users have fully responded to changes in electricity prices in this area, and their load transfer rate has reached the maximum value. The user's response behavior is directly based on the maximum value of the load transfer rate, which means that the user's response behavior is no longer affected by further changes in the price difference.

[0065] In the above steps, further optionally, the step of correcting the first predicted output data or the second predicted output data by using the load fuzzy response mechanism model can be implemented as follows:

[0066] The corresponding load transfer rate in each time period is calculated through the load fuzzy response mechanism model; the load transfer rate is composed of at least an optimistic response prediction value and a pessimistic response prediction value; the load transfer rate in each time period is used to correct the second predicted output data to obtain the second preset total energy demand in each time period.

[0067] For example, suppose there is a simple virtual power plant (VPP) whose customers include residential and commercial users. The electricity demand of these users in different time periods varies due to changes in electricity prices. The goal is to simulate the load response behavior of users through the load fuzzy response mechanism model and modify the predicted output data accordingly. Collect historical electricity price data, user load historical data, and time-of-use electricity price information. Use optimistic response prediction values ​​and pessimistic response prediction values. For example, for a period T1, historical data shows that the user's electricity consumption will decrease by 10% to 30% during high electricity price periods. 10% is set as the pessimistic response prediction value and 30% is set as the optimistic response prediction value. The load transfer rate refers to the ratio of the user's load transferred from one period to another. For each period, two values ​​are calculated: the optimistic response transfer rate (based on the optimistic prediction value) and the pessimistic response transfer rate (based on the pessimistic prediction value).

[0068] Assume that the initial forecast output data for a period T1 is 100MW. The load fuzzy response mechanism model is used to apply the load transfer rate to correct the initial forecast output data. Assuming that the calculated load transfer rate for the T1 period is 20% (an intermediate value between the optimistic and pessimistic forecasts), the revised preset total energy demand is reduced by 20%. In this way, the load transfer rate is used to correct the forecast output data for each period. Therefore, if the initial forecast output data is 100MW and the load transfer rate is 20%, the revised preset total energy demand will be 80MW.

[0069] In actual application, this correction method is also applicable to the second predicted output data of the day. Assuming that the latest real-time predicted output data of the day is 90MW and the load transfer rate is 15%, the corrected preset total energy demand will be 76.5MW. By calculating the load transfer rate, the model can more accurately simulate user response behavior, thereby adjusting the forecast data more accurately. This method not only helps the virtual power plant to optimize the bidding strategy in the day-ahead market and the real-time market, but also can better carry out the dispatch strategy of the energy storage system, ultimately making the entire system more competitive and economical in the process of participating in multi-market transactions.

[0070] For example, taking peak-valley load transfer as an example, a fuzzy response mechanism model based on logistic function is established, such as Figure 2 shown. Figure 2 In, λ PV is the load transfer rate, which can be used to describe the corresponding values ​​of different electricity price differences and different response curves, that is, the corresponding part of the curve in the figure; m is the optimistic response membership, which is used to describe the probability that the user meets the optimistic response estimate, that is, the area enclosed by the large semi-trapezoidal membership function in the bar chart. is the electricity price difference; a pv and b pvIt is the demarcation point for the regional division of electricity price difference. This model is divided into dead zone, response zone and saturation zone. In the dead zone, the electricity price difference is too small, and the user response behavior is highly random, so it is determined by the average of the optimistic and pessimistic response predictions. In the response zone, as the electricity price difference increases, the user's response enthusiasm is mobilized, and the response behavior is more inclined to the optimistic response curve. Therefore, the optimistic response membership is considered and used as a probabilistic constraint of the demand response mechanism. The large-scale semi-trapezoidal membership function is used for calculation. In the saturation zone, the two curves coincide, and the user response behavior can be expressed by the maximum value of the load transfer rate.

[0071] The logistic function uses variable parameters to increase the span of load transfer rate changes, and its function model is shown in formula (1). The response area is used to characterize the behavioral characteristics of users who tend to be more optimistic about the response curve. The optimistic response membership corresponding to different electricity price differences is used as a probability constraint, and the comprehensive load transfer rate is shown in formulas (2) and (3).

[0072] As an optional embodiment, the logistic function involved in this application is expressed as the following formula:

[0073]

[0074] In the above formula, λ PV is the load transfer rate, which is used to describe the corresponding values ​​of different electricity price differences and different response curves; is the electricity price difference; a, c, μ are known quantities in the Logistic function; b is a variable parameter.

[0075] Further optionally, the calculation process of the comprehensive load transfer rate in the load transfer rate corresponding to each time period calculated by the load fuzzy response mechanism model is expressed as:

[0076]

[0077] Among them, a pv and b pv The regional demarcation point for electricity price difference; PV / is the actual load transfer rate; m is the optimistic response membership, which is used to describe the probability that the user meets the optimistic response estimate; λ PV min , PV max are the load transfer rates for pessimistic and optimistic response predictions, respectively.

