User income determination method and device for virtual power plant, equipment, medium and product

Abstract

The invention discloses a user income determination method and device for a virtual power plant, equipment, a medium and a product. The method comprises the steps of obtaining multi-cycle power utilization characteristics of the virtual power plant based on power utilization data of each user of the virtual power plant; obtaining medium and long term transaction decisions and overall medium and long term benefits of the virtual power plant based on the multi-cycle power utilization characteristics of the virtual power plant and the medium and long term transaction rules of the virtual power plant; obtaining a day-ahead spot declaration transaction decision and spot market curve declaration income based on the virtual power plant multi-cycle power consumption characteristics and the prediction model; based on the overall adjustment characteristic base value of the virtual power plant and the power utilization adjustment deviation of each user of the virtual power plant, obtaining user individual excess profit recovery cost; and based on the overall medium and long term income of the virtual power plant, the spot market curve declaration income and the user individual excess profit recovery cost, a virtual power plant user individual income model is constructed, and the virtual power plant user bonus income is determined. According to the invention, rationality and fairness of user income distribution can be realized.

Description

Technical Field

[0001] The present application relates to the technical field of power automation, and particularly to a method, device, equipment, medium and product for determining the user benefits of a virtual power plant. Background Art

[0002] In the case of large fluctuations in new energy, the regulation capacity and potential of conventional energy have been deeply explored. Especially when facing scenarios of no wind, no light or continuous large power generation over a long period of time, traditional energy management systems are difficult to effectively respond. To better solve these problems, the virtual power plant (VPP) has gradually emerged as an innovative solution. It aggregates various types of regulation resources such as controllable industrial loads, distributed photovoltaics and energy storage systems, electric vehicles and commercial buildings, realizes centralized management and optimized scheduling of these dispersed resources, and thus provides flexible power supply services, becoming an important means for power supply guarantee and new energy consumption.

[0003] In multi-period electricity energy trading under the spot mode, virtual power plants face complex challenges. On the one hand, virtual power plants need to accurately submit electricity energy buying and selling quotes according to the predicted market price trends to maximize profits; on the other hand, due to the price volatility and uncertainty of the power market, if the medium- and long-term trading strategies of virtual power plants are incorrect or the adjustment direction of spot declarations is opposite to the actual demand, significant economic losses may occur, which all pose risks to the operation of virtual power plants.

[0004] Therefore, in order to reduce the operation risks of virtual power plants and protect the economic interests of virtual power plants and their users, an effective mechanism must be established to accurately measure the adjustment electricity provided by each user and reasonably calculate the dividend sharing ratio. In the prior art, due to the response behavior differences among different users, when virtual power plants adjust user benefits, there is a lack of fairness and reasonableness, which is not conducive to improving the profitability of each user and stimulating the enthusiasm of users to participate in the market with their regulation resources. Therefore, there is an urgent need to provide a relatively fair and reasonable user benefit distribution scheme. Summary of the Invention

[0005] In view of the above-mentioned defects or deficiencies in the related art, the purpose of the present application is to provide a method, device, equipment, medium and product for determining the user benefits of a virtual power plant, which can construct an individual user benefit model of the virtual power plant according to the response deviations of different users, realize the rationality and fairness of user benefit distribution, and solve the problems that are not conducive to improving the profitability of each user and stimulating the enthusiasm of users to participate in the market with their regulation resources.

[0006] To achieve the above purpose, the present application provides the following solutions:

[0007] In a first aspect, the present application provides a method for determining the user benefits of a virtual power plant, including:

[0008] Performing dimensionality reduction processing and clustering analysis on the obtained power consumption data of each user in the virtual power plant to obtain the multi-period power consumption characteristics of the virtual power plant;

[0009] Generating a medium- and long-term trading decision based on the multi-period power consumption characteristics of the virtual power plant and the medium- and long-term trading rules of the virtual power plant, and obtaining the actual medium- and long-term trading result and the average spot clearing price under the medium- and long-term trading decision to obtain the overall medium- and long-term benefit of the virtual power plant;

[0010] Generating a day-ahead spot declaration trading decision based on the multi-period power consumption characteristics of the virtual power plant and a prediction model, and determining the declared revenue of the spot market curve under the day-ahead spot declaration trading decision;

[0011] Obtaining the individual user's excess profit recovery cost based on the overall regulation characteristic base value of the virtual power plant and the power consumption regulation deviation of each user in the virtual power plant;

[0012] Constructing an individual user benefit model of the virtual power plant based on the overall medium- and long-term benefit of the virtual power plant, the declared revenue of the spot market curve, and the individual user's excess profit recovery cost, and determining the user dividend benefit of the virtual power plant based on the individual user benefit model of the virtual power plant.

[0013] Optionally, the performing dimensionality reduction processing and clustering analysis on the obtained power consumption data of each user in the virtual power plant to obtain the multi-period power consumption characteristics of the virtual power plant includes: performing feature dimensionality reduction on the power consumption data of each user in the virtual power plant by using the principal component analysis method to obtain an original data matrix; the power consumption data of each user in the virtual power plant is a data set of multi-dimensional influencing factors of the power consumption behavior of each user in the virtual power plant; calculating the covariance matrix of the original data matrix, as well as the eigenvectors and eigenvalues of the covariance matrix, and determining the principal component vectors of the multi-dimensional influencing factors of the power consumption behavior of each user in the virtual power plant based on the eigenvectors and the eigenvalues; performing clustering processing on the principal component vectors by using a self-organizing competitive neural network to obtain the monthly sub-period power consumption characteristics of the virtual power plant.

[0014] Optionally, generate medium- and long-term trading decisions based on the multi-period electricity consumption characteristics of the virtual power plant and the medium- and long-term trading rules of the virtual power plant, and obtain the actual medium- and long-term trading results and the average spot clearing price under the medium- and long-term trading decisions to obtain the overall medium- and long-term revenue of the virtual power plant, including: establishing a coupling relationship between the historical load factor and quotation distribution of thermal power based on the multi-period electricity consumption characteristics of the virtual power plant, and generating medium- and long-term trading decisions based on the coupling relationship between the historical load factor and quotation distribution of thermal power and the medium- and long-term trading rules of the virtual power plant; when the virtual power plant participates in the spot trading based on the medium- and long-term trading decisions, obtain the trading electricity volume, trading electricity price, and weighted average price of the virtual power plant in each time period of different trading markets, and obtain the clearing electricity price of the day-ahead spot market in each time period; based on the trading electricity volume, the trading electricity price, the weighted average price, and the clearing electricity price, obtain the financial revenue of each time period in the medium- and long-term trading of the virtual power plant; superimpose the financial revenues of each time period in the medium- and long-term trading of the virtual power plant to obtain the financial operation revenue of the virtual power plant in the medium- and long-term electricity market trading.

