Method and system for virtual power plant resource allocation optimization and computing device

Abstract

The invention provides a method and system for virtual power plant resource allocation optimization and computing equipment, and is applied to the technical field of new energy prediction. The method comprises the following steps: collecting data of a distributed energy production and elimination main body through a centralized control center; establishing prediction data by using the prediction model; forming an internal scheduling plan by using a master-slave game model so as to determine the output and income of each distributed energy production and elimination main body; the operation state of the distributed energy production and elimination main body is monitored in real time through a sensor, intelligent metering equipment and a communication network, and the internal scheduling plan is dynamically adjusted according to the operation state, so that the stability and economy of the system are ensured. By using the method and the system of the invention, flexibility and economy of internal and external resource allocation of the virtual power plant can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power systems and energy management, and in particular to a method and system and computing equipment for optimizing resource allocation of a virtual power plant. Background Art

[0002] With the rapid development of renewable energy and the popularization of distributed energy, virtual power plants, as a new organizational model that integrates multiple distributed energy resources and participates in the power market in a unified manner, are gradually becoming an important part of the power system. Virtual power plants aggregate distributed energy resources such as wind power, photovoltaics, energy storage, and controllable loads to form an adjustable virtual energy supply unit to participate in the bidding and dispatching of the power market.

[0003] However, in the operation of virtual power plants, various market players, such as power generators, energy storage facilities, and demand response users, may adopt different strategic behaviors in order to maximize their own interests, such as bidding strategies, energy storage charging and discharging strategies, and demand response strategies. These strategic behaviors not only affect the internal operation of virtual power plants, but also have a profound impact on the stability and economy of the entire power market.

[0004] Therefore, a method for optimizing resource allocation of virtual power plants is needed to accurately analyze and predict the strategic behaviors of these market players, and then optimize the operating strategy and resource allocation of virtual power plants. Summary of the invention

[0005] The present invention aims to provide a method and computing equipment for optimizing resource allocation of virtual power plants, so as to more scientifically and comprehensively evaluate the power trading situation of new energy enterprises.

[0006] According to one aspect of the present invention, a method for optimizing resource allocation of a virtual power plant is provided, comprising: Collect data from distributed energy producers and consumers through a centralized control center; Use predictive models to build predictive data; The master-slave game model is used to form an internal scheduling plan to determine the output and benefits of each distributed energy producer and consumer; The operating status of distributed energy production and consumption entities is monitored in real time through sensors, smart metering equipment and communication networks, and the internal scheduling plan is dynamically adjusted according to the operating status to ensure the stability and economy of the system.

[0007] According to some embodiments, the collecting of data of distributed energy production and consumption entities through a centralized control center includes: Collect electricity price data, load demand data, and renewable energy output data; Obtain the power generation, power consumption and energy storage status of the distributed energy production and consumption entity.

[0008] According to some embodiments, the collecting of data of distributed energy production and consumption entities through a centralized control center further includes preprocessing the data: Clean the data to remove outliers and missing values; Standardize the data format to ensure uniform processing of data from different sources; Perform feature extraction on the data, including calculation of load peak, average value, and standard deviation.

[0009] According to some embodiments, the using the prediction model to establish prediction data includes: Use time series analysis to forecast load demand; Combined with historical electricity price data, machine learning algorithms are used to predict electricity prices; Based on weather forecast data, use physical models or data-driven models to predict the power generation of photovoltaic and wind energy.

[0010] According to some embodiments, forming an internal scheduling plan using a master-slave game model includes repeating the following process until a Nash equilibrium is reached or a predetermined convergence condition is satisfied: Define the first objective function of the virtual power plant operator and the second objective function of the distributed energy production and consumption entity; According to the forecast data, setting a first power purchase and sale price signal of the virtual power plant operator, and sending the first power purchase and sale price signal to the distributed energy production and consumption entity; The distributed energy production and consumption entities adjust their respective power generation or power consumption plans through the second objective function according to the first power purchase and sales price signal, and submit the output and quotation information to the virtual power plant operator; After collecting the responses of the distributed energy production and consumption entities, the price signal is readjusted to obtain a second electricity purchase and sales price signal, and the second electricity purchase and sales price signal is sent to the distributed energy production and consumption entities again.

[0011] According to some embodiments, the method further includes: adjusting the internal scheduling plan according to market feedback.

[0012] According to some embodiments, the method further comprises risk-adjusting the internal scheduling plan using a risk cost model: Using probability distribution functions to quantify the statistical characteristics of uncertainties, including electricity price fluctuations, load demand changes, and renewable energy output fluctuations; The operating costs or benefits of the virtual power plant under different scenarios are calculated through the Monte Carlo simulation method, and the internal scheduling plan is adjusted according to the set risk preference threshold.