[0078] Further, optionally, the actual load transfer rate λ from peak to flat and from flat to valley in the corresponding load transfer rate in each time period is calculated by the load fuzzy response mechanism model. PF / 、λ FV / After that, the load transfer amount and load value after user demand response are calculated as follows:

[0079]

[0080] L t =L t0 +Q t (5)

[0081] Among them, T P 、T F 、T V Corresponding to peak, valley and normal times of electricity prices respectively; The average values ​​of loads during peak, flat and valley periods before the implementation of time-of-use electricity prices respectively; Q t is the load transfer amount due to demand response at time t; L t0 , L t They are the load values ​​before and after the implementation of time-of-use electricity prices at time t respectively.

[0082] In the embodiment of the present application, under the optimistic response prediction, a is 0.1, b is 0, c is 0.4, and μ is 0.1; under the pessimistic response prediction, a is 0.104, b is -0.0036, c is 0.4, and μ is 0.1; the demarcation point a for the electricity price difference division area is pv 0.1 yuan / kWh,b pv It is 0.7 yuan / kWh.

[0083] As an optional embodiment, the optimization of the power dispatching strategy and the charging and discharging strategy of the energy storage system based on the real-time preset total energy demand can be implemented as follows: based on the real-time preset total energy demand, the corresponding charging and discharging recommendation information and the power dispatching strategy of the energy storage system are obtained. Furthermore, after optimizing the power dispatching strategy and the charging and discharging strategy of the energy storage system based on the real-time preset total energy demand in 108, the charging and discharging recommendation information can also be pushed to the owners of various types of vehicles; the balancing market operation is started, and the corresponding amount is delivered based on the power dispatching strategy of the energy storage system to absorb the output deviation of renewable energy.

[0084] In this optional embodiment, more efficient energy management is achieved by optimizing the power dispatching strategy and charging and discharging strategy of the energy storage system based on the real-time preset total energy demand. First, determine the real-time preset total energy demand, which can be obtained from various forecasting and monitoring systems of the power grid. On this basis, subsequent operations can be performed more accurately. First, optimize the power dispatching strategy of the energy storage system based on the real-time preset total energy demand. This includes deciding when to charge and when to discharge to balance the load and demand of the power grid. Second, refine the specific charging and discharging plans to ensure that the energy storage system charges and discharges the battery at the most appropriate time. This strategy will be formulated based on factors such as real-time demand changes, price signals, and the current state of the energy storage system.

[0085] Next, based on the optimized energy storage system strategy, charging and discharging recommendation information suitable for various types of electric vehicles connected to the grid is generated. These recommendations are adjusted according to the current electricity price, vehicle battery status and expected usage patterns. Then, the generated charging and discharging recommendations are pushed to the vehicle owner through an application or other communication methods. The owner can adjust their charging and discharging behavior based on these recommendations. Some owners may choose to charge during periods of low electricity prices and feed electricity back to the grid during periods of high electricity prices.

[0086] Virtual power plants (VPPs) have begun to participate in balancing market operations. The goal of this market is to balance real-time grid supply and demand, and to absorb the output deviation of renewable energy by dispatching energy storage systems and other flexible resources. According to the power dispatch strategy of the energy storage system, the VPP performs corresponding fund settlement in the balancing market. This settlement process includes paying or obtaining funds to balance the supply and demand imbalance caused by the output deviation of renewable energy.

[0087] In this way, real-time data derived from current load and power demand forecasts is used to guide the next energy management operation. By optimizing the scheduling and charging and discharging strategies of the energy storage system, renewable energy can be used efficiently and the problems caused by the mismatch between supply and demand can be reduced. This information is provided directly to electric vehicle owners to help them charge or discharge at the right time to match the overall grid demand. This is a real-time market that is mainly used to balance the supply and demand differences of the power grid. By adjusting the energy storage system and other flexible resources, the output deviation of renewable energy with strong volatility can be absorbed. In the balancing market, through the scheduling strategy of the energy storage system, operators and other participants will have corresponding funds delivered to compensate for the supply and demand imbalance caused by the output deviation of renewable energy.

[0088] Through this implementation, the virtual power plant can not only optimize the scheduling and charging and discharging strategies of the energy storage system based on real-time energy demand, but also effectively mobilize electric vehicle owners to participate in optimizing energy use. Ultimately, in the balancing market operation, the virtual power plant not only absorbs the output deviation of renewable energy, but also maximizes economic benefits.

[0089] In the bilateral open electricity market trading model, both generators and users can participate in it, and the settlement is based on the unified clearing price of the electricity market at the end of the transaction. There are both generators and loads in the VPP, so in each trading period, the VPP can choose to participate in the bidding as a generator or a user. Based on the capacity limit of the VPP, this application considers the VPP participating in the trading activities of the electricity market as a price receiver, and the VPP's quotation will not affect the market clearing results. When the VPP acts as a price receiver, it can submit a lower electricity sales price and a higher electricity purchase price to the market operator (MO), thereby ensuring that all the bid electricity (sales or purchase) is successful, and the VPP only needs to optimize its bid electricity according to the predicted electricity market price. The electricity markets in which VPP participates include bilateral contract markets, date markets, real-time markets, and balancing markets, and its bidding process is divided into the following three stages:

[0090] Day-ahead market: Before DAM opens, VPP signs a contract with MO in the bilateral contract market and completes the preliminary trading plan. The DAM market opens at 10 a.m. on the day before the trading day. At this time, the wind power and photovoltaic output, DAM and RTM electricity prices are unknown. EMS formulates corresponding bidding strategies based on historical data forecast results and submits the day-ahead bidding plan to MO. The next day, VPP needs to complete the DAM transaction according to the submitted bidding electricity. At 13:00 on the day before the trading day, the DAM market closes and MO clears the DAM electricity price.