[0015] Optionally, generate day-ahead spot declaration trading decisions based on the overall regulation characteristic base value of the virtual power plant and the electricity consumption regulation deviation of each user of the virtual power plant, and determine the spot market curve declaration revenue under the day-ahead spot declaration trading decisions, including: training a pre-created random forest regression model based on the multi-period electricity consumption characteristics of the virtual power plant to obtain the prediction model; obtaining the day-ahead clearing price and the real-time-day-ahead price difference of the virtual power plant based on the prediction model and the real-time data of the virtual power plant in the spot market; generating day-ahead spot declaration trading decisions based on the day-ahead clearing price and the real-time-day-ahead price difference of the virtual power plant; obtaining the day-ahead spot declaration financial operation revenue based on the day-ahead spot declaration assessment rules of the virtual power plant and the day-ahead spot declaration trading decisions.

[0016] Optionally, obtain the individual user's excess profit recovery cost based on the overall regulation characteristic base value of the virtual power plant and the electricity consumption regulation deviation of each user of the virtual power plant, including: obtaining the electricity consumption deviation of each user of the virtual power plant based on the day-ahead electricity consumption and the actual electricity consumption; obtaining the individual user's excess profit recovery cost based on the electricity consumption deviation of each user of the virtual power plant and the overall regulation characteristic base value of the virtual power plant.

[0017] Optionally, constructing a virtual power plant user individual income model based on the overall medium- and long-term income of the virtual power plant, the declared income of the spot market curve, and the recovered fees for individual user excess profits, including: constructing the income contribution degree of each user in the virtual power plant based on the Shapley value index; determining the virtual power plant user dividend sharing coefficient based on the income contribution degree of each user in the virtual power plant; constructing the virtual power plant user individual income model based on the overall medium- and long-term income of the virtual power plant, the declared income of the spot market curve, the recovered fees for individual user excess profits, and the virtual power plant user dividend sharing coefficient.

[0018] In a second aspect, the present application provides a device for determining the income of users of a virtual power plant, including:

[0019] A dimensionality reduction analysis module for performing dimensionality reduction processing and clustering analysis on the electricity consumption data of each user in the virtual power plant obtained, to obtain the multi-period electricity consumption characteristics of the virtual power plant;

[0020] A first determination module for generating a medium- and long-term trading decision based on the multi-period electricity consumption characteristics of the virtual power plant and the medium- and long-term trading rules of the virtual power plant, and obtaining the actual medium- and long-term trading result and the average spot clearing price under the medium- and long-term trading decision, to determine the overall medium- and long-term income of the virtual power plant;

[0021] A second determination module for generating a day-ahead spot declaration trading decision based on the multi-period electricity consumption characteristics of the virtual power plant and the day-ahead spot declaration assessment rules of the virtual power plant, and determining the declared income of the spot market curve under the day-ahead spot declaration trading decision;

[0022] A third determination module for obtaining the recovered fees for individual user excess profits based on the overall regulation characteristic base value of the virtual power plant and the electricity consumption regulation deviation of each user in the virtual power plant;

[0023] A construction determination module for constructing a virtual power plant user individual income model based on the overall medium- and long-term income of the virtual power plant, the declared income of the spot market curve, and the recovered fees for individual user excess profits, and determining the virtual power plant user dividend income based on the virtual power plant user individual income model.

[0024] In a third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the computer program to implement the steps of the method for determining the income of users of a virtual power plant described in any one of the above.

[0025] In a fourth aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method for determining the income of users of a virtual power plant described in any one of the above are implemented.

[0026] In a fifth aspect, the present application provides a computer program product, including a computer program which, when executed by a processor, implements the steps of the method for determining the user benefits of the virtual power plant described in any one of the above.

[0027] According to the specific embodiments provided by the present application, the following technical effects are disclosed:

[0028] The present application provides a method, device, equipment, medium and product for determining the user benefits of a virtual power plant. By performing dimensionality reduction processing on the power consumption data of each user in the virtual power plant, complex data can be simplified, facilitating subsequent clustering analysis. By performing clustering analysis on the power consumption data of each user in the virtual power plant after dimensionality reduction processing, the power consumption characteristics of the virtual power plant in each period can be obtained, providing data support for the formulation of medium- and long-term trading decisions and day-ahead spot trading decisions. By formulating medium- and long-term trading decisions and day-ahead spot trading decisions, when the virtual power plant participates in spot trading, it can timely adjust the electricity energy buying and selling quotes according to the market price trend, achieving profit maximization and reducing operation risks. By obtaining the overall medium- and long-term benefits of the virtual power plant, the spot market curve declaration benefits, and the user individual excess profit recovery fees, a virtual power plant user individual benefit model can be constructed. By using the constructed virtual power plant user individual benefit model, a relatively accurate dividend sharing ratio can be obtained for the response deviations of different users, realizing the rationality and fairness of user benefit distribution, which is beneficial to improving the profitability of each user and stimulating the enthusiasm of users to adjust resources to participate in the market. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0030] Figure 1 It is a schematic flowchart of a method for determining the user benefits of a virtual power plant provided by an embodiment of the present application;

[0031] Figure 2 It is a schematic diagram of the functional modules of a device for determining the user benefits of a virtual power plant provided by an embodiment of the present application;

[0032] Figure 3 It is a schematic diagram of the structure of a computer device provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0033] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts belong to the scope of protection of the present application.