[0013] According to some embodiments, further comprising: Calculate the contribution of the distributed energy production and consumption entities to the virtual power plant, and select a corresponding benefit allocation method to calculate the profit share of each distributed energy production and consumption entity.

[0014] According to another aspect of the present invention, a system for optimizing resource allocation of a virtual power plant is provided, comprising: A centralized control center module, through which data of distributed energy production and consumption entities are collected; A master-slave game model module, through which an internal scheduling plan is formed to determine the output and income of each distributed energy production and consumption entity; The real-time monitoring module monitors the operating status of distributed energy production and consumption entities in real time through sensors, intelligent metering equipment and communication networks, and dynamically adjusts the internal scheduling plan according to the operating status to ensure the stability and economy of the system.

[0015] According to another aspect of the present invention, there is provided a computing device, comprising: Processor; and A memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to perform any of the aforementioned methods.

[0016] According to an example embodiment of the present invention, the centralized control center is able to collect data from all distributed energy producers and consumers. Based on the comprehensive data, the centralized control center can make more scientific and accurate scheduling decisions to ensure the optimal allocation of resources. The prediction model can accurately predict the energy demand and supply situation in the future, thereby achieving more accurate resource scheduling. The master-slave game model is used to form an internal scheduling plan, which can effectively coordinate the interests of each distributed energy producer and consumer, achieve the optimal allocation of resources, improve the operating efficiency, reliability and economic benefits of the system, and promote the use of renewable energy and environmental protection. Sensors and intelligent metering equipment can be used to monitor the operating status of each distributed energy producer and consumer in real time, and the internal scheduling plan can be dynamically adjusted according to the operating status, thereby ensuring the stability and economy of the system.

[0017] According to the example embodiments, real-time monitoring and dynamic adjustment enable the virtual power plant to respond quickly to various changes, thereby flexibly adjusting resource allocation. The flexibility ensures that the system can maintain efficient operation under different operating conditions, reducing the operational risks of the virtual power plant caused by market uncertainties; calculating the contribution of the distributed energy production and consumption entities to the virtual power plant, selecting the corresponding benefit allocation method to calculate the profit share of each distributed energy production and consumption entity, and promoting the transparency and fairness of energy transactions.

[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for describing the embodiments are briefly introduced below.

[0020] Figure 1 A flow chart illustrating a method for virtual power plant resource allocation optimization according to an example embodiment.

[0021] Figure 2 A block diagram of system components for optimizing virtual power plant resource allocation according to an example embodiment is shown.

[0022] Figure 3 The working mode of the two-stage two-tier bidding scenario and the game model according to the example embodiment is shown.

[0023] Figure 4 The operation steps of benefit allocation according to an example embodiment are shown.

[0024] Figure 5 A block diagram of a computing device according to an example embodiment of the invention is shown. DETAILED DESCRIPTION

[0025] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that the present invention will be comprehensive and complete and fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0026] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the embodiments of the present invention. However, those skilled in the art will appreciate that the technical solution of the present invention can be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known methods, devices, implementations or operations are not shown or described in detail to avoid blurring various aspects of the present invention.

[0027] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0028] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0029] It should be understood that although the terms first, second, third, etc. may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another component. Therefore, the first component discussed below can be referred to as the second component without departing from the teachings of the present inventive concept. As used herein, the term "and / or" includes any one of the associated listed items and all combinations of one or more.

[0030] The user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in the present invention are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with the relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0031] Those skilled in the art will appreciate that the drawings are merely schematic diagrams of example embodiments, and the modules or processes in the drawings are not necessarily necessary for implementing the present invention, and therefore cannot be used to limit the protection scope of the present invention.

[0032] As an emerging field, the new energy power market is experiencing an increasingly in-depth market participation process of new energy power stations. Given that the power trading system for new energy is not yet perfect, there are significant deficiencies in the comprehensive evaluation of trading capabilities.

[0033] The current market mainly relies on a single-dimensional evaluation standard, that is, either based solely on the transaction results of the power spot market or solely on the final settlement electricity price of the power plant, to determine the profit and loss and performance of the transaction. This single-perspective evaluation method ignores the full range of considerations from medium- and long-term power transaction planning, spot transaction execution to final settlement results and related new energy power plant assessments, which may lead to a misjudgment of the actual trading capabilities.

[0034] In addition, the evaluation process lacks sufficient objectivity. The power market, especially in the field of new energy, is highly volatile and is affected by uncontrollable factors such as the accuracy of weather forecasts, and market conditions often change suddenly. Therefore, when evaluating the power transactions of new energy enterprises, the impact of non-transaction factors must be fully considered, and the interference of these external factors must be eliminated or reduced through scientific methods to ensure that the evaluation of the transaction level can objectively and fairly reflect the authenticity of the transaction process.