[0091] Real-time market: On the trading day, the RTM market is opened period by period. At this time, the DAM electricity price and bidding power are known, and the wind power and photovoltaic output forecast values ​​are more accurate. EMS re-formulates and submits the RTM bidding strategy to MO period by period. Similarly, during the trading period, VPP needs to complete the RTM transaction according to the submitted bidding power. MO clears the RTM electricity price after the RTM market closes.

[0092] Balancing market: During the trading period, EMS optimizes the operating power of each aggregation unit in VPP in real time and completes the power transaction. MO settles the transaction with VPP according to the DAM and RTM clearing prices. The balancing market is opened after the RTM closes. It is responsible for absorbing the deviation of wind power and photovoltaic power output and charging VPP for the cost of balancing power. The specific implementation form is that when the actual output is greater than the planned output, VPP sells the excess power at a price lower than the RTM unified clearing price. Otherwise, VPP purchases the insufficient power at a price higher than the RTM unified clearing price.

[0093] In the first stage, VPP guides users to make load transfers according to the time-of-use electricity price based on the fuzzy response mechanism of the logistic function, and uses the result after demand response as the total amount of bidding in multiple markets. Considering that the bidding power of DAM and RTM must meet the power balance constraint, the bidding power of VPP in RTM will affect the bidding power of DAM. Therefore, VPP formulates the bidding strategies of DAM and RTM at the same time, but only needs to submit the bidding strategy of DAM. The objective function of its bidding model is divided into four parts, as shown in formula (13). The first part represents the bidding cost of DAM, the second part represents the power cost of micro gas turbine, the third part represents the compensation cost of IBDR project, and the last part represents the battery loss cost of electric vehicle.

[0094]

[0095]

[0096] In the above formula, formula (7) represents the bidding cost of DAM, With D CON Sign bilateral contracts on behalf of VPP for electricity prices and volumes, and represents the predicted DAM and RTM electricity prices, k B With k S Represents the power purchase coefficient and the power sales coefficient, corresponding to the ratio of the power purchase price of the VPP participating in the bidding to the power sales price and the market power price, P t DA and Represents the amount of electricity purchased and sold by DAM, P t RT and represents the power purchase and sales of RTM. Formula (8) represents the power cost of the gas turbine, P GT.t represents the gas turbine output, a GT 、b GT With c GT Represent the cost coefficient, k GT with u GT Represents the startup cost and startup status of the gas turbine, n f Represents the amount of pollutant gas, Q gt represents the emission intensity of the fth pollutant gas from the gas turbine, V f With Y f They represent the environmental value and fine magnitude of the fth pollutant gas, respectively. The specific implementation standards are derived from the environmental value table of pollutants in China's power industry. Formula (9) represents the compensation cost of the IBDR project. represents the incentive cost of the shiftable load, Represents the transferable load. A positive value indicates that the load is reduced during period t, while a negative value indicates that the load is increased. represents the amount of transferable load in HL, represents the fuzzy response of user load based on logistic function before DAM is turned on. The relationship between the two corresponds to formula (16), n r Represents the interrupt level number, represents the compensation price for the rth level of interrupted load, represents the interruption load of level r in period t. (10) represents the battery loss cost of EV, n v is the number of EVs, is the battery purchase cost of the vth EV, is the number of charge and discharge cycles in the battery life cycle of the vth EV, is the battery capacity of the vth EV, is the discharge depth of the vth EV battery, which is taken as 100% in this application. and is the charging power and discharging power of the vth car in time period t, and is the charging efficiency and discharging efficiency of the vth car, and Represent the status flags of EV charging, discharging and traveling respectively, and are restricted by formula (24). is the driving distance of the vth EV in period t, k EV is the power consumed by the vth EV per unit driving distance. Formula (11) limits the range of variation of the signed bilateral contract volume, where With D BC Indicates the range of variation and the specified bilateral contract quantity. Formula (12) is the restriction on power purchase and power sales in DAM and RTM at time t. Formula (13) is the restriction on power purchase and power sales in DAM and RTM. Formula (14) is the output restriction of MG, and formula (15) is the ramp power restriction of MG. Formula (17) limits the power of load that can be transferred at time t, where Corresponding to the maximum load that can be transferred by HL at time t, formula (18) limits the total amount of load that can be transferred by HL in one day. Formula (19) limits the power of each level of interruptible load at time t, where is the maximum share of each level of interruptible load, and formula (20) limits the interruption amount of each level of interruptible load at adjacent moments, and is the maximum interruptible share of each level of interruptible load in adjacent time periods. Formulas (21)-(27) are the constraints of EV, while formulas (28)-(34) are the constraints of ESS. It is worth noting that and That is, the charging and discharging power of ESS, which is also the first-stage variable. Formulas (35) and (36) represent the power limits of WT and PV, where and represents the predicted value of WT and PV output in the DA market during period t. Formula (37) represents the internal power balance constraint of the VPP.

