Virtual power plant edge control method and system and electronic equipment

Abstract

The invention relates to the technical field of intelligent power grids, and discloses a virtual power plant edge control method and system and electronic equipment, and the virtual power plant edge control method comprises the following steps: S1, collecting state data of at least one distributed energy resource in real time, including power output, energy storage state and battery electric quantity, transmitting the data to an edge computing platform; s2, preprocessing the data through an edge computing platform, scheduling the distributed energy resources in real time by using an optimal scheduling algorithm, and generating a scheduling control instruction; and S3, based on the intelligent prediction model, predicting the power demand and the market price in a period of time in the future, adjusting a scheduling strategy according to a prediction result, and optimizing resource configuration. Through innovative application of edge calculation and an intelligent scheduling technology, the response speed, the economic benefit and the sustainability of the virtual power plant are greatly improved while stable power supply is ensured, and technical support is provided for construction of an intelligent power grid and a green power system.

Description

Technical Field

[0001] The present invention relates to the field of smart grid technology, and specifically to a virtual power plant edge control method, system and electronic equipment. Background Art

[0002] At present, with the widespread application of renewable energy, the complexity and uncertainty of the power system have increased significantly, and the traditional power system faces huge challenges in resource scheduling, market transactions, and provision of ancillary services. The introduction of smart grid technology, especially the concept of virtual power plant (VPP), aims to improve the flexibility and efficiency of the power system by aggregating distributed energy resources (DERs).

[0003] Existing virtual power plant control technology mainly relies on centralized scheduling strategies. Although this strategy can optimize resource scheduling to a certain extent, it has limitations in response speed, cost-effectiveness and flexibility.

[0004] Centralized dispatching strategies are difficult to adjust in real time to cope with rapidly changing electricity demand and market price fluctuations, resulting in low resource utilization, limited market returns, and inability to effectively participate in demand response projects and provide high-quality ancillary services, which in turn affects the economic benefits and social value of virtual power plants. Summary of the invention

[0005] In view of the shortcomings of the existing technology, the present invention provides a virtual power plant edge control method, system and electronic equipment to solve the problem that the existing virtual power plant control technology is limited by the centralized scheduling strategy, resulting in insufficient resource scheduling flexibility and difficulty in real-time response to electricity demand and market price fluctuations, thereby affecting market revenue and resource utilization.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A virtual power plant edge control method comprises the following steps: S1. Collect status data of at least one distributed energy resource in real time, including power output, energy storage status, and battery power, and transmit the data to the edge computing platform; S2. Preprocess the data through the edge computing platform, and use the optimized scheduling algorithm to schedule the distributed energy resources in real time and generate scheduling control instructions; S3. Based on the intelligent prediction model, predict the power demand and market price in the future, and adjust the dispatch strategy according to the prediction results to optimize resource allocation; S4. According to the dispatch control instructions and prediction results, adjust the operating status of distributed energy resources, optimize power output or energy storage charging and discharging operations, so as to achieve a balance between power supply and demand; S5. Communicate with the power operator through the demand response interface, respond to demand response instructions in real time, and adjust resource output to meet the regulation needs of the power grid; S6. Provide auxiliary services by monitoring the frequency and voltage information of the power grid, dynamically adjusting resource output, and supporting the stable operation of the power grid; Specifically, real-time data collection and processing can realize the intelligent dispatch of distributed energy resources in virtual power plants. Through the low-latency data processing of the edge computing platform, it can respond to fluctuations in power demand and market prices in real time to ensure the power balance and stable operation of the power grid. Through the intelligent prediction model, future demand and electricity prices can be predicted in advance, resource allocation can be optimized, market benefits can be increased, and demand response and auxiliary services can be provided to enhance the regulation capacity of the power grid.

[0007] Preferably, the optimization scheduling algorithm includes at least one of linear programming, dynamic programming or heuristic algorithm; Specifically, the optimization scheduling algorithm is the core part of the virtual power plant control. By using linear programming, dynamic programming or heuristic algorithms, it ensures that distributed energy resources are optimally scheduled according to factors such as power market demand, the status of energy storage equipment and grid load. The algorithm can efficiently handle multiple resources and constraints, improve resource utilization and the economic benefits of the system, ensure the balance of power supply and demand and reduce energy waste.