[0034] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0035] In an exemplary embodiment, as Figure 1 shown, a method for determining the user benefits of a virtual power plant is provided. This method is executed by a computer device, specifically, it can be executed independently by a computer device such as a terminal or a server, or jointly executed by a terminal and a server. In the embodiments of the present application, the method for determining the user benefits of the virtual power plant includes the following steps S110 to step S150. Among them:

[0036] Step S110: Perform dimensionality reduction processing and clustering analysis on the obtained power consumption data of each user in the virtual power plant to obtain the multi-period power consumption characteristics of the virtual power plant.

[0037] In the exemplary embodiment, the power consumption data of each user in the virtual power plant includes the historical data of the user's individual power consumption time-sharing curve and the data of the user's individual regulation ability time-sharing curve; among them, the historical data of the user's individual power consumption time-sharing curve is a data set recording the power consumption of a single power user at different time points (such as specific periods per hour, per day, etc.); the historical data of the user's individual power consumption time-sharing curve may include how many kilowatt-hours (kWh) of electricity the user consumed at each sampling time point, the specific date and time of each power consumption record, the user identification, the weather conditions at that time, whether it is a working day, etc. Through the historical data of the user's individual power consumption time-sharing curve, the user's power consumption patterns in different periods such as peak periods, flat periods, and valley periods can be reflected.

[0038] The time - sharing curve data of the user's individual regulation ability is data that records the ability of a single power user to respond to dispatching instructions and adjust its power consumption at different time points. The time - sharing curve data of the user's individual regulation ability includes the difference between the maximum and minimum active power outputs, the specific date and time corresponding to each data point, the range of power that the user can increase or decrease within a specific time period, the actual adjustment amount achieved by the user after receiving the dispatching instruction, the speed at which the user responds to the dispatching instruction, the cost of performing the adjustment operation (for example, the cost of starting / stopping a large - scale motor, the charging / discharging cost of using an energy storage system, etc.), and the user identification; among them, the difference between the maximum and minimum active power outputs refers to the difference between the maximum and minimum active power outputs that the aggregated virtual power plant can provide, indicating the degree to which the user responds to the dispatching instruction and adjusts its power generation or consumption ability. Through the time - sharing curve data of the user's individual regulation ability, the adjustable potential of the user in different time periods such as peak hours, flat hours, and valley hours can be reflected, that is, the user can support the flexibility of the power grid by reducing or increasing power consumption.

[0039] It should be noted that the multi - cycle electricity consumption characteristics of the virtual power plant include the characteristics reflected by the historical time - sharing curve data of the user's individual electricity consumption and the time - sharing curve data of the user's individual regulation ability. For example, the electricity consumption patterns of the user in different time periods such as peak hours, flat hours, and valley hours, and the adjustable potential of the user in different time periods such as peak hours, flat hours, and valley hours.

[0040] In a specific embodiment, the above - mentioned step S110 includes steps S1101 to S1103, that is,

[0041] Step S1101, using the principal component analysis method to perform feature dimensionality reduction on the electricity consumption data of each user in the virtual power plant to obtain the original data matrix.

[0042] In an exemplary embodiment, the power consumption data of each user in the virtual power plant is a dataset of multi-dimensional influencing factors of the power consumption behavior of each user in the virtual power plant; that is, the multi-dimensional influencing factors of the power consumption behavior of each user in the virtual power plant may include time dimension factors, geographical dimension factors, economic dimension factors, technical dimension factors, socio-cultural dimension factors, relevant regulations dimension factors, and market dimension factors; among them, the time dimension factors may include power consumption changes in different time periods (for example, peak-valley electricity prices, real-time electricity prices, etc. will affect when users choose to consume electricity), seasonal power consumption changes, and power consumption changes between weekdays and non-working days. Geographical dimension factors may include power consumption changes in geographical locations (for example, factors such as climate conditions, living habits, and economic development levels in different regions will affect users' power consumption habits), and power consumption changes in the characteristics of regional power grids (for example, users' power consumption habits generated by the distribution of power generation resources within the region). Economic dimension factors may include power consumption changes in electricity costs, power consumption changes in users' income levels, and power consumption changes in economic incentive measures (for example, energy-saving subsidies and reward strategies provided by power companies). Technical dimension factors may include power consumption changes in the application of smart devices, power consumption changes in the access of renewable energy (for example, the popularization of new energy devices such as distributed photovoltaic panels and wind turbines enables some users to self-power and even sell electricity to the grid), and power consumption changes in the configuration of energy storage systems (for example, battery energy storage devices can charge at low electricity prices and discharge during peak hours to reduce costs or participate in demand response). Socio-cultural dimension factors may include power consumption changes in lifestyle and consumption concepts, and power consumption changes in community effects. Market dimension factors may include power consumption changes in medium- and long-term trading strategies (for example, through bilateral negotiation, centralized bidding, etc., power wholesale transactions with time spans of several years, annual, quarterly, monthly, etc. are carried out, and the power purchase and sale prices for a certain future time period are formulated, and the power consumption changes affected by the power purchase and sale prices), and spot market price fluctuations (for example, the declared earnings in the day-ahead spot market, the spread arbitrage opportunities in the real-time spot market, etc. will prompt users to adjust their power consumption curves to obtain benefits).

[0043] Step S1102, calculate the covariance matrix of the original data matrix, as well as the eigenvectors and eigenvalues of the covariance matrix, and based on the eigenvectors and eigenvalues, determine the principal component vectors of the multi-dimensional influencing factors of the power consumption behavior of each user in the virtual power plant.

[0044] In an exemplary embodiment, during the principal component analysis process, a set of mutually correlated variables is converted into a set of linearly uncorrelated variables through a linear transformation, and the newly generated uncorrelated variables are called "principal components"; each principal component is a linear combination of the original variables, and the principal components are orthogonal to each other (that is, uncorrelated). The principal component vector is also called the eigenvector, which defines the direction along which the data is projected into the low-dimensional space, so that the projected data can retain as much information of the original data as possible.

[0045] Step S1103: Use a self-organizing competitive neural network to cluster the principal component vectors to obtain the monthly time-of-use electricity consumption characteristics of the virtual power plant.

[0046] As can be understood from the above embodiments, the principal component analysis method is used to reduce the dimensionality of the multi-dimensional influencing factor data of the electricity consumption behaviors of each user in the virtual power plant.