[0097] In the second stage, VPP needs to formulate RTM bidding strategies for each period. At this time, the clearing price and bidding quantity of DAM are known quantities, and the predicted values ​​of wind power and photovoltaic output are close to the actual situation. On the basis of retaining the bidding results of DAM and the variables of the first stage, the bidding model of the second stage is:

[0098]

[0099] In the above formula, They represent the bilateral contract signing amount, power purchase amount, power sales amount, clearing power price, MG output and transferable load based on incentives in DAM during period t. represents the fuzzy response of the user load based on the logistic function before RTM is turned on. The newly added constraint (48) limits the interruptible load. and Corresponding to the real-time predicted values ​​of WT and PV output at time period t, (52) updates the power balance.

[0100] As an optional embodiment, after receiving the second bid result that matches the real-time market bidding strategy and the second bidding electricity price information, the last round of rolling can be performed on the IBDR project after the real-time market RTM is closed on the day of participating in multi-market transactions; the settlement information of the day is calculated according to the day-ahead market bidding strategy and the real-time market bidding strategy; the settlement information of the day includes at least: the clearing electricity price, and the electricity market transaction settlement information corresponding to the virtual power plant.

[0101] After receiving the second bidding results that match the real-time market bidding strategy and the second bidding electricity price information, the virtual power plant (VPP) can further optimize and execute the multi-market trading process. The virtual power plant formulates corresponding bidding strategies based on changes in the real-time market to ensure that the optimal quotation and output level are maintained under current conditions. Reconfirm and adjust the output plan of the virtual power plant based on the electricity price information obtained in the second bidding stage and the corresponding bidding results. After the real-time market is closed, the virtual power plant makes the final round of rolling adjustments to the flexible load demand response project (IBDR). This step is mainly to fine-tune and optimize when actual supply and demand change. According to the bidding strategies of the day-ahead market and the real-time market, the virtual power plant calculates the settlement information of the day. The settlement information of the day includes the following two key parts:

[0102] Clearing price: It is the electricity transaction price determined by the market after the supply and demand are balanced. The clearing price is usually determined by a unified calculation based on the bids and electricity demand of all participants. This is a market equilibrium price.

[0103] Electricity market transaction settlement information: The transaction volume of virtual power plants includes the actual transaction volume in different markets (such as the day-ahead market and the real-time market). Calculate the total revenue of virtual power plants in each market and the fees to be paid. Revenue includes income from electricity sales, and fees may include electricity purchase costs, fines (such as fines for failure to supply electricity as planned), etc. If a country or region has incentives for demand response, virtual power plants can obtain corresponding subsidies or incentives based on their response.

[0104] In the day-ahead market, the virtual power plant determines its electricity sales volume and corresponding revenue in the day-ahead market based on its bidding strategy and market clearing results. In the real-time market, the virtual power plant determines its electricity sales volume and revenue in the real-time market based on its real-time adjusted bidding strategy and market clearing results. Combining the results of the day-ahead market and the real-time market, the virtual power plant summarizes and calculates its total settlement information for the whole day. This includes total electricity sales, total revenue and total expenses. Through the above steps, the virtual power plant can accurately calculate and obtain comprehensive settlement information for the day, thereby clarifying its revenue situation in multi-power market transactions. This not only helps the virtual power plant optimize its operating strategy, but also provides data support for future trading decisions.

[0105] In the third phase, the RTM market is closed and the IBDR project executes the last round of rolling. MO settles the first two phases of transactions in the power market with VPP according to the clearing electricity prices of DAM and RTM, and sends the confirmed EV charging and discharging plans to car owners. At the same time, the balancing market is opened, and VPP needs to pay a certain amount of money to absorb the output deviation of renewable energy. The bidding model for the third phase is:

[0106]

[0107] (28)-(41)(64)

[0108]

[0109] In the above formula, They represent the power purchase, power sales, clearing price, and MG output in RTM during period t. Represents the fuzzy response of user load based on logistic function after RTM is closed. and They represent the ratio of the purchase price and sales price of MO to the clearing price when the balancing market absorbs the unbalanced power in period t. and Corresponding to the actual values ​​of WT and PV output during period t, (67) is the total power balance.

[0110] To verify the validity of the above model, this application selects a VPP consisting of a gas turbine, an energy storage device, a wind turbine, a photovoltaic unit and 4,000 households. The pollutants emitted by the micro gas turbine are set to CO2, CO, SO2, NO x The emission quantity, environmental value and fine magnitude are shown in Table 1. T = 24, the source load output in each time period is as follows Figure 3 shown.

[0111] Table 1 Micro gas turbine pollutant gas parameters

[0112]

[0113] For example, 4000 sets of electricity prices from the day-ahead market and the real-time market in Henan Province, China are selected and clustered into four typical scenarios. The specific electricity prices and initial probability distributions are shown in Figure 4 , where the peak and valley periods of various electricity prices follow the notice issued by the Henan Provincial Development and Reform Commission in 2022. To distinguish the purchase price from the sales price, the purchase coefficient is set to 1.1 and the sales price is set to 0.9. In the balanced market, the purchase price and sales price are 1.3 and 0.8 times the real-time market clearing price, respectively. Assuming that 4,000 households own 1,000 EVs of Nissan LEAF, BYD E6, Mitsubishi iMi and BMW MINIE types, the parameters of EVs and their travel patterns are shown in Table 2, and other equipment parameters are shown in Table 3.