[0035] The present invention provides a method for optimizing resource allocation of virtual power plants, which assists new energy enterprises to correctly reflect the situation of power transactions from a professional, scientific and objective perspective by analyzing data from medium- and long-term transactions to spot transactions of target power stations.

[0036] VPP (Virtual Power Plant) is a new energy system that integrates dispersed distributed energy resources through advanced information technology, control technology and communication technology to participate in the electricity market as a whole.

[0037] DER (Distributed Energy Resource) refers to a series of small or medium-sized power generation and energy storage equipment installed at the end of the power system close to the end user. These resources can be directly connected to the distribution network to improve energy efficiency and enhance grid reliability and flexibility.

[0038] Exemplary embodiments of the present invention are described below with reference to the accompanying drawings.

[0039] Figure 1 A flow chart of a method for virtual power plant resource allocation optimization according to an example embodiment is shown.

[0040] According to an example embodiment, by Figure 1 The virtual power plant resource allocation optimization method shown can improve the flexibility and economy of internal and external resource allocation of the virtual power plant.

[0041] See also Figure 1 ,In S101, the data of distributed energy production and consumption entities are collected through a centralized control center.

[0042] According to an example embodiment, data of distributed energy prosumers may be collected through a centralized control center, which is responsible for data collection, processing, and decision-making. For example, the data of distributed energy prosumers collected through a centralized control center may include electricity price data, load demand data, and renewable energy output data, as well as the power generation, power consumption, and energy storage status of the distributed energy prosumers. The centralized control center may collect electricity price data, load demand data, and renewable energy output data over a period of time in the past, and obtain operating parameters of each distributed energy prosumer, such as power generation, power consumption, energy storage status, etc.

[0043] According to some embodiments, after collecting data from distributed energy producers and consumers, the centralized control center also pre-processes the data, for example, cleaning the data to remove outliers and missing values; processing the data in a standardized format to ensure uniform processing of data from different sources; and extracting features from the data, including calculating the load peak, average, and standard deviation.

[0044] In S103, prediction data is created using the prediction model.

[0045] According to the example embodiments, the prediction model can be used to predict load, electricity price and renewable energy output. For example, the load demand is predicted using the time series analysis method, taking into account the influence of weather factors, seasonal changes and user behavior patterns. The time series analysis method can use the autoregressive integrated moving average model (ARIMA) and the long short-term memory neural network (LSTM) to predict future load demand; combine historical electricity price data, use machine learning algorithms to predict electricity prices, and combine market supply and demand conditions to use machine learning algorithms such as random forests and support vector machines to predict electricity prices in future periods; according to meteorological forecast data, such as solar radiation intensity, wind speed, etc., use physical models or data-driven models to predict photovoltaic and wind power generation.

[0046] In S105, an internal scheduling plan is formed using a master-slave game model to determine the output and income of each distributed energy producer and consumer.

[0047] According to an example embodiment, a master-slave game model is used to repeat the following process until a Nash equilibrium is reached or a predetermined convergence condition is met, thereby forming an internal scheduling plan: defining a first objective function of the virtual power plant operator and a second objective function of the distributed energy producer and consumer; setting a first electricity purchase and sales price signal of the virtual power plant operator according to the forecast data, and sending the first electricity purchase and sales price signal to the distributed energy producer and consumer; the distributed energy producer and consumer adjusts their respective power generation or power consumption plans through the second objective function according to the first electricity purchase and sales price signal, and submits the output and quotation information to the virtual power plant operator; after collecting the responses of the distributed energy producer and consumer, the price signal is readjusted to obtain a second electricity purchase and sales price signal, and the second electricity purchase and sales price signal is sent to the distributed energy producer and consumer again.

[0048] In S107, the operating status of the distributed energy production and consumption entities is monitored in real time through sensors, intelligent metering equipment and communication networks, and the internal scheduling plan is dynamically adjusted according to the operating status, so as to ensure the stability and economy of the system.

[0049] According to an example embodiment, the communication network may use high-speed, low-latency communication technology to ensure the timeliness and reliability of data transmission, and may use security protocols such as TLS / SSL to protect privacy and security during data transmission. The communication network may implement two-way communication, allowing the control center to send scheduling instructions to each distributed energy producer and consumer and receive status feedback.

[0050] Each market player can send real-time operating status data, such as power generation, energy storage level, load demand, etc., to the central dispatch center through sensors and communication networks. Virtual power plant operators can monitor the operating status of each distributed energy producer and consumer in real time through sensors and smart metering equipment, and dynamically adjust the dispatch plan according to actual conditions to ensure the stability and economy of the system. Each market player adjusts its own behavior according to the dispatch instructions and promptly feedbacks the execution results so that the central dispatch center can make dynamic adjustments.