[0008] Preferably, the intelligent prediction model is at least one of a regression analysis, a neural network or a time series analysis model based on machine learning; Specifically, the intelligent prediction model is trained through machine learning algorithms to accurately predict future electricity demand and market price fluctuations and provide precise scheduling predictions. Using regression analysis, neural networks or time series analysis models, the system can identify trends in advance and adjust scheduling strategies, thereby optimizing resource allocation and improving the competitiveness and profitability of virtual power plants in the market.

[0009] Preferably, the distributed energy resources are at least one of solar energy, wind energy, battery energy storage or load equipment; specifically, by scheduling these distributed resources, the virtual power plant can reasonably allocate power generation and energy storage resources according to changes in electricity demand and market prices, thereby achieving efficient use of energy, reducing dependence on fossil energy, and helping the power grid balance the load and reduce carbon emissions.

[0010] A virtual power plant edge control system, comprising: a data collection module for collecting real-time data from at least one distributed energy resource and a power market; An edge computing platform is used to receive the data in real time, and to process, analyze and make decisions based on the preset optimization scheduling algorithm and intelligent prediction model to generate scheduling control instructions; An optimization scheduling module, used to adjust the operating state of distributed energy resources according to the data and prediction results, and optimize power output or energy storage charging and discharging operations; A control execution module, used to adjust the power output, energy storage state or other operations of the distributed energy resources according to the dispatch control instructions; Demand response and ancillary services module, which is used to establish communication links with power operators or government departments, respond to demand response instructions in real time and provide grid stability support; Specifically, by integrating multiple modules such as data collection, edge computing, optimized scheduling, control execution and demand response, the virtual power plant can be dispatched in real time when power demand and power market changes. Through the low-latency data processing and intelligent prediction of the edge computing platform, the system can quickly respond to grid load fluctuations and achieve optimal resource allocation, while providing necessary auxiliary services to maintain stable operation of the grid.

[0011] Preferably, the edge computing platform is a computing device deployed at the edge node of the power network for low-latency, high-performance data processing; Specifically, through the powerful computing power of the edge computing platform, the system can quickly make scheduling decisions when electricity demand and market prices fluctuate, ensuring the efficient operation of the virtual power plant.

[0012] Preferably, the optimization scheduling module uses at least one of linear programming, dynamic programming or heuristic algorithm to schedule distributed energy resources; Specifically, by using linear programming, dynamic programming or heuristic algorithms, the optimal dispatching scheme under multiple constraints can be flexibly calculated. These algorithms can efficiently handle complex constraints such as power demand, output of distributed energy, capacity of energy storage equipment, etc., to ensure the optimal allocation of virtual power plant resources in the market, both to meet power demand and to improve the economic benefits of the system.

[0013] Preferably, the intelligent prediction module trains a machine learning model based on historical data and real-time data to predict future electricity demand and market prices; Specifically, by using machine learning algorithms and training prediction models based on historical data and real-time data, it is possible to predict future trends in electricity demand and market prices, so as to respond to changes in the electricity market in advance and maximize the economic benefits of virtual power plants by intelligently adjusting distributed energy output.

[0014] An electronic device, comprising: A data collection unit, used to collect status data of distributed energy resources; Edge computing unit, used to perform data preprocessing, scheduling optimization and control decision-making; A control execution unit is used to execute the dispatch control instructions generated by the edge computing platform and adjust the operating status of distributed energy resources; A communication module for communicating with power operators or power market systems to respond to demand response instructions; Specifically, through this equipment, the system can perform real-time data collection, scheduling optimization, control instruction execution and demand response functions, enhancing the adaptability of the virtual power plant to power market and grid load fluctuations.

[0015] Preferably, the electronic device further comprises a sensor module for real-time monitoring of grid frequency and voltage, supporting auxiliary service functions; Specifically, through real-time monitoring of the power grid status, the system can dynamically adjust the output of the virtual power plant, participate in auxiliary services such as frequency regulation and load balancing of the power grid, and ensure the stable operation of the power grid.

[0016] The present invention provides a virtual power plant edge control method, system and electronic equipment, which have the following beneficial effects: 1. The present invention moves data processing and decision-making to the edge nodes of the power grid through the edge computing platform, significantly reducing the delay of data transmission. This design ensures that the virtual power plant can quickly respond to changes in power demand, market price fluctuations, and power grid load fluctuations, thereby improving the real-time and flexibility of power dispatch. Through the deployment of edge computing, the system can make decisions and implement control within milliseconds, avoiding the time delay caused by traditional centralized dispatching, and greatly improving the system's emergency response capabilities.

[0017] 2. The present invention effectively improves the stability of the power grid by introducing demand response and auxiliary service functions. By real-time monitoring of important indicators such as power grid frequency and voltage, the system can dynamically adjust the distributed energy resources in the virtual power plant according to fluctuations in power demand and market prices. Especially when power demand surges or the power grid becomes unstable, the system can automatically provide auxiliary services such as frequency modulation and peak load regulation to ensure load regulation and frequency stability of the power grid, thereby improving the reliability of the power system.

[0018] 3. The present invention uses intelligent prediction models and optimized scheduling algorithms to accurately predict electricity demand and market price fluctuations, thereby optimizing resource scheduling. When electricity prices are low, the system can adjust the charging of energy storage devices. When electricity prices are high, the electricity in the energy storage devices is released to the market to obtain higher returns. Through this flexible scheduling strategy, the utilization efficiency of distributed energy resources can be maximized, the market competitiveness of virtual power plants can be improved, market revenue can be increased, and operating costs can be reduced.

[0019] 4. The present invention can efficiently integrate renewable energy such as wind energy and solar energy, and optimize their use in the power grid. Through real-time prediction and scheduling, the system prioritizes the scheduling of renewable energy and reduces dependence on high-carbon emission energy such as traditional coal-fired power plants. Through the intelligent prediction module, the system can predict factors such as wind energy and light intensity in advance to ensure that the virtual power plant can quickly adjust the output of energy storage and other energy resources when energy output fluctuates greatly, support the efficient use of renewable energy, and promote the development of green and low-carbon electricity. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a schematic diagram of the coordinated dispatching of electric power according to the present invention; Figure 2 It is a schematic diagram of the steps of the edge control method of the virtual power plant in the present invention; Figure 3 It is a schematic diagram of the framework of the virtual power plant edge control system in the present invention. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the specification of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0022] Embodiment 1: Please refer to the attached Figure 1 and attached Figure 3 , an embodiment of the present invention provides a virtual power plant edge control system: The virtual power plant edge control system of the present invention adopts a highly integrated modular design and includes the following key modules: 1. Data acquisition and transmission module The data acquisition and transmission module is responsible for acquiring various data from distributed energy equipment and the power market in real time. The data sources include: Distributed energy data: power output, charging status, energy storage capacity, etc. of solar energy, wind energy, and energy storage equipment.

[0023] Electricity market data: electricity demand, market electricity prices, grid load, electricity price fluctuation trends, etc.

[0024] Meteorological data: Environmental parameters such as temperature, wind speed, and light intensity, which have a significant impact on the power generation of renewable energy sources (such as wind power and solar power).

[0025] The module collects data in real time through smart meters, sensors and other devices, and transmits the data to the edge computing platform through wireless communication technologies (such as 4G / 5G, LoRa, Wi-Fi, etc.). Data transmission needs to ensure low latency and high bandwidth to ensure the real-time performance of the system.

[0026] 2. Edge Computing Platform The edge computing platform is located at the edge node of the power grid and has strong computing power. It can quickly process large amounts of real-time data and generate scheduling decisions. The edge computing platform has the following functions: Data preprocessing and analysis: Receive and process data in real time, perform denoising, outlier detection and standardization to ensure data quality.

[0027] Optimize scheduling and control decisions: Based on the optimization scheduling algorithm, the edge computing platform generates control instructions based on real-time data, market prices, resource constraints, etc. to optimize resource scheduling.

[0028] Intelligent prediction: Through the integrated intelligent prediction model, future electricity demand and market electricity prices are predicted, providing predictions for resource scheduling and planning scheduling strategies in advance.

[0029] 3. Optimize the scheduling module The optimization scheduling module is the core part of the system, which uses the following algorithms to achieve intelligent scheduling of distributed energy resources: Objective function: Optimization objectives usually include maximizing market revenue, minimizing carbon emissions, minimizing operating costs, etc.

[0030] Scheduling algorithm: Optimization methods such as linear programming (LP), dynamic programming (DP), genetic algorithm (GA) or particle swarm optimization (PSO) are used to calculate the optimal scheduling strategy by considering the availability of various resources, power demand, market electricity prices and constraints (such as generator power range, energy storage charging and discharging restrictions, etc.).

[0031] 4. Intelligent prediction module The intelligent prediction module predicts future electricity demand and market electricity price fluctuations through the following steps: Data collection and preprocessing: Extract power demand, electricity prices, meteorological data, etc. from historical data, and perform data cleaning and feature extraction.

[0032] Model selection and training: Use machine learning methods such as regression analysis, neural network (NN), support vector machine (SVM), etc. to train prediction models for power demand and market electricity prices.

[0033] Model evaluation and optimization: The prediction accuracy of the model is evaluated through indicators such as mean square error (MSE) and root mean square error (RMSE), and the model parameters are optimized.

[0034] 5. Control Execution Module The control execution module executes control instructions based on the optimized scheduling results, adjusts the power output of distributed energy resources and the charging and discharging status of energy storage devices, ensures power balance of the power grid, and optimizes resource utilization. Specific execution methods include: Power output control: Adjust the power output of distributed energy such as photovoltaic and wind power through devices such as inverters and generator control units.

[0035] Energy storage regulation: Through the energy storage device control unit, the charging and discharging operations of the energy storage device are adjusted to ensure the optimal utilization of the energy storage capacity.

[0036] 6. Demand Response and Ancillary Services Module The demand response and ancillary services module provides two major functions: Demand response: Establish a communication link with power operators or government departments, receive demand response instructions in real time, and adjust the resource output of the virtual power plant according to the instructions.

[0037] Auxiliary services: Provide frequency regulation, peak regulation, emergency standby and other auxiliary services to ensure grid stability. This module responds to grid regulation needs in real time by monitoring grid frequency, power and other information.

[0038] Embodiment 2: Please refer to the attached Figure 1 and attached Figure 2 As part of this application, the present invention also provides a virtual power plant edge control method, including: 1. Data Collection and Processing Data collection: Various types of data are collected in real time through smart meters, sensors and other equipment, including the power output and storage status of photovoltaic power generation, wind power generation, and energy storage equipment, as well as electricity prices, load demand and other information in the power market.

[0039] Data preprocessing: The collected data is subjected to denoising, outlier detection and missing value filling to ensure data integrity and consistency. After data standardization, it is transmitted to the edge computing platform.

[0040] 2. Resource Scheduling and Optimization Objective function setting: Set the objective function of the dispatch (such as maximizing market revenue, ensuring grid stability, minimizing carbon emissions, etc.).

[0041] Assuming that the dispatching goal is to maximize market revenue and taking into account carbon emission constraints, the objective function can be set as: Where, pi(t) represents the power output of the ith distributed energy source, pmarket (t) is the market electricity price, C i (t) is the carbon emission of the ith distributed energy source, and λ is the weight coefficient of carbon emission.

[0042] Constraint setting: Power output constraint: The power output of each distributed energy source must be between its maximum power and minimum power: Energy storage state constraints: The charge state of the energy storage device must comply with the physical limitations of the device: SOC min ≤SOC i (t)≤SOC max Among them, SOC i (t) is the charging state of the i-th energy storage device, SOC min and SOC max They are the minimum and maximum energy storage states of the device respectively.

[0043] Optimization solution: Use linear programming (LP), dynamic programming (DP) or heuristic algorithms (such as genetic algorithms) to solve and obtain the optimal scheduling plan for each time period.

[0044] 3. Intelligent prediction and scheduling adjustment Smart Prediction: Through the intelligent prediction module, we can predict future electricity demand, market prices and other factors. We use machine learning methods such as regression analysis and neural networks to predict electricity demand and market electricity prices.

[0045] Scheduling adjustments: According to the forecast results, adjust the existing dispatch strategy. The forecast results are the future power demand D pred (t+1) and market electricity price (P pre d(t+1): D pred (t+1)=f model (X(t+1), T(t+1)) P pred (t+1)=g model (X(t+1), T(t+1) The power generation capacity of each distributed energy source is dynamically adjusted according to these predicted values ​​to ensure maximum market benefits and grid stability.

[0046] 4. Executive Control and Feedback Execution Control: Execute dispatching control instructions, and adjust the power output of each distributed energy device and the charging and discharging status of the energy storage device through the inverter, energy storage device control unit, etc.

[0047] Feedback Mechanism: Real-time monitoring of grid load, power generation and other information, and adjustment of dispatch strategies based on feedback. For example, when the grid load is too high, the dispatch system will automatically increase the discharge of energy storage equipment to provide backup power and avoid grid overload.

[0048] V. Demand Response and Ancillary Services Demand Response: According to demand response instructions from the electricity market or grid operators, the output of the virtual power plant is adjusted to respond to grid load fluctuations.

[0049] Auxiliary services: Provide frequency regulation, peak regulation and other services to ensure the stability of grid frequency and meet the ancillary service needs of the power market.

[0050] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A virtual power plant edge control method, characterized in that: The following steps are involved: S1. Collect status data of at least one distributed energy resource in real time, including power output, energy storage status, and battery power, and transmit the data to the edge computing platform; S2. Preprocess the data through the edge computing platform, and use the optimized scheduling algorithm to schedule the distributed energy resources in real time and generate scheduling control instructions; S3. Based on the intelligent prediction model, predict the power demand and market price in the future, and adjust the dispatch strategy according to the prediction results to optimize resource allocation; S4. According to the dispatch control instructions and prediction results, adjust the operating status of distributed energy resources, optimize power output or energy storage charging and discharging operations, so as to achieve a balance between power supply and demand; S5. Communicate with the power operator through the demand response interface, respond to demand response instructions in real time, and adjust resource output to meet the regulation needs of the power grid; S6. Provide auxiliary services by monitoring the frequency and voltage information of the power grid, dynamically adjusting resource output, and supporting the stable operation of the power grid.

2. The virtual power plant edge control method, system and electronic device according to claim 1, characterized in that: The optimization scheduling algorithm includes at least one of linear programming, dynamic programming or heuristic algorithm.

3. The virtual power plant edge control method according to claim 1, characterized in that: The intelligent prediction model is at least one of a regression analysis, a neural network or a time series analysis model based on machine learning.

4. The virtual power plant edge control method according to claim 1, characterized in that: The distributed energy resource is at least one of solar energy, wind energy, battery energy storage or load equipment.

5. A virtual power plant edge control system, characterized in that: The virtual power plant edge control method according to any one of claims 1 to 4 comprises: a data collection module for collecting real-time data from at least one distributed energy resource and a power market; An edge computing platform is used to receive the data in real time, and to process, analyze and make decisions based on the preset optimization scheduling algorithm and intelligent prediction model to generate scheduling control instructions; An optimization scheduling module, used to adjust the operating state of distributed energy resources according to the data and prediction results, and optimize power output or energy storage charging and discharging operations; A control execution module, used to adjust the power output, energy storage state or other operations of the distributed energy resources according to the dispatch control instructions; The demand response and ancillary service module is used to establish a communication link with power operators or government departments, respond to demand response instructions in real time and provide grid stability support.

6. The virtual power plant edge control system according to claim 5, characterized in that: The edge computing platform is a computing device deployed at the edge nodes of the power network, used for low-latency, high-performance data processing.

7. The virtual power plant edge control system according to claim 5, characterized in that: The optimization scheduling module uses at least one of linear programming, dynamic programming or heuristic algorithm to schedule distributed energy resources.

8. The virtual power plant edge control system according to claim 5, characterized in that: The intelligent prediction module trains a machine learning model based on historical data and real-time data to predict future electricity demand and market prices.

9. An electronic device, characterized in that: Using the method or system according to any one of claims 1 to 8, comprising: A data collection unit, used to collect status data of distributed energy resources; Edge computing unit, used to perform data preprocessing, scheduling optimization and control decision-making; A control execution unit is used to execute the dispatch control instructions generated by the edge computing platform and adjust the operating status of distributed energy resources; A communication module is used to communicate with the power operator or the power market system to respond to demand response instructions.

10. An electronic device according to claim 9, characterized in that: It further includes sensor modules for real-time monitoring of grid frequency and voltage, supporting ancillary service functions.

Images