[0114] Table 2 EV parameters

[0115]

[0116] Table 3 Main operating parameters of VPP

[0117]

[0118] Through example simulation, the fuzzy response results of HL based on logistic function proposed in this application are as follows Figure 5 As shown, the bidding results of VPP and the power balance are as follows Figure 6 As shown, the IBDR results are as follows Figure 7 As shown in Figure 2, the EV travel results are as follows: Figure 8 To illustrate the benefits of VPP aggregating multiple types of resources, the following four benchmarks are used as comparison cases, and the optimization results are shown in Table 4.

[0119] Table 4 Optimization cost of different benchmarks

[0120]

[0121] In the energy market bidding and management process, VPPs can adopt different strategies to optimize their bidding and dispatch decisions. Below is a description of four benchmark approaches:

[0122] Benchmark 1: Multi-market bidding with fixed residential load. In this benchmark approach, VPP does not consider the fuzzy response results of users, but conducts multi-market bidding based on fixed residential load. This means that VPP assumes that all user loads are deterministic and immutable, and does not consider any possible changes in user behavior or uncertainty in response during the bidding process.

[0123] Benchmark 2: IBDR projects that only implement interruptible loads. Under this approach, VPP does not consider the shiftable load portion of residential loads and only implements interruptible loads in demand response (IBDR) projects. This means that VPP only focuses on loads that can be interrupted in a short period of time, while ignoring those loads that can be flexibly adjusted or shifted in time.

[0124] Benchmark 3: Single Level of Interruptible and Shiftable Loads in an IBDR Project. In this benchmark approach, the VPP performs demand response that includes shiftable and interruptible loads in an IBDR project, but only maintains one level of interruptible loads. Thus, while the VPP exploits the flexibility of both load types, it maintains simplicity in its interruption load strategy by managing only one specific level of interruptible loads.

[0125] Benchmark 4: 90% EV participation, 10% only meet travel power requirements. In this approach, the VPP aggregates 90% of EVs to participate in power optimization and electricity market bidding, while the remaining 10% of EVs only meet their basic travel power requirements and do not participate in power optimization. This strategy ensures that most EVs contribute to the balance and optimization of the grid, while the remaining part ensures that users' travel needs are not affected.

[0126] These benchmark strategies demonstrate the decision-making methods and priorities of VPPs in different scenarios, reflecting how VPPs optimize their energy management and market bidding under different user load characteristics and response strategies.

[0127] Compared with benchmark 1, the model proposed in this application takes into account the fuzzy response results made by users based on time-of-use electricity prices. After taking into account the response results of users, VPP reduces the compensation for incentive transferable loads at peak times. Even if a small amount of first-level load interruptions are triggered at valley times (1h and 3h), the reduced power purchase cost still provides help for VPP in the face of interference from unknown information. Comparison with benchmark 2 can better illustrate the advantages of transferable loads in IBDR projects. Although the proportion of transferable loads in the total cost is low, when VPP lacks such resources, it can only eliminate the uncertainty by increasing the amount of electricity purchased. In addition, unlike benchmark 3, which reduces the load transfer amount of IBDR projects and the power purchase cost of VPP by cutting off a large number of interruptable loads, the model proposed in this application takes into account the actual power satisfaction and load priority, and by calling the power conversion of valley loads and the participation of third-level loads at more times (such as 5, 7, 22-24 hours), it not only smoothes the final energy consumption curve, but also brings economic benefits to VPP. Finally, compared with benchmark 4, the model proposed in this application aggregates 10% more electric vehicles to balance power, which not only reduces the burden of purchasing electricity, but also reduces the battery loss of individual electric vehicles. This also proves the advantage of flexible calling of electric vehicle resources in helping to output unknown information interference. The above simulation results verify the effectiveness and practicality of the embodiments of this application. In the process of VPP participating in multi-market bidding, the embodiments of this application take into account the limited rational response results of residential users to time-of-use electricity prices, and effectively combine them with distributed energy, so as to maximize the benefits of VPP under the conditions of smoothing the output fluctuations of renewable energy and meeting power supply needs.

[0128] In the embodiment of the present application, historical and real-time data are used to predict and correct through the load fuzzy response mechanism model to ensure accurate prediction and real-time adjustment. The user load response behavior is analyzed through the Logistic model, and the model is gradually corrected and optimized taking into account the limited rationality of the user. Based on the characteristics of different markets, accurate bidding strategies are formulated and dynamically adjusted to ensure that economic benefits are maximized in multi-market transactions. Through the reasonable scheduling of the energy storage system, the supply and demand relationship is further balanced, and the overall reliability and economy of the system are improved. Through the above technical solution, VPP can effectively deal with the limited rationality of users in the demand response process, and realize the effective combination of user demand response results and DER output. This not only improves the accuracy of the prediction, but also optimizes the bidding strategy in multi-market transactions.