[0051] This method builds a highly intelligent energy management system by integrating data acquisition, machine learning prediction, game theory optimization and Internet of Things communication technology, which can not only help virtual power plants effectively manage their resources, but also promote the popularization of renewable energy and the realization of energy conservation and emission reduction goals.

[0052] Figure 2 A block diagram of system components for optimizing virtual power plant resource allocation according to an example embodiment is shown.

[0053] According to an example embodiment, see Figure 2 The system for optimizing resource allocation of virtual power plants includes a centralized control center module, a prediction module, a master-slave game module and a real-time monitoring module, wherein the centralized control center module collects data of distributed energy producers and consumers, the prediction module is used to establish a prediction model to predict data, and predict future load demand, electricity prices and renewable energy output; the master-slave game module is used to set an initial price signal, receive responses from each distributed energy producer and consumer, and re-evaluate and adjust the price signal, and form an internal scheduling plan through the master-slave game module to determine the output and income of each distributed energy producer and consumer; the real-time monitoring module monitors the operating status of the distributed energy producer and consumer in real time through sensors, intelligent metering equipment and communication networks, and dynamically adjusts the internal scheduling plan according to the operating status, thereby ensuring the stability and economy of the system.

[0054] According to an example embodiment, the system for optimizing resource allocation of virtual power plants also includes a data collection module, a data preprocessing module, a market bidding module, a risk management module, a dynamic adjustment module, and a benefit allocation module. The data collection module is used to collect historical electricity prices, load demand data, and renewable energy output data; the data preprocessing module is used to clean, standardize, and extract features from the data; the market bidding module is used for the VPP to participate in the bidding in the electricity market as a whole, and adjust the internal scheduling plan according to market feedback; the risk management module is used to quantify uncertainty factors and adjust the VPP's quotation strategy accordingly; the dynamic adjustment module is used to dynamically adjust the scheduling plan according to actual conditions; the benefit allocation module is used to calculate the revenue share of each distributed energy producer and consumer, and regularly review and adjust the allocation plan.

[0055] The risk management module is used to quantify risks, using probability distribution functions such as normal distribution and Poisson distribution to describe the statistical characteristics of uncertainty factors, and calculating the VPP operating costs or benefits under different scenarios through methods such as Monte Carlo simulation, setting risk thresholds based on risk preferences, and adjusting the VPP quotation strategy accordingly.

[0056] The centralized control center is used to collect and process the data of distributed energy producers and consumers, connect each distributed energy producer and consumer with the control center through a high-speed, low-latency communication network, and ensure the security of data transmission. Use time series analysis methods to predict future load demand, use machine learning algorithms to predict electricity prices in future time periods, and use physical models or data-driven models to predict photovoltaic and wind power generation.

[0057] The present invention proposes a method and system for optimizing resource allocation of virtual power plants, aiming to improve the operational efficiency and economic benefits of VPPs by coordinating the behaviors of different market participants, and optimizing the strategies and behaviors of multiple market entities of virtual power plants (VPPs) through the master-slave game theory. The master-slave game model includes two role definitions: "Leader" and "Followers". The Leader refers to the operator of the virtual power plant, who is responsible for formulating the overall power purchase and sales strategy, and the Followers refer to the distributed energy production and consumption entities, including but not limited to photovoltaic, wind power, energy storage systems, electric vehicle charging stations, etc. The goal of VPP operators is to maximize revenue or minimize costs, while considering the reliability and stability of the system; the goal of distributed energy production and consumption entities is to maximize their own economic interests, such as maximizing profits or minimizing costs.

[0058] Through the master-slave game model, the VPP operator first sets an initial power purchase and sales price signal based on market demand forecasts and internal resource conditions. Each distributed energy producer and consumer adjusts its power generation or consumption plan based on this price signal to maximize its own interests. After collecting responses from all distributed energy producers and consumers, the VPP operator re-evaluates and adjusts the price signal until an equilibrium state is reached.

[0059] Due to changes in market supply and demand, there may be great uncertainty in electricity prices. Users' electricity consumption behavior may change due to factors such as weather and seasons, resulting in changes in load demand. Renewable energy sources such as solar energy and wind energy are greatly affected by natural conditions, resulting in fluctuations in renewable energy output. Taking into account the impact of uncertainty factors, this method performs risk cost modeling, adjusts the internal scheduling plan according to market feedback, uses a risk cost model to adjust the risk of the internal scheduling plan, and uses a probability distribution function to quantify the statistical characteristics of uncertainty factors. The uncertainty factors include electricity price fluctuations, load demand changes, and renewable energy output fluctuations. The operating costs or benefits of virtual power plants under different scenarios are calculated using the Monte Carlo simulation method, and the internal scheduling plan is adjusted according to the set risk preference threshold.