[0047] For example, assume that there are n users in total, and each user's electricity consumption behavior influencing factor data has p indicators, X1, X2, …, X p is the dataset of randomly set variables at the beginning. First, obtain the original data matrix X, and the original data matrix X is as shown in the following formula (1):

[0048]

[0049] Among them, a linear combination of the arrays in the p indicators of the original data matrix X gives the following formula (2):

[0050]

[0051] In the formula: a ip is the coefficient matrix and satisfies i = 1, 2, …, p; x1, x2, …, x p are the corresponding values of each indicator; F1, F2, …, F p are the new uncorrelated variables.

[0052] After that, use formula (3) to calculate the mean (μ) of the original data matrix X, that is:

[0053]

[0054] After that, based on the mean of the original data matrix X, obtain the covariance matrix, and calculate the eigenvectors and eigenvalues (λ i ) of the covariance matrix; determine the principal component vectors according to the eigenvectors and eigenvalues (λ i ) of the covariance matrix. Among them, when extracting the principal components of the multi-dimensional influencing factors of the electricity consumption behaviors of each user in the virtual power plant, select the first k characteristic indicators with eigenvalues greater than 1 and the cumulative variance contribution rate reaching more than 85%. The cumulative contribution rate of the first k characteristic indicators is expressed as the following formula (4):

[0055]

[0056] Use a self-organizing competitive neural network to perform secondary clustering on the adjustable potential on the user side of the virtual power plant, that is, use the principal component vectors after dimensionality reduction as the input layer of the secondary clustering.

[0057] It should be noted that the self-organizing competitive neural network in the embodiments of this application belongs to an unsupervised learning algorithm. Before using the self-organizing competitive neural network to cluster the adjustable potential on the user side of the virtual power plant, the self-organizing competitive neural network needs to be trained. By training the self-organizing competitive neural network, the self-organizing competitive neural network can classify the historical data of the individual user's power consumption time-sharing curve and the data of the individual user's adjustment ability time-sharing curve on the user side of the virtual power plant submitted. Among them, the classified virtual power plant includes three modes: interruptible mode, shiftable mode, or reducible mode, so as to achieve the purpose of clustering the principal component vectors.

[0058] Among them, the training steps of the self-organizing competitive neural network may include the following steps S1 to S3:

[0059] Step S1, perform normalization processing on the principal component vectors; that is, after obtaining the principal component vectors X through the above-mentioned principal component analysis method for feature dimensionality reduction j , the principal component vectors X j and the inner star weight vectors W j (j = 1, 2,..., m) corresponding to each neuron in the competition layer of the self-organizing competitive neural network are normalized to obtain the principal component vectors and the inner star weight vectors W j (j = 1, 2,..., m).

[0060] Step S2, calculate the winning neuron of the self-organizing competitive neural network. When the self-organizing competitive neural network obtains a principal component vector , all the inner star weight vectors W j (j = 1, 2,..., m) in the competition layer of the self-organizing competitive neural network are compared with for similarity. The W with the greatest similarity to j (j = 1, 2,..., m) is determined as the competition winning neuron, denoted as Among them, the similarity is measured by calculating the Euclidean distance (or cosine of the included angle) between and .

[0061] Step S3, adjust the input and weights of the self-organizing competitive neural network. According to the "winner takes all" competition rule of the self-organizing competitive neural network, only the weight vector of the competition winning neuron is adjusted, and only the winning neuron outputs 1, and the other neurons output 0. The adjusted weight vector is the following formula (5):

[0062]

[0063] Among them, α in the above formula represents the learning rate, and the value of α gradually decreases as the learning progresses, where α ∈ (0, 1]. j* represents the serial number of the winning weight vector in the previous round in the self-organizing competitive neural network When j ≠ j* , since the "winner" inhibits them and does not allow them to be excited, the weight values of the corresponding neurons are not adjusted accordingly.

[0064] After step S3 is executed, step S1 is executed to continue training until α decays to 0 or a preset value, and then steps S1 to S3 are stopped from being executed, and the training result is output to obtain the monthly sub-period electricity consumption characteristics and the base value of the regulation range of the virtual power plant.

[0065] By performing dimensionality reduction processing on the electricity consumption data of each user in the virtual power plant, complex data can be simplified, facilitating subsequent clustering analysis; by performing clustering analysis on the electricity consumption data of each user in the virtual power plant after dimensionality reduction processing, the electricity consumption characteristics of the virtual power plant in each cycle can be obtained, providing data support for the formulation of medium- and long-term trading decisions and day-ahead spot declaration trading decisions.

[0066] Step S120, generate medium- and long-term trading decisions based on the multi-cycle electricity consumption characteristics of the virtual power plant and the medium- and long-term trading rules of the virtual power plant, and obtain the actual medium- and long-term trading results and the average spot clearing price under the medium- and long-term trading decisions, so as to obtain the overall medium- and long-term revenue of the virtual power plant.

[0067] In the exemplary embodiment, the medium- and long-term trading rules of the virtual power plant are the "Basic Rules for Medium- and Long-Term Electricity Trading" issued by the National Development and Reform Commission and the National Energy Administration. That is, market players such as power generation enterprises, electricity users, and electricity sales companies can carry out electricity wholesale trading with time spans of multiple years, annual, quarterly, monthly, etc. through bilateral negotiation, centralized bidding, etc. As an aggregator, the virtual power plant can represent its internal members to sign long-term contracts with external market participants and formulate electricity buying and selling prices for a certain future time period. In addition, the "Basic Rules for Medium- and Long-Term Electricity Trading" also stipulates the specific trading process, settlement mechanism, and default handling, etc., providing guarantees for the smooth progress of the trading.

[0068] In a specific implementation manner, the above step S120 may include steps S1201 to S1204. Specifically,

[0069] Step S1201, establish a coupling relationship between the historical load rate - bid distribution of thermal power based on the multi-cycle electricity consumption characteristics of the virtual power plant, and generate medium- and long-term trading decisions based on the coupling relationship between the historical load rate - bid distribution of thermal power and the medium- and long-term trading rules of the virtual power plant.