[0129] In another embodiment of the present application, a multi-market transaction prediction system for a virtual power plant is also provided. Fig. 9 The system comprises the following units:

[0130] The day-ahead transaction prediction unit is configured to obtain first predicted output data of a preset energy source in each time period according to historical electricity price data, user load historical data, and time-of-use electricity price information before participating in multi-market transactions; correct the first predicted output data through a load fuzzy response mechanism model to obtain a first preset energy total demand in each time period; generate a day-ahead market bidding strategy and corresponding first bidding electricity price information based on the first preset energy total demand;

[0131] The real-time transaction prediction unit is configured to obtain, on the day of participating in multi-market transactions, second predicted output data of the preset energy in each time period according to real-time electricity price data, user load real-time data, and time-of-use electricity price information; after receiving the first bidding result matching the day-ahead market bidding strategy and the first bidding electricity price information, based on the first bidding result, the second predicted output data, and the user load real-time data, correct the second predicted output data through the load fuzzy response mechanism model to obtain the second preset energy total demand in each time period; based on the second preset energy total demand and the collected user real-time load response data, generate a real-time market bidding strategy and corresponding second bidding electricity price information;

[0132] The balancing adjustment unit is configured to dynamically adjust the corresponding real-time preset total energy demand in the current period through the load fuzzy response mechanism model after receiving the second bidding result matching the real-time market bidding strategy and the second bidding electricity price information; based on the real-time preset total energy demand, optimize the power dispatching strategy and charging and discharging strategy of the energy storage system to balance the energy reserves after multi-market transactions.

[0133] Further optionally, the day-ahead transaction prediction module and / or the real-time transaction prediction unit corrects the first predicted output data or the second predicted output data through a load fuzzy response mechanism model, and is configured as follows:

[0134] The load transfer rate corresponding to each time period is calculated by using the load fuzzy response mechanism model; the load transfer rate is composed of at least an optimistic response prediction value and a pessimistic response prediction value;

[0135] The second predicted output data is corrected by using the load transfer rate in each time period to obtain the second preset total energy demand in each time period.

[0136] Further optionally, the load fuzzy response mechanism model is constructed based on a logistic function; the stages of the load fuzzy response mechanism model are divided into: dead zone, response zone, and saturation zone;

[0137] The logistic function is expressed as the following formula: In the above formula, λ PVis the load transfer rate, which is used to describe the corresponding values ​​of different electricity price differences and different response curves; is the electricity price difference; a, c, μ are known quantities in the Logistic function; b is a variable parameter.

[0138] Further optionally, the calculation process of the comprehensive load transfer rate in the load transfer rate corresponding to each time period calculated by the load fuzzy response mechanism model is expressed as:

[0139]

[0140] Among them, a pv and b pv The regional demarcation point for electricity price difference; PV / is the actual load transfer rate; m is the optimistic response membership, which is used to describe the probability that the user meets the optimistic response estimate; λ PV min , PV max are the load transfer rates for pessimistic and optimistic response predictions, respectively.

[0141] Further optionally, the day-ahead transaction prediction module and / or the real-time transaction prediction unit is configured to calculate the actual load transfer rate λ from peak to flat and from flat to valley in the corresponding load transfer rate in each time period through the load fuzzy response mechanism model. PF / , FV / After that, the load transfer amount and load value after user demand response are calculated as follows:

[0142]

[0143] L t =L t0 +Q t

[0144] Among them, T P 、T F 、T V Corresponding to peak, valley and normal times of electricity prices respectively; The average values ​​of loads during peak, flat and valley periods before the implementation of time-of-use electricity prices respectively; Q t is the load transfer amount due to demand response at time t; L t0 , L t They are the load values ​​before and after the implementation of time-of-use electricity prices at time t respectively.

[0145] Further, optionally, under the optimistic response prediction, a is 0.1, b is 0, c is 0.4, and μ is 0.1; under the pessimistic response prediction, a is 0.104, b is -0.0036, c is 0.4, and μ is 0.1; the demarcation point a for the electricity price difference division area is pv 0.1 yuan / kWh,b pv It is 0.7 yuan / kWh.

[0146] Further optionally, the real-time transaction prediction unit is further configured to:

[0147] After receiving the second bidding result matched with the real-time market bidding strategy and the second bidding electricity price information, on the day of participating in multi-market transactions, after the real-time market RTM is closed, performing a final round of rolling for the IBDR project;

[0148] The settlement information for the day is calculated according to the day-ahead market bidding strategy and the real-time market bidding strategy; the settlement information for the day includes at least: the clearing electricity price, and the electricity market transaction settlement information corresponding to the virtual power plant.

[0149] Further optionally, the balancing adjustment unit optimizes the power dispatching strategy and the charging and discharging strategy of the energy storage system based on the real-time preset total energy demand, and is configured to:

[0150] Based on the real-time preset total energy demand, obtaining charging and discharging recommendation information corresponding to each type of vehicle and the power dispatch strategy of the energy storage system;

[0151] After optimizing the power dispatch strategy and the charging and discharging strategy of the energy storage system based on the real-time preset total energy demand, the charging and discharging recommendation information is pushed to the owners of various types of vehicles;

[0152] The balancing market operation is started, and the corresponding amount is delivered based on the power dispatch strategy of the energy storage system to absorb the output deviation of renewable energy.

[0153] The system can implement various steps in the above method embodiment, which will not be expanded here.

[0154] In the embodiment of the present application, a load fuzzy response mechanism model is adopted to solve the limited rationality problem of controllable loads in the demand response process, and to achieve an effective combination of user demand response results and DER, and to propose a solution for VPP to participate in bidding plans for multiple types of electricity markets.

