Spot transaction electric quantity segmentation method considering virtual power plant aggregation main body intention

Abstract

The invention relates to the technical field of marketization transaction electric quantity segmentation, in particular to a spot transaction electric quantity segmentation method considering the will of a virtual power plant aggregation subject, and the method comprises the steps: assisting a user to determine the theoretical optimal value of the quantity report and quotation information of each time period, and improving the user experience. According to the method, a user can manually adjust the transaction electric quantity ratio in each time period in combination with own willingness, and then a virtual power plant operator determines the overall submitted electric quantity and price by calculating the price-flexibility comprehensive coefficient of each user. Theoretical and model support can be provided for market mechanism design fully considering demand side resource willingness in the future, power-assisted power system implementation of supply and demand balance and the like. Therefore, the problem that in the prior art, the individual willingness and the flexibility release level of distributed resource users in the process of participating in marketization transaction through aggregation are not fully reflected is solved.

Description

Technical Field

[0001] The present application relates to the technical field of market-based electricity segmentation, and in particular to a method for spot electricity segmentation that takes into account the wishes of virtual power plant aggregation entities. Background Art

[0002] The gradual implementation of the "dual carbon" action has accelerated the construction of my country's new power system. However, due to the strong randomness and volatility of new energy output, the continuous increase in its grid-connected proportion has also brought a series of problems to the power grid. It is urgent to tap the flexibility potential of demand-side resources to provide key support for the safe and stable operation of the power system.

[0003] Against this backdrop, virtual power plants (VPPs), an organizational management model that aggregates vast user resources and acts as a proxy for user participation in system operations and market transactions, are considered an effective solution for unlocking the flexibility of demand resources. In recent years, numerous scholars have conducted research on VPPs as proxy users in electricity markets, focusing on equating the market-based transaction process to an optimization model that considers numerous constraints and developing strategies to maximize overall economic benefits.

[0004] In the process of virtual power plants aggregating users to actually participate in transactions, the agreement signed with users does not stipulate the proportion of participating electricity and the method of profit settlement, but basically unfolds in a model of full electricity agency combined with shared profit / risk. However, some distributed resource users lack a systematic understanding of the market operation rules when being represented by virtual power plants to participate in the spot market. They want to truly feel the price fluctuations in the spot market in order to grasp the market changes in advance, but do not want to bear too much potential risks brought about by price fluctuations. At the same time, from the perspective of power grid and market operators, while there is an urgent need for demand-side flexibility resources to help the system achieve real-time balance between supply and demand, it is also expected to quantify the degree of release of the flexibility potential of the aggregated entities. However, the existing technology still lacks a method to reflect the user entity's willingness to participate and the level of flexibility release.

[0005] In summary, the existing technology does not adequately reflect the individual willingness and flexibility of distributed resource users in participating in market-based transactions through aggregation, and this issue needs to be addressed urgently. Summary of the Invention

[0006] This application provides a spot trading electricity segmentation method that takes into account the willingness of virtual power plant aggregation entities, so as to solve the problems in the existing technology of insufficient reflection of the individual willingness and flexibility release level of distributed resource users in the process of participating in market-based transactions through aggregation.

[0007] The first embodiment of the present application provides a method for splitting spot trading electricity that takes into account the intentions of the virtual power plant aggregation subject, including the following steps: obtaining the historical supply and demand matching situation, historical price data and meteorological data of the spot market on the actual trading day within the target time and space range, and inputting the historical supply and demand matching situation, the historical price data and the meteorological data into a pre-built long-short-term memory network model to output the prediction results of the market electricity demand gap and price on future trading days; based on the prediction results, each distributed resource user constructs an economic benefit target model respectively, solves the economic benefit target model to obtain the quotation information of each time period, and adjusts the preset market-based trading electricity ratio according to the quotation information and the willingness of each distributed resource user to obtain the corresponding quotation expectation, and feeds back the quotation expectation to the virtual power plant operator; through The virtual power plant operator calculates the price-flexibility comprehensive coefficient of each distributed resource user in different time periods according to the quotation expectations, and sorts the price-flexibility comprehensive coefficients in descending order to obtain corresponding sorting results, and calculates the corresponding overall reported electricity and reported price according to the sorting results, and reports the overall reported electricity and reported price to the market operation platform to determine multiple winning users and the actual benefits corresponding to the multiple winning users after the market is cleared on the actual operation day; judge whether the actual benefits meet the quotation expectations of the distributed resource users and the virtual power plant operator, wherein if the actual benefits do not meet the quotation expectations, the long short-term memory network model is retrained by the virtual power plant operator, and each distributed resource user adjusts the corresponding proportion of market-based trading electricity, and re-executes the reporting operation.

[0008] Optionally, in one embodiment of the present application, the historical supply and demand matching situation, historical price data and meteorological data of the actual trading day of the spot market within the target time and space range are obtained, and the historical supply and demand matching situation, the historical price data and the meteorological data are input into a pre-built long-short-term memory network model to output the prediction results of the market electricity demand gap and price on future trading days, including: collecting the meteorological data of the actual trading day of the market, wherein the meteorological data includes the wind speed, light intensity, relative humidity, temperature and precipitation information of the actual trading day of the market; inputting the historical supply and demand matching situation, the historical price data and the meteorological data into the long-short-term memory network model to obtain corresponding input gate output information, and generating the prediction results of the market electricity demand gap and price on future trading days based on the input gate output information.

[0009] Optionally, in one embodiment of the present application, based on the prediction results, each distributed resource user constructs an economic benefit target model respectively, solves the economic benefit target model to obtain the quotation information for each time period, and adjusts the preset market-based transaction electricity ratio according to the quotation information and the willingness of each distributed resource user to obtain the corresponding quotation expectation, and feeds back the quotation expectation to the virtual power plant operator, including: obtaining the payment unit electricity purchase economic cost and the purchase amount of each distributed resource user, and calculating the electricity purchase economic cost according to the payment unit electricity purchase economic cost and the purchase amount; collecting the market-based transaction electricity sales and price signals corresponding to the distributed resource users, and calculating the market-based transaction economic benefits through the market-based transaction electricity sales and the price signals; obtaining the total energy storage charging capacity and the unit economic cost of energy storage charging and discharging loss corresponding to the energy storage facilities in the distributed resource users, and calculating the energy storage charging and discharging loss economic cost according to the total energy storage charging capacity and the unit economic cost; based on the The economic cost of purchasing electricity, the economic benefits of market-based transactions and the economic costs of energy storage charging and discharging losses are used to construct the economic benefit target model; a preset simulated annealing algorithm is used to calculate the quotation information of each time period, and based on the quotation information of each time period, each distributed resource user adjusts the proportion of market-based transaction electricity in different time periods according to its own willingness to participate in market transactions in different time periods, so as to determine the target coefficient value corresponding to the proportion of market-based transaction electricity; the energy storage electricity at the initial moment, the energy storage configuration capacity and the energy storage electricity at adjacent moments are determined, and based on the energy storage electricity at the initial moment, the energy storage configuration capacity and the energy storage electricity at adjacent moments, a plurality of energy storage facility constraints are constructed, wherein the plurality of energy storage facility constraints include energy storage initial capacity constraint, energy storage capacity constraint, energy storage capacity constraint at adjacent moments, energy storage SOC state consistency constraint and energy storage charging and discharging state uniqueness constraint; the target coefficient value is adjusted based on the plurality of energy storage facility constraints and the own willingness of each distributed resource user to obtain the corresponding quotation expectation.

[0010] Optionally, in one embodiment of the present application, the virtual power plant operator calculates the price-flexibility comprehensive coefficient of each distributed resource user in different time periods according to the reported quantity and quotation expectations, and sorts the price-flexibility comprehensive coefficients in descending order to obtain corresponding sorting results, and calculates the corresponding overall reported electricity and reported price according to the sorting results, and reports the overall reported electricity and reported price to the market operation platform to determine multiple winning users and the actual benefits corresponding to the multiple winning users after the market is cleared on the actual operation day, including: determining the theoretical flexibility adjustment upper limit and theoretical flexibility adjustment lower limit of the distributed resource users in the different time periods, and the reported price upper limit and reported price lower limit of all aggregated entities of the virtual power plant operator in different time periods; based on the theoretical flexibility adjustment upper limit, the theoretical flexibility adjustment lower limit, the reported price upper limit and the reported price lower limit, calculate the price competitiveness coefficient and flexibility of different distributed resource users in the different time periods on an actual market operation day. the price-flexibility comprehensive coefficients corresponding to the different distributed resource users are calculated according to the price competitiveness coefficient and the flexibility release level, and the price-flexibility comprehensive coefficients are sorted in descending order by the virtual power plant operator to obtain the sorting result; based on the sorting result, the top k distributed resource users reported in each time period are determined, and in each time period, the virtual power plant operator calculates the reported electricity and reported price according to the reported quantity and quotation expectations corresponding to the top k distributed resource users, and reports the reported electricity and the reported price to the market operation platform, so as to determine a plurality of successful bidders among the top k distributed resource users after the market is cleared on the actual operation day, where k is a positive integer; the actual clearing information of the spot market is obtained, so that the virtual power plant operator obtains a plurality of dispatching periods issued by the target power grid according to the actual clearing information, allocates the plurality of dispatching periods to the plurality of successful bidders, and calculates the actual income corresponding to each of the plurality of successful bidders.