[0070] In an exemplary embodiment, the coupling relationship between the historical load factor and quotation distribution of thermal power refers to the correlation between the historical power generation load factor of a thermal power plant and the price it quotes when participating in market transactions in the electricity market. Due to factors such as start-up costs and minimum stable operation output limits of thermal power plants, in the electricity spot market, thermal power plants need to declare in advance the expected power generation volume and corresponding price for a certain future period, which helps to better predict the market price trend and generate medium- and long-term trading decisions.

[0071] Step S1202, in the case where the virtual power plant participates in the spot transaction based on the medium- and long-term trading decision, obtain the transaction power, transaction electricity price, and weighted average price of the virtual power plant in each time period of different trading markets, and obtain the clearing electricity price of the day-ahead spot market in each time period.

[0072] Step S1203, based on the transaction power, transaction electricity price, weighted average price, and clearing electricity price, obtain the financial benefits of each time period in the medium- and long-term trading of the virtual power plant.

[0073] Step S1204, superimpose the financial benefits of each time period in the medium- and long-term trading of the virtual power plant to obtain the financial operation benefits of the virtual power plant in the medium- and long-term electricity market trading.

[0074] As can be understood from the above embodiments, medium- and long-term trading decisions are formulated based on the medium- and long-term trading rules of the virtual power plant and medium- and long-term price forecasts, and the overall medium- and long-term benefits of the virtual power plant are calculated based on the actual medium- and long-term trading results and the spot clearing average price. The expressions are as follows in equations (6) and (7):

[0075]

[0076] Among them, in the above equation (6), F z represents the financial operation benefits of the virtual power plant users in the medium- and long-term electricity market trading; in the above equation (7), is the financial benefit corresponding to the medium- and long-term trading time period i; Q sti , Q mti , Q xti , are the transaction powers of the bilateral, monthly, ten-day, and daily rolling trading markets in time period i respectively, P sti , P mti , P xti , are the transaction electricity prices and weighted average prices of the bilateral, monthly, ten-day, and daily rolling trading markets in time period i respectively, is the clearing electricity price of the day-ahead spot market in time period i.

[0077] Step S130, generate a day-ahead spot declaration trading decision based on the multi-period electricity consumption characteristics and prediction model of the virtual power plant, and determine the spot market curve declaration benefits under the day-ahead spot declaration trading decision.

[0078] In the exemplary embodiment, the prediction model is a model that predicts future market price trends based on historical data, macroeconomic indicators, and other relevant factors. Examples of prediction models include LSTM networks, random forests, etc. In the electricity market, there are many factors affecting prices, including but not limited to weather conditions, seasonal demand fluctuations, fuel cost changes, policy adjustments, etc. When constructing a prediction model, causal regression analysis prediction method or time series analysis prediction method in quantitative analysis methods is usually adopted. Among them, the causal regression analysis prediction method focuses on the relationship between price and its influencing factors; the time series analysis prediction method focuses on using past data patterns to infer future data trends. Therefore, when selecting or constructing a prediction model, it can be determined according to actual applications to obtain a more accurate electricity price prediction.

[0079] In a specific implementation manner, the above step S130 may include steps S1301 to S1303. Specifically:

[0080] Step S1301: Train a pre-created random forest regression model based on the multi-cycle electricity consumption characteristics of the virtual power plant to obtain a prediction model.

[0081] Step S1302: Based on the prediction model and the real-time data of the virtual power plant in the spot market, obtain the day-ahead clearing price and the real-time - day-ahead price difference of the virtual power plant.

[0082] Step S1303: Generate a day-ahead spot declaration trading decision based on the day-ahead clearing price and the real-time - day-ahead price difference of the virtual power plant.

[0083] Step S1304: Obtain the day-ahead spot declaration financial operation income based on the day-ahead spot declaration assessment rules and the day-ahead spot declaration trading decision of the virtual power plant.

[0084] Combined with the above embodiments, it can be understood that by predicting the day-ahead real-time price and price difference in the spot market to generate a day-ahead spot declaration trading decision and calculating the day-ahead spot declaration financial operation income, that is, calculating the curve declaration income in the spot market as shown in the following formulas (8) and (9):

[0085]

[0086] F mri =(Q rmqi -Q rmsi )*(P rmsi -P rmqi )(9)

[0087] Wherein, in the above formula (8), F r is the day-ahead spot declaration financial operation income of the virtual power plant for this month; in the above formula (9), F mriThe day-ahead spot declaration financial operation revenue for period i of m days in the spot market; Q rmqi and Q rmsi are respectively the day-ahead electricity consumption and the actual electricity consumption declared for period i of m days in the spot market; P rmsi and P rmqi are respectively the day-ahead real-time clearing price and the day-ahead clearing price for period i of m days in the spot market; M represents month, and 1 to 24 represent 24 time periods.

[0088] It should be noted that the spread prediction is the day-ahead price prediction of the virtual power plant in the spot market by the prediction model according to the multi-period electricity consumption characteristics of the virtual power plant, and the day-ahead clearing price of each time period is obtained; then the difference between the obtained day-ahead clearing price of each time period and the day-ahead real-time clearing price is calculated to obtain the spread prediction.

[0089] Step S140, based on the overall regulation characteristic base value of the virtual power plant and the electricity consumption regulation deviation of each user of the virtual power plant, obtain the individual user's excess profit recovery cost.

[0090] Specifically, based on the obtained day-ahead electricity consumption and the actual electricity consumption, the electricity consumption deviation of each user of the virtual power plant is obtained; based on the electricity consumption deviation of each user of the virtual power plant and the overall regulation characteristic base value of the virtual power plant, the individual user's excess profit recovery cost is obtained; the specific expression is as follows in formula (10):

[0091]

[0092] Among them, in the above formula, F chi is the individual user's excess profit recovery cost; Q rmqi and Q rmsi are respectively the day-ahead electricity consumption and the actual electricity consumption declared for period i of m days in the spot market, Q rmsi -Q rmqi is the electricity consumption deviation of each user of the virtual power plant; P rmsi and P rmqi are respectively the day-ahead real-time clearing price and the day-ahead clearing price for period i of m days in the spot market, P rmsi -P rmqi is the overall regulation characteristic base value of the virtual power plant; M represents month, 1 to 24 represent 24 time periods; δ is the deviation threshold, δ is a constant and lower than the market rule limit, and in the embodiment of the present application, δ is 0.1. It should be noted that the day-ahead electricity consumption is the predicted electricity consumption obtained by using the prediction model.

[0093] Step S150, based on the overall medium- and long-term revenue of the virtual power plant, the declared revenue of the spot market curve, and the individual user's excess profit recovery cost, construct an individual user revenue model of the virtual power plant, and determine the dividend revenue of the virtual power plant users based on the individual user revenue model of the virtual power plant.

[0094] Specifically, based on the Shapley value index, the revenue contribution degree of each user in the virtual power plant is constructed; based on the revenue contribution degree of each user in the virtual power plant, the virtual power plant user dividend sharing coefficient is determined; the overall medium- and long-term revenue of the virtual power plant, the revenue declared in the spot market curve, the recovery cost of individual user excess profits, and the virtual power plant user dividend sharing coefficient are used to construct the individual revenue model of the virtual power plant users.

[0095] It can be understood that the Shapley value index is used to construct the revenue contribution degree of each user in the virtual power plant, forming a virtual power plant user dividend sharing coefficient and a user revenue calculation method. The specific process includes the following steps S1501 to step S1503, that is:

[0096] Step S1501, calculate the revenue contribution degree of each user in the virtual power plant.

[0097] The concept of the Shapley value originated from game theory, which can quantitatively explain the contribution degree of each member in the coalition, so as to analyze the value of the member in the cooperative game, and is an important reference basis for the distribution of coalition interests. Assume that the coalition game C=(N, V), where N represents the virtual power plant user individual data set, and the function v is called the characteristic function. The calculation formulas (11) and (12) are as follows:

[0098]

[0099] Among them, in the above formula (11), p rofit (S) represents the maximum revenue of the coalition S participating in the market. The above formula (11) maps the coalition S to a real number, corresponding to the total medium- and long-term revenue of the virtual power plant that the members in the coalition S can obtain through cooperation; in the above formula (12), φ i (v) is the average marginal contribution of a certain member to all possible coalitions.

[0100] It should be noted that in the embodiment of the present application, p rofit (S) can represent the maximum revenue of the aggregated virtual power plant participating in the spot market, and φ i (v) is the average marginal contribution degree of each user in the virtual power plant.

[0101] Step S1502, calculate the virtual power plant user dividend sharing coefficient.

[0102] Calculate the virtual power plant user dividend sharing coefficient corresponding to the user according to the revenue contribution degree of each user in the virtual power plant. First, calculate the revenue contribution degree and average contribution degree of all users in the virtual power plant respectively, and select the maximum contribution degree as the dividend sharing base. The calculation process is as follows formula (13):

[0103]

[0104] Among them, in the above formula k ihis the dividend sharing coefficient for user individual i, where 0 < k ih ≤ 1.

[0105] Step S1503: Construct a virtual power plant user individual income model. The virtual power plant user individual income model is as shown in the following formula (14):

[0106] F i = (F Z + F r - F chi ) * k ih * (1 - K)(14)

[0107] where, in the above formula, F i is the dividend sharing income of user individual i, K is the basic service sharing ratio coefficient of the virtual power plant platform operator, and 0 < K ≤ 1.

[0108] By implementing the above steps S110 to S150, through dimensionality reduction processing of the power consumption data of each user in the virtual power plant, complex data can be simplified, facilitating subsequent clustering analysis; through clustering analysis of the power consumption data of each user in the virtual power plant after dimensionality reduction processing, the power consumption characteristics of the virtual power plant in each cycle can be obtained, providing data support for the formulation of medium- and long-term trading decisions and day-ahead spot declaration trading decisions; by formulating medium- and long-term trading decisions and day-ahead spot declaration trading decisions, when the virtual power plant participates in the spot trading, it can adjust the electricity energy buying and selling quotes in a timely manner according to the market price trend, realizing profit maximization and reducing operation risks; by obtaining the overall medium- and long-term income of the virtual power plant, the spot market curve declaration income, and the user individual excess profit recovery fee, a virtual power plant user individual income model can be constructed; through the constructed virtual power plant user individual income model, a relatively accurate dividend sharing ratio can be obtained for the response deviation of different users, realizing the rationality and fairness of user income distribution, which is beneficial to improving the profitability of each user and stimulating the enthusiasm of users to adjust resources to participate in the market.

[0109] Based on the same inventive concept, the embodiment of the present application also provides a virtual power plant user income determination device for implementing the above-mentioned virtual power plant user income determination method. The implementation solutions provided by this device to solve problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more of the following virtual power plant user income determination device embodiments can refer to the limitations on the virtual power plant user income determination method in the above text, and will not be repeated here.

[0110] In an exemplary embodiment, as Figure 2 shown, a virtual power plant user income determination device is provided. The virtual power plant user income determination device 200 includes:

[0111] The dimensionality reduction analysis module 210 is used to perform dimensionality reduction processing and clustering analysis on the obtained power consumption data of each user in the virtual power plant, so as to obtain the multi-period power consumption characteristics of the virtual power plant;

[0112] The first determination module 220 is used to generate medium- and long-term trading decisions based on the multi-period power consumption characteristics of the virtual power plant and the medium- and long-term trading rules of the virtual power plant, obtain the actual medium- and long-term trading results and the average spot clearing price under the medium- and long-term trading decisions, and determine the overall medium- and long-term revenue of the virtual power plant;

[0113] The second determination module 230 is used to generate day-ahead spot declaration trading decisions based on the multi-period power consumption characteristics of the virtual power plant and the day-ahead spot declaration assessment rules of the virtual power plant, and determine the spot market curve declaration revenue under the day-ahead spot declaration trading decisions;

[0114] The third determination module 240 is used to obtain the individual user's excess profit recovery cost based on the overall regulation characteristic base value of the virtual power plant and the power consumption regulation deviation of each user in the virtual power plant;

[0115] The construction determination module 250 is used to construct an individual user revenue model of the virtual power plant based on the overall medium- and long-term revenue of the virtual power plant, the spot market curve declaration revenue, and the individual user's excess profit recovery cost, and determine the user dividend revenue of the virtual power plant based on the individual user revenue model of the virtual power plant.