[0155] See also Fig.10 , Fig.10 Schematic diagram of an electronic device provided in an embodiment of the present application. Fig.10As shown, the embodiment of the present application provides an electronic device 500, including a memory 510, a processor 5102, and a computer program 511 stored in the memory 510 and executable on the processor 5102. When the processor 5102 executes the computer program 511, the following steps are implemented: before participating in multi-market transactions, the first predicted output data of the preset energy in each time period is obtained according to the historical electricity price data, the user load historical data, and the time-of-use electricity price information. The first predicted output data is corrected by the load fuzzy response mechanism model to obtain the first preset energy total demand in each time period. Based on the first preset energy total demand, a day-ahead market bidding strategy and the corresponding first bidding electricity price information are generated. Furthermore, on the day of participating in multi-market transactions, the second predicted output data of the preset energy in each time period is obtained according to the real-time electricity price data, the user load real-time data, and the time-of-use electricity price information. After receiving the first bidding result matching the day-ahead market bidding strategy and the first bidding electricity price information, the second predicted output data is corrected by the load fuzzy response mechanism model based on the first bidding result, the second predicted output data, and the user load real-time data, to obtain the second preset energy total demand in each time period. Based on the second preset total energy demand and the collected real-time user load response data, a real-time market bidding strategy and the corresponding second bidding electricity price information are generated. After receiving the second bidding result that matches the real-time market bidding strategy and the second bidding electricity price information, the corresponding real-time preset total energy demand in the current period is dynamically adjusted through the load fuzzy response mechanism model. Finally, based on the real-time preset total energy demand, the power dispatching strategy and the charging and discharging strategy of the energy storage system are optimized to balance the energy reserves after multi-market transactions.

[0156] See also Fig.11 , Fig.11 The following is a schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present application. Fig.11As shown, this embodiment provides a computer-readable storage medium 600, on which a computer program 611 is stored. When the computer program 611 is executed by a processor, the following steps are implemented: before participating in multi-market transactions, the first predicted output data of the preset energy in each time period is obtained according to the historical electricity price data, the user load historical data, and the time-of-use electricity price information. The first predicted output data is corrected by the load fuzzy response mechanism model to obtain the first preset energy total demand in each time period. The day-ahead market bidding strategy and the corresponding first bidding electricity price information are generated based on the first preset energy total demand. Furthermore, on the day of participating in multi-market transactions, the second predicted output data of the preset energy in each time period is obtained according to the real-time electricity price data, the user load real-time data, and the time-of-use electricity price information. After receiving the first bidding result matching the day-ahead market bidding strategy and the first bidding electricity price information, the second predicted output data is corrected by the load fuzzy response mechanism model based on the first bidding result, the second predicted output data, and the user load real-time data, to obtain the second preset energy total demand in each time period. Based on the second preset total energy demand and the collected real-time user load response data, a real-time market bidding strategy and the corresponding second bidding electricity price information are generated. After receiving the second bidding result that matches the real-time market bidding strategy and the second bidding electricity price information, the corresponding real-time preset total energy demand in the current period is dynamically adjusted through the load fuzzy response mechanism model. Finally, based on the real-time preset total energy demand, the power dispatching strategy and the charging and discharging strategy of the energy storage system are optimized to balance the energy reserves after multi-market transactions.

[0157] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0158] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0159] The embodiments of the present application are described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0160] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0161] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0162] Although the preferred embodiments of the present application have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present application.

[0163] Obviously, those skilled in the art can make various changes and modifications to the embodiments of the present application without departing from the spirit and scope of the embodiments of the present application. Thus, if these modifications and variations of the embodiments of the present application fall within the scope of the claims of the embodiments of the present application and their equivalents, the embodiments of the present application are also intended to include these modifications and variations.

Claims

1. A multi-market transaction prediction method for a virtual power plant, characterized in that: The method comprises: Before participating in multi-market transactions, obtain the first predicted output data of the preset energy in each time period based on historical electricity price data, user load historical data, and time-of-use electricity price information; Correcting the first predicted output data by using a load fuzzy response mechanism model to obtain a first preset total energy demand in each time period; Generate a day-ahead market bidding strategy and corresponding first bidding electricity price information based on the first preset total energy demand; On the day of participating in multi-market transactions, obtain the second predicted output data of the preset energy in each time period based on the real-time electricity price data, user load real-time data, and time-of-use electricity price information; After receiving the first bidding result matching the day-ahead market bidding strategy and the first bidding electricity price information, based on the first bidding result, the second predicted output data, and the user load real-time data, the second predicted output data is corrected through a load fuzzy response mechanism model to obtain a second preset total energy demand in each time period; Based on the second preset total energy demand and the collected user real-time load response data, generate a real-time market bidding strategy and corresponding second bidding electricity price information; After receiving the real-time market bidding strategy and the second bidding result matching the second bidding electricity price information, dynamically adjusting the corresponding real-time preset total energy demand in the current period through the load fuzzy response mechanism model; Based on the real-time preset total energy demand, the power dispatch strategy and the charging and discharging strategy of the energy storage system are optimized to balance the energy reserves after multi-market transactions.