[0011] Optionally, in one embodiment of the present application, the judgment of whether the actual profit meets the quotation expectations of the distributed resource users and the virtual power plant operator, wherein if the actual profit does not meet the quotation expectation, the virtual power plant operator retrains the long short-term memory network model so that each distributed resource user adjusts the corresponding market-based transaction electricity ratio and re-executes the submission operation, including: judging whether the actual profit corresponding to each winning user meets the quotation expectation, wherein if the actual profit does not meet the quotation expectation, the virtual power plant operator updates the input data of the long short-term memory network model and retrains the long short-term memory network model using the updated input data; based on each distributed resource user, obtaining the market winning information corresponding to the spot market, and solving the economic benefit target model according to the market winning information and the retrained long short-term memory network model to obtain new quotation information, and adjusting the market-based transaction electricity ratio through the new quotation information to adjust the quotation profit corresponding to each winning user.

[0012] The second aspect of the present application provides a spot trading electricity segmentation device that takes into account the intentions of the virtual power plant aggregation subject, including: a prediction module, which is used to obtain the historical supply and demand matching situation, historical price data and meteorological data of the spot market within the target time and space range, and input the historical supply and demand matching situation, the historical price data and the meteorological data into a pre-built long-short-term memory network model to output the prediction results of the market electricity demand gap and price on future trading days; a solution module, which is used to enable each distributed resource user to construct an economic benefit target model based on the prediction results, solve the economic benefit target model to obtain the quotation information of each time period, and adjust the preset market-based trading electricity ratio according to the quotation information and the willingness of each distributed resource user to obtain the corresponding quotation expectation, and feed back the quotation expectation to the virtual power plant operator; a declaration module , used to calculate the price-flexibility comprehensive coefficient of each distributed resource user in different time periods according to the quotation expectation through the virtual power plant operator, and sort the price-flexibility comprehensive coefficient in descending order to obtain the corresponding sorting result, and calculate the corresponding overall reported electricity and reported price according to the sorting result, and report the overall reported electricity and the reported price to the market operation platform to determine multiple winning users and the actual benefits corresponding to the multiple winning users after the market is cleared on the actual operation day; a judgment module is used to judge whether the actual benefit meets the quotation expectation of the distributed resource user and the virtual power plant operator, wherein if the actual benefit does not meet the quotation expectation, the long short-term memory network model is retrained by the virtual power plant operator, and each distributed resource user adjusts the corresponding market-based transaction electricity ratio, and re-executes the reporting operation.

[0013] Optionally, in one embodiment of the present application, the prediction module includes: a first acquisition unit, used to collect meteorological data of the actual trading day of the market, wherein the meteorological data includes wind speed, light intensity, relative humidity, temperature and precipitation information of the actual trading day of the market; a generation unit, used to input the historical supply and demand matching situation, the historical price data and the meteorological data into the long short-term memory network model to obtain corresponding input gate output information, and based on the input gate output information, generate the prediction results of the market electricity demand gap and price on the future trading day.

[0014] Optionally, in one embodiment of the present application, the solution module includes: a first calculation unit, used to obtain the economic cost of electricity purchase per payment unit and the amount of electricity purchased of each distributed resource user, so as to calculate the economic cost of electricity purchase based on the economic cost of electricity purchase per payment unit and the amount of electricity purchased; a second collection unit, used to collect the market-based transaction electricity sales and price signals corresponding to the distributed resource users, and calculate the market-based transaction economic benefits through the market-based transaction electricity sales and the price signals; an acquisition unit, used to obtain the unit economic cost of the total energy storage charge and energy storage charge and discharge loss corresponding to the energy storage facilities in the distributed resource users, and calculate the energy storage charge and discharge loss economic cost based on the total energy storage charge and the unit economic cost; a first construction unit, used to construct the economic benefit target model based on the economic cost of electricity purchase, the market-based transaction economic benefits and the energy storage charge and discharge loss economic cost; a second calculation unit, used to use a preset simulation The annealing algorithm calculates the quotation information of each time period, and based on the quotation information of each time period, each distributed resource user adjusts the proportion of market-based transaction electricity in different time periods according to his own willingness to participate in market transactions in different time periods, so as to determine the target coefficient value corresponding to the proportion of market-based transaction electricity; the second construction unit is used to determine the energy storage electricity at the initial moment, the energy storage configuration capacity and the energy storage electricity at adjacent moments, and construct multiple energy storage facility constraints based on the energy storage electricity at the initial moment, the energy storage configuration capacity and the energy storage electricity at adjacent moments, wherein the multiple energy storage facility constraints include energy storage initial capacity constraint, energy storage capacity constraint, energy storage capacity constraint at adjacent moments, energy storage SOC state consistency constraint, and energy storage charge and discharge state uniqueness constraint; the third calculation unit is used to adjust the target coefficient value based on the multiple energy storage facility constraints and the own willingness of each distributed resource user to obtain the corresponding quotation expectation.

[0015] Optionally, in one embodiment of the present application, the declaration module includes: a first determination unit, used to determine the theoretical flexibility adjustment upper limit and theoretical flexibility adjustment lower limit of the distributed resource user in the different time periods, and the declared price upper limit and declared price lower limit of all aggregated entities of the virtual power plant operator in different time periods; a fourth calculation unit, used to calculate the price competitiveness coefficient and flexibility release level of different distributed resource users in the different time periods within an actual market operation day based on the theoretical flexibility adjustment upper limit, the theoretical flexibility adjustment lower limit, the declared price upper limit and the declared price lower limit; a sorting unit, used to calculate the price-flexibility comprehensive coefficient corresponding to the different distributed resource users according to the price competitiveness coefficient and the flexibility release level, and sort the price-flexibility comprehensive coefficient through the virtual power plant operator. Sorting in descending order to obtain the sorting result; a second determination unit, for determining the top k distributed resource users reported in each time period based on the sorting result, and in each time period, enabling the virtual power plant operator to calculate the reported electricity and reported price according to the reported quantity and quotation expectations corresponding to the top k distributed resource users, and report the reported electricity and the reported price to the market operation platform, so as to determine a plurality of successful bidders among the top k distributed resource users after the market is cleared on the actual operation day, wherein k is a positive integer; an allocation unit, for obtaining the actual clearing information of the spot market, so that the virtual power plant operator obtains a plurality of dispatching periods issued by the target power grid according to the actual clearing information, and allocates the plurality of dispatching periods to the plurality of successful bidders, and calculates the actual income corresponding to each of the plurality of successful bidders.

[0016] Optionally, in one embodiment of the present application, the judgment module includes: an analysis unit, used to determine whether the actual profit corresponding to each successful bidder meets the quotation expectation, wherein if the actual profit does not meet the quotation expectation, the virtual power plant operator updates the input data of the long short-term memory network model, and retrains the long short-term memory network model using the updated input data; an adjustment unit, used to obtain the market successful bid information corresponding to the spot market based on each distributed resource user, and solve the economic benefit target model according to the market successful bid information and the retrained long short-term memory network model to obtain new quotation information, and adjust the proportion of market-based transaction electricity through the new quotation information to adjust the quotation profit corresponding to each successful bidder.

[0017] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the spot trading electricity splitting method taking into account the wishes of the virtual power plant aggregation entity as described in the above embodiment.

[0018] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above-mentioned spot trading electricity splitting method considering the wishes of the virtual power plant aggregation entity.

[0019] The fifth aspect of the present application provides a computer program product, including a computer program, which is executed to implement the above-mentioned spot trading electricity splitting method considering the willingness of the virtual power plant aggregation entity.

[0020] Therefore, the embodiments of the present application have the following beneficial effects:

[0021] The embodiments of the present application can obtain the historical supply and demand matching situation, historical price data and meteorological data of the spot market on the actual trading day within the target time and space range, and input the historical supply and demand matching situation, historical price data and meteorological data into a pre-built long-short-term memory network model to output the prediction results of the market electricity demand gap and price on future trading days; based on the prediction results, each distributed resource user constructs an economic benefit target model respectively, solves the economic benefit target model to obtain the quotation information of each time period, and adjusts the preset market-based transaction electricity ratio according to the quotation information and the own wishes of each distributed resource user to obtain the corresponding quotation expectation, and feeds back the quotation expectation to the virtual power plant operator; through the virtual power plant operator according to the quotation The quantity quotation expectation calculates the price-flexibility comprehensive coefficient of each distributed resource user in different time periods, and sorts the price-flexibility comprehensive coefficient in descending order to obtain the corresponding sorting result, and calculates the corresponding overall reported electricity and reported price based on the sorting result, and reports the overall reported electricity and reported price to the market operation platform to determine the actual benefits corresponding to multiple winning users and multiple winning users after the market is cleared on the actual operation day; judge whether the actual benefits meet the quantity quotation expectations of the distributed resource users and the virtual power plant operators, wherein, if the actual benefits do not meet the quantity quotation expectations, the long short-term memory network model is retrained by the virtual power plant operator, and each distributed resource user adjusts the corresponding market-based transaction electricity ratio, and re-executes the reporting operation. This application can achieve the optimal allocation of the two parts of electricity for different distributed resource users to participate in aggregated transactions and their own power supply and demand balance, effectively reduce the operational risks of users with insufficient market power, and provide a reliable theoretical basis and model support for building a virtual power plant market trading model that fully considers the wishes of user resource entities and helps the power grid implement supply and demand balance. This solves the problem of insufficient reflection of the individual willingness and flexibility release level of distributed resource users in the process of participating in market-based transactions through aggregation in the existing technology.

[0022] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0024] Figure 1 This is a flow chart of a spot trading electricity splitting method that takes into account the will of a virtual power plant aggregation entity according to an embodiment of the present application;

[0025] Figure 2A schematic diagram of a virtual power plant operator predicting power demand and price during corresponding periods of a trading day using a long short-term memory network is provided in one embodiment of the present application;

[0026] Figure 3 A schematic diagram of the execution logic of a spot trading electricity splitting method considering the will of a virtual power plant aggregation entity provided in one embodiment of the present application;

[0027] Figure 4 This is an example diagram of a spot trading electricity splitting device that takes into account the will of a virtual power plant aggregation entity according to an embodiment of the present application;

[0028] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application.

[0029] Among them, 10-spot trading electricity splitting device taking into account the willingness of the virtual power plant aggregation subject; 100-prediction module, 200-solution module, 300-declaration module, 400-judgment module; 501-memory, 502-processor, 503-communication interface. DETAILED DESCRIPTION

[0030] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0031] The following describes a method for splitting spot-trading electricity that takes into account the will of the virtual power plant aggregation subject in an embodiment of the present application with reference to the accompanying drawings. In response to the problems mentioned in the above background technology, the present application provides a method for splitting spot-trading electricity that takes into account the will of the virtual power plant aggregation subject. In this method, the historical supply and demand matching situation, historical price data and meteorological data of the spot market on the actual trading day within the target time and space range are obtained, and the historical supply and demand matching situation, historical price data and meteorological data are input into a pre-built long-short-term memory network model to output the prediction results of the market electricity demand gap and price on future trading days; based on the prediction results, each distributed resource user constructs an economic benefit target model respectively, solves the economic benefit target model to obtain the quotation information for each time period, and adjusts the preset market-based trading electricity ratio according to the quotation information and the willingness of each distributed resource user to obtain the corresponding quotation expectation, and calculates the quotation expectation. Feedback to the virtual power plant operator; the virtual power plant operator calculates the price-flexibility comprehensive coefficient of each distributed resource user in different time periods according to the quotation expectations, and sorts the price-flexibility comprehensive coefficients in descending order to obtain the corresponding sorting results, and calculates the corresponding overall reported electricity and reported price according to the sorting results, and reports the overall reported electricity and reported price to the market operation platform to determine the actual benefits of multiple winning users and multiple winning users after the market is cleared on the actual operation day; judge whether the actual benefits meet the quotation expectations of the distributed resource users and the virtual power plant operator, wherein, if the actual benefits do not meet the quotation expectations, the virtual power plant operator retrains the long short-term memory network model, and each distributed resource user adjusts the corresponding market-based transaction electricity ratio, and re-executes the reporting operation. This application can achieve the optimal allocation of the two parts of electricity for different distributed resource users to participate in aggregated transactions and their own power supply and demand balance, effectively reduce the operational risks of users with insufficient market power, and provide a reliable theoretical basis and model support for building a virtual power plant market trading model that fully considers the wishes of user resource entities and helps the power grid implement supply and demand balance. This solves the problem of insufficient reflection of the individual willingness and flexibility release level of distributed resource users in the process of participating in market-based transactions through aggregation in the existing technology.

[0032] Specifically, Figure 1 A flowchart of a spot trading electricity splitting method that takes into account the wishes of virtual power plant aggregation entities provided in an embodiment of the present application.

[0033] like Figure 1 As shown in FIG, the spot transaction electricity splitting method considering the willingness of the virtual power plant aggregation subject includes the following steps:

[0034] In step S101, the historical supply and demand matching situation, historical price data and meteorological data of the spot market on actual trading days within the target time and space range are obtained, and the historical supply and demand matching situation, historical price data and meteorological data are input into a pre-built long-short-term memory network model to output the prediction results of the market electricity demand gap and price on future trading days.

[0035] The embodiment of the present application can first obtain the hourly output of distributed photovoltaic power, energy storage installed capacity, power load demand, supply and demand situation in each time period of the spot market, historical data of spot market electricity prices, and wind speed, light intensity, relative humidity, temperature, and precipitation data for future time periods based on weather forecasts for various types of users within a certain time and space range (i.e., the target time and space range).

[0036] Afterwards, the virtual power plant operator in the embodiment of the present application can predict the market electricity demand gap and corresponding prices for future trading days based on the historical supply and demand matching and historical price data of the spot market, as well as the future market trading day data based on weather forecasts, combined with the long-short-term memory network model, and inform the distributed resource users of the prediction results.

[0037] Optionally, in one embodiment of the present application, the historical supply and demand matching situation, historical price data and meteorological data of the actual trading day of the spot market within the target time and space range are obtained, and the historical supply and demand matching situation, historical price data and meteorological data are input into a pre-built long-short-term memory network model to output the prediction results of the market electricity demand gap and price on future trading days, including: collecting meteorological data on the actual trading day of the market, wherein the meteorological data includes wind speed, light intensity, relative humidity, temperature and precipitation information on the actual trading day of the market; inputting the historical supply and demand matching situation, historical price data and meteorological data into the long-short-term memory network model to obtain corresponding input gate output information, and based on the input gate output information, generating the prediction results of the market electricity demand gap and price on future trading days.

[0038] Those skilled in the art should understand that changes in the supply and demand of electricity depend largely on the output of renewable energy on actual trading days. Predicting future supply and demand of electricity based solely on historical data will make it difficult to capture special situations where market prices change dramatically due to sudden climate changes.

[0039] Therefore, the embodiment of the present application can further add wind speed, light intensity, relative humidity, temperature, and precipitation information on the actual trading day of the market on the basis that the input variables of the long-short-term memory network model include the electricity demand in each time period of the spot market and the historical data of electricity prices in each time period, so as to effectively solve the problem of the prediction model predicting historical data through historical data, and improve the accuracy of the electricity demand prediction results for the trading day to a certain extent.

[0040] Specifically, if Figure 2 As shown in the figure, the process of predicting the electricity demand gap and the price of the corresponding period in the future market trading day based on the long short-term memory network model is as follows:

[0041] 1. Input the historical supply and demand matching situation and historical price data of the spot market into the forget gate of the long short-term memory network. The forget gate is responsible for checking the current input and current output of the model and outputting a number from 0 to 1 for each number in the cell, where 1 means completely retain and 0 means completely delete. Its mathematical expression is:

[0042] f t =σ(W f ·[h t-1 ,x t ]+b f )

[0043] Among them, f t is the output of the model after passing through the forget gate at time t; W f 、b f are the weight and bias corresponding to the forget gate respectively; h t-1 is the output of the previous cell; x t is the input of the current cell; σ is the current input value x of the cell t Converge to the range of 0 to 1, thereby strengthening the LSTM network's recognition of the current cell input feature's Sigmoid function. The specific expression is:

[0044]

[0045] 2. Determine the amount of new information added to the cell. This part of the work is completed by the input gate and the state unit. The specific expression is:

[0046] i t =σ(W g ·[h t-1 , x t ]+b g )

[0047]

[0048] Among them, i t is the output of the model after passing through the input gate at time t; W g 、b g are the weights and biases corresponding to the input gate respectively; is the alternative content that needs to be updated at time t; W c 、b c are the weights and biases corresponding to the state units, respectively. At this time, the state unit C can be updated tThe value of is used to get the prediction result of the model, as shown in the following formula:

[0049] C t =f t ·C t-1 +i t ·C t

[0050] o t =σ(W o [h t-1 ,x t ]+b o )

[0051] h t =o t tanh(C t )

[0052] Among them, t is the output obtained after passing through the output gate at time t; W o 、b o are the weight and bias corresponding to the output gate respectively; h t The final output of the model is determined based on the output gate.

[0053] In step S102, based on the prediction results, each distributed resource user constructs an economic benefit target model and solves the economic benefit target model to obtain the quotation information for each time period, and adjusts the preset market-based transaction electricity ratio according to the quotation information and the willingness of each distributed resource user to obtain the corresponding quotation expectations, and feeds back the quotation expectations to the virtual power plant operator.

[0054] Furthermore, the distributed resource users in the embodiments of the present application, based on obtaining forecast information and fully considering their own wishes, aim to maximize economic benefits by participating in market-based transactions, and divide their power generation capacity in each time period into two parts: aggregated trading and supply and demand self-balancing. They also promptly feed back the output results considering their own wishes and the expected market prices to the virtual power plant operator.

[0055] Optionally, in one embodiment of the present application, based on the prediction results, each distributed resource user is allowed to construct an economic benefit target model respectively, solve the economic benefit target model to obtain the quotation information for each time period, and adjust the preset market-based transaction electricity ratio according to the quotation information and the willingness of each distributed resource user to obtain the corresponding quotation expectation, and feed back the quotation expectation to the virtual power plant operator, including: obtaining the payment unit electricity purchase economic cost and the purchase amount of each distributed resource user, and calculating the electricity purchase economic cost based on the payment unit electricity purchase economic cost and the purchase amount; collecting the market-based transaction electricity sales and price signals corresponding to the distributed resource users, and calculating the market-based transaction economic benefits through the market-based transaction electricity sales and price signals; obtaining the total energy storage charging capacity and the unit economic cost of energy storage charging and discharging loss corresponding to the energy storage facilities in the distributed resource users, and calculating the energy storage charging and discharging loss economic cost based on the total energy storage charging capacity and the unit economic cost; based on the purchase The economic cost of electricity, the economic benefits of market-based transactions, and the economic cost of energy storage charging and discharging losses are used to construct an economic benefit target model; a preset simulated annealing algorithm is used to calculate the quotation information for each time period, and based on the quotation information for each time period, each distributed resource user adjusts the proportion of market-based transactions in different time periods according to their own willingness to participate in market transactions in different time periods, so as to determine the target coefficient value corresponding to the proportion of market-based transactions; the energy storage electricity at the initial moment, the energy storage configuration capacity, and the energy storage electricity at adjacent moments are determined, and based on the energy storage electricity at the initial moment, the energy storage configuration capacity, and the energy storage electricity at adjacent moments, multiple energy storage facility constraints are constructed, wherein the multiple energy storage facility constraints include energy storage initial capacity constraint, energy storage capacity constraint, energy storage capacity constraint at adjacent moments, energy storage SOC state consistency constraint, and energy storage charging and discharging state uniqueness constraint; the target coefficient value is adjusted based on the multiple energy storage facility constraints and the own willingness of each distributed resource user to obtain the corresponding quotation expectation.

[0056] In the actual implementation process, the embodiment of the present application first needs to build a target model for maximizing user economic benefits.

[0057] Specifically, each distributed resource user with a certain number of distributed photovoltaic and energy storage facilities can purchase electricity from the grid or power sales company when their own load demand is not met. Users can respond to market price signals with the goal of minimizing economic costs while meeting their own energy needs.

[0058] It should be noted that for a certain distributed resource user, the specific expressions of the objective function and related variables of the economic benefit target model are as follows:

[0059]

[0060] Among them, F represents the economic benefit target model; Ibuy (i) is the economic cost paid by the user to the power grid or power sales company for purchasing electricity at time i; I sell (i) is the economic benefit obtained by the user participating in the market transaction at time i; ess (i) is the economic cost of energy storage charging and discharging loss at time i.

[0061] I in the above objective function buy The mathematical expression of (i) is:

[0062] I buy (i)=I price (i) E self (i)

[0063] E self (i)=(P load (i)-P pv (i)-P ess_dis (i)+P ess_chr_grid (i))·Δt

[0064] Among them, I price (i) is the economic cost of the unit electricity purchased by the user at time i, which is settled according to the time-of-use electricity price of the corresponding period; E self (i) is the amount of electricity purchased by the user at time i; P load (i) is the power load demand of the user at time i; P pv (i) is the output of distributed photovoltaic at time i; P ess_dis (i) is the discharge power of the energy storage at time i; P ess_chr_grid (i) is the charging power of the energy storage when purchasing electricity from the grid at time i; △t is the time step, with a unit of 1 hour.

[0065] I in the above objective function sell The mathematical expression of (i) is:

[0066] I sell (i)=I market (i) E market (i)

[0067] E market (i)=(P pv (i)-P load (i)+P ess_dis (i)-P ess_chr_pv (i))·Δt

[0068] Among them, I market (i) The predicted price signals provided by the virtual power plant operator to distributed resource users at different time periods; E market (i) is the electricity sales of users participating in market transactions at time i; Pess_chr_pv (i) is the charging power of the energy storage when absorbing the distributed photovoltaic output at time i.

[0069] I in the above objective function ess The mathematical expression of (i) is:

[0070] I ess (i) = α(E ess_chr (i)+E ess_dis (i))

[0071] E ess_chr (i)=(P ess_chr_grid (i)+P ess_chr_pv (i))·Δt

[0072] Where α is the unit economic cost of energy storage charging and discharging loss; E ess_chr (i) is the total charge capacity of the energy storage at time i.

[0073] In addition, in order to fully consider the wishes of the user resource subject, the embodiment of the present application can set the variable E market (i) Modify the discharge power P of the energy storage at different time periods by determining ess_dis (i) Whether it is used for market-based transactions or self-balancing of supply and demand to fully represent the intentions of each distributed resource subject, as shown in the following formula:

[0074] E market (i) = E market_spot (i)+E market_other (i)

[0075] E market_spot (i) = β·P ess_dis (i) Δt

[0076] E market_other (i) = (1-β)·P ess_dis (i) Δt

[0077] Among them, E market_spot (i) The amount of electricity that the user chooses to participate in spot trading; E market_other (i) The user selects the amount of electricity that satisfies their own electricity supply and demand; β is the proportional coefficient of the user's electricity volume participating in spot trading, ranging from 0 to 1. Distributed resource users can adjust the value of β to use part of the energy storage discharge volume for participating in spot trading and the other part of the energy storage discharge volume for achieving self-balancing of electricity supply and demand; E ess_dis (i) is the discharge amount of the energy storage at time i.

[0078] Furthermore, in the process of constructing the above optimization model, the embodiments of the present application can approximate the decision-making process of a user determining the proportion β of their own electricity consumption in spot trading as a process of gradually approaching the optimal solution through an optimization algorithm. That is, the goal of the user is to achieve the optimal economic benefit under information constraints by choosing the value of β. Therefore, the embodiments of the present application can assist distributed resource users of different categories to automatically determine the optimal value of β under limited information by using the simulated annealing algorithm. The specific process is as follows:

[0079] 1. Randomly generate an initial solution x current , set the initial temperature T0, set the number of iterations L, the termination temperature T final , the perturbation compensation Δx, and the cooling coefficient α, and generate a new solution x new :

[0080] x new =x current +Δx

[0081] where Δx is a random perturbation term, following a Gaussian distribution N(0,σ) or a uniform distribution.

[0082] ΔE = E new -E current

[0083] 2. Calculate the objective function value E new =F(x new ), and compare it with the energy E current =F(x current ) of the current solution to obtain the energy change:

[0084] x current =x new

[0085] In the actual execution process, it is necessary to decide whether to accept the new solution according to the energy change ΔE and the current temperature T: if ΔE < 0, directly accept the new solution; if ΔE ≥ 0, then accept the worse solution with a probability P(ΔE,T) = e -ΔE / T . In the specific implementation process, the embodiments of the present application generate a random number r ~ U(0,1), and if r < P(ΔE,T), then accept the new solution.

[0086] If the objective function value of the new solution is better than the historical optimal solution, update the historical optimal solution:

[0087] x best =x new

[0088] 3. After completing L iterations at the current temperature T, lower the temperature:

[0089] T = α·T

[0090] Among them, α is the cooling coefficient, which is usually 0.8 to 0.99.

[0091] 4. When T drops to the termination temperature T final Or when other stopping conditions are met (for example, the optimal solution has not changed after several consecutive iterations), the algorithm is terminated and the historical optimal solution x is output. best and the minimum value E best .

[0092] It's important to note that since adjustments to the β value (i.e., the proportion of electricity traded in the market) affect the level of flexibility released by users, selecting a smaller β value will result in a relatively low price-flexibility coefficient for that period, potentially affecting the winning bid for the final electricity volume declared for that period. If a user's declared electricity volume for a given period is not awarded, or if they are unsatisfied with the expected returns for that period, or if they believe they have a full understanding of market price fluctuations, they can manually change the β value for that period and complete the declaration process.

[0093] In addition, during the optimization process, the user's energy storage facilities must also meet the following constraints:

[0094] (1) Initial capacity constraints of energy storage:

[0095] E ess_ini =0.5ess bat

[0096] (2) Energy storage capacity constraints:

[0097] 0.1ess bat ≤E ess (i)≤0.9ess bat

[0098] (3) Capacity constraints of energy storage at adjacent times i and i-1:

[0099] E ess (i) = E ess (i-1)+E ess_chr (i)-E ess_dis (i)

[0100] (4) Energy storage SOC state consistency constraints:

[0101] E ess_ini =E ess_end

[0102] (5) Uniqueness constraint of energy storage charging and discharging state:

[0103] P ess_chr_grid (i)·P ess_dis (i)=0

[0104] Pess_chr_pv (i)·P ess_dis (i)=0

[0105] Among them, E ess_ini is the power at the initial moment of energy storage; ess bat Allocate capacity for energy storage; E ess (i) is the corresponding amount of energy stored at time i; E ess (i-1) is the corresponding amount of energy stored at time i-1; E ess_end The power level at the end of energy storage.

[0106] In step S103, the virtual power plant operator calculates the price-flexibility comprehensive coefficient of each distributed resource user in different time periods according to the quotation expectations, and sorts the price-flexibility comprehensive coefficient in descending order to obtain the corresponding sorting results, and calculates the corresponding overall reported electricity and reported price according to the sorting results, and reports the overall reported electricity and reported price to the market operation platform to determine multiple winning users and the actual benefits corresponding to the multiple winning users after the market is cleared on the actual operation day.

[0107] Furthermore, the embodiments of the present application also need to collect statistics on the quantity and quotation information of different users (i.e., quantity and quotation expectations) through the virtual power plant operator, and calculate the price-flexibility comprehensive coefficient of each user in different time periods respectively; then, the embodiments of the present application can superimpose the total power generation reported by the selected entities in the corresponding time period in order of the user comprehensive coefficient from high to low and calculate the average electricity price, and report the calculated quantity-price information (i.e., the overall reported quantity and reported price) to the market operation platform to complete the day-ahead declaration behavior of the electricity spot market.

[0108] Optionally, in one embodiment of the present application, the virtual power plant operator calculates the price-flexibility comprehensive coefficient of each distributed resource user in different time periods according to the reported quantity and quotation expectations, and sorts the price-flexibility comprehensive coefficients in descending order to obtain corresponding sorting results, and calculates the corresponding overall reported electricity and reported price according to the sorting results, and reports the overall reported electricity and reported price to the market operation platform to determine multiple winning users and the actual benefits corresponding to multiple winning users after the market is cleared on the actual operation day, including: determining the theoretical flexibility adjustment upper limit and theoretical flexibility adjustment lower limit of distributed resource users in different time periods, and the upper limit and lower limit of the reported price of all aggregated entities of the virtual power plant operator in different time periods; based on the theoretical flexibility adjustment upper limit, theoretical flexibility adjustment lower limit, upper limit and lower limit of the reported price, calculate the price competitiveness coefficients of different distributed resource users in different time periods on an actual market operation day. number and flexibility release level; calculate the price-flexibility comprehensive coefficient corresponding to different distributed resource users according to the price competitiveness coefficient and flexibility release level, and sort the price-flexibility comprehensive coefficient in descending order through the virtual power plant operator to obtain the sorting result; based on the sorting result, determine the top k distributed resource users reported in each time period, and in each time period, enable the virtual power plant operator to calculate the reported electricity and reported price according to the reported quantity and quotation expectations corresponding to the top k distributed resource users, and report the reported electricity and reported price to the market operation platform, so as to determine multiple successful bidders among the top k distributed resource users after the market is cleared on the actual operation day, where k is a positive integer; obtain the actual clearing information of the spot market, so that the virtual power plant operator can obtain multiple dispatching periods issued by the target power grid according to the actual clearing information, allocate the multiple dispatching periods to multiple successful bidders, and calculate the actual income corresponding to each successful bidder among the multiple successful bidders.

[0109] In actual implementation, the calculation process of the price-flexibility comprehensive coefficient for each user in the embodiment of the present application is as follows:

[0110] 1. For each distributed resource user i, assume that the reported quantity and price information at time j in 24 hours are E i,j and P i,j The agreement signed with the virtual power plant aggregator stipulates that the upper limit of its own theoretical flexibility adjustment in each period is E i,j ', the lower limit is E i,j ", the upper limit of the declared price of all aggregated entities of the virtual power plant in different time periods is max(P all,j ), the lower limit is min(P all,j ), the virtual power plant operator calculates the price competitiveness coefficient P of different users in each period of the actual operation day of a market i,j_norm with flexibility release level FUi.j The specific mathematical expression is as follows:

[0111] P i,j_norm =(max(P all,j )-P i,j ) / (max(P all,j )-min(P all,j ))

[0112] FU i,j =(E i,j -E i,j ”) / (E i,j '-E i,j ”)

[0113] It should be noted that the above two mathematical expressions have ensured that the dimensions and positive and negative effects of the user price coefficient and the flexibility coefficient are consistent, that is, P i,j_norm with FU i.j The value range of is 0 to 1, and the closer to 1 the better. On this basis, the embodiment of the present application can calculate the price-flexibility comprehensive coefficient CU of each user i,j , as shown in the following formula:

[0114] CU i,j =(P i,j_norm +FU i,j ) / 2

[0115] 2. Virtual power plant operators shall calculate the price-flexibility coefficient CU i,j Arrange in descending order, comprehensively analyze the historical clearing data of the spot market, determine the top k users (i.e., the top k distributed resource users) reporting in each period j, and on this basis, the virtual power plant operator reports the electricity TU to the spot market as a subject in each period j. j and the quoted price TP j The calculation expression is:

[0116]

[0117] 3. Based on the actual clearing situation of the day-ahead market, the virtual power plant operator allocates the various time slots issued by the grid to the first k′ users who actually won the bid (i.e., multiple winning users). The corresponding revenue expression for each winning user i is as follows:

[0118] I sell-real (i,j)=I market-real (i,j)·E market-real (i,j)

[0119] Among them, I sell-real (i, j) is the actual income of the winning user i at time j; I market-real(i, j) is the actual settlement price of the winning bidder i at time j; E market-real (i, j) is the amount of electricity actually traded by the winning user i at time j.

[0120] In step S104, it is determined whether the actual revenue meets the quotation expectations of the distributed resource users and the virtual power plant operator. If the actual revenue does not meet the quotation expectations, the virtual power plant operator retrains the long short-term memory network model, and each distributed resource user adjusts the corresponding market-based transaction electricity ratio, and re-executes the reporting operation.

[0121] Finally, the embodiments of the present application can determine whether the actual revenue meets the quotation expectations of distributed resource users and virtual power plant operators, and when the actual revenue does not meet the quotation expectations, retrain the long short-term memory network model to adjust the quotation revenue so that it meets the quotation expectations.

[0122] Optionally, in one embodiment of the present application, it is determined whether the actual revenue meets the quotation expectations of the distributed resource users and the virtual power plant operator, wherein if the actual revenue does not meet the quotation expectations, the long short-term memory network model is retrained by the virtual power plant operator to enable each distributed resource user to adjust the corresponding market-based transaction electricity ratio and re-execute the submission operation, including: determining whether the actual revenue corresponding to each successful bidder meets the quotation expectations, wherein if the actual revenue does not meet the quotation expectations, the input data of the long short-term memory network model is updated by the virtual power plant operator, and the long short-term memory network model is retrained using the updated input data; based on each distributed resource user, the market winning information corresponding to the spot market is obtained, and the economic benefit target model is solved according to the market winning information and the retrained long short-term memory network model to obtain new quotation information, and the market-based transaction electricity ratio is adjusted according to the new quotation information to adjust the quotation revenue corresponding to each successful bidder.

[0123] It should be noted that after the spot market completes the clearing and settlement, the virtual power plant operator will feedback the corresponding information to the user. When the quotation revenue does not meet the expected expectations of the distributed resource users and the virtual power plant operator (i.e., the quotation expectation), the virtual power plant operator can roll over the historical data of the long short-term memory network model and retrain it. The user can combine the feedback of the market bidding situation (i.e., the market bidding information of the spot market obtained through multiple winning users), and increase their own willingness to declare and the level of flexibility release by increasing the proportion of market-based trading electricity β, and repeat the above-mentioned day-ahead declaration behavior and actual revenue-quotation expectation judgment operation.

[0124] It is understandable that compared with the relevant research on the aggregation of existing distributed resource users by virtual power plants to participate in market-based transactions, the existing technology neither takes into account the differentiated willingness of massive distributed resource users in participating in market-based transactions and economic risk aversion, nor reflects the level of their flexibility release; in the actual process of market-based transactions, distributed resource users do not necessarily want their own power generation capacity to be fully represented by virtual power plants to participate in transactions, but due to their lack of full understanding of the market operation rules, it is difficult to determine the relevant methods for participating in market-based transactions and the proportion of electricity consumption for self-balancing of supply and demand.

[0125] Therefore, the embodiments of the present application can assist users in determining the most suitable method for participating in the proportion of electricity consumption on the basis of fully considering the willingness of different types of distributed resource users to participate in the market and the level of flexibility release, and continuously incentivize them to release their own flexibility through market prices, which will help provide theoretical and model support for the future design of market mechanisms that fully consider the willingness of demand-side resources and assist the power system in implementing supply and demand balance.

[0126] The following describes the execution logic of the spot trading electricity splitting method of this application that takes into account the wishes of the virtual power plant aggregation entity in combination with the accompanying drawings.

[0127] Figure 3 This is a schematic diagram of the execution logic of the spot trading electricity splitting method considering the willingness of the virtual power plant aggregation subject in this application. Figure 3 As shown, the execution process of the spot trading electricity splitting method considering the willingness of the virtual power plant aggregation subject in this application is as follows:

[0128] S301: Obtain hourly distributed photovoltaic output, energy storage installed capacity, power load demand, spot market supply and demand in each period, spot market electricity price historical data for various types of users within a certain time and space range, as well as future wind speed, light intensity, relative humidity, temperature, and precipitation data based on weather forecasts;

[0129] S302: The virtual power plant operator uses the long short-term memory network model to predict the market power demand gap and corresponding price for future trading days based on the historical supply and demand matching and price data of the spot market and weather forecasts, and informs the distributed resource users of the prediction results.

[0130] S303: Distributed resource users, based on forecast information and taking into account their own preferences, aim to maximize economic benefits by participating in market-based transactions. They divide their power generation capacity at each time period into two parts: aggregated trading and supply-demand self-balancing. They then promptly provide feedback to the virtual power plant operator on their output results, which take into account their preferences, and their desired market price.

[0131] S304: The virtual power plant operator collects the reported power and price information of different users and calculates the price-flexibility coefficient for each user in different time periods. Then, according to the user comprehensive coefficients from high to low, the operator adds the total power generation reported by the selected entities in the corresponding time period and calculates the average power price. The calculated power volume-price information is submitted to the market operation platform, completing the day-ahead declaration in the power spot market.

[0132] S305: After the spot market completes clearing and settlement, the virtual power plant operator will provide feedback to users. If the revenue does not meet the expectations of distributed resource users and the virtual power plant operator, the virtual power plant operator can roll over the historical data of the long-term short-term memory network model in S302 and retrain it. Users can then, based on the feedback from the market bidding results, increase their bidding willingness and flexibility by increasing the proportion of market-based electricity transactions, and repeat the steps in S304 and S305.

[0133] Therefore, the embodiments of the present application can achieve the optimal allocation of electricity for different distributed resource users to participate in aggregated transactions and balance their own electricity supply and demand, effectively reduce the operational risks of users with insufficient market power, and provide a theoretical basis and model support for building a virtual power plant market trading model that fully considers the wishes of user resource entities and helps the power grid implement supply and demand balance.

[0134] According to the spot trading electricity segmentation method proposed in the embodiment of the present application, which takes into account the willingness of the virtual power plant aggregation subject, the historical supply and demand matching situation, historical price data and meteorological data of the spot market on the actual trading day of the market are obtained within the target time and space range, and the historical supply and demand matching situation, historical price data and meteorological data are input into a pre-built long-short-term memory network model to output the prediction results of the market electricity demand gap and price on future trading days; based on the prediction results, each distributed resource user constructs an economic benefit target model respectively, solves the economic benefit target model to obtain the quotation information of each time period, and adjusts the preset market-based trading electricity ratio according to the quotation information and the willingness of each distributed resource user to obtain the corresponding quotation expectation, and feeds the quotation expectation back to the virtual power plant operation Business; the virtual power plant operator calculates the price-flexibility comprehensive coefficient of each distributed resource user in different time periods according to the quotation expectations, and sorts the price-flexibility comprehensive coefficients in descending order to obtain the corresponding sorting results, and calculates the corresponding overall reported electricity and reported price according to the sorting results, and reports the overall reported electricity and reported price to the market operation platform to determine the actual benefits corresponding to multiple winning users and multiple winning users after the market is cleared on the actual operation day; judge whether the actual benefits meet the quotation expectations of the distributed resource users and the virtual power plant operator, wherein, if the actual benefits do not meet the quotation expectations, the virtual power plant operator retrains the long-term and short-term memory network model, and each distributed resource user adjusts the corresponding market-based transaction electricity ratio, and re-executes the reporting operation. This application can achieve the optimal allocation of the two parts of electricity for different distributed resource users to participate in aggregated transactions and their own power supply and demand balance, effectively reduce the operational risks of users with insufficient market power, and provide a reliable theoretical basis and model support for building a virtual power plant market trading model that fully considers the wishes of user resource entities and helps the power grid implement supply and demand balance.

[0135] Secondly, with reference to the accompanying drawings, a spot trading electricity splitting device that takes into account the wishes of the virtual power plant aggregation entity according to an embodiment of the present application is described.

[0136] Figure 4 It is a block diagram of a spot trading electricity splitting device that takes into account the wishes of the virtual power plant aggregation entity in an embodiment of the present application.

[0137] like Figure 4 As shown, the spot trading electricity splitting device 10 taking into account the willingness of the virtual power plant aggregation subject includes: a prediction module 100, a solution module 200, a declaration module 300 and a judgment module 400.

[0138] Among them, the prediction module 100 is used to obtain the historical supply and demand matching situation, historical price data and meteorological data of the spot market on the actual trading day within the target time and space range, and input the historical supply and demand matching situation, historical price data and meteorological data into a pre-built long-short-term memory network model to output the prediction results of the market electricity demand gap and price on future trading days.

[0139] The solution module 200 is used to enable each distributed resource user to construct an economic benefit target model based on the prediction results, solve the economic benefit target model, and obtain the quotation information for each time period, and adjust the preset market-based trading electricity ratio according to the quotation information and the willingness of each distributed resource user to obtain the corresponding quotation expectations, and feed back the quotation expectations to the virtual power plant operator.

[0140] The declaration module 300 is used to calculate the price-flexibility comprehensive coefficient of each distributed resource user in different time periods according to the reported quantity and quotation expectations by the virtual power plant operator, and sort the price-flexibility comprehensive coefficient in descending order to obtain the corresponding sorting results, and calculate the corresponding overall reported electricity and reported price according to the sorting results, and report the overall reported electricity and reported price to the market operation platform to determine multiple winning users and the actual benefits corresponding to the multiple winning users after the market is cleared on the actual operation day.

[0141] The judgment module 400 is used to judge whether the actual profit meets the quotation expectations of the distributed resource users and the virtual power plant operator. If the actual profit does not meet the quotation expectations, the long short-term memory network model is retrained by the virtual power plant operator, and each distributed resource user adjusts the corresponding market-based transaction electricity ratio and re-executes the reporting operation.

[0142] Optionally, in one embodiment of the present application, the prediction module 100 includes: a first acquisition unit and a generation unit.

[0143] Among them, the first collection unit is used to collect meteorological data on the actual market trading day, wherein the meteorological data includes wind speed, light intensity, relative humidity, temperature and precipitation information on the actual market trading day.

[0144] The generation unit is used to input historical supply and demand matching conditions, historical price data and meteorological data into the long short-term memory network model to obtain corresponding input gate output information, and based on the input gate output information, generate prediction results for market electricity demand gap and price in future trading days.

[0145] Optionally, in one embodiment of the present application, the solution module 200 includes: a first calculation unit, a second collection unit, an acquisition unit, a first construction unit, a second calculation unit, a second construction unit and a third calculation unit.

[0146] The first calculation unit is used to obtain the payment unit economic cost of electricity purchase and the purchased electricity amount of each distributed resource user, so as to calculate the electricity purchase economic cost based on the payment unit economic cost of electricity purchase and the purchased electricity amount.

[0147] The second collection unit is used to collect the market-based transaction electricity sales volume and price signals corresponding to the distributed resource users, and calculate the market-based transaction economic benefits through the market-based transaction electricity sales volume and price signals.

[0148] The acquisition unit is used to obtain the total energy storage charging capacity and the unit economic cost of energy storage charging and discharging loss corresponding to the energy storage facilities in the distributed resource users, and calculate the economic cost of energy storage charging and discharging loss based on the total energy storage charging capacity and the unit economic cost.

[0149] The first construction unit is used to construct an economic benefit target model based on the economic cost of purchasing electricity, the economic benefits of market-based transactions, and the economic cost of energy storage charging and discharging losses.

[0150] The second calculation unit is used to calculate the quotation information of each time period by using a preset simulated annealing algorithm, and based on the quotation information of each time period, each distributed resource user adjusts the proportion of market-based trading electricity in different time periods according to his own willingness to participate in market transactions in different time periods, so as to determine the target coefficient value corresponding to the proportion of market-based trading electricity.

[0151] The second construction unit is used to determine the energy storage power at the initial moment, the energy storage configuration capacity and the energy storage power at adjacent moments, and construct multiple energy storage facility constraints based on the energy storage power at the initial moment, the energy storage configuration capacity and the energy storage power at adjacent moments, wherein the multiple energy storage facility constraints include energy storage initial capacity constraint, energy storage capacity constraint, energy storage capacity constraint at adjacent moments, energy storage SOC state consistency constraint, and energy storage charge and discharge state uniqueness constraint.

[0152] The third calculation unit is used to adjust the target coefficient value based on multiple energy storage facility constraints and the willingness of each distributed resource user to obtain corresponding quotation expectations.

[0153] Optionally, in one embodiment of the present application, the declaration module 300 includes: a first determination unit, a fourth calculation unit, a sorting unit, a second determination unit and an allocation unit.

[0154] Among them, the first determination unit is used to determine the theoretical flexibility adjustment upper limit and theoretical flexibility adjustment lower limit of distributed resource users in different time periods, as well as the upper limit and lower limit of the declared prices of all aggregated entities of virtual power plant operators in different time periods.

[0155] The fourth calculation unit is used to calculate the price competitiveness coefficient and flexibility release level of different distributed resource users in different time periods during the actual operation of a market based on the theoretical flexibility adjustment upper limit, the theoretical flexibility adjustment lower limit, the declared price upper limit and the declared price lower limit.

[0156] The sorting unit is used to calculate the price-flexibility comprehensive coefficient corresponding to different distributed resource users based on the price competitiveness coefficient and the flexibility release level, and sort the price-flexibility comprehensive coefficient in descending order through the virtual power plant operator to obtain the sorting result.

[0157] The second determination unit is used to determine the top k distributed resource users who submitted reports in each time period based on the sorting results, and in each time period, enable the virtual power plant operator to calculate the reported electricity and reported price according to the reported quantity and price expectations corresponding to the top k distributed resource users, and report the reported electricity and reported price to the market operation platform, so as to determine multiple winning users among the top k distributed resource users after the market is cleared on the actual operation day, where k is a positive integer.

[0158] The allocation unit is used to obtain the actual clearing information of the spot market so that the virtual power plant operator can obtain multiple scheduling periods issued by the target power grid based on the actual clearing information, allocate the multiple scheduling periods to multiple winning users, and calculate the actual benefits corresponding to each of the multiple winning users.

[0159] Optionally, in one embodiment of the present application, the judgment module 400 includes: an analysis unit and an adjustment unit.

[0160] Among them, the analysis unit is used to determine whether the actual profit corresponding to each successful bidder meets the quotation expectation. If the actual profit does not meet the quotation expectation, the virtual power plant operator updates the input data of the long short-term memory network model and uses the updated input data to retrain the long short-term memory network model.

[0161] The adjustment unit is used to obtain the market winning bid information corresponding to the spot market based on each distributed resource user, and solve the economic benefit target model based on the market winning bid information and the retrained long short-term memory network model to obtain new quotation information, and adjust the proportion of market-based transaction electricity through the new quotation information to adjust the quotation income corresponding to each winning user.

[0162] It should be noted that the above explanation of the embodiment of the spot trading electricity splitting method considering the wishes of the virtual power plant aggregation subjects is also applicable to the spot trading electricity splitting device considering the wishes of the virtual power plant aggregation subjects in this embodiment, and will not be repeated here.

[0163] According to the embodiment of the present application, a spot trading electricity segmentation device that takes into account the intentions of the virtual power plant aggregation subject includes a prediction module 100, which is used to obtain the historical supply and demand matching situation, historical price data and meteorological data of the spot market within the target time and space range, and input the historical supply and demand matching situation, historical price data and meteorological data into a pre-built long-short-term memory network model to output the prediction results of the market electricity demand gap and price in future trading days; a solution module 200, which is used to enable each distributed resource user to construct an economic benefit target model based on the prediction results, solve the economic benefit target model to obtain the quotation information for each time period, and adjust the preset market-based trading electricity ratio according to the quotation information and the willingness of each distributed resource user to obtain the corresponding quotation expectation, and feed the quotation expectation back to the virtual power plant operation Business; the declaration module 300 is used to calculate the price-flexibility comprehensive coefficient of each distributed resource user in different time periods according to the quotation expectation of the virtual power plant operator, and sort the price-flexibility comprehensive coefficient in descending order to obtain the corresponding sorting result, and calculate the corresponding overall submitted electricity and submitted price according to the sorting result, and submit the overall submitted electricity and submitted price to the market operation platform to determine the actual benefits of multiple winning users and multiple winning users after the market is cleared on the actual operation day; the judgment module 400 is used to judge whether the actual benefits meet the quotation expectations of the distributed resource users and the virtual power plant operator, wherein, if the actual benefits do not meet the quotation expectations, the long short-term memory network model is retrained by the virtual power plant operator, and each distributed resource user adjusts the corresponding market-based transaction electricity ratio, and re-executes the submission operation. This application can achieve the optimal allocation of the two parts of electricity for different distributed resource users to participate in aggregated transactions and their own power supply and demand balance, effectively reduce the operational risks of users with insufficient market power, and provide a reliable theoretical basis and model support for building a virtual power plant market trading model that fully considers the wishes of user resource entities and helps the power grid implement supply and demand balance.

[0164] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0165] Memory 501 , processor 502 , and computer programs stored in the memory 501 and executable on the processor 502 .

[0166] When the processor 502 executes the program, the spot trading electricity splitting method provided in the above embodiment considering the will of the virtual power plant aggregation entity is implemented.

[0167] Furthermore, the electronic device further includes:

[0168] The communication interface 503 is used for communication between the memory 501 and the processor 502 .

[0169] The memory 501 is used to store computer programs that can be run on the processor 502 .

[0170] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0171] If the memory 501, processor 502, and communication interface 503 are implemented independently, the communication interface 503, memory 501, and processor 502 can be connected to each other via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0172] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0173] The processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0174] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned spot trading electricity splitting method taking into account the wishes of the virtual power plant aggregation entity.

[0175] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed, is used to implement the above-mentioned spot trading electricity splitting method that takes into account the wishes of the virtual power plant aggregation entity.

[0176] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0177] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0178] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing a custom logical function or process step, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0179] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or N wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program can be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing it in other suitable ways as necessary, and then storing it in a computer memory.

[0180] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0181] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0182] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0183] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A spot trading electricity splitting method considering the willingness of virtual power plant aggregation entities, characterized by: The following steps are involved: Obtaining historical supply and demand matching conditions, historical price data, and meteorological data of the spot market on actual trading days within a target time and space range, and inputting the historical supply and demand matching conditions, the historical price data, and the meteorological data into a pre-built long-short-term memory network model to output prediction results for market electricity demand gaps and prices on future trading days; Based on the prediction results, each distributed resource user constructs an economic benefit target model, solves the economic benefit target model to obtain quotation information for each time period, and adjusts the preset market-based transaction electricity ratio according to the quotation information and the willingness of each distributed resource user to obtain corresponding quotation expectations, and feeds back the quotation expectations to the virtual power plant operator; The virtual power plant operator calculates the price-flexibility comprehensive coefficient of each distributed resource user in different time periods according to the reported quantity and quotation expectations, and sorts the price-flexibility comprehensive coefficients in descending order to obtain corresponding sorting results, and calculates the corresponding overall reported electricity and reported price according to the sorting results, and reports the overall reported electricity and reported price to the market operation platform to determine multiple successful bidders and actual benefits corresponding to the multiple successful bidders after the market is cleared on the actual operation day; Determine whether the actual revenue meets the quotation expectations of the distributed resource users and the virtual power plant operator, wherein, if the actual revenue does not meet the quotation expectations, the virtual power plant operator will retrain the long short-term memory network model, and each distributed resource user will adjust the corresponding market-based transaction electricity ratio, and re-execute the reporting operation.

2. The method for splitting spot transaction electricity quantity considering the will of the virtual power plant aggregation subject according to claim 1 is characterized in that: The method obtains the historical supply and demand matching situation, historical price data and meteorological data of the spot market on the actual trading day within the target time and space range, and inputs the historical supply and demand matching situation, the historical price data and the meteorological data into a pre-built long-short-term memory network model to output the prediction results of the market electricity demand gap and price on the future trading day, including: Collecting meteorological data on the actual trading day of the market, wherein the meteorological data includes wind speed, light intensity, relative humidity, temperature and precipitation information on the actual trading day of the market; The historical supply and demand matching situation, the historical price data and the meteorological data are input into the long short-term memory network model to obtain corresponding input gate output information, and based on the input gate output information, a forecast result of the market electricity demand gap and price on the future trading day is generated.

3. The method for splitting spot trading electricity quantity considering the will of the virtual power plant aggregation subject according to claim 1 is characterized in that: Based on the prediction results, each distributed resource user constructs an economic benefit target model, solves the economic benefit target model to obtain quotation information for each time period, and adjusts a preset market-based transaction electricity ratio according to the quotation information and the willingness of each distributed resource user to obtain a corresponding quotation expectation, and feeds back the quotation expectation to the virtual power plant operator, including: Obtaining the payment unit economic cost of electricity purchase and the purchased electricity amount of each distributed resource user, so as to calculate the electricity purchase economic cost based on the payment unit economic cost of electricity purchase and the purchased electricity amount; Collecting market-based transaction power sales and price signals corresponding to the distributed resource users, and calculating market-based transaction economic benefits based on the market-based transaction power sales and the price signals; Obtaining the total energy storage charge capacity and the unit economic cost of energy storage charge and discharge losses corresponding to the energy storage facilities of the distributed resource users, and calculating the economic cost of energy storage charge and discharge losses based on the total energy storage charge capacity and the unit economic cost; Constructing the economic benefit target model based on the economic cost of electricity purchase, the economic benefit of market-based transactions, and the economic cost of energy storage charging and discharging losses; Calculate the quotation information for each time period using a preset simulated annealing algorithm, and based on the quotation information for each time period, enable each distributed resource user to adjust the proportion of market-based transaction electricity in different time periods according to their own willingness to participate in market transactions in different time periods, so as to determine a target coefficient value corresponding to the proportion of market-based transaction electricity; Determine the energy storage capacity at the initial moment, the energy storage configuration capacity, and the energy storage capacity at adjacent moments, and construct multiple energy storage facility constraints based on the energy storage capacity at the initial moment, the energy storage configuration capacity, and the energy storage capacity at adjacent moments, wherein the multiple energy storage facility constraints include energy storage initial capacity constraint, energy storage capacity constraint, energy storage capacity constraint at adjacent moments, energy storage SOC state consistency constraint, and energy storage charge and discharge state uniqueness constraint; The target coefficient value is adjusted based on the multiple energy storage facility constraints and the willingness of each distributed resource user to obtain corresponding quotation expectations.

4. The method for splitting spot trading electricity quantity considering the will of the virtual power plant aggregation subject according to claim 3 is characterized in that: The virtual power plant operator calculates the price-flexibility comprehensive coefficient of each distributed resource user in different time periods according to the reported quantity and quotation expectations, and sorts the price-flexibility comprehensive coefficients in descending order to obtain corresponding sorting results, and calculates the corresponding overall reported electricity and reported price according to the sorting results, and reports the overall reported electricity and reported price to the market operation platform to determine multiple successful bidders and actual benefits corresponding to the multiple successful bidders after the market is cleared on the actual operation day, including: Determine the theoretical flexibility adjustment upper limit and theoretical flexibility adjustment lower limit of the distributed resource users in the different time periods, and the upper limit and lower limit of the declared prices of all aggregated entities of the virtual power plant operator in different time periods; Calculate the price competitiveness coefficients and flexibility release levels of different distributed resource users in different time periods during an actual market operation day based on the theoretical flexibility adjustment upper limit, the theoretical flexibility adjustment lower limit, the declared price upper limit, and the declared price lower limit; Calculating the price-flexibility comprehensive coefficients corresponding to the different distributed resource users according to the price competitiveness coefficient and the flexibility release level, and sorting the price-flexibility comprehensive coefficients in descending order by the virtual power plant operator to obtain the sorting result; Based on the ranking results, the top k distributed resource users who submitted bids in each time period are determined, and in each time period, the virtual power plant operator calculates the submitted electricity and the submitted price according to the expected bids corresponding to the top k distributed resource users, and submits the submitted electricity and the submitted price to the market operation platform, so as to determine a plurality of successful bidders among the top k distributed resource users after the market is cleared on the actual operation day, where k is a positive integer; The actual clearing information of the spot market is obtained so that the virtual power plant operator can obtain multiple scheduling periods issued by the target power grid according to the actual clearing information, allocate the multiple scheduling periods to the multiple successful bidders, and calculate the actual benefits corresponding to each of the multiple successful bidders.

5. The method for splitting spot transaction electricity quantity considering the will of the virtual power plant aggregation subject according to claim 4 is characterized in that: The determining whether the actual revenue meets the quotation expectations of the distributed resource users and the virtual power plant operator, wherein if the actual revenue does not meet the quotation expectations, the virtual power plant operator retrains the long short-term memory network model so that each distributed resource user adjusts the corresponding market-based transaction electricity ratio and re-executes the quotation operation, including: Determining whether the actual revenue corresponding to each successful bidder meets the bid quotation expectation, wherein if the actual revenue does not meet the bid quotation expectation, updating the input data of the long short-term memory network model by the virtual power plant operator, and retraining the long short-term memory network model using the updated input data; Based on each distributed resource user, the market winning bid information corresponding to the spot market is obtained, and the economic benefit target model is solved according to the market winning bid information and the retrained long short-term memory network model to obtain new quotation information, and the proportion of market-based transaction electricity is adjusted according to the new quotation information to adjust the quotation income corresponding to each winning bidder.

6. A spot trading electricity splitting device that takes into account the will of the virtual power plant aggregation subject, characterized in that: include: A forecasting module is used to obtain historical supply and demand matching conditions, historical price data, and meteorological data of the spot market on actual trading days within a target time and space range, and input the historical supply and demand matching conditions, the historical price data, and the meteorological data into a pre-built long-short-term memory network model to output forecast results for the market electricity demand gap and price on future trading days; A solution module is configured to enable each distributed resource user to construct an economic benefit target model based on the prediction results, solve the economic benefit target model to obtain quotation information for each time period, adjust the preset market-based transaction electricity ratio according to the quotation information and the willingness of each distributed resource user, obtain corresponding quotation expectations, and feed back the quotation expectations to the virtual power plant operator; a reporting module, configured to calculate, by the virtual power plant operator, the price-flexibility comprehensive coefficient of each distributed resource user in different time periods according to the reported quantity and quotation expectations, and sort the price-flexibility comprehensive coefficients in descending order to obtain corresponding sorting results, and calculate the corresponding overall reported electricity and reported price according to the sorting results, and report the overall reported electricity and reported price to the market operation platform, so as to determine multiple successful bidders and the actual benefits corresponding to the multiple successful bidders after the market is cleared on the actual operation day; A judgment module is used to judge whether the actual profit meets the quotation expectations of the distributed resource users and the virtual power plant operator. If the actual profit does not meet the quotation expectations, the virtual power plant operator will retrain the long short-term memory network model, and each distributed resource user will adjust the corresponding market-based transaction electricity ratio and re-execute the reporting operation.

7. The spot transaction electricity splitting device considering the will of the virtual power plant aggregation subject according to claim 6 is characterized in that: The prediction module includes: a first collection unit, configured to collect meteorological data on the actual trading day of the market, wherein the meteorological data includes wind speed, light intensity, relative humidity, temperature, and precipitation information on the actual trading day of the market; A generation unit is used to input the historical supply and demand matching situation, the historical price data and the meteorological data into the long short-term memory network model to obtain corresponding input gate output information, and based on the input gate output information, generate the prediction results of the market electricity demand gap and price on the future trading day.

8. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a method for splitting spot-trading electricity that takes into account the will of a virtual power plant aggregation entity as described in any one of claims 1 to 5.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement a spot trading electricity splitting method taking into account the willingness of a virtual power plant aggregation subject as described in any one of claims 1 to 5.

10. A computer program product comprising a computer program, characterized in that The program is executed to implement the spot trading electricity splitting method considering the willingness of the virtual power plant aggregation subject as described in any one of claims 1 to 5.

Images