[0116] As an optional implementation manner, the above-mentioned dimensionality reduction analysis module 210 is specifically used to: perform feature dimensionality reduction on the power consumption data of each user in the virtual power plant by using the principal component analysis method to obtain the original data matrix; the power consumption data of each user in the virtual power plant is a data set of multi-dimensional influencing factors of the power consumption behavior of each user in the virtual power plant; calculate the covariance matrix of the original data matrix, as well as the eigenvectors and eigenvalues of the covariance matrix, and determine the principal component vectors of the multi-dimensional influencing factors of the power consumption behavior of each user in the virtual power plant based on the eigenvectors and eigenvalues; perform clustering processing on the principal component vectors by using a self-organizing competitive neural network to obtain the monthly sub-period power consumption characteristics of the virtual power plant.

[0117] As an alternative implementation, the above-mentioned first determination module 220 is specifically configured to: establish a coupling relationship between the historical load rate and quotation distribution of thermal power based on the multi-period electricity consumption characteristics of the virtual power plant, and generate medium- and long-term trading decisions based on the coupling relationship between the historical load rate and quotation distribution of thermal power and the medium- and long-term trading rules of the virtual power plant; when the virtual power plant participates in the spot trading based on the medium- and long-term trading decisions, obtain the trading electricity volume, trading electricity price, and weighted average price of the virtual power plant in each time period of different trading markets, and obtain the clearing electricity price of the day-ahead spot market in each time period; based on the trading electricity volume, trading electricity price, weighted average price, and clearing electricity price, obtain the financial benefits of each time period in the medium- and long-term trading of the virtual power plant; and superimpose the financial benefits of each time period in the medium- and long-term trading of the virtual power plant to obtain the financial operation benefits of the virtual power plant in the medium- and long-term electricity market trading.

[0118] As an alternative implementation, the above-mentioned second determination module 230 is specifically configured to: train a pre-created random forest regression model based on the multi-period electricity consumption characteristics of the virtual power plant to obtain a prediction model; obtain the day-ahead clearing price and the real-time-day-ahead price difference of the virtual power plant based on the prediction model and the real-time data of the virtual power plant in the spot market; generate a day-ahead spot declaration trading decision based on the day-ahead clearing price and the real-time-day-ahead price difference of the virtual power plant; and obtain the day-ahead spot declaration financial operation benefits based on the day-ahead spot declaration assessment rules of the virtual power plant and the day-ahead spot declaration trading decision.

[0119] As an alternative implementation, the above-mentioned third determination module 240 is specifically configured to: obtain the electricity consumption deviation of each user of the virtual power plant based on the obtained day-ahead electricity consumption and actual electricity consumption; and obtain the individual user excess profit recovery cost based on the electricity consumption deviation of each user of the virtual power plant and the overall regulation characteristic base value of the virtual power plant.

[0120] As an alternative implementation, the above-mentioned construction determination module 250 is specifically configured to: construct the revenue contribution degree of each user of the virtual power plant based on the Shapley value index; determine the virtual power plant user dividend sharing coefficient based on the revenue contribution degree of each user of the virtual power plant; and construct the virtual power plant user individual revenue model based on the overall medium- and long-term revenue of the virtual power plant, the revenue from the spot market curve declaration, the individual user excess profit recovery cost, and the virtual power plant user dividend sharing coefficient.

[0121] Among them, when implementing this implementation method, by performing dimensionality reduction processing on the power consumption data of each user in the virtual power plant, complex data can be simplified, facilitating subsequent clustering analysis; by performing clustering analysis on the power consumption data of each user in the virtual power plant after dimensionality reduction processing, the power consumption characteristics of the virtual power plant in each period can be obtained, providing data support for formulating medium- and long-term trading decisions and day-ahead spot trading decisions; by formulating medium- and long-term trading decisions and day-ahead spot trading decisions, when the virtual power plant participates in spot trading, it can adjust the electricity energy buying and selling quotes in a timely manner according to the market price trend, achieving profit maximization and reducing operation risks; by obtaining the overall medium- and long-term income of the virtual power plant, the income from spot market curve declarations, and the recovery fees for individual user excess profits, a virtual power plant user individual income model can be constructed; through the constructed virtual power plant user individual income model, a relatively accurate dividend sharing ratio can be obtained for the response deviations of different users, realizing the rationality and fairness of user income distribution, which is beneficial to improving the profitability of each user and stimulating the enthusiasm of users to adjust resources to participate in the market.

[0122] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structural diagram can be as Figure 3 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the user income determination data of the virtual power plant. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, it implements a method for determining the user income of a virtual power plant.

[0123] Those skilled in the art can understand that Figure 3 the structure shown in

[0124] In an exemplary embodiment, a computer device is further provided, which includes a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0125] In an exemplary embodiment, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0126] In an exemplary embodiment, a computer program product is provided, which includes a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0127] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use, and processing of relevant data need to comply with relevant regulations.

[0128] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to the memory, database, or other media used in the various embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0129] In each of the embodiments provided in this application, the databases involved may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., without limitation. In each of the embodiments provided in this application, the processor may be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without limitation.

[0130] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0131] Specific examples are used in this article to elaborate on the principles and implementation manners of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A method for determining the user benefits of a virtual power plant, characterized in that, The method for determining the user benefits of the virtual power plant includes: Performing dimensionality reduction processing and clustering analysis on the electricity consumption data of each user in the virtual power plant to obtain the multi-period electricity consumption characteristics of the virtual power plant; Generating medium- and long-term trading decisions based on the multi-period electricity consumption characteristics of the virtual power plant and the medium- and long-term trading rules of the virtual power plant, and obtaining the actual medium- and long-term trading results and the average spot clearing price under the medium- and long-term trading decisions to obtain the overall medium- and long-term benefits of the virtual power plant; Generating day-ahead spot declaration trading decisions based on the multi-period electricity consumption characteristics of the virtual power plant and a prediction model, and determining the declared revenue of the spot market curve under the day-ahead spot declaration trading decisions; Obtaining the individual user's excess profit recovery fee based on the overall regulation characteristic base value of the virtual power plant and the electricity consumption regulation deviation of each user in the virtual power plant; Constructing an individual user benefit model of the virtual power plant based on the overall medium- and long-term benefits of the virtual power plant, the declared revenue of the spot market curve, and the individual user's excess profit recovery fee, and determining the user dividend benefit of the virtual power plant based on the individual user benefit model of the virtual power plant.