2. The multi-market transaction prediction method of a virtual power plant according to claim 1, characterized in that: The step of correcting the first predicted output data or the second predicted output data by using the load fuzzy response mechanism model includes: The load transfer rate corresponding to each time period is calculated by using the load fuzzy response mechanism model; the load transfer rate is composed of at least an optimistic response prediction value and a pessimistic response prediction value; The second predicted output data is corrected by using the load transfer rate in each time period to obtain the second preset total energy demand in each time period.

3. The multi-market transaction prediction method of a virtual power plant according to claim 2, characterized in that: The load fuzzy response mechanism model is constructed based on the logistic function; the stages of the load fuzzy response mechanism model are divided into: dead zone, response zone, and saturation zone; The logistic function is expressed as the following formula: In the above formula, λ PV is the load transfer rate, which is used to describe the corresponding values ​​of different electricity price differences and different response curves; is the electricity price difference; a, c, μ are known quantities in the Logistic function; b is a variable parameter.

4. The multi-market transaction prediction method of a virtual power plant according to claim 3 is characterized in that: The calculation process of the comprehensive load transfer rate in the corresponding load transfer rate in each period is expressed as follows through the load fuzzy response mechanism model: as well as Among them, a pv and b pv The regional demarcation point for electricity price difference; PV / is the actual load transfer rate; m is the optimistic response membership, which is used to describe the probability that the user meets the optimistic response estimate; λ PV min , PV max are the load transfer rates for pessimistic and optimistic response predictions, respectively.

5. The multi-market transaction prediction method of a virtual power plant according to claim 4, characterized in that: The actual load transfer rate λ of the load transfer rate from peak to flat and from flat to valley in each period is calculated by the load fuzzy response mechanism model. PF / , FV / After that, the load transfer amount and load value after user demand response are calculated as follows: L t =L t0 +Q t Among them, T P 、T F 、T V Corresponding to peak, valley and normal times of electricity prices respectively; The average values ​​of loads during peak, flat and valley periods before the implementation of time-of-use electricity prices respectively; Q t is the load transfer amount due to demand response at time t; L t0 , L t They are the load values ​​before and after the implementation of time-of-use electricity prices at time t respectively.

6. The multi-market transaction prediction method of a virtual power plant according to claim 5, characterized in that: Under the optimistic response prediction, a is 0.1, b is 0, c is 0.4, and μ is 0.1; under the pessimistic response prediction, a is 0.104, b is -0.0036, c is 0.4, and μ is 0.1; the demarcation point a for the price difference division area pv 0.1 yuan / kWh,b pv It is 0.7 yuan / kWh.

7. The multi-market transaction prediction method of a virtual power plant according to claim 1, characterized in that: After receiving the real-time market bidding strategy and the second bidding result matching the second bidding electricity price information, the method further includes: On the day of participating in multi-market trading, the last rollover of the IBDR program is performed after the real-time market (RTM) closes; The settlement information for the day is calculated according to the day-ahead market bidding strategy and the real-time market bidding strategy; the settlement information for the day includes at least: the clearing electricity price, and the electricity market transaction settlement information corresponding to the virtual power plant.

8. The multi-market transaction prediction method of a virtual power plant according to claim 1, characterized in that: The optimizing the power dispatching strategy and the charging and discharging strategy of the energy storage system based on the real-time preset total energy demand includes: Based on the real-time preset total energy demand, obtaining charging and discharging recommendation information corresponding to each type of vehicle and the power dispatch strategy of the energy storage system; After optimizing the power dispatch strategy and the charging and discharging strategy of the energy storage system based on the real-time preset total energy demand, the method further includes: Pushing the charging and discharging recommendation information to owners of various types of vehicles; The balancing market operation is started, and the corresponding amount is delivered based on the power dispatch strategy of the energy storage system to absorb the output deviation of renewable energy.

9. A multi-market transaction prediction system for a virtual power plant, characterized in that: The system comprises the following units, wherein: The day-ahead transaction prediction unit is configured to obtain first predicted output data of a preset energy source in each time period according to historical electricity price data, user load historical data, and time-of-use electricity price information before participating in multi-market transactions; correct the first predicted output data through a load fuzzy response mechanism model to obtain a first preset energy total demand in each time period; generate a day-ahead market bidding strategy and corresponding first bidding electricity price information based on the first preset energy total demand; The real-time transaction prediction unit is configured to obtain, on the day of participating in multi-market transactions, second predicted output data of the preset energy in each time period according to real-time electricity price data, user load real-time data, and time-of-use electricity price information; after receiving the first bidding result matching the day-ahead market bidding strategy and the first bidding electricity price information, based on the first bidding result, the second predicted output data, and the user load real-time data, correct the second predicted output data through the load fuzzy response mechanism model to obtain the second preset energy total demand in each time period; based on the second preset energy total demand and the collected user real-time load response data, generate a real-time market bidding strategy and corresponding second bidding electricity price information; The balancing adjustment unit is configured to dynamically adjust the corresponding real-time preset total energy demand in the current period through the load fuzzy response mechanism model after receiving the second bidding result matching the real-time market bidding strategy and the second bidding electricity price information; based on the real-time preset total energy demand, optimize the power dispatching strategy and charging and discharging strategy of the energy storage system to balance the energy reserves after multi-market transactions.

10. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the multi-market transaction prediction method for a virtual power plant as described in any one of claims 1-8.

Images