Virtual power plant anomaly detection system and anomaly detection method thereof

Abstract

The invention discloses a virtual power plant anomaly detection system and an anomaly detection method thereof, and relates to the technical field of anomaly detection.The similarity coefficient between energy storage devices of every two virtual power plants is calculated, the energy storage devices in the virtual power plants are grouped according to the similarity coefficients, and a plurality of power plant groups are obtained; a similarity coefficient difference value between any two virtual power plant energy storage devices in each power plant group is smaller than a preset highest difference value; calculating a priority detection coefficient for each power plant group; the monitoring platform performs anomaly detection on the energy storage equipment of each power plant group according to a descending order of the priority detection coefficients; when anomaly detection is performed on the operation data of the energy storage equipment in the virtual power plant through the monitoring platform, the detection complexity can be reduced, the influence of disorder or misjudgment of the anomaly detection result of the energy storage equipment of the virtual power plant by the monitoring platform is reduced, and the anomaly detection result of the monitoring platform is ensured to be accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of anomaly detection, and in particular to a virtual power plant anomaly detection system and an anomaly detection method thereof. Background Art

[0002] A virtual power plant is a collection of multiple distributed energy resources (such as solar energy, wind power generation, energy storage equipment, electric vehicle charging piles, etc.), which realizes the optimal distribution and utilization of electricity through intelligent management and scheduling. In particular, the energy storage equipment of the virtual power plant, whether the energy storage equipment is abnormal or not is directly related to the flexibility and response speed of the virtual power plant scheduling and the stability of the entire power grid scheduling. Therefore, it is necessary to detect the abnormality of the energy storage equipment in the virtual power plant to ensure the stability of the power grid scheduling. In the energy storage equipment detection of the virtual power plant, the operating data of the energy storage equipment of multiple power plants will be uniformly collected and uploaded to the monitoring platform for centralized management and monitoring. The monitoring platform uses advanced anomaly detection technology and real-time collected data to determine whether there are any abnormal conditions. Anomaly detection methods mainly include threshold-based methods, statistical analysis-based methods, machine learning-based algorithms (such as K-means clustering, support vector machines, etc.), and time series analysis-based models (such as LSTM), etc. These methods can identify abnormal conditions that may occur in the operation of the energy storage equipment of the virtual power plant, provide early warning information, and help power plants and related operation and maintenance personnel take quick and effective response measures to ensure the stability of power supply and the safe operation of the power grid.

[0003] However, when performing anomaly detection on the operating data of energy storage devices in a virtual power plant through a monitoring platform, anomaly detection is generally performed on the operating data of each virtual power plant energy storage device at the same time. The data is huge and complex, which can easily lead to confusion or misjudgment of the monitoring platform's anomaly detection results for the virtual power plant energy storage devices, resulting in low accuracy of the monitoring platform's anomaly detection results. Summary of the invention

[0004] The purpose of the present invention is to solve the above-mentioned problems and to provide a virtual power plant anomaly detection system and an anomaly detection method thereof.

[0005] In a first aspect of the present invention, a method for detecting anomalies in a virtual power plant is first proposed, the method comprising: For the energy storage equipment of each virtual power plant, obtain the equipment type and working environment of the energy storage equipment in every two virtual power plants, and calculate the similarity coefficient of the corresponding two virtual power plants based on the equipment type and working environment; The energy storage devices in the virtual power plant are grouped according to the similarity coefficients of every two virtual power plants to obtain a number of power plant groups; and the difference in similarity coefficients between any two virtual power plant energy storage devices in each power plant group is less than a preset maximum difference; For each power plant group, the historical abnormal times and historical discharge times of the energy storage equipment in each virtual power plant in each power plant group are obtained to calculate the priority detection coefficient of each power plant group; The monitoring platform performs abnormal detection on the energy storage equipment of each power plant group in the order of priority detection coefficient from large to small.

[0006] Optionally, the steps of obtaining the device type and working environment of the energy storage devices in every two virtual power plants, and calculating the similarity values ​​of the corresponding two virtual power plants according to the device type and the working environment are: Obtain the type of equipment type of the energy storage equipment in each virtual power plant, and collect the equipment type set of the corresponding energy storage equipment; And the Jaccard similarity between the two virtual power plants is calculated based on the device type set of energy storage devices in the two virtual power plants; The types of equipment with the same type in the equipment type set of the energy storage equipment in the two virtual power plants are recorded as common types, and the minimum number of the equipment in the energy storage equipment of the two virtual power plants corresponding to each common type is recorded as the common number of the common type; Add up the common categories of all categories, and divide the sum by the total number of energy storage devices in the two virtual power plants to obtain the quantity similarity between the two virtual power plants; According to the Jaccard similarity and quantity similarity between the two virtual power plants, the equipment similarity values ​​of the two virtual power plants are obtained: The similarity coefficients of the two virtual power plants are calculated based on the equipment similarity values ​​and working environment.

[0007] Optionally, the steps of calculating the similarity coefficients corresponding to the two virtual power plants according to the equipment similarity values ​​and the working environment are: For the energy storage devices in the two virtual power plants, environmental data of the environments in which the two energy storage devices are located within a preset time period are obtained, and the environmental data of the environments in which the energy storage devices in the two virtual power plants are located are preprocessed; Construct a distance matrix, in which each element is the distance between an environmental data point of the environment in which the energy storage device in one virtual power plant is located and an environmental data point of the environment in which the energy storage device in another virtual power plant is located; A dynamic programming algorithm is used to calculate the shortest path in the distance matrix to find the best match between the environmental data sequences of the environments where the energy storage devices in the two virtual power plants are located; Based on the calculated shortest path, the environmental data sequences of the environments where the energy storage devices in the two virtual power plants are located are aligned; According to the aligned environmental data sequences of the environments in which the energy storage devices in the two virtual power plants are located, the similarity between them is calculated, and the calculated similarity is used as the environmental similarity value of the energy storage devices in the corresponding two virtual power plants; The similarity coefficients of the two virtual power plants are calculated based on the equipment similarity values ​​and the environment similarity values.

[0008] Optionally, the steps of calculating the similarity coefficients corresponding to the two virtual power plants according to the equipment similarity value and the environment similarity value are: ; In the formula, is the similarity coefficient of the two virtual power plants, , are the device similarity value and the environment similarity value respectively, They are , The preset scaling factor of Both are greater than 0.

[0009] Optionally, for each power plant group, the steps of obtaining the historical abnormal number and the historical discharge number of the energy storage device in each virtual power plant in each power plant group to calculate the priority detection coefficient of each power plant group are: Obtain the total number of abnormalities detected in the historical detection records of each virtual power plant energy storage device in each power plant group, and divide the total number of abnormalities by the total working time of the energy storage device to obtain the abnormal frequency of the energy storage device; Obtain the capacity of the energy storage device in each virtual power plant, and multiply the capacity of the energy storage device by the corresponding abnormal frequency to obtain the weighted abnormal value of the energy storage device in the corresponding virtual power plant; add the weighted abnormal values ​​of the energy storage device in each virtual power plant in each power plant group to obtain the total weighted abnormal value of the corresponding power plant group; The priority detection coefficient of each power plant group is calculated according to the weighted total abnormal value of each power plant group and the historical discharge times of the energy storage equipment in each virtual power plant.

[0010] Optionally, the step of calculating the priority detection coefficient of each power plant group according to the weighted total abnormal value of each power plant group and the historical discharge times of the energy storage device in each virtual power plant is: Obtain the historical discharge times of the energy storage device in each virtual power plant of each power plant group, and obtain the actual discharge capacitance and the capacitance before discharge during each discharge, divide the actual discharge capacitance by the capacitance before discharge to obtain the discharge depth; and calculate the mean discharge depth of the energy storage device in each virtual power plant as the average discharge depth; According to the discharge depth of each energy storage device in each virtual power plant, the standard deviation of the corresponding discharge depth is calculated, and the standard deviation is used as the unstable value of the discharge depth of the energy storage device in each virtual power plant; The discharge frequency of the energy storage equipment in each virtual power plant is obtained, and the discharge frequency is normalized to obtain the discharge frequency value. The discharge influence coefficient of each power plant group is calculated according to the discharge frequency value, average discharge depth and discharge depth instability value. The calculation formula is: In the formula, is the discharge influence coefficient of the power plant group, Indicates the order number of the energy storage equipment in the virtual power plant in the power plant group. Indicates the total number of energy storage devices in the virtual power plant in the power plant group; , and They represent the average discharge depth, the unstable value of discharge depth and the discharge frequency value respectively; , , They are , and Preset weight values, and , , All are greater than 0; The priority detection coefficient of each power plant group is calculated based on the weighted total abnormal value and discharge influence coefficient of each power plant group.

[0011] Optionally, the step of calculating the priority detection coefficient of each power plant group according to the weighted total abnormal value and the discharge influence coefficient of each power plant group is: ; In the formula, For each power plant group, the priority detection coefficient, , are the weighted total abnormal value and discharge influence coefficient of each power plant group, They are , The preset scaling factor of Both are greater than 0.

[0012] In a second aspect of the present invention, a virtual power plant anomaly detection system is provided, the system comprising: Similarity module: For the energy storage equipment of each virtual power plant, the device type and working environment of the energy storage equipment in every two virtual power plants are obtained, and the similarity coefficient of the corresponding two virtual power plants is calculated based on the device type and working environment; Grouping module: grouping the energy storage devices in the virtual power plant according to the similarity coefficients of every two virtual power plants to obtain power plant groups; and the difference in similarity coefficients between any two virtual power plant energy storage devices in each power plant group is less than a preset maximum difference; Priority detection module: For each power plant group, the historical abnormal number and historical discharge number of energy storage equipment in each virtual power plant in each power plant group are obtained to calculate the priority detection coefficient of each power plant group; Abnormal detection module: The monitoring platform performs abnormal detection on the energy storage equipment of each power plant group in the order of priority detection coefficient from large to small.

[0013] Beneficial effects of the present invention: The present invention proposes a virtual power plant anomaly detection system and an anomaly detection method thereof, which calculates the similarity coefficient between energy storage devices of every two virtual power plants, and groups the energy storage devices in the virtual power plants according to the similarity coefficient of every two virtual power plants, so as to obtain power plant groups, and the difference in similarity coefficient between any two virtual power plant energy storage devices in each power plant group is less than a preset maximum difference; and calculates the priority detection coefficient for each power plant group; the monitoring platform performs anomaly detection on the energy storage devices of each power plant group in the order of the priority detection coefficient from large to small; in this way, when the operating data of the energy storage devices in the virtual power plant are detected for anomalies through the monitoring platform, the operating data of each virtual power plant energy storage device can be reasonably detected for anomalies in sequence, thereby reducing the complexity of detection, reducing the influence of confusion or misjudgment of the abnormal detection results of the virtual power plant energy storage devices by the monitoring platform, and ensuring the accuracy of the abnormal detection results of the monitoring platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present invention will be further described below in conjunction with the accompanying drawings.

[0015] Figure 1 is a flow chart of a virtual power plant anomaly detection method; Figure 2 A framework diagram of a virtual power plant anomaly detection system. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in the field without making any creative work shall fall within the scope of protection of the present invention.

[0018] The embodiment of the present invention provides a method for detecting abnormalities in a virtual power plant. Figure 1 , Figure 1 A flowchart of a virtual power plant anomaly detection method provided by an embodiment of the present invention. The method comprises the following steps: For the energy storage equipment of each virtual power plant, obtain the equipment type and working environment of the energy storage equipment in every two virtual power plants, and calculate the similarity coefficient of the corresponding two virtual power plants based on the equipment type and working environment; The energy storage devices in the virtual power plant are grouped according to the similarity coefficients of every two virtual power plants to obtain a number of power plant groups; and the difference in similarity coefficients between any two virtual power plant energy storage devices in each power plant group is less than a preset maximum difference; For each power plant group, the historical abnormal times and historical discharge times of the energy storage equipment in each virtual power plant in each power plant group are obtained to calculate the priority detection coefficient of each power plant group; The monitoring platform performs abnormal detection on the energy storage equipment of each power plant group in the order of priority detection coefficient from large to small.

[0019] Based on a virtual power plant anomaly detection method provided by an embodiment of the present invention, through the above-mentioned method, when the operating data of the energy storage equipment in the virtual power plant is detected for anomalies through the monitoring platform, the operating data of each virtual power plant energy storage device can be reasonably detected for anomalies in sequence, thereby reducing the complexity of detection, reducing the impact of confusion or misjudgment of the abnormal detection results of the virtual power plant energy storage equipment by the monitoring platform, and ensuring the accuracy of the abnormal detection results of the monitoring platform.

[0020] In one embodiment, the steps of obtaining the device type and working environment of the energy storage devices in every two virtual power plants and calculating the similarity values ​​of the corresponding two virtual power plants according to the device type and working environment are as follows: Obtain the type of equipment type of the energy storage equipment in each virtual power plant, and collect the equipment type set of the corresponding energy storage equipment; And the Jaccard similarity between the two virtual power plants is calculated based on the device type set of energy storage devices in the two virtual power plants; The types of equipment with the same type in the equipment type set of the energy storage equipment in the two virtual power plants are recorded as common types, and the minimum number of the equipment in the energy storage equipment of the two virtual power plants corresponding to each common type is recorded as the common number of the common type; Add up the common categories of all categories, and divide the sum by the total number of energy storage devices in the two virtual power plants to obtain the quantity similarity between the two virtual power plants; According to the Jaccard similarity and quantity similarity between the two virtual power plants, the equipment similarity values ​​of the two virtual power plants are obtained: The similarity coefficients of the two virtual power plants are calculated based on the equipment similarity values ​​and working environment.

[0021] It should be noted that the device types of virtual power plant energy storage devices can include many different types of energy storage devices, such as lithium batteries, lead-acid batteries, supercapacitors, etc.; these device types reflect the different technologies and applications of energy storage systems, and have different energy storage and release characteristics; in the above calculation process, the data involved mainly include the type and quantity of each virtual power plant energy storage device, which is usually obtained from the equipment installation records in the monitoring platform of the virtual power plant; Jaccard similarity is a statistic used to measure the similarity of two sets, defined as the size of the intersection of the two sets divided by the size of the union of the two sets; the similarity of the two sets is evaluated by comparing the ratio of common elements to all elements in the two sets; specifically for the example of virtual power plant energy storage devices, Jaccard similarity can be used to measure the similarity of energy storage device types in two virtual power plants.

[0022] The steps to obtain the equipment similarity values ​​of the two virtual power plants based on the Jaccard similarity and quantity similarity between the two virtual power plants are as follows: , where is the equipment similarity value of the two virtual power plants, , They are Jaccard similarity and quantity similarity, They are , The preset scaling factor of are greater than 0; in addition, It is set by professionals according to the actual situation. Generally, The sum of is 1, for example They can be 0.55, 0.45, or other numbers, without limitation.

[0023] It should be noted that when the equipment similarity value of the two virtual power plants is larger, the monitoring platform will detect more accurately when the data is uploaded to the monitoring platform for anomaly detection. The reason is that when the equipment similarity value of the two virtual power plants is larger, it means that the types and quantities of their energy storage devices are relatively close, which to a certain extent indicates that the equipment of the two power plants has a high consistency in operation mode, performance and response characteristics. Therefore, when the monitoring platform detects anomalies on these devices, the detection results will be more accurate. The reason is that a higher similarity value can help the monitoring platform better understand the normal operation mode and expected behavior of the equipment, and then more accurately identify which data deviates from the normal range; if the equipment characteristics of the two virtual power plants are quite different, the detection system may need to make complex adjustments and optimizations in multiple dimensions, increasing the risk of misjudgment or missed judgment. When the equipment similarity value is high, the monitoring platform can rely on the historical data and typical behavior of similar equipment groups for more detailed analysis, thereby improving the reliability and accuracy of anomaly detection. In short, high similarity provides a stable benchmark for anomaly detection, improving the response speed of the system and the accuracy of fault diagnosis.

[0024] In one embodiment, the steps of calculating the similarity coefficients corresponding to two virtual power plants according to the equipment similarity values ​​and the working environment are as follows: For the energy storage devices in the two virtual power plants, environmental data of the environments in which the two energy storage devices are located within a preset time period are obtained, and the environmental data of the environments in which the energy storage devices in the two virtual power plants are located are preprocessed; Construct a distance matrix, in which each element is the distance between an environmental data point of the environment in which the energy storage device in one virtual power plant is located and an environmental data point of the environment in which the energy storage device in another virtual power plant is located; A dynamic programming algorithm is used to calculate the shortest path in the distance matrix to find the best match between the environmental data sequences of the environments where the energy storage devices in the two virtual power plants are located; Based on the calculated shortest path, the environmental data sequences of the environments where the energy storage devices in the two virtual power plants are located are aligned; According to the aligned environmental data sequences of the environments in which the energy storage devices in the two virtual power plants are located, the similarity between them is calculated, and the calculated similarity is used as the environmental similarity value of the energy storage devices in the corresponding two virtual power plants; The similarity coefficients of the two virtual power plants are calculated based on the equipment similarity values ​​and the environment similarity values.

[0025] It should be noted that the preset time period is set by professionals based on actual conditions, and no specific restrictions or elaborations are made; for each energy storage device of the two virtual power plants, the environmental data of the environment in which it is located within the preset time period is collected, and relevant meteorological data can be obtained through the external meteorological data provider where the energy storage device is located. These environmental data include temperature, humidity, air pressure, wind speed, etc. These factors will affect the working status and performance of the energy storage device, and thus affect the abnormal detection of the equipment; in order to make the data effectively comparable, the environmental data needs to be preprocessed, which includes denoising, standardization or normalization processing to ensure the comparability between different data sources; after the environmental data is preprocessed, a distance matrix is ​​constructed, in which each element represents the distance between the environmental data points of the two energy storage devices. In order to calculate the "distance" between environmental data points, Euclidean distance, Manhattan distance or other distance measurement methods suitable for environmental data types can be used; after constructing the distance matrix, a dynamic programming algorithm is used to calculate the shortest path in the distance matrix, with the aim of finding the best match between the environmental data sequences of the environments in which the energy storage devices in the two virtual power plants are located; the dynamic time warping algorithm can effectively handle the nonlinear alignment problem in time series data, ensuring that even in the case of time misalignment, the minimum matching error between the two sets of data can be found; the shortest path calculated by dynamic programming can align the environmental data sequences of the energy storage devices of the two virtual power plants. This alignment process enables the environmental data points of the two devices at different times to correspond, reducing the errors caused by time or data misalignment; finally, based on the aligned environmental data sequences, the environmental similarity between the two virtual power plant energy storage devices can be calculated; common calculation methods include calculating the root mean square error (RMSE) and Pearson correlation coefficient between the aligned sequences. These indicators can reflect the degree of similarity between the environments in which the two energy storage devices are located. For example, the closer the Pearson correlation coefficient is to 1, the higher the similarity between the two devices in the environment.

[0026] It should be noted that when the environmental similarity values ​​of the two virtual power plants are greater, the monitoring platform will detect more accurately when they are uploaded to the monitoring platform for anomaly detection. The reason is that a high environmental similarity value means that the energy storage devices of the two virtual power plants are operating under similar environmental conditions and may face similar external influencing factors, such as temperature changes, humidity fluctuations, or voltage fluctuations. Therefore, the monitoring platform can make more accurate anomaly predictions and identifications based on these similar environmental characteristics. Environmental factors often have an important impact on the performance and stability of energy storage equipment. When two devices operate in similar environments, their abnormal patterns and frequencies may also be similar, which allows the monitoring platform to quickly identify potential abnormalities through comparison and model training, avoiding misjudgments or missed judgments due to equipment differences or inconsistent environmental factors. Therefore, the higher the environmental similarity, the more similar data features the monitoring platform can use when detecting anomalies, thereby improving detection accuracy and response speed.

[0027] In one embodiment, the steps of calculating the similarity coefficients corresponding to two virtual power plants according to the equipment similarity value and the environment similarity value are as follows: ; In the formula, is the similarity coefficient of the two virtual power plants, , are the device similarity value and the environment similarity value respectively, They are , The preset scaling factor of All are greater than 0; It should be noted that It is set by professionals according to the actual situation. Generally, The sum of is 1, for example They can be 0.5, 0.5, or other numbers respectively, and are not specifically limited.

[0028] In one embodiment, the energy storage devices in the virtual power plant are grouped according to the similarity coefficients of every two virtual power plants to obtain power plant groups; and the difference in similarity coefficients between any two virtual power plant energy storage devices in each power plant group is less than a preset maximum difference; Grouping the energy storage devices in the virtual power plant according to the similarity coefficient of every two virtual power plants is actually quantifying the similarity between the energy storage devices through similarity, so as to effectively perform subsequent anomaly detection. The core goal of this step is to group energy storage devices with high similarity together so that when the monitoring platform performs anomaly detection, it can focus on those devices with similar environment and equipment characteristics, thereby improving the accuracy and efficiency of detection.

[0029] In the specific grouping process, the similarity coefficient between each two virtual power plants is first calculated to measure the similarity of their equipment and environment. If the similarity coefficient of two virtual power plants is less than a preset maximum difference (threshold), the two virtual power plants and their energy storage devices are grouped into the same group. This preset threshold (maximum difference) is used to ensure that there is sufficient similarity between the virtual power plants within each group, so as to avoid mistakenly classifying energy storage devices with too large differences into the same group; specifically, if the difference in the similarity coefficient between the two virtual power plants is large, it means that their energy storage devices are very different in terms of equipment type, working environment, etc., and such devices should not be placed in the same group for processing; and if their similarity coefficient is small, it can be considered that their energy storage devices are very similar in certain features and are combined into the same group for centralized monitoring and detection.

[0030] In one implementation, the benefit of such grouping is that by grouping energy storage devices with high similarity into the same group, the management efficiency of the monitoring platform for each virtual power plant energy storage device can be effectively improved. First, the grouped devices can reduce errors and inaccurate judgments caused by equipment differences under similar environments and equipment characteristics, ensuring that the monitoring system can more accurately identify potential faults and abnormal conditions. Secondly, through grouping, the monitoring platform can formulate corresponding detection strategies and priorities according to the characteristics of different groups to avoid indiscriminate full-volume detection, which not only improves the accuracy of detection, but also saves computing and processing resources. In addition, grouping also helps to respond to potential risks more quickly. For example, when an energy storage device in a group is abnormal, the root cause of the problem can be quickly determined based on the common characteristics of the group, improving the timeliness of emergency response. In general, such a grouping mechanism makes the monitoring platform more flexible and efficient when facing large and diverse energy storage devices, and can improve the overall efficiency of management and operation while ensuring safety.

[0031] In one embodiment, for each power plant group, the steps of obtaining the historical abnormal times and the historical discharge times of the energy storage equipment in each virtual power plant in each power plant group and calculating the priority detection coefficient of each power plant group are as follows: Obtain the total number of abnormalities detected in the historical detection records of each virtual power plant energy storage device in each power plant group, and divide the total number of abnormalities by the total working time of the energy storage device to obtain the abnormal frequency of the energy storage device; Obtain the capacity of the energy storage device in each virtual power plant, and multiply the capacity of the energy storage device by the corresponding abnormal frequency to obtain the weighted abnormal value of the energy storage device in the corresponding virtual power plant; add the weighted abnormal values ​​of the energy storage device in each virtual power plant in each power plant group to obtain the total weighted abnormal value of the corresponding power plant group; The priority detection coefficient of each power plant group is calculated according to the weighted total abnormal value of each power plant group and the historical discharge times of the energy storage equipment in each virtual power plant.

[0032] It should be noted that the total number of abnormalities in historical detection records is usually obtained through a monitoring system or maintenance records. The monitoring platform will record the failures and abnormalities of each energy storage device, including downtime, performance degradation, etc. When obtaining the total working time of the energy storage device, it can be extracted through the equipment's operation records, life cycle logs, or working time data accumulated in the energy management system. The capacity of the energy storage device is usually obtained through the equipment's technical specifications or equipment management system, which are usually provided by the equipment manufacturer and recorded in the system. Finally, the calculation of the weighted outlier value requires combining the actual operating data of the equipment with the detection history, and weighting the capacity and abnormal frequency through an algorithm. All of these data are automatically collected, summarized, and processed through an integrated energy management platform or monitoring system.

[0033] It should be noted that when the total weighted anomaly value of each power plant group is larger, the virtual power plant in the corresponding power plant group will be placed higher in the order of anomaly detection through the monitoring platform. The reason is that when the total weighted anomaly value of each power plant group is larger, it means that the frequency of abnormalities in the energy storage equipment in the virtual power plant in the power plant group is higher, and the capacity of these energy storage devices is larger, so their importance and impact in normal operation are also greater. The total weighted anomaly value not only reflects the failure frequency of the equipment, but also takes into account the capacity of the equipment, which means that the energy storage equipment of the power plant may have a more significant impact on the stability of the power grid and the flexibility of the virtual power plant dispatch. Since these devices have a higher potential failure risk and may cause a large fluctuation in power supply when a failure occurs, the monitoring platform will give priority to anomaly detection for power plant groups with higher total weighted anomaly values, so as to ensure that the problem can be discovered as early as possible and timely measures can be taken to avoid serious impact on the stability of the power grid. Through such sequential detection, the accuracy and response speed of detection can be effectively improved, and potential power failures caused by ignoring high-risk equipment can be reduced.

[0034] In one implementation, the benefit of analyzing the weighted total abnormal value of each power plant group for the abnormal detection results of the virtual power plant energy storage equipment by the monitoring platform is that the weighted total abnormal value of each power plant group can provide an objective and comprehensive basis for the evaluation of the priority of abnormal detection for the monitoring platform. By combining the abnormal frequency and capacity of the energy storage equipment, the platform can not only identify the equipment with a high failure rate, but also consider the importance of the equipment, thereby effectively improving the efficiency and accuracy of abnormal detection. Specifically, when the weighted total abnormal value is large, it indicates that the energy storage equipment in the power plant group has a high abnormal risk and may have a greater impact on the stability of the power system. Prioritizing the detection of these devices helps the platform to discover potential fault problems at the first time, avoiding grid failures or energy supply interruptions due to ignoring high-risk equipment. Therefore, this method of calculating the weighted total abnormal value can significantly improve the response speed of the monitoring platform, warn of possible abnormalities in advance, and ensure that the operation of the power system is more stable and reliable.

[0035] In one embodiment, the step of calculating the priority detection coefficient of each power plant group according to the weighted total abnormal value of each power plant group and the historical discharge times of the energy storage device in each virtual power plant is: Obtain the historical discharge times of the energy storage device in each virtual power plant of each power plant group, and obtain the actual discharge capacitance and the capacitance before discharge during each discharge, divide the actual discharge capacitance by the capacitance before discharge to obtain the discharge depth; and calculate the mean discharge depth of the energy storage device in each virtual power plant as the average discharge depth; According to the discharge depth of each energy storage device in each virtual power plant, the standard deviation of the corresponding discharge depth is calculated, and the standard deviation is used as the unstable value of the discharge depth of the energy storage device in each virtual power plant; The discharge frequency of the energy storage equipment in each virtual power plant is obtained, and the discharge frequency is normalized to obtain the discharge frequency value. The discharge influence coefficient of each power plant group is calculated according to the discharge frequency value, average discharge depth and discharge depth instability value. The calculation formula is: , where is the discharge influence coefficient of the power plant group, Indicates the order number of the energy storage equipment in the virtual power plant in the power plant group. Indicates the total number of energy storage devices in the virtual power plant in the power plant group; , and They represent the average discharge depth, the unstable value of discharge depth and the discharge frequency value respectively; , , They are , and Preset weight values, and , , All are greater than 0; The priority detection coefficient of each power plant group is calculated based on the weighted total abnormal value and discharge influence coefficient of each power plant group.

[0036] It should be noted that , , It is set by professionals according to the actual situation. Generally, , , The sum of is 1, for example , , They can be 0.3, 0.3, 0.4 respectively, or other numbers, without specific limitation.

[0037] It should be noted that in the above calculation process, the main data acquisition method involved is first to obtain the historical discharge times of energy storage devices in each virtual power plant through the control system or monitoring platform of the energy storage device. These systems will record detailed information of each discharge, including the start and end time of the discharge and the amount of electricity discharged. The actual discharge capacitance and the capacitance before discharge can be monitored in real time by the battery management system (BMS) of the energy storage device. These data provide battery status information of the device during the discharge process. The calculation of the discharge depth is obtained by mathematically processing the ratio of the actual discharge capacitance to the undischarged capacitance, while the mean and standard deviation of the discharge depth are calculated by statistical analysis tools (such as pandas or NumPy libraries in Python), which reflect the discharge mode and stability of the device. The discharge frequency is obtained by calculating the number of discharges of the device in a certain period of time, which can usually be directly obtained on the monitoring platform. For the normalization of the discharge frequency, common standardization methods (such as minimum-maximum normalization or Z-Score normalization) are used to adjust it to a unified scale for subsequent calculations. By acquiring these key data and combining them with preset weight coefficients, the discharge impact coefficient of each power plant group can be accurately calculated, thereby providing strong support for the power plant's equipment scheduling, maintenance decisions and anomaly detection.

[0038] It should be noted that when the discharge influence coefficient of each power plant group is larger, the virtual power plant in the corresponding power plant group will be placed higher in the order of abnormality detection through the monitoring platform. The reason is that when the discharge influence coefficient of each power plant group is larger, it means that the virtual power plant energy storage equipment in the power plant group has experienced a higher frequency and depth of discharge during the discharge process, and the instability of its discharge is also higher. This indicates that the health of these energy storage devices is relatively poor and there may be a higher risk of failure. Because energy storage equipment is prone to large battery loss and temperature rise during frequent and deep discharge, the probability of equipment aging or failure increases. Therefore, the virtual power plant energy storage equipment in the power plant group with a higher discharge influence coefficient should be given priority for abnormality detection. This priority ranking can help the monitoring platform detect abnormalities in time before potential failures occur in the equipment, thereby reