An energy system external characteristic representation method and system based on virtual power plant technology
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- DONGYING POWER SUPPLY COMPANY STATE GRID SHANDONG ELECTRIC POWER
- Filing Date
- 2026-02-10
- Publication Date
- 2026-06-09
Smart Images
Figure CN122174148A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of power system and energy management technology, and in particular relates to a method and system for characterizing the external characteristics of an energy system based on virtual power plant technology. Background Technology
[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.
[0003] With the deepening of energy transition, industrial parks, as important units of energy consumption, are seeing an increasing proportion of distributed energy within them. Virtual power plant technology is a key means of aggregating dispersed resources within industrial parks to participate in grid interaction and improve system flexibility. However, the diverse types and characteristics of resources within industrial parks, coupled with the dynamic coupling of multiple complex factors such as market prices, weather, and production plans, result in the aggregated entity—the virtual power plant within the industrial park—exhibiting discrete, time-varying, and non-standard external characteristics. Traditional modeling methods for individual resources are difficult to directly describe the overall behavior of such aggregates.
[0004] Currently, research on the external characteristics of virtual power plants largely focuses on theoretical modeling or aggregation of single-type resources, lacking a standardized characterization system that considers the complex application scenarios of real industrial parks and the coupling effects of multiple factors. This leads to two core problems: First, grid dispatching agencies or the electricity market struggle to accurately and quickly grasp the actual regulation capabilities of virtual power plants in specific industrial parks, such as maximum adjustable power, ramp rate, and response time, affecting the scientific validity and security of dispatching instructions. Second, industrial park operators themselves are unable to standardize the "packaging" and credible "reporting" of their tradable or available regulation services, hindering their efficient participation in the electricity market and the attainment of reasonable profits. Summary of the Invention
[0005] To overcome the shortcomings of existing technologies, this invention proposes a method and system for characterizing the external characteristics of energy systems based on virtual power plant technology. This method comprehensively and quantitatively analyzes the impact of multiple factors, including market environment and resource spatiotemporal characteristics, on the overall external behavior of industrial parks through a scientific, systematic, and operable characterization approach based on virtual power plant technology. It outputs a standardized set of external characteristic parameters, clearly depicting the capability boundaries and dynamic characteristics of the interaction between the virtual power plant and the power grid within the industrial park. This invention provides a systematic and standardized method for characterizing the external characteristics of virtual power plants in industrial parks, laying the foundation for subsequent reliable regulation, accurate assessment, and market transactions. It is applicable to the unified and standardized mathematical description and quantitative modeling of the overall external operating characteristics of integrated energy systems in industrial parks and commercial parks that incorporate various heterogeneous resources such as distributed photovoltaics, energy storage, adjustable loads, and electric vehicle charging stations.
[0006] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions: In a first aspect, the present invention discloses a method for characterizing the external characteristics of an energy system based on virtual power plant technology, comprising: Based on historical and real-time data of the electricity market where the industrial park is located and the operational data of the resource entities within the industrial park, a data-driven model is constructed to quantify the impact of the electricity market environment on the overall resource interaction willingness of the industrial park and output the expected response characteristics under the market scenario. Historical and real-time operation data and geographic information of distributed power sources, energy storage, and loads within the industrial park are collected. Time series analysis and spatial data analysis methods are used respectively to extract the temporal variation patterns and spatial distribution characteristics of the resources. By integrating the expected response characteristics, the temporal variation patterns and spatial distribution characteristics of resources, a spatiotemporal coupled characterization model of the external characteristics of the virtual power plant in the industrial park is constructed to predict the power boundary and dynamic parameters of the industrial park aggregate. For a preset power grid interaction scenario, feature selection is performed on the power boundary and dynamic parameters, and standardized core external characteristic parameters are calculated. These parameters are then encapsulated and output in a structured format to form a standardized capability description of the virtual power plant in the industrial park.
[0007] Secondly, this invention discloses an energy system external characteristic characterization system based on virtual power plant technology, comprising: The data-driven module is used to build a data-driven model based on historical and real-time data of the electricity market where the industrial park is located and the operational data of the resource entities within the industrial park. This model quantifies the impact of the electricity market environment on the overall resource interaction willingness of the industrial park and outputs the expected response characteristics under the market scenario. The feature extraction module is used to collect historical and real-time operation data and geographic information of distributed power sources, energy storage, and loads in the industrial park. It uses time series analysis and spatial data analysis methods to extract the temporal variation patterns and spatial distribution characteristics of the resources. The coupling prediction module is used to integrate the expected response characteristics, the temporal variation law and spatial distribution characteristics of resources to construct a spatiotemporal coupling characterization model of the external characteristics of the virtual power plant in the industrial park, and to predict the power boundary and dynamic parameters of the industrial park aggregate. The feature description module is used to select features from the power boundary and dynamic parameters for a preset power grid interaction scenario, calculate standardized core external characteristic parameters, and encapsulate and output them in a structured format to form a standardized capability description of the virtual power plant in the industrial park.
[0008] Thirdly, the present invention discloses an electronic device, including a memory and a processor, and computer instructions stored in the memory and running on the processor, wherein the computer instructions, when run by the processor, complete the steps of the above-mentioned energy system external characteristic characterization method based on virtual power plant technology.
[0009] Fourthly, the present invention discloses a computer-readable storage medium for storing computer instructions, which, when executed by a processor, complete the steps of the above-described method for characterizing the external characteristics of an energy system based on virtual power plant technology.
[0010] Compared with the prior art, the beneficial effects of the present invention are as follows: (1) Systematic: From the two dimensions of market-driven and physical characteristics, the complex factors affecting the external characteristics of virtual power plants in industrial parks are systematically analyzed, avoiding the one-sidedness of a single perspective.
[0011] (2) Accuracy: The advanced spatiotemporal coupling model dynamically depicts the aggregation characteristics. Compared with static or simple superposition models, it can more accurately reflect the overall time-varying behavior and spatial coupling effect of the industrial park.
[0012] (3) Standardization: The core parameter system of output standardization makes the capabilities of virtual power plants in different industrial parks comparable, and provides key input for the power grid dispatch to formulate unified interface standards and market design of standardized trading varieties.
[0013] (4) Practicality: The generated external characteristic "digital profile" can directly serve multiple business processes of virtual power plants in industrial parks, such as capacity assessment, market bidding, scheduling plan formulation, and post-operation effect evaluation, forming a complete application chain. The advantages of additional aspects of this invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description
[0014] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.
[0015] Figure 1 This is a flowchart of the energy system external characteristic characterization method based on virtual power plant technology described in Embodiment 1 of the present invention. Detailed Implementation
[0016] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.
[0017] It should be noted that the terminology used herein is for the purpose of describing particular implementations only and is not intended to limit the exemplary implementations of the present invention.
[0018] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.
[0019] Example 1 In one or more embodiments, a method for characterizing the external characteristics of an energy system based on virtual power plant technology is disclosed, such as... Figure 1 As shown, it includes the following steps: Step S1: Based on historical and real-time data of the electricity market where the industrial park is located and the operational data of the resource entities within the industrial park, construct a data-driven model to quantify the impact of the electricity market environment on the overall resource interaction willingness of the industrial park and output the expected response characteristics under the market scenario.
[0020] The data-driven model is a kernel extreme learning machine-Gaussian process regression model. The input features of the data-driven model include at least the electricity market price, ancillary service price, demand response subsidy amount, resource self-regulation cost, and operational constraints.
[0021] Specifically, historical and real-time data on the electricity spot market, medium- and long-term market, and ancillary services market in the target industrial park area are collected, including internal factors, trading rule factors, and entry condition factors. This data is used to investigate the production processes, energy consumption habits, and cost structures of various resource entities within the industrial park. Internal factors include transaction costs, price fluctuations, transaction revenue, and operational factors; trading rule factors include trading models, trading products, trading processes, and pricing mechanisms; and entry condition factors include resource scale, regulation capacity, response time, and ramp-up rate.
[0022] Then, the factors influencing willingness are quantitatively analyzed to obtain the correlation between market price signals, subsidy amounts, production constraints, and resource response behavior. Behavioral economics and game theory are used to quantify the relationship between information asymmetry factors and interaction willingness. Risk matrix and sensitivity analysis are applied to transaction rule factors to obtain the relationship between coping strategy factors and interaction willingness. Cost-benefit analysis is used to obtain the relationship between cost-benefit factors and interaction willingness. These relationships should be understood as functions where each factor is an independent variable and interaction willingness is a dependent variable. A data-driven model based on Kernel Extreme Learning Machine-Gaussian Process Regression (KELM-GPR) is used to quantify the comprehensive interaction willingness probability or expected response capacity of resources such as adjustable load and energy storage systems within the industrial park under different market scenarios, forming a mapping model from the market environment to the overall response tendency of the industrial park.
[0023] Preferably, the input features of the KELM-GPR model include electricity market prices, ancillary service prices, demand response subsidy amounts, resource self-regulation costs, and operational constraints.
[0024] Step S2: Collect historical and real-time operation data and geographic information of distributed power sources, energy storage, and loads within the industrial park. Use time series analysis and spatial data analysis methods to extract the temporal variation patterns and spatial distribution characteristics of the resources.
[0025] First, acquire historical and real-time operational data of all distributed photovoltaic, wind turbine, energy storage, adjustable load, and electric vehicle charging piles within the industrial park, as well as meteorological data, geographic information data, and the industrial park's power grid topology.
[0026] Secondly, time series analysis methods, including Long Short-Term Memory Network (LSTM) and time series decomposition, are used to extract the time series variation patterns of resources, including the time series variation patterns, fluctuation characteristics and periodic features of the output and load of various resources.
[0027] Preferably, a Long Short-Term Memory (LSTM) network is used to extract time-series dependent features, and wavelet packet transform is used for time-frequency analysis to distinguish fluctuation components at different time scales. In this embodiment, when extracting time-series features, wavelet packet transform is used to analyze the frequency domain characteristics of load and renewable energy output to distinguish their fast-changing and slow-changing components, providing a basis for characterizing external characteristics at different time scales.
[0028] Finally, spatial data analysis methods are employed, including density-based spatial clustering (DBSCAN) algorithm to obtain the variation patterns of power generation or load of various resources, and weighted regression of the clustered results according to geographic data (geographic coordinates) to analyze the spatial distribution characteristics of resources and identify resource clustering areas, including the clustering and dispersion of resources in the geographic space of industrial parks and their correlation with power grid nodes. The weights of the weighted regression can be assigned according to the operational characteristics of geographic data. As one implementation method, the weights are determined based on the frequency of use of the location; the more frequently a region is used, the greater its weight, and vice versa.
[0029] Step S3: Integrate the expected response characteristics, the temporal variation patterns and spatial distribution characteristics of resources to construct a spatiotemporal coupled characterization model of the external characteristics of the virtual power plant in the industrial park, and predict the power boundary and dynamic parameters of the industrial park aggregate.
[0030] Specifically, the expected response features obtained in step S1 are integrated with the resource temporal variation patterns and spatial distribution features extracted in step S2, serving as edges, nodes, and features of the spatiotemporal graph model. This spatiotemporal graph model is then used to construct a dynamic representation model of the external characteristics of the virtual power plant in the industrial park. This model can predict the power boundary and dynamic parameters of the industrial park aggregate based on the input future scenario. The dynamic representation model employs a spatiotemporal coupling model, which can include a Transformer mechanism model and a coupling model. The coupling model includes Euclidean distance time delay evaluation and Copula joint distribution calculation of the data processed by the Transformer mechanism model, before inputting it into the spatiotemporal graph convolutional network.
[0031] Among them, the spatiotemporal graph model preferably adopts the spatiotemporal graph convolutional network (ST-GCN), which abstracts the topology of the power grid in the industrial park into a graph structure. Nodes represent resource access points or key buses, and edges represent electrical connections. The feature vectors of nodes contain resource types, real-time status, and market influence factors, namely the aforementioned fused expected response features, temporal and spatial features. Spatial correlations are captured through graph convolution, and temporal evolution is captured through temporal convolution, thereby outputting the predicted values of aggregated power boundaries, adjustable potential range, and key dynamic characteristic parameters of the virtual power plant in the industrial park at any future time in an integrated manner.
[0032] In this embodiment, the spatiotemporal coupling model can output differentiated external characteristic parameter sets of the virtual power plant in the industrial park under different preset scenarios, such as "normal operating conditions", "extreme weather", and "market incentives".
[0033] Step S4: For the preset power grid interaction scenario, feature selection is performed on the power boundary and dynamic parameters, and standardized core external characteristic parameters are calculated. These parameters are then encapsulated and output in a structured format to form a standardized capability description of the virtual power plant in the industrial park.
[0034] For typical power grid interaction scenarios such as peak shaving, frequency regulation, and reserve, the spatiotemporal coupling representation model from step S3 is compared with the actual operating data. The model with the highest fit is selected, and a set of standardized external characteristic core parameters are calculated. The standardized core external characteristic parameters include at least: reliable regulating capacity, maximum ramp rate, average response delay time, steady-state regulation accuracy, continuous regulation time, and spatiotemporal adjustable domain. The above parameters, their confidence intervals, applicable time scales (annual, day-ahead, real-time), and boundary conditions are encapsulated and output in a structured data format to form a standardized capability description of the virtual power plant in the industrial park, including capability tags or digital profiles.
[0035] Preferably, the spatiotemporal adjustable domain parameters are geometrically represented by projecting a high-dimensional feasible domain onto the active-reactive power plane, which intuitively demonstrates the safe operating area of the virtual power plant in the industrial park under all internal constraints.
[0036] In summary, this embodiment analyzes and models the impact of the market environment on the willingness of industrial parks to interact with resources; extracts the spatiotemporal distribution characteristics of distributed photovoltaic, energy storage, and load resources within the industrial park; integrates market and spatiotemporal characteristics, and constructs a dynamic representation model of the external characteristics of virtual power plants in industrial parks using spatiotemporal graph convolutional networks; based on the model output, it generates and outputs an external characteristic system containing standardized parameters such as reliable capacity, ramp rate, and response time. This invention solves the problem of non-standardized and inaccurate external characteristic representation of virtual power plants in industrial parks due to the diversity of resources and complexity of factors, and provides a systematic method from factor analysis and feature extraction to model construction and parameter generation, providing key foundational technical support for the precise scheduling, market trading, and reliable assessment of virtual power plants in industrial parks.
[0037] Furthermore, taking a certain equipment manufacturing industrial park as an example, the present invention will be described in further detail. The industrial park includes a 20MW distributed photovoltaic system, a 5MW / 10MWh energy storage system, several adjustable precision machining loads, and a public electric vehicle charging station.
[0038] Step S1: Collect the province's electricity spot price data, frequency regulation ancillary service clearing prices, and electricity contracts of enterprises in the industrial park over the past year. Through surveys and smart meter data, analysis reveals a strong willingness for energy storage systems within the industrial park to participate in arbitrage when the electricity price difference is greater than 0.3 yuan / kWh. A large processing enterprise can provide approximately 2MW of interrupted load for 2 hours during production breaks. After training the KELM-GPR model, inputting the next day's electricity price forecast curve, the expected response capacity curves for the industrial park as a whole participating in peak shaving at various times the following day can be output.
[0039] Step S2: Collect second-level / minute-level data from photovoltaic inverters, energy storage BMS, load control terminals, and charging pile management platforms within the industrial park. Use an LSTM model to predict that the photovoltaic output fluctuation range for the next hour is 12MW to 18MW. DBSCAN analysis reveals that the charging load is mainly concentrated in two clusters: the office area and the logistics area. Wavelet packet transform analysis shows that the power variation of the precision machine tool load mainly includes hour-level program switching cycles and second-level start-stop transients.
[0040] Step S3: Using the 10kV distribution network topology of the industrial park, the market response tendency curve obtained in Step S1, and the time-series characteristics of each node's resources extracted in Step S2 (such as predicted photovoltaic output, available SOC of energy storage, and predicted base load) as inputs, construct the ST-GCN model. After training with historical data, this model can dynamically extrapolate the maximum active / reactive power support range, maximum load reduction capacity, and rate of change that the industrial park as a whole can provide to the grid's point of common connection at any future time, under the condition of satisfying internal network constraints.
[0041] Step S4: For the scenario of "providing intraday peak-shaving services", extract and calculate the following parameters from the model output of Step S3: The intraday peak-shaving reliable capacity of the industrial park virtual power plant is 8MW (confidence level 95%), the maximum upward ramp rate is 4MW / min, the maximum downward ramp rate is 5MW / min, the average command response delay is 45 seconds, and the steady-state adjustment error does not exceed ±3%. Generate a standard JSON format "External Characteristic Parameter Report" along with the corresponding calculation time and boundary conditions. This report will serve as the basis for the industrial park virtual power plant to apply for day-ahead peak-shaving market participation and for evaluation by dispatching agencies.
[0042] Example 2 In one or more embodiments, an energy system external characteristic characterization system based on virtual power plant technology is disclosed, specifically including: The data-driven module is used to build a data-driven model based on historical and real-time data of the electricity market where the industrial park is located and the operational data of the resource entities within the industrial park. This model quantifies the impact of the electricity market environment on the overall resource interaction willingness of the industrial park and outputs the expected response characteristics under the market scenario. The feature extraction module is used to collect historical and real-time operation data and geographic information of distributed power sources, energy storage, and loads in the industrial park. It uses time series analysis and spatial data analysis methods to extract the temporal variation patterns and spatial distribution characteristics of the resources. The coupling prediction module is used to integrate the expected response characteristics, the temporal variation law and spatial distribution characteristics of resources to construct a spatiotemporal coupling characterization model of the external characteristics of the virtual power plant in the industrial park, and to predict the power boundary and dynamic parameters of the industrial park aggregate. The feature description module is used to select features from the power boundary and dynamic parameters for a preset power grid interaction scenario, calculate standardized core external characteristic parameters, and encapsulate and output them in a structured format to form a standardized capability description of the virtual power plant in the industrial park.
[0043] Example 3 This embodiment provides an electronic device, including a memory and a processor, as well as computer instructions stored in the memory and running on the processor. When the computer instructions are executed by the processor, they complete the steps of the above-described method for characterizing the external characteristics of an energy system based on virtual power plant technology.
[0044] Example 4 This embodiment provides a computer-readable storage medium for storing computer instructions, which, when executed by a processor, complete the steps of the above-described method for characterizing the external characteristics of an energy system based on virtual power plant technology.
[0045] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0046] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0047] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment, whereby a series of operational steps are performed to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0048] The descriptions of each embodiment in the above embodiments have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.
[0049] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.
Claims
1. A method for characterizing the external characteristics of an energy system based on virtual power plant technology, characterized in that, include: Based on historical and real-time data of the electricity market where the industrial park is located and the operational data of the resource entities within the industrial park, a data-driven model is constructed to quantify the impact of the electricity market environment on the overall resource interaction willingness of the industrial park and output the expected response characteristics under the market scenario. Historical and real-time operation data and geographic information of distributed power sources, energy storage, and loads within the industrial park are collected. Time series analysis and spatial data analysis methods are used respectively to extract the temporal variation patterns and spatial distribution characteristics of the resources. By integrating the expected response characteristics, the temporal variation patterns and spatial distribution characteristics of resources, a spatiotemporal coupled characterization model of the external characteristics of the virtual power plant in the industrial park is constructed to predict the power boundary and dynamic parameters of the industrial park aggregate. For a preset power grid interaction scenario, feature selection is performed on the power boundary and dynamic parameters, and standardized core external characteristic parameters are calculated. These parameters are then encapsulated and output in a structured format to form a standardized capability description of the virtual power plant in the industrial park.
2. The method for characterizing the external characteristics of an energy system based on virtual power plant technology as described in claim 1, characterized in that, The data-driven model is a kernel extreme learning machine-Gaussian process regression model. The input features of the data-driven model include at least the electricity market price, ancillary service price, demand response subsidy amount, resource self-regulation cost, and operational constraints.
3. The method for characterizing the external characteristics of an energy system based on virtual power plant technology as described in claim 1, characterized in that, The time series analysis method includes long short-term memory networks and time series decomposition to extract the time series variation patterns of resources, including the time series variation patterns, fluctuation characteristics and periodic features of the output and load of various resources; Specifically, a long short-term memory network is used to extract temporal dependency features, and the temporal decomposition uses wavelet packet transform for time-frequency analysis to distinguish fluctuation components at different time scales.
4. The method for characterizing the external characteristics of an energy system based on virtual power plant technology as described in claim 1, characterized in that, The spatial data analysis method includes a density-based spatial clustering algorithm and a weighted regression analysis of the clustered results based on geographical data to analyze the spatial distribution characteristics of resources, including the aggregation and dispersion of resources in the geographical space of the industrial park and their correlation with power grid nodes.
5. The method for characterizing the external characteristics of an energy system based on virtual power plant technology as described in claim 1, characterized in that, The spatiotemporal coupling representation model is a dynamic representation model of the external characteristics of a virtual power plant in an industrial park, constructed using a spatiotemporal graph model. The dynamic representation model predicts the power boundary and dynamic parameters of the industrial park aggregate based on the input future scenario. The spatiotemporal graph model employs a spatiotemporal graph convolutional network to abstract the topology of the industrial park's power grid into a graph structure. Nodes represent resource access points or key buses, and edges represent electrical connections. The feature vectors of nodes contain resource types, real-time status, and market influencing factors. Spatial correlations are captured through graph convolution, and temporal evolution is captured through temporal convolution. The model outputs predicted values of the aggregated power boundary, adjustable potential range, and key dynamic characteristic parameters of the virtual power plant in the industrial park at any future time.
6. The method for characterizing the external characteristics of an energy system based on virtual power plant technology as described in claim 1, characterized in that, A set of standardized external characteristic core parameters are selected and calculated from the spatiotemporal coupling characterization model. The standardized core external characteristic parameters include at least: reliable regulation capacity, maximum ramp rate, average response delay time, steady-state regulation accuracy, continuous regulation time, and spatiotemporal adjustable domain. The standardized external characteristic core parameters, their confidence intervals, applicable time scales, and boundary conditions are encapsulated and output in a structured data format to form a standardized capability description of the virtual power plant in the industrial park.
7. The method for characterizing the external characteristics of an energy system based on virtual power plant technology as described in claim 1, characterized in that, The spatiotemporal adjustable domain parameters are obtained by projecting the high-dimensional operational feasible domain onto the active-reactive power plane, and are used to geometrically characterize the operational range of the virtual power plant in the industrial park under all internal safety constraints.
8. A system for characterizing the external characteristics of an energy system based on virtual power plant technology, characterized in that, include: The data-driven module is used to build a data-driven model based on historical and real-time data of the electricity market where the industrial park is located and the operational data of the resource entities within the industrial park. This model quantifies the impact of the electricity market environment on the overall resource interaction willingness of the industrial park and outputs the expected response characteristics under the market scenario. The feature extraction module is used to collect historical and real-time operation data and geographic information of distributed power sources, energy storage, and loads in the industrial park. It uses time series analysis and spatial data analysis methods to extract the temporal variation patterns and spatial distribution characteristics of the resources. The coupling prediction module is used to integrate the expected response characteristics, the temporal variation law and spatial distribution characteristics of resources to construct a spatiotemporal coupling characterization model of the external characteristics of the virtual power plant in the industrial park, and to predict the power boundary and dynamic parameters of the industrial park aggregate. The feature description module is used to select features from the power boundary and dynamic parameters for a preset power grid interaction scenario, calculate standardized core external characteristic parameters, and encapsulate and output them in a structured format to form a standardized capability description of the virtual power plant in the industrial park.
9. An electronic device, characterized in that, It includes a memory and a processor, as well as computer instructions stored in the memory and running on the processor, which, when executed by the processor, perform the method for characterizing the external characteristics of an energy system based on virtual power plant technology as described in any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, Used to store computer instructions, which, when executed by a processor, complete the method for characterizing the external characteristics of an energy system based on virtual power plant technology as described in any one of claims 1-7.