2. The method for determining the user benefits of a virtual power plant according to claim 1, wherein The performing dimensionality reduction processing and clustering analysis on the electricity consumption data of each user in the virtual power plant to obtain the multi-period electricity consumption characteristics of the virtual power plant includes: Using the principal component analysis method to perform feature dimensionality reduction on the electricity consumption data of each user in the virtual power plant to obtain the original data matrix; the electricity consumption data of each user in the virtual power plant is a dataset of multi-dimensional influencing factors of the electricity consumption behavior of each user in the virtual power plant; Calculating the covariance matrix of the original data matrix, as well as the eigenvectors and eigenvalues of the covariance matrix, and determining the principal component vectors of the multi-dimensional influencing factors of the electricity consumption behavior of each user in the virtual power plant based on the eigenvectors and the eigenvalues; Using a self-organizing competitive neural network to perform clustering processing on the principal component vectors to obtain the monthly sub-period electricity consumption characteristics of the virtual power plant.

3. The method for determining the user benefits of a virtual power plant according to claim 2, wherein, The generating medium- and long-term trading decisions based on the multi-period electricity consumption characteristics of the virtual power plant and the medium- and long-term trading rules of the virtual power plant, and obtaining the actual medium- and long-term trading results and the average spot clearing price under the medium- and long-term trading decisions to obtain the overall medium- and long-term benefits of the virtual power plant includes: Establishing a coupling relationship between the historical load factor - bid distribution of thermal power based on the multi-period electricity consumption characteristics of the virtual power plant, and generating medium- and long-term trading decisions based on the coupling relationship between the historical load factor - bid distribution of thermal power and the medium- and long-term trading rules of the virtual power plant; When the virtual power plant participates in spot trading based on the medium- and long-term trading decisions, obtaining the trading electricity volume, trading electricity price, and weighted average price of the virtual power plant in each time period in different trading markets, and obtaining the clearing electricity price of the day-ahead spot market in each time period; Obtaining the financial benefits of each time period in the medium- and long-term trading of the virtual power plant based on the trading electricity volume, the trading electricity price, the weighted average price, and the clearing electricity price; Adding up the financial benefits of each time period in the medium- and long-term trading of the virtual power plant to obtain the financial operation benefits of the virtual power plant in the medium- and long-term electricity market trading.

4. The method for determining the user benefit of the virtual power plant according to claim 3, characterized in that, The generating day-ahead spot declaration trading decisions based on the multi-period electricity consumption characteristics of the virtual power plant and a prediction model, and determining the declared revenue of the spot market curve under the day-ahead spot declaration trading decisions includes: Training a pre-created random forest regression model based on the multi-period electricity consumption characteristics of the virtual power plant to obtain the prediction model; Based on the prediction model and the real-time data of the virtual power plant in the spot market, obtaining the day-ahead clearing price and the real-time-day-ahead price difference of the virtual power plant; Generating a day-ahead spot declaration trading decision based on the day-ahead clearing price and the real-time-day-ahead price difference of the virtual power plant; Obtaining the financial operation income of the day-ahead spot declaration based on the day-ahead spot declaration assessment rules of the virtual power plant and the day-ahead spot declaration trading decision; 5. The method for determining the user benefit of a virtual power plant according to claim 4, wherein The obtaining of the individual user's excess profit recovery cost based on the overall regulation characteristic base value of the virtual power plant and the electricity consumption regulation deviation of each user of the virtual power plant includes: Based on the obtained day-ahead electricity consumption and actual electricity consumption, obtaining the electricity consumption deviation of each user of the virtual power plant; Based on the electricity consumption deviation of each user of the virtual power plant and the overall regulation characteristic base value of the virtual power plant, obtaining the individual user's excess profit recovery cost; 6. The method for determining the user benefit of a virtual power plant according to claim 5, wherein The constructing of the individual user income model of the virtual power plant based on the overall medium- and long-term income of the virtual power plant, the declared income of the spot market curve, and the individual user's excess profit recovery cost includes: Constructing the income contribution degree of each user of the virtual power plant based on the Shapley value index; Determining the dividend sharing coefficient of the virtual power plant users based on the income contribution degree of each user of the virtual power plant; Constructing the individual user income model of the virtual power plant from the overall medium- and long-term income of the virtual power plant, the declared income of the spot market curve, the individual user's excess profit recovery cost, and the dividend sharing coefficient of the virtual power plant users; 7. A user benefit determination device for a virtual power plant, characterized in that, The device for determining the user income of the virtual power plant includes: A dimensionality reduction analysis module for performing dimensionality reduction processing and clustering analysis on the electricity consumption data of each user of the virtual power plant obtained to obtain the multi-period electricity consumption characteristics of the virtual power plant; A first determination module for generating a medium- and long-term trading decision based on the multi-period electricity consumption characteristics of the virtual power plant and the medium- and long-term trading rules of the virtual power plant, and obtaining the actual medium- and long-term trading result and the spot clearing average price under the medium- and long-term trading decision, and determining the overall medium- and long-term income of the virtual power plant; A second determination module for generating a day-ahead spot declaration trading decision based on the multi-period electricity consumption characteristics of the virtual power plant and the day-ahead spot declaration assessment rules of the virtual power plant, and determining the declared income of the spot market curve under the day-ahead spot declaration trading decision; A third determination module for obtaining the individual user's excess profit recovery cost based on the overall regulation characteristic base value of the virtual power plant and the electricity consumption regulation deviation of each user of the virtual power plant; A construction determination module for constructing an individual user income model of the virtual power plant based on the overall medium- and long-term income of the virtual power plant, the declared income of the spot market curve, and the individual user's excess profit recovery cost, and determining the dividend income of the virtual power plant users based on the individual user income model of the virtual power plant; 8. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that the processor executes the computer program to implement the steps of the method for determining the user income of the virtual power plant according to any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method for determining the user benefits of the virtual power plant according to any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method for determining the user benefits of the virtual power plant according to any one of claims 1-6.

Images