An intelligent risk early warning method and related equipment for a virtual power plant

Abstract

The present invention provides an intelligent risk warning method and related equipment for a virtual power plant, which is applied to the field of data processing technology. This application obtains the virtual power plant information to be evaluated; processes the virtual power plant information to be evaluated to generate a set of target virtual power plant operation risk impact factors; processes the set of target virtual power plant operation risk impact factors to generate target virtual power plant risk identification information; obtains an initial virtual power plant risk warning model and a training sample set; processes the training sample set based on a preset processing rule to generate a training set and a verification set; processes the initial virtual power plant risk warning model based on the training set and the verification set to generate a target virtual power plant risk warning model; processes the positive ideal solution and the negative ideal solution based on the target virtual power plant risk warning model to generate a virtual power plant risk warning value; processes the virtual power plant risk warning value to generate a virtual power plant risk level.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to an intelligent risk warning method for a virtual power plant and related devices. Background Art

[0002] With the continuous development of virtual power plant technology, multi-energy complementary virtual power plants mainly composed of electric vehicles and distributed photovoltaics have attracted increasing attention. The virtual power plant is an important direction of the deep integration of energy technology and information technology. During the operation of the virtual power plant, it can improve the adaptability of China's power market to a high proportion of new energy and realize the construction of an integrated intelligent energy system for power sources, grids, loads, and energy storage. At the same time, as a new energy technology, the virtual power plant is also an important technical means for China to steadily and orderly promote the "dual-carbon" green transformation and enter the carbon-neutral era.

[0003] Since the virtual power plant aggregates a large number of power batteries (electric vehicles) and energy storage batteries, the safety issues of lithium batteries during the charging and discharging process remain the focus of attention in the industry. The patent with the publication number CN117196173B and the patent name "A Distributed Scheduling Method for a Virtual Power Plant Considering Operational Risks and Network Transmissions" discloses the steps: 1) establishing an objective function for the distributed scheduling model of the virtual power plant considering operational risks and network transmissions; 2) establishing constraint conditions for the distributed scheduling model of the virtual power plant considering operational risks and network transmissions; 3) solving the distributed scheduling model of the virtual power plant considering operational risks and network transmissions to obtain the distributed scheduling decision of the virtual power plant; 4) calculating the risk loss cost of the virtual power plant based on step (3); 5) establishing a revenue distribution model for the virtual power plant based on generalized Nash bargaining to achieve the revenue distribution of the distributed scheduling of the virtual power plant. Existing virtual power plant risk control technologies focus on managing and controlling risks from the aspect of power dispatch optimization, lacking a scientific grading assessment and effective warning function for risk levels. In addition, the existing technology does not consider the impact of the current development of digital technology and systems on the risk warning process of the virtual power plant.

[0004] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present disclosure, and thus may include information that does not constitute prior art known to those of ordinary skill in the art. Summary of the Invention

[0005] The purpose of this application is to provide an intelligent risk early warning method and related equipment for a virtual power plant, which can at least overcome the problems existing in the prior art to a certain extent, conduct an overall hierarchical evaluation of multiple risk factors in the operation of the virtual power plant, construct a multi-level early warning ability for the risks of the virtual power plant, timely discover potential risk points of the virtual power plant, intervene and solve them after low-level risk early warning, timely contain the spread and expansion of the risks of the virtual power plant to high-level risks, avoid major economic losses to virtual power plant enterprises, and improve the effective measurement ability of technical managers for the operation risks of virtual power plants.

[0006] Other features and advantages of this application will become apparent through the following detailed description, or be learned in part through the practice of the present invention.

[0007] According to one aspect of this application, an intelligent risk early warning method for a virtual power plant is provided, including: obtaining information of the virtual power plant to be evaluated; processing the information of the virtual power plant to be evaluated to generate a set of target virtual power plant operation risk impact factors; processing the set of target virtual power plant operation risk impact factors to generate target virtual power plant risk identification information, where the target virtual power plant risk identification information includes a positive ideal solution and a negative ideal solution; obtaining an initial virtual power plant risk early warning model matching the target virtual power plant risk identification information and a training sample set matching the initial virtual power plant risk early warning model; processing the training sample set based on a preset processing rule to generate a training set and a validation set; processing the initial virtual power plant risk early warning model based on the training set and the validation set to generate a target virtual power plant risk early warning model; processing the positive ideal solution and the negative ideal solution based on the target virtual power plant risk early warning model to generate a virtual power plant risk early warning value; processing the virtual power plant risk early warning value to generate a virtual power plant risk level.

[0008] In an embodiment of this application, processing the information of the virtual power plant to be evaluated to generate a set of target virtual power plant operation risk impact factors includes: processing the information of the virtual power plant to be evaluated to generate physical attribute information of the virtual power plant to be evaluated; performing feature extraction processing on the physical attribute information of the virtual power plant to be evaluated to generate several feature sample types; performing feature screening processing on the several feature sample types to generate real-time feature sample data; generating a set of target virtual power plant operation risk impact factors based on several real-time feature sample data.

[0009] In an embodiment of the present application, processing the set of target virtual power plant operation risk impact factors to generate target virtual power plant risk identification information includes: obtaining a target virtual power plant operation rated value matrix, a weight vector of target virtual power plant operation risk impact factors, and an initial evaluation matrix; processing the initial evaluation matrix and the target virtual power plant operation rated value matrix to generate a deviation matrix of target virtual power plant operation risk impact factors; processing the deviation matrix of target virtual power plant operation risk impact factors and the weight vector of target virtual power plant operation risk impact factors to generate a weighted matrix of target virtual power plant operation risk impact factors; processing the weighted matrix of target virtual power plant operation risk impact factors to generate a positive ideal solution and a negative ideal solution; the method includes a calculation formula for calculating the positive ideal solution, and the calculation formula is:

[0010] ; ;

[0011] The method includes a calculation formula for calculating the negative ideal solution, and the calculation formula is: ;

[0012] ; where, is the positive ideal solution, is the negative ideal solution, is the deviation matrix of target virtual power plant operation risk impact factors, is the weight vector of target virtual power plant operation risk impact factors, is the target virtual power plant operation rated value matrix.

[0013] In one embodiment of the present application, the training dataset is processed based on preset processing rules to generate a training set and a validation set, including: obtaining other virtual power plant information that matches the target virtual power plant risk identification information; extracting features from the other virtual power plant information to generate a feature dataset; obtaining any number of data features in the feature dataset; generating adjacent features based on the distance between any number of data features and other numbers of data features of the same category, where the adjacent features include a preset number of the any number of data features; determining a sampling ratio based on the number of data features in the training set; determining a sampling rate based on the sampling ratio; sampling the adjacent features based on the sampling rate to generate a preset number of sampled features; generating multiple groups of data groups based on any data feature and each sampled feature, where each group of data groups contains a preset number of data samples, and at least one data sample includes identification information; processing the multiple groups of data groups to generate a training set and a validation set, where both the training set and the validation set include a number of data features.

[0014] In one embodiment of the present application, the positive ideal solution and the negative ideal solution are processed based on the target virtual power plant risk warning model to generate a virtual power plant risk warning value, including:

[0015] Processing the positive ideal solution based on the target virtual power plant risk warning model to generate a first Euclidean distance;

[0016] Processing the negative ideal solution based on the target virtual power plant risk warning model to generate a second Euclidean distance;

[0017] The target virtual power plant risk warning model includes a calculation formula for calculating the first Euclidean distance, and the calculation formula is:

[0018] ;

[0019] Wherein, is the Euclidean distance from the virtual power plant risk factor to the positive ideal solution at time t;

[0020] The target virtual power plant risk warning model includes a calculation formula for calculating the second Euclidean distance, and the calculation formula is:

[0021] ;

[0022] Wherein, is the Euclidean distance from the virtual power plant risk factor to the negative ideal solution at time t.

[0023] In an embodiment of the present application, processing the positive ideal solution and the negative ideal solution based on the target virtual power plant risk warning model to generate a virtual power plant risk warning value, including: The target virtual power plant risk warning model includes a calculation formula for calculating the virtual power plant risk warning value, and the calculation formula is:

[0024] ; where is the virtual power plant risk warning value.

[0025] In an embodiment of the present application, after processing the virtual power plant risk warning value to generate a virtual power plant risk level, it includes: Obtaining a preset virtual power plant risk warning table; Processing the virtual power plant risk level based on the preset virtual power plant risk warning table to generate a target warning time and a warning level matching the target warning time; Processing the target warning time and the warning level matching the target warning time to generate a risk correlation factor, where the risk correlation factor is generated based on the virtual power plant operation risk impact factors corresponding to the same warning level and adjacent warning times; Processing the risk correlation factor to generate risk warning information.

[0026] Another aspect of the present application is an intelligent risk warning device for a virtual power plant, characterized by including: An acquisition module, configured to acquire information of a virtual power plant to be evaluated; Acquiring an initial virtual power plant risk warning model matching the target virtual power plant risk identification information and a training sample set matching the initial virtual power plant risk warning model; A processing module, configured to process the information of the virtual power plant to be evaluated to generate a set of target virtual power plant operation risk impact factors; Processing the set of target virtual power plant operation risk impact factors to generate target virtual power plant risk identification information, where the target virtual power plant risk identification information includes a positive ideal solution and a negative ideal solution; Processing the training sample set based on a preset processing rule to generate a training set and a validation set; Processing the initial virtual power plant risk warning model based on the training set and the validation set to generate a target virtual power plant risk warning model; Processing the positive ideal solution and the negative ideal solution based on the target virtual power plant risk warning model to generate a virtual power plant risk warning value; Processing the virtual power plant risk warning value to generate a virtual power plant risk level.

[0027] According to still another aspect of the present application, an electronic device is characterized by including: A first processor; And a memory for storing executable instructions of the first processor; Wherein, the first processor is configured to execute the intelligent risk warning method of the virtual power plant as described above by executing the executable instructions.

[0028] According to another aspect of the present application, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a second processor, the intelligent risk warning method of the virtual power plant described above is implemented.

[0029] According to another aspect of the present application, there is provided a computer program product, including a computer program, characterized in that when the computer program is executed by a third processor, the intelligent risk warning method of the virtual power plant described above is implemented.

[0030] The intelligent risk warning method and related devices for a virtual power plant provided by the present application perform an overall hierarchical evaluation on multiple risk factors in the operation of the virtual power plant by the server, construct a multi-level warning ability for the virtual power plant risks, timely discover potential risk points of the virtual power plant, intervene and solve them after a low-level risk warning, timely contain the spread and expansion of the virtual power plant risks to high-level risks, avoid major economic losses to virtual power plant enterprises, and improve the effective measurement ability of technical managers for the operation risks of virtual power plants.

[0031] It should be understood that the above general description and subsequent detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A flowchart showing an intelligent risk warning method for a virtual power plant provided by an embodiment of the present application;

[0033] Figure 2 A schematic structural diagram showing an intelligent risk warning device for a virtual power plant provided by an embodiment of the present application;

[0034] Figure 3 A schematic structural diagram showing an electronic device provided by an embodiment of the present application;

[0035] Figure 4 A schematic diagram showing a storage medium provided by an embodiment of the present application;

[0036] Figure 5 A schematic interface design diagram showing an intelligent risk warning system for a virtual power plant provided by an embodiment of the present application;

[0037] Figure 6 A schematic interface design diagram showing another intelligent risk warning system for a virtual power plant provided by an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0038] The following describes the preferred embodiments of the present invention with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only for the purpose of illustration and explanation of the present invention, and are not used to limit the present invention.

[0039] The following will be combined with Figure 1 to describe the intelligent risk early warning method for a virtual power plant according to an exemplary embodiment of the present application. It should be noted that the following application scenarios are only shown for the convenience of understanding the spirit and principle of the present application, and the embodiments of the present application are not limited in this regard. On the contrary, the embodiments of the present application can be applied to any applicable scenario.

[0040] In one embodiment, the present application also proposes an intelligent risk early warning method for a virtual power plant and related devices. Figure 1 Schematically shows a flowchart of an intelligent risk early warning method for a virtual power plant according to an embodiment of the present application. As Figure 1 shown, this method is applied to a server and includes:

[0041] S101, obtaining information of the virtual power plant to be evaluated.

[0042] In one embodiment, a virtual power plant (VPP) is a new type of power source coordination management system realized through information and communication technology. It aggregates various distributed resources such as distributed power sources, energy storage devices, and controllable loads through software and intelligent technologies to achieve optimized control and scheduling of these resources. A virtual power plant is not a physical power plant but a smart grid technology that can participate in the operation and scheduling of the power grid, provide electric energy and auxiliary services, and has the characteristics of flexibility and economy.

[0043] The key technologies of the virtual power plant include Internet of Things communication technology, intelligent metering technology, energy Internet technology, load forecasting technology, and optimization and control technology. The Internet of Things communication technology receives status information through an edge gateway and sends control signals. The intelligent metering technology provides the basis for real-time monitoring and control. The energy Internet technology realizes the bidirectional flow and sharing of energy. The load forecasting technology predicts the time and space distribution of the power load, and the optimization and control technology uses data-driven methods for resource optimization allocation. By obtaining the relevant actual operation data of the information of the virtual power plant to be evaluated, the risk assessment of the target virtual power plant is carried out. Among them, the relevant actual operation data of the information of the virtual power plant to be evaluated include but are not limited to real-time voltage, real-time current, temperature, humidity, load power, and load quantity.

[0044] S102, processing the information of the virtual power plant to be evaluated to generate a set of target virtual power plant operation risk impact factors.

[0045] In one implementation, the virtual power plant information to be evaluated is processed to generate the physical attribute information of the virtual power plant information to be evaluated. Feature extraction processing is performed on the physical attribute information of the virtual power plant information to be evaluated to generate several feature sample types. Feature screening processing is performed on the several feature sample types to generate real-time feature sample data. Based on the several real-time feature sample data, a set K of target virtual power plant operation risk impact factors is generated, where there are n impact factors, and the weight vector of the impact factors is calculated by the eigenvector method integrating information entropy. The weight vector result is denoted as where and the vector satisfies the numerical constraint requirements of.

[0046] Specifically, in the process of processing the virtual power plant information to be evaluated, first, the physical attribute information is extracted from the original data of the virtual power plant, including data such as voltage, current, temperature, and equipment status. These data can be obtained in real time through intelligent metering devices and sensors and subjected to preliminary processing, such as data cleaning and standardization.

[0047] After obtaining the physical attribute information, the next step is feature extraction. Feature extraction is a key step in understanding and analyzing the state of the virtual power plant and can be carried out from multiple dimensions such as "real-time voltage, real-time current, air temperature, humidity, load power, and load quantity". Among them, electrical signal data can be collected by sensors and used to analyze the working state and load conditions of the virtual power plant. Feature extraction may include the effective value, root mean square value, waveform parameters, etc. of voltage and current. These features help monitor the operation status of equipment and prevent potential failures; air temperature data is particularly important for virtual power plants because temperature-sensitive loads account for a relatively large proportion of electricity demand. Feature extraction may involve time series analysis of air temperature. For example, a small sample of data is augmented using a Time Series Generative Adversarial Network (TimeGAN), and then predicted through a Convolutional-Long Short-Term Memory Neural Network (CNN-LSTM); the measurement of humidity can reflect environmental conditions and is particularly important for maintaining power equipment. Feature extraction of humidity may include statistical analysis of relative humidity and correlation analysis with equipment failure rates; load power is an important indicator for measuring the output capacity of the virtual power plant. Feature extraction may include distribution characteristics of power, peak power, power change rate, etc. These features help optimize the allocation and scheduling of power resources; the load quantity reflects the number of devices or users connected to the virtual power plant. Feature extraction may involve time series analysis of the load quantity and trends and patterns of changes in the load quantity.

[0048] By extracting and processing the information on these physical properties, key information helpful for describing and understanding the state of the virtual power plant can be generated, thereby providing support for the optimal operation and risk management of the virtual power plant. For example, through feature extraction, a risk assessment index library of the virtual power plant can be constructed, and then the evaluation scores of each level of indicators can be obtained using the cloud model evaluation method based on Bayesian feedback correction to evaluate the risk level of the virtual power plant. In addition, the results of feature extraction can also be used for non-intrusive load identification, and features are extracted from the current waveform diagram of the visual image to improve the accuracy of load identification.

[0049] After the feature extraction is completed, several feature sample types are generated. These sample types can be based on different working conditions and operating conditions to ensure that the performance and state of the virtual power plant can be comprehensively evaluated. The feature sample types are subjected to feature screening processing to generate real-time feature sample data. Feature screening is a key step, which helps to reduce the complexity of the model, improve the performance of the model, and speed up the training speed. Feature screening can be carried out using statistical methods, model-based methods, and embedded methods.

[0050] Finally, a set of target virtual power plant operation risk impact factors is generated based on the real-time feature sample data. This can be achieved by constructing a risk assessment index library and an evaluation model. For example, the ordered weighted average (OWA) and the improved analytic hierarchy process (AHP) are used to assign weights to the indicators, and the cloud model evaluation method based on Bayesian feedback correction is used to obtain the evaluation scores of each level of indicators, so as to comprehensively evaluate the operation risk of the virtual power plant and provide support and guidance for the construction and operation of the virtual power plant.

[0051] S103. Process the set of target virtual power plant operation risk impact factors to generate target virtual power plant risk identification information.

[0052] In one implementation, obtain the target virtual power plant operation rated value matrix ( ), the weight vector of the target virtual power plant operation risk impact factor , and the initial evaluation matrix. Specifically, the operation risk of the target virtual power plant is related to six elements, namely real-time voltage, real-time current, temperature, humidity, load power, and load quantity. The weight vectors of its target virtual power plant operation risk impact factors are [0.2, 0.2, 0.2, 0.1, 0.2, 0.1] respectively, and the target virtual power plant operation rated value matrix is [380, 200, 26, 30, 5000, 1200]. In addition, the early warning period is from 9:00 to 12:00 in the morning, and the risk early warning level is updated every hour.

[0053] Based on the virtual power plant intelligent data acquisition device, record the data of the virtual power plant operation, that is, the initial evaluation matrix, as shown below:

[0054]

[0055] Process the initial evaluation matrix and the target virtual power plant operating rated value matrix to generate a deviation matrix of the target virtual power plant operating risk impact factor. The calculation of the deviation matrix is as follows: Subtract the corresponding values of the target virtual power plant operating rated value matrix [380, 200, 26, 30, 5000, 1200] from the values at each moment (each row) of the initial matrix to obtain the following matrix.

[0056]

[0057] Process the deviation matrix of the target virtual power plant operating risk impact factor and the weight vector of the target virtual power plant operating risk impact factor to generate a weighted matrix of the target virtual power plant operating risk impact factor. Specifically, multiply the values of each row in the deviation matrix by the values of the weight matrix [0.2, 0.2, 0.2, 0.1, 0.2, 0.1], and the calculation results are as follows.

[0058]

[0059] The risk identification information of the target virtual power plant includes the positive ideal solution and the negative ideal solution. Process the weighted matrix of the target virtual power plant operating risk impact factor to generate the positive ideal solution and the negative ideal solution. Among them, this application includes a calculation formula for the positive ideal solution, and the calculation formula is:

[0060] ; ;

[0061] The method includes a calculation formula for the negative ideal solution, and the calculation formula is:

[0062] ; ;

[0063] ;

[0064] Among them, is the positive ideal solution, is the negative ideal solution, is the deviation matrix of the target virtual power plant operating risk impact factor, is the weight vector of the target virtual power plant operating risk impact factor, is the target virtual power plant operating rated value matrix.

[0065] Exemplarily, for all risk elements, the greater the value, the greater the risk. The positive ideal solution is the maximum value in each column of the weighted matrix of the target virtual power plant operation risk impact factors; the negative ideal solution is the minimum value in each column of the weighted matrix of the target virtual power plant operation risk impact factors. That is, the positive ideal solution is: [0.2, 10, 1.8, 1, 600, 30], and the negative ideal solution is: [-0.6, 1.8, 0, 0, -700, -70].

[0066] S104. Obtain an initial virtual power plant risk early warning model that matches the target virtual power plant risk identification information and a training sample set that matches the initial virtual power plant risk early warning model.

[0067] In one implementation, in order to construct an initial virtual power plant risk early warning model, the applicant mainly focuses on several key aspects: operation risk, economic risk, safety risk, and management risk. These risk elements can be quantified and evaluated through a series of indicators to achieve the classification and early warning of the virtual power plant operation risk.

[0068] It involves equipment availability, failure rate, power outage events, etc. For example, the equipment availability factor, the equipment failure outage rate, and the power outage time caused by relay protection are all important third-level indicators, which can reflect the operation efficiency and reliability of the virtual power plant. It includes the operation and maintenance costs of the renewable energy power generation system, the purchase and sale electricity prices of the energy storage system, the response rate of the controllable load, etc. These indicators help to evaluate the economic feasibility and market competitiveness of the virtual power plant. Data security, information security index, compliance degree of business information system data standards, etc. are all key indicators, which can reveal the potential risks of the virtual power plant in terms of information security. It involves technological innovation risk, investment / merger and acquisition risk, marketing management risk, etc. These indicators help to evaluate the internal management efficiency and external market adaptability of the virtual power plant.

[0069] After constructing the initial virtual power plant risk early warning model, the applicant needs to develop a matching training sample set. This sample set should contain historical data covering all the above risk elements and corresponding indicators. By analyzing these data, the model can be trained to identify patterns of different risk levels and predict possible future risks.

[0070] In order to improve the effective measurement ability of technical managers for the virtual power plant operation risk, a cloud model evaluation method based on Bayesian feedback correction can be adopted. This method can assign weights to indicators through ordered weighted averaging (OWA) and improved analytic hierarchy process (AHP), and obtain the evaluation scores of each level of indicators, thereby evaluating the risk degree of the virtual power plant. By comprehensively considering multiple risk elements and using appropriate evaluation tools, a multi-level risk early warning ability can be effectively constructed to provide support for the stable operation of the virtual power plant.

[0071] S105. Process the training sample set based on a preset processing rule to generate a training set and a validation set.

[0072] In one implementation, obtain other virtual power plant information that matches the target virtual power plant risk identification information, extract features from the other virtual power plant information to generate a feature dataset. Specifically, collect relevant operation data from different virtual power plants, including but not limited to physical attribute information such as real-time voltage, real-time current, temperature, humidity, load power, and load quantity. These data are the basis for constructing the feature dataset. Process the collected data to extract key information that can describe and understand the state of the virtual power plant. For example, features such as voltage stability and current fluctuation can be extracted from real-time voltage and current data; features such as the impact of environmental conditions on equipment operation can be extracted from temperature and humidity data; features such as demand response ability and system load characteristics can be extracted from load power and quantity. Based on the feature extraction, the most representative features for virtual power plant risk assessment are selected through statistical analysis or machine learning methods. This step is to reduce the complexity of the dataset and improve the generalization ability and prediction accuracy of the model.

[0073] Generate adjacent features based on the distance between any number of data features and other numbers of data features of the same category, where the adjacent features include a preset number of any number of data features; in the field of data analysis and machine learning, generating adjacent features based on the distance between data features is a feature engineering method aimed at discovering the mutual relationships and patterns between features. Specifically, select a certain number of data features from the feature dataset that can reflect the usage of electronic certificates, use a distance metric (such as Euclidean distance, Manhattan distance, or cosine similarity) to calculate the distance between any data feature and other data features of the same category, and based on the calculated distance, determine the other data features that are closest to any data feature. These features are considered adjacent. Set a preset number, that is, the number of data features that are expected to be included in the adjacent feature set. For each data feature, select the preset number of data features that are closest to it to form an adjacent feature set, analyze the adjacent feature set, identify the potential relationships and patterns between the features. These relationships may be crucial for understanding the usage of electronic certificates, and evaluate the importance of each data feature in the adjacent feature set to determine which features are most critical for predicting the target variable. That is, in which time periods the user may go to which places, and whether there is a sequence of appearances between different places, etc.

[0074] If the number of features in adjacent feature sets is too large, it may be necessary to apply dimensionality reduction techniques (such as principal component analysis PCA) to reduce the number of features while retaining important information. The generated adjacent feature sets are used to train a machine learning model to predict or classify the usage of electronic certificates, evaluate the performance of the model, such as accuracy, recall, and F1 score, and optimize the model as needed. It may be necessary to adjust the preset quantity and distance metric method multiple times to find the optimal feature set. Through this method, the complexity of electronic certificate usage can be better understood, and the prediction ability of the early warning model can be improved. This is very important for the security management and risk assessment of electronic certificates. At the same time, it also helps to enhance the model's ability to identify abnormal behaviors and ensure the security and reliability of the electronic certificate system.

[0075] Based on the number of data features in the training set, determine the sampling ratio. Based on the sampling ratio, determine the sampling rate. Sample adjacent features based on the sampling rate to generate a preset number of sampled features. Based on any data feature and each sampled feature, generate multiple groups of data groups, where each group of data groups contains a preset number of data samples, and at least one data sample includes identification information.

[0076] In data analysis and machine learning, determine the sampling ratio and sampling rate based on the number of data features in the training set. By counting the number of data features in the training set, understand the distribution of different features, and determine the sampling ratio according to the number of data features and the scale of the data set. The sampling ratio can help the applicant decide how many samples to draw from each feature. Based on the sampling ratio, calculate the specific sampling rate. The sampling rate is the ratio of the actual sampling quantity to the total quantity. Use the sampling rate to sample adjacent features to generate a preset number of sampled features. This process ensures the representativeness and diversity of the samples. Through the sampling process, generate a set of sampled features, which will be used for subsequent data analysis and model training. Based on any data feature and each sampled feature, construct multiple groups of data groups. Each group of data groups contains a preset number of data samples. Ensure the diversity of the samples in each group of data groups, and at least include one sample with identification information, which helps the model learn the feature performance in different situations. Use these data groups for model training, evaluate the contribution of different features to the prediction target, train a machine learning model using the sampled feature set, and evaluate the performance of the model through the validation set. According to the results of model training and validation, it may be necessary to adjust the sampling ratio and rate to optimize the prediction ability of the model. Through this method, large-scale data sets can be effectively processed while maintaining the quality of the data and the generalization ability of the model, helping to identify potential security risks and abnormal behaviors.

[0077] S106. Process the initial virtual power plant risk early warning model based on the training set and the validation set to generate a target virtual power plant risk early warning model.

[0078] In one implementation, the selected features are integrated into a feature dataset, which will be used to train and validate the virtual power plant risk early warning model. The dataset should contain labels, that is, the risk level or category corresponding to each piece of data, to facilitate model learning. Use the constructed feature dataset to train the initial virtual power plant risk early warning model, and evaluate the performance of the model through methods such as cross-validation. The model should be able to conduct an overall hierarchical evaluation of multiple risk factors in the operation of the virtual power plant and build a multi-level early warning capability.

[0079] Use the validation set to evaluate the trained model, check the performance metrics of the model, such as accuracy, recall rate, F1 score, ROC-AUC, etc. To ensure the stability and generalization ability of the model, use the cross-validation method to further evaluate the model. According to the evaluation results, optimize the model. This may include adjusting the model structure, reselecting features, using feature selection algorithms, adjusting hyperparameters, etc.

[0080] Use an independent validation set or through model evaluation techniques (such as confusion matrix analysis) to verify the prediction ability of the model, ensure that the model accurately identifies risks, and iteratively update the model according to the performance of the model on the validation set until the expected performance standard is reached. Deploy the finally trained and validated model to the production environment for real-time monitoring and early warning of the operation risks of the virtual power plant. Through the above steps, an effective virtual power plant risk early warning model can be constructed and a matching training sample set can be generated to provide support for the stable operation and risk management of the virtual power plant.

[0081] S107. Process the positive ideal solution and the negative ideal solution based on the target virtual power plant risk early warning model to generate a virtual power plant risk early warning value.

[0082] In one implementation, process the positive ideal solution based on the target virtual power plant risk early warning model to generate a first Euclidean distance; process the negative ideal solution based on the target virtual power plant risk early warning model to generate a second Euclidean distance; the target virtual power plant risk early warning model includes a calculation formula for calculating the first Euclidean distance, and the calculation formula is:

[0083] ;

[0084] where is the Euclidean distance from the virtual power plant risk factor to the positive ideal solution at time t;

[0085] The target virtual power plant risk early warning model includes a calculation formula for calculating the second Euclidean distance, and the calculation formula is as follows:

[0086] ;

[0087] Among them, is the Euclidean distance from the virtual power plant risk factor to the negative ideal solution at time t.

[0088] In another implementation, the target virtual power plant risk early warning model includes a calculation formula for calculating the virtual power plant risk early warning value, and the calculation formula is as follows:

[0089] ;

[0090] Among them, is the virtual power plant risk early warning value.

[0091] According to the positive and negative ideal point situations of each risk factor, combined with the above calculation formulas of the first Euclidean distance and the second Euclidean distance, calculate the Euclidean distances of the corresponding data at the above four moments, as shown below:

[0092]

[0093] Combined with the above calculation formula for calculating the virtual power plant risk early warning value, calculate the risk numerical results, as shown below:

[0094]

[0095] S108. Process the virtual power plant risk early warning value to generate a virtual power plant risk level.

[0096] In one implementation, classify the risk early warning level based on the calculation results. The larger the value, the higher the risk early warning level. The smaller the value, the lower the risk early warning level. If the value is 0, it means there is no risk for the time being. The specific risk level classification is as follows:

[0097] 1) If the value is in the interval [0.8, 1], it is designated as a first-level risk early warning;

[0098] 2) If the value is in the interval [0.6, 0.8), it is designated as a second-level risk early warning;

[0099] 3) If the value is in the interval [0.4, 0.6), it is designated as a third-level risk early warning;

[0100] 4) When the numerical value is within the interval [0.2, 0.4), it is defined as a level 4 risk warning;

[0101] 5) When the numerical value is within the interval (0, 0.2), it is defined as a level 5 risk warning.

[0102] According to the above results of the virtual power plant risk warning values and combined with the grading criteria set by the present invention, the warning level is divided as follows:

[0103]

[0104] Optionally, in another embodiment based on the above method of the present application, after processing the virtual power plant risk warning value to generate a virtual power plant risk level, it includes:

[0105] Obtain a preset virtual power plant risk warning table;

[0106] Based on the preset virtual power plant risk warning table, process the virtual power plant risk level to generate a target warning time and a warning level matching the target warning time;

[0107] Process the target warning time and the warning level matching the target warning time to generate a risk correlation factor, where the risk correlation factor is generated based on the virtual power plant operation risk impact factors corresponding to the same warning level and adjacent warning times;

[0108] Process the risk correlation factor to generate risk warning information.

[0109] In one implementation, the applicant presets a corresponding virtual power plant risk warning table according to actual needs. This table usually contains the definition criteria of different risk levels and corresponding warning indicators. By using the real-time data and historical data of the virtual power plant and combining with the risk warning table, the risk level of the current virtual power plant can be judged, which can be achieved by analyzing key indicators such as equipment failure rate and load response rate. Determine the target warning time, that is, the specific time point when the risk reaches a certain level, and generate it together with the warning level matching this time point, which can be obtained through real-time data analysis of the monitoring system.

[0110] Conduct an in-depth analysis of the target warning time and warning level to identify the key factors that affect the change in risk level. These factors may include the operating status of equipment, environmental factors, market changes, etc. In particular, it is necessary to analyze the correlation between the warning levels corresponding to the same warning level and adjacent warning times, as well as other warning times with the same current warning level and their adjacent warning times. For example, if a risk with a warning level of 2 occurs at 9 am and another risk with a warning level of 2 occurs again at 6 pm, it is necessary to analyze whether the risk factors at 6 pm are the same as those at 9 am to better solve and investigate problems in subsequent work.

[0111] Based on the above analysis results, generate risk warning information. These information should clearly indicate the risk level, warning time, influencing factors and their influencing degrees, providing decision-making support for risk management. The generation of risk warning information should consider the management of risk factors, adjust the operating environment that may cause potential losses by reducing the level of risk factors, changing their distribution or the enterprise's sensitivity to risk factors. In addition, risk classification and control measures are also an important part of the process of generating risk warning information. According to the severity of the risk, corresponding control measures can be formulated, such as strengthening monitoring, formulating rules and regulations, setting alarms and warning signals, etc., to ensure that the risk is effectively controlled, so as to accurately predict and evaluate the operation risk of the virtual power plant and provide a scientific basis for risk warning.

[0112] In another implementation method, if the risk warning value of the virtual power plant >= 0.8, specifically, there are deviation values of real-time voltage, real-time current, etc. in the operation indicators reaching the corresponding thresholds, then it can be judged that the first-level risk level standard of the virtual power plant is reached, belonging to the existence of major explosion risks. Correspondingly, the managers of the virtual power plant need to execute corresponding response actions according to the risk prompt, including cutting off the load and conducting manual inspections.

[0113] During the implementation process, if the risk warning value of the virtual power plant is in the interval [0.6, 0.8), specifically, there are deviation values of real-time voltage, real-time current, etc. in the operation indicators reaching the corresponding thresholds, then it can be judged that the second-level risk level standard of the virtual power plant is reached, belonging to a severe deviation from the normal safety threshold. Correspondingly, the managers of the virtual power plant need to execute corresponding response actions according to the risk prompt, including reducing the load and conducting manual inspections.

[0114] During the implementation process, if the risk warning value of the virtual power plant is in the interval [0.4, 0.6), specifically, there are deviation values of real-time voltage, real-time current, etc. in the operation indicators reaching the corresponding thresholds, then it can be judged that the third-level risk level standard of the virtual power plant is reached, belonging to a moderate deviation from the normal safety threshold. Correspondingly, the managers of the virtual power plant need to execute corresponding response actions according to the risk prompt and conduct manual inspections.

[0115] During the implementation process, if the virtual power plant risk warning value is within the range of [0.2, 0.4), specifically, there are deviation values of real-time voltage, real-time current, etc. in the operation indicators reaching the corresponding thresholds, then it can be judged at this time that the virtual power plant reaches the fourth-level risk rating standard, belonging to a mild deviation from the normal safety threshold. Correspondingly, the virtual power plant management personnel need to execute corresponding response actions according to the risk prompt to perform remote load adjustment.

[0116] During the implementation process, if the virtual power plant risk warning value is within the range of [0, 0.2), specifically, there are deviation values of real-time voltage, real-time current, etc. in the operation indicators reaching the corresponding thresholds, then it can be judged at this time that the virtual power plant reaches the fifth-level risk rating standard, belonging to a small fluctuation in the operation of the virtual power plant. Correspondingly, the virtual power plant management personnel need to execute corresponding response actions according to the risk prompt to strengthen remote monitoring.

[0117] During the implementation process, the virtual power plant risk warning situation will be fed back to the intelligent risk warning system of the virtual power plant. The present invention also designs the intelligent risk warning system of the virtual power plant. The following combines the Figure 5 and Figure 6 , and the interface design diagram of the intelligent risk warning system of the virtual power plant is used to explain the intelligent risk warning system of the virtual power plant. Figure 5 shows the interface design composition of the intelligent risk warning system of the virtual power plant, which belongs to the interface composition under normal conditions. Among them, it includes real-time input voltage, real-time input current, current internal temperature, rated input voltage, rated input current, rated working temperature, voltage deviation degree, current deviation degree, internal temperature deviation degree, etc. At the same time, it also includes a status indication output box indicating whether there is a risk in the current power plant operation. The current status indicates that there is no risk in the operation of the virtual power plant for the time being. Figure 6 shows the interface design composition of the intelligent risk warning system of the virtual power plant in the case of a risk warning. Among them, it includes real-time input voltage, real-time input current, current internal temperature, rated input voltage, rated input current, rated working temperature, voltage deviation degree, current deviation degree, internal temperature deviation degree, etc. At the same time, it also includes an indicator of the virtual power plant operation risk level index. In this embodiment, the voltage and current deviation rates meet the requirements of the secondary risk warning index. Therefore, the current warning information: secondary warning will be displayed in the current status bar. In addition, in the interface of the intelligent risk warning system of the virtual power plant of the virtual power plant, a triangular exclamation mark risk identifier will pop up to remind the virtual power plant management personnel to pay attention.

[0118] This application obtains the virtual power plant information to be evaluated by the server; processes the virtual power plant information to be evaluated to generate the physical attribute information of the virtual power plant information to be evaluated; performs feature extraction processing on the physical attribute information of the virtual power plant information to be evaluated to generate several feature sample types; performs feature screening processing on several feature sample types to generate real-time feature sample data; generates a set of target virtual power plant operation risk impact factors based on several real-time feature sample data; obtains the target virtual power plant operation rated value matrix, the weight vector of the target virtual power plant operation risk impact factor, and the initial evaluation matrix; processes the initial evaluation matrix and the target virtual power plant operation rated value matrix to generate the deviation matrix of the target virtual power plant operation risk impact factor; processes the deviation matrix of the target virtual power plant operation risk impact factor and the weight vector of the target virtual power plant operation risk impact factor to generate the weighted matrix of the target virtual power plant operation risk impact factor; processes the weighted matrix of the target virtual power plant operation risk impact factor to generate the positive ideal solution and the negative ideal solution.

[0119] Obtain the initial virtual power plant risk warning model that matches the target virtual power plant risk identification information and the training sample set that matches the initial virtual power plant risk warning model; obtain other virtual power plant information that matches the target virtual power plant risk identification information; perform feature extraction on other virtual power plant information to generate a feature data set; obtain any number of data features in the feature data set; generate adjacent features based on the distance between any number of data features and other numbers of data features of the same category, where the adjacent features include a preset number of any number of data features; determine the sampling ratio based on the number of each data feature in the training set; determine the sampling rate based on the sampling ratio; sample the adjacent features based on the sampling rate to generate a preset number of sampled features; generate multiple groups of data sets based on any data feature and each sampled feature, where each group of data sets contains a preset number of data samples, where each group of data sets contains a preset number of data samples, and at least one data sample includes identification information; process multiple groups of data sets to generate a training set and a validation set, where both the training set and the validation set include several data features; process the initial virtual power plant risk warning model based on the training set and the validation set to generate the target virtual power plant risk warning model.

[0120] Process the positive ideal solution based on the target virtual power plant risk early warning model to generate the first Euclidean distance; process the negative ideal solution based on the target virtual power plant risk early warning model to generate the second Euclidean distance; process the virtual power plant risk early warning value to generate the virtual power plant risk level; obtain the preset virtual power plant risk early warning table; process the virtual power plant risk level based on the preset virtual power plant risk early warning table to generate the target early warning time and the warning level matching the target early warning time; process the target early warning time and the warning level matching the target early warning time to generate a risk correlation factor, where the risk correlation factor is generated based on the virtual power plant operation risk impact factors corresponding to the same warning level and adjacent early warning times; process the risk correlation factor to generate risk early warning information. Conduct an overall hierarchical assessment of multiple risk elements in the operation of the virtual power plant, construct the multi-level early warning ability of the virtual power plant risk, timely discover potential risk points of the virtual power plant, intervene and solve them after a low-level risk early warning, timely contain the spread and expansion of the virtual power plant risk to a high-level risk, avoid major economic losses of the virtual power plant enterprise, and improve the effective measurement ability of technical managers for the operation risk of the virtual power plant.

[0121] In one implementation, as Figure 2 shown, the present application also provides an intelligent risk early warning device for a virtual power plant, including:

[0122] An acquisition module 201, configured to acquire information of the virtual power plant to be evaluated; acquire an initial virtual power plant risk early warning model matching the target virtual power plant risk identification information and a training sample set matching the initial virtual power plant risk early warning model;

[0123] A processing module 202, configured to process the information of the virtual power plant to be evaluated to generate a set of target virtual power plant operation risk impact factors; process the set of target virtual power plant operation risk impact factors to generate target virtual power plant risk identification information, where the target virtual power plant risk identification information includes a positive ideal solution and a negative ideal solution; process the training sample set based on a preset processing rule to generate a training set and a validation set; process the initial virtual power plant risk early warning model based on the training set and the validation set to generate a target virtual power plant risk early warning model; process the positive ideal solution and the negative ideal solution based on the target virtual power plant risk early warning model to generate a virtual power plant risk early warning value; process the virtual power plant risk early warning value to generate a virtual power plant risk level.

[0124] An embodiment of the present application provides an electronic device, as Figure 3As shown, the electronic device 3 includes a first processor 300, a memory 301, a bus 302, and a communication interface 303. The first processor 300, the communication interface 303, and the memory 301 are connected through the bus 302. A computer program that can run on the first processor 300 is stored in the memory 301. When the first processor 300 runs the computer program, it executes the intelligent risk warning method of the virtual power plant provided in any of the foregoing embodiments of this application.

[0125] Among them, the memory 301 may include a high-speed random access memory (RAM: Random Access Memory), or may also include a non-volatile memory, such as at least one disk memory. Through at least one communication interface 303 (which can be wired or wireless), a communication connection is realized between this system network element and at least one other network element, and the Internet, wide area network, local area network, metropolitan area network, etc. can be used.

[0126] The bus 302 can be an ISA bus, a PCI bus, an EISA bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. Among them, the memory 301 is used to store programs. After receiving an execution instruction, the first processor 300 executes the program. The intelligent risk warning method of the virtual power plant disclosed in any of the foregoing embodiments of this application can be applied to the first processor 300 or implemented by the first processor 300.

[0127] The first processor 300 may be an integrated circuit chip with signal processing capabilities. In the implementation process, the steps of the above method can be completed by the integrated logic circuit of the hardware in the first processor 300 or the instructions in the form of software. The above-mentioned first processor 300 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. It can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory 301, and the first processor 300 reads the information in the memory 301 and combines its hardware to complete the steps of the above method.

[0128] The electronic device provided by the above embodiment of the present application and the intelligent risk warning method of the virtual power plant provided by the embodiment of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0129] The embodiment of the present application provides a computer-readable storage medium, such as Figure 4 shown, the computer-readable storage medium 401 stores a computer program, and when the computer program is read and run by the second processor 402, it implements the intelligent risk warning method of the virtual power plant as described above.

[0130] The technical solution of the embodiment of the present application can be embodied in the form of a software product in essence, that is, the part that contributes to the prior art or all or part of the technical solution. The computer software product is stored in a storage medium and includes several instructions for causing an electronic device (which may be an air conditioner, a refrigeration device, a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method described in the embodiment of the present application. The aforementioned storage medium includes: various media such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disc that can store program codes.

[0131] The computer-readable storage medium provided in the above embodiments of the present application and the intelligent risk warning method of the virtual power plant provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0132] The embodiments of the present application provide a computer program product, including a computer program, and the computer program is executed by a third processor to implement the method as described above.

[0133] The computer program product provided in the above embodiments of the present application and the intelligent risk warning method of the virtual power plant provided in the embodiments of the present application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0134] It should be noted that in the present application, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the element.

[0135] Each embodiment in the present application is described in a related manner. The same or similar parts among the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the embodiments of the intelligent risk warning method, electronic devices, electronic equipment, and readable storage media for evaluating virtual power plants, since they are basically similar to the embodiments of the above-mentioned intelligent risk warning method of virtual power plants, the description is relatively simple, and the relevant parts can be referred to the partial description of the embodiments of the above-mentioned intelligent risk warning method of virtual power plants.

[0136] Although the present application is disclosed as above, the present application is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the protection scope of the present application should be subject to the scope defined by the claims.

Claims

1. An intelligent risk early warning method for a virtual power plant, characterized in that: include: Obtain information about the virtual power plant to be evaluated, including voltage, current, temperature, and equipment status; Processing the virtual power plant information to be evaluated to generate a set of target virtual power plant operation risk influencing factors, where the target virtual power plant operation risk influencing factors include real-time voltage, real-time current, temperature, humidity, load power, and load quantity; Processing the target virtual power plant operation risk influencing factor set to generate target virtual power plant risk identification information, wherein the target virtual power plant risk identification information includes a positive ideal solution and a negative ideal solution; Acquire an initial virtual power plant risk warning model that matches the target virtual power plant risk identification information and a training sample set that matches the initial virtual power plant risk warning model; Process the training sample set based on preset processing rules to generate a training set and a validation set; Processing the initial virtual power plant risk warning model based on the training set and the validation set to generate a target virtual power plant risk warning model; Processing the positive ideal solution and the negative ideal solution based on a target virtual power plant risk warning model to generate a virtual power plant risk warning value; The risk warning value of the virtual power plant is processed to generate a risk level of the virtual power plant. If the risk warning value of the virtual power plant is greater than or equal to 0.8, the real-time voltage and real-time current reach the corresponding threshold value, and it is judged that the first-level risk level standard of the virtual power plant is reached; if the risk warning value of the virtual power plant is in the interval [0.6, 0.8), the real-time voltage and real-time current reach the corresponding threshold value, and it is judged that the second-level risk level standard of the virtual power plant is reached; if the risk warning value of the virtual power plant is in the interval [0.4, 0.6), the real-time voltage and real-time current reach the corresponding threshold value, and it is judged that the third-level risk level standard of the virtual power plant is reached; if the risk warning value of the virtual power plant is in the interval [0.2, 0.4), the real-time voltage and real-time current reach the corresponding threshold value, and it is judged that the fourth-level risk level standard of the virtual power plant is reached; if the risk warning value of the virtual power plant is in the interval [0, 0.2), the real-time voltage and real-time current reach the corresponding threshold value, and it is judged that the fifth-level risk level standard of the virtual power plant is reached; The target virtual power plant operation risk impact factor set is processed to generate the target virtual power plant risk identification information, including: obtaining the target virtual power plant operation rated value matrix, the weight vector of the target virtual power plant operation risk impact factor and the initial evaluation matrix; processing the initial evaluation matrix and the target virtual power plant operation rated value matrix to generate the deviation matrix of the target virtual power plant operation risk impact factor; processing the deviation matrix of the target virtual power plant operation risk impact factor and the weight vector of the target virtual power plant operation risk impact factor to generate the weighted matrix of the target virtual power plant operation risk impact factor; processing the weighted matrix of the target virtual power plant operation risk impact factor to generate a positive ideal solution and a negative ideal solution; the calculation formula for calculating the positive ideal solution is: ； ； The calculation formula for calculating the negative ideal solution is: ； ； ； in, is a positive ideal solution, is a negative ideal solution, is the deviation matrix of the risk influencing factors of the target virtual power plant operation, is the weight vector of the risk influencing factors of the target virtual power plant operation, The rated value matrix for the target virtual power plant operation, Risk factors for virtual power plants; The positive ideal solution and the negative ideal solution are processed based on the target virtual power plant risk warning model to generate a virtual power plant risk warning value, including: processing the positive ideal solution based on the target virtual power plant risk warning model to generate a first Euclidean distance; processing the negative ideal solution based on the target virtual power plant risk warning model to generate a second Euclidean distance; the target virtual power plant risk warning model includes a calculation formula for calculating the first Euclidean distance, and the calculation formula is: ； in, For Risk factors of virtual power plants at all times To the positive ideal solution The Euclidean distance of The target virtual power plant risk warning model includes a calculation formula for calculating the second Euclidean distance: ； in, For Risk factors of virtual power plants at all times To negative ideal solution The Euclidean distance of The target virtual power plant risk warning model includes a calculation formula for calculating the virtual power plant risk warning value: in, is the risk warning value of the virtual power plant.

2. The method according to claim 1, characterized in that The virtual power plant information to be evaluated is processed to generate a set of operating risk influencing factors of the target virtual power plant, including: Processing the virtual power plant information to be evaluated to generate physical attribute information of the virtual power plant information to be evaluated; Performing feature extraction processing on the physical attribute information of the virtual power plant information to be evaluated to generate a number of feature sample types; Performing feature screening processing on the several feature sample types to generate real-time feature sample data; A set of target virtual power plant operation risk influencing factors is generated based on several real-time characteristic sample data.

3. The method according to claim 1, characterized in that The training sample set is processed based on the preset processing rules to generate the training set and the validation set, including: Acquire other virtual power plant information matching the target virtual power plant risk identification information; Extract features of other virtual power plant information to generate feature data sets; Obtaining any number of data features in the feature data set; Generate adjacent features based on the distance between the any number of data features and other numbers of data features of the same category, wherein the adjacent features include a preset number of the any number of data features; Determining a sampling ratio based on the number of each data feature in the training set; Based on the sampling ratio, determining a sampling ratio; Sampling the adjacent features based on the sampling ratio to generate a preset number of sampling features; Based on any data feature and each sampling feature, generating a plurality of data groups, wherein each data group comprises a preset number of data samples, wherein each data group comprises a preset number of data samples, wherein at least one data sample comprises identification information; The plurality of data sets are processed to generate a training set and a validation set, wherein the training set and the validation set both include a number of data features.

4. The method according to claim 1, characterized in that After the risk warning value of the virtual power plant is processed to generate the risk level of the virtual power plant, it includes: Obtain the preset virtual power plant risk warning table; Processing the risk level of the virtual power plant based on the preset virtual power plant risk warning table to generate a target warning time and a warning level matching the target warning time; Processing the target warning moment and the warning level matching the target warning moment to generate a risk association factor, wherein the risk association factor is generated based on the virtual power plant operation risk impact factor corresponding to the same warning level and adjacent warning moments; Process risk-related factors and generate risk warning information.

5. An intelligent risk early warning device for a virtual power plant, characterized in that: For implementing the method according to claim 1, the device comprises: An acquisition module is used to acquire information of a virtual power plant to be evaluated; acquire an initial virtual power plant risk warning model that matches the risk identification information of a target virtual power plant and a training sample set that matches the initial virtual power plant risk warning model; A processing module is used to process the virtual power plant information to be evaluated and generate a set of target virtual power plant operation risk influencing factors; process the target virtual power plant operation risk influencing factors set and generate target virtual power plant risk identification information, wherein the target virtual power plant risk identification information includes positive ideal solutions and negative ideal solutions; process the training sample set based on preset processing rules to generate a training set and a verification set; process the initial virtual power plant risk warning model based on the training set and the verification set to generate a target virtual power plant risk warning model; process the positive ideal solution and the negative ideal solution based on the target virtual power plant risk warning model to generate a virtual power plant risk warning value; process the virtual power plant risk warning value to generate a virtual power plant risk level.

6. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; Wherein, the first processor is configured to execute the intelligent risk warning method for a virtual power plant as described in any one of claims 1 to 4 by executing the executable instructions.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the intelligent risk warning method for a virtual power plant as described in any one of claims 1 to 4 is implemented.

Images