[0060] The present invention establishes a master-slave game model and a risk cost model, and uses mathematical optimization tools such as linear programming, mixed integer programming, etc. to solve the model, thereby obtaining an optimal scheduling plan.

[0061] According to some embodiments, it is assumed that the virtual power plant consists of hybrid resources, including distributed photovoltaic power plants, energy storage power plants and electric vehicle charging stations. The goal is to minimize the total operating cost within a day, ensure the security and reliability of power supply, and use renewable energy as much as possible.

[0062] The input data of the model include electricity price data, load demand, weather forecast data and equipment parameters. The electricity price data is the predicted electricity price per hour, the load demand is the predicted electricity demand per hour, and the light intensity is predicted through the weather forecast data, which affects the photovoltaic power generation; the equipment parameters include the startup cost, operating cost, maximum / minimum output of each power generation unit; the charging and discharging efficiency and maximum capacity of the energy storage system, etc.

[0063] The objective functions of the master-slave game model and the risk cost model are: Minimize total cost = power generation cost + startup cost + power purchase cost - power sales income - renewable energy subsidy; In each hour period, the power balance constraint is: Total power generation + energy storage release - energy storage absorption = total load demand + power sold to the grid; Among them, the operation of power generation units and energy storage must be within their technical parameters to ensure the safe and stable operation of the power grid and avoid overload.

[0064] Dispatching and coordinating are carried out from distributed photovoltaic power stations, energy storage power stations and electric vehicle charging stations respectively. Distributed photovoltaic power stations can arrange the behavior of other market players in advance according to weather forecasts to ensure that photovoltaic panels are used to the maximum extent when there is sufficient sunlight, and work with energy storage systems to store excess photovoltaic power for emergency use. Energy storage power stations can charge during low electricity price periods or when there is excess renewable energy generation, and discharge during peak electricity price periods. For example, during the day, photovoltaic panels are charged when there is excess power generation, and at night, when electricity prices are high, they are discharged. As an emergency backup power source, when the system encounters an emergency (such as a failure of a power generation unit), it is quickly put into operation to maintain stable power supply. Electric vehicle charging stations can delay charging during peak electricity price periods or when the system is under great pressure, and increase power consumption and charge in a centralized manner during low electricity price periods or when the system load is light.

[0065] The coordination mechanism of this embodiment enables VPP to maximize economic benefits, maximize resource utilization efficiency, and achieve system stability, ensuring that the interests of all market players are reasonably protected. Through scheduling plans, VPP can not only effectively reduce operating costs, but also promote the use of renewable energy and improve the flexibility and reliability of the system. In addition, reasonable energy storage charging and discharging strategies and load regulation can also help balance the contradiction between supply and demand and improve overall economic and social benefits.

[0066] Figure 3 The working mode of the two-stage two-tier bidding scenario and the game model according to the example embodiment is shown.

[0067] In the context of virtual power plants, the combination of the "two-stage two-tier bidding mechanism" and the "game model" is to effectively manage and optimize distributed energy resources distributed in different geographical locations, including but not limited to power generation resources, energy storage, load resources, etc.

[0068] According to some embodiments, the first stage of the two-stage two-tier bidding mechanism involves preliminary preparations such as signing long-term contracts and market access assessments. In the first stage, the virtual power plant operator negotiates with other market participants (such as other VPP operators, large power companies, etc.) to determine long-term cooperation intentions; in addition, it also includes estimating and negotiating electricity prices and supply volumes in the future (such as quarters and years). The second stage of the two-stage two-tier bidding mechanism refers to specific power trading activities on a shorter time scale, such as days, hours, or even shorter time intervals. In the second stage, VPP operators will adjust their power generation plans and bidding strategies based on the latest market information, weather forecasts, and other factors, and participate in the competition in the short-term power market to maximize profits.

[0069] The VPP operator sets a preliminary price signal for electricity purchase and sale, and sends the price signal to each distributed energy producer and consumer. Each distributed energy producer and consumer adjusts the power generation or electricity consumption plan according to the price signal, and submits power and quotation information. After collecting the responses of all distributed energy producers and consumers, the VPP operator re-evaluates and adjusts the price signal until the Nash equilibrium is reached or the predetermined convergence conditions are met. VPP participates in the bidding in the electricity market as a whole, submits bids according to market rules, and adjusts internal scheduling plans according to market feedback. It uses probability distribution functions to quantify uncertainty factors, calculates VPP operating costs or benefits under different scenarios through Monte Carlo simulation and other methods, and adjusts VPP's quotation strategy accordingly.

[0070] In the upper pricing model of the two-stage two-tier bidding mechanism, the VPP operator releases preliminary price signals, and each distributed energy producer and consumer submits their own output plan and quotation. The VPP operator optimizes the scheduling based on this information and determines the final output and remuneration of each distributed energy producer and consumer. In the lower management model of the two-stage two-tier bidding mechanism, the VPP participates in the bidding of the power market as a whole, submits bids according to market rules, including total output, price and other relevant parameters, and adjusts the internal scheduling plan according to market feedback to ensure consistency with market requirements.

[0071] The game model is used to simulate and predict the interactive behaviors between different market participants, transmit key information such as transaction price and transaction volume, and help VPP operators formulate more reasonable strategies. In the two-stage two-tier bidding mechanism, the game model can regard the VPP operator as the Leader and other market participants as Followers. The VPP operator first announces its production plan or quotation strategy, and then other participants respond based on this information.

[0072] By establishing a master-slave game model, VPP operators can predict the behavior of competitors and optimize their own strategies. The game model enables information sharing and coordination, helps reduce market uncertainty, and improves the operating efficiency of the entire power system. The theoretical framework and tools provided by the game model can help VPP operators better understand market dynamics and optimize their bidding strategies, so that they can occupy a favorable position in the competition and promote cooperation with other participants.

[0073] In this example embodiment, the two-stage two-tier bidding mechanism provides a temporal and spatial framework, and the game model is a key tool for achieving refined management and strategy optimization within this framework. The combination of the two can effectively improve the operational efficiency and market competitiveness of virtual power plants.

[0074] Figure 4 The operation steps of benefit allocation according to an example embodiment are shown.

[0075] Consider fairness and incentive compatibility, ensure that each distributed energy producer and consumer receives a return that matches its contribution, and encourage distributed energy producers and consumers to actively participate in the operation of VPP and provide real information. Figure 4 .

[0076] According to the example embodiment, first, determine the resources and demand, initialize the allocation and make preliminary allocation arrangements for the resources. The algorithm will allocate resources in ascending order according to the size of the demand. Determine whether there are still unallocated resources and whether the weight needs to be considered. If there are still unallocated resources and the weight factor needs to be considered in the current allocation process, continue to analyze the allocation results. According to the previous analysis results, make necessary adjustments and optimizations to the existing resource allocation plan to obtain better results.

[0077] The specific implementation steps of benefit distribution include calculating the contribution of each distributed energy producer and consumer to the VPP; selecting an appropriate benefit distribution method (such as the Shapley value method, proportional distribution method, marginal contribution method, etc.), and calculating each party’s share of benefits based on the selected distribution method; and regularly reviewing and adjusting the distribution plan to adapt to market and technological changes.

[0078] According to some embodiments, the Shapley value method is based on the concept of Shapley value in cooperative game theory to fairly distribute the total revenue within the alliance. The proportional distribution method distributes the revenue according to the actual contribution ratio of each distributed energy producer and consumer. The marginal contribution method distributes according to the marginal contribution of each distributed energy producer and consumer to the overall benefit of the VPP.

[0079] In the Shapley value method, the revenue share of each participant (distributed energy production and consumption entity) depends on its marginal contribution to the overall cooperation. The specific calculation steps include listing all possible combinations of participants and calculating the total revenue of each combination; for each participant, calculating its marginal contribution in all combinations; calculating the Shapley value of each participant, that is, the average of its marginal contribution in all combinations. The Shapley value method takes into account the real contribution of each participant and has good fairness.

[0080] The proportional distribution method is used to distribute benefits, and the benefits are distributed according to the proportion of each participant in the total output. The proportion of each participant in the total output is calculated, and the total benefits are distributed according to the proportion; the proportional distribution method is simple, easy to understand and implement. However, when some participants have special contributions, it will not be considered comprehensively.

[0081] The marginal contribution method is used to distribute benefits, and the benefits are distributed according to the marginal contribution of each participant to the total benefits. The benefits of each participant when operating alone are calculated, the total benefits when all participants operate together are calculated, and the marginal contribution of each participant is calculated, that is, the total benefits minus the benefits when other participants operate together, and the total benefits are distributed according to the marginal contribution. The marginal contribution method takes into account the real contribution of each participant.

[0082] According to some embodiments, assume that a VPP consists of three distributed energy prosumers (A, B, C) with a total revenue of 100 units. The steps for calculating the revenue share of each prosumer using the Shapley value method are: List all possible combinations: {A}, {B}, {C} {A, B}, {A, C}, {B, C} {A, B, C} Calculate the total payoff for each combination: {A}: 30 {B}: 20 {C}: 10 {A, B}: 50 {A, C}: 40 {B, C}: 30 {A, B, C}: 100 Calculate the marginal contribution of each participant: A's marginal contribution: Add A to {B, C}: 100 - 30 = 70 Add A to {B}: 50 - 20 = 30 Add A to {C}: 40 - 10 = 30 Average contribution margin: (70 + 30 + 30) / 3 = 43.33 B's marginal contribution: Add B to {A, C}: 100 - 40 = 60 Add B to {A}: 50 - 30 = 20 Add B to {C}: 30 - 10 = 20 Average contribution margin: (60 + 20 + 20) / 3 = 33.33 Marginal contribution of C: Add C to {A, B}: 100 - 50 = 50 Add C to {A}: 40 - 30 = 10 Add C to {B}: 30 - 20 = 10 Average contribution margin: (50 + 10 + 10) / 3 = 23.33 Profit distribution: A's profit share: 43.33 B's share of revenue: 33.33 C's share of revenue: 23.33 The benefit distribution using the Shapley value method listed in this embodiment can fairly distribute the total benefits within the alliance.

[0083] Through simulation verification and testing, a simulation environment including multiple distributed energy production and consumption entities is constructed to simulate real power market conditions. Through simulation testing, the effectiveness of the method of the present invention in improving VPP operating efficiency, reducing costs, and enhancing system flexibility is evaluated, and compared with existing methods, the advantages and improvements of the present invention are demonstrated.

[0084] The method of the present invention is gradually deployed and tested in actual VPP projects, operation data is collected, and the system is further optimized and improved. Through the above detailed implementation methods, the present invention can effectively coordinate the behaviors of multiple market players within the VPP.

[0085] The method and system for optimizing resource allocation of virtual power plants proposed in the present invention can help virtual power plants better participate in power market transactions through real-time monitoring, seize opportunities of electricity price fluctuations, increase revenue, reduce operating costs, and improve the flexibility and economy of internal and external resource allocation of virtual power plants; through optimized scheduling, virtual power plants can reduce unnecessary power generation and transmission costs and improve energy utilization efficiency. The system can formulate emergency plans based on real-time data to ensure that stable operation can be quickly restored in the event of an emergency, reduce losses, and reduce the operational risks of virtual power plants caused by market uncertainties.

[0086] The method of the present invention can help virtual power plants to better manage and coordinate newly connected new energy equipment, enhance the virtual power plant's support capacity for new energy access, and maximize the use of renewable energy, reduce dependence on traditional energy, and improve energy sustainability; through scientific scheduling and management strategies, virtual power plants can ensure that the interests of all participating entities are reasonably protected, avoid monopoly and unfair competition, and transparent data and fair mechanisms help to establish a healthy and orderly energy market.

[0087] Figure 5 A block diagram of a computing device according to an example embodiment of the invention is shown.

[0088] like Figure 5As shown, computing device 30 includes processor 12 and memory 14. Computing device 30 may also include bus 22, network interface 16, and I / O interface 18. Processor 12, memory 14, network interface 16, and I / O interface 18 may communicate with each other via bus 22.

[0089] The processor 12 may include one or more general-purpose CPUs (Central Processing Units, processors), microprocessors, or application-specific integrated circuits, etc., for executing relevant program instructions.

[0090] The memory 14 may include a machine system readable medium in the form of a volatile memory, such as a random access memory (RAM), a read-only memory (ROM) and / or a cache memory. The memory 14 is used to store one or more programs including instructions and data. The processor 12 may read the instructions stored in the memory 14 to execute the above-mentioned method according to the embodiment of the present invention.

[0091] The computing device 30 may also communicate with one or more networks via the network interface 16. The network interface 16 may be a wireless network interface.

[0092] The bus 22 may include an address bus, a data bus, a control bus, etc. The bus 22 provides a path for exchanging information between components.

[0093] It should be noted that, in the specific implementation process, the computing device 30 may also include other components necessary for normal operation. In addition, those skilled in the art may understand that the above device may only include components necessary for implementing the embodiments of this specification, and need not include all components shown in the figure.

[0094] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above method when the program is executed by a processor. The computer-readable storage medium may include, but is not limited to, any type of disk, including a floppy disk, an optical disk, a DVD, a CD-ROM, a micro drive, and a magneto-optical disk, a ROM, a RAM, an EPROM, an EEPROM, a DRAM, a VRAM, a flash memory device, a magnetic card or an optical card, a nanosystem (including a molecular memory IC), a network storage device, a cloud storage device, or any type of medium or device suitable for storing instructions and / or data.

[0095] An embodiment of the present invention also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any method recorded in the above method embodiments.

[0096] Those skilled in the art can clearly understand that the technical solution of the present invention can be implemented with the help of software and / or hardware. "Unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array, an integrated circuit, etc.

[0097] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0098] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0099] In the several embodiments provided by the present invention, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0100] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0101] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0102] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention.

[0103] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0104] The exemplary embodiments of the present invention are specifically shown and described above. It should be understood that the present invention is not limited to the detailed structures, configurations or implementations described herein; on the contrary, the present invention is intended to cover various modifications and equivalent configurations included in the spirit and scope of the appended clauses.

[0105] Those skilled in the art can clearly understand that the technical solution of the present invention can be implemented with the help of software and / or hardware. "Unit" and "module" in this specification refer to software and / or hardware that can independently complete or cooperate with other components to complete specific functions, where the hardware can be, for example, a field programmable gate array, an integrated circuit, etc.

[0106] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0107] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0108] In the several embodiments provided by the present invention, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0109] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0110] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0111] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the methods of various embodiments of the present invention.

[0112] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0113] The exemplary embodiments of the present invention are specifically shown and described above. It should be understood that the present invention is not limited to the detailed structures, configurations or implementations described herein; on the contrary, the present invention is intended to cover various modifications and equivalent configurations included in the spirit and scope of the appended clauses.

Claims

1. A method for optimizing resource allocation of a virtual power plant, characterized in that: include: Collect data from distributed energy producers and consumers through a centralized control center; Use predictive models to build predictive data; The master-slave game model is used to form an internal scheduling plan to determine the output and benefits of each distributed energy producer and consumer; The operating status of distributed energy production and consumption entities is monitored in real time through sensors, smart metering equipment and communication networks, and the internal scheduling plan is dynamically adjusted according to the operating status to ensure the stability and economy of the system.

2. The method according to claim 1, characterized in that: The data collected by the centralized control center on distributed energy production and consumption entities include: Collect electricity price data, load demand data, and renewable energy output data; Obtain the power generation, power consumption and energy storage status of the distributed energy production and consumption entity.

3. The method according to claim 1, characterized in that: The data of distributed energy production and consumption entities are collected through the centralized control center, and the data are pre-processed: Clean the data to remove outliers and missing values; Standardize the data format to ensure uniform processing of data from different sources; Perform feature extraction on the data, including calculation of load peak, average value, and standard deviation.

4. The method according to claim 1, characterized in that: The method of using the prediction model to establish prediction data includes: Use time series analysis to forecast load demand; Combined with historical electricity price data, machine learning algorithms are used to predict electricity prices; Based on weather forecast data, use physical models or data-driven models to predict the power generation of photovoltaic and wind energy.

5. The method according to claim 1, characterized in that The forming of the internal scheduling plan by using the master-slave game model includes repeating the following process until a Nash equilibrium is reached or a predetermined convergence condition is satisfied: Define the first objective function of the virtual power plant operator and the second objective function of the distributed energy prosumer; According to the forecast data, setting a first power purchase and sale price signal of the virtual power plant operator, and sending the first power purchase and sale price signal to the distributed energy production and consumption entity; The distributed energy production and consumption entities adjust their respective power generation or power consumption plans through the second objective function according to the first power purchase and sales price signal, and submit the output and quotation information to the virtual power plant operator; After collecting the responses of the distributed energy production and consumption entities, the price signal is readjusted to obtain a second power purchase and sales price signal, and the second power purchase and sales price signal is sent to the distributed energy production and consumption entities again.

6. The method according to claim 1, characterized in that Also includes: Adjust the internal scheduling plan based on market feedback.

7. The method according to claim 1, characterized in that The method further includes risk-adjusting the internal scheduling plan using a risk cost model: quantifying the statistical characteristics of uncertainties using probability distribution functions, including electricity price fluctuations, load demand changes, and renewable energy output fluctuations; The operating costs or benefits of the virtual power plant under different scenarios are calculated through the Monte Carlo simulation method, and the internal scheduling plan is adjusted according to the set risk preference threshold.

8. The method according to claim 1, characterized in that Also includes: Calculate the contribution of the distributed energy production and consumption entities to the virtual power plant, and select a corresponding benefit allocation method to calculate the profit share of each distributed energy production and consumption entity.

9. A system for optimizing resource allocation of a virtual power plant, characterized in that: include: A centralized control center module, through which data of distributed energy production and consumption entities are collected; Prediction module, used to establish prediction model and predict data; A master-slave game module, through which an internal scheduling plan is formed to determine the output and income of each distributed energy production and consumption entity; A real-time monitoring module monitors the operating status of distributed energy production and consumption entities in real time through sensors, intelligent metering equipment and communication networks, and dynamically adjusts the internal scheduling plan according to the operating status to ensure the stability and economy of the system.

10. A computing device, characterized in that: include: processor; as well as A memory storing a computer program, which, when executed by the processor, enables the processor to perform the method according to any one of claims 1 to 8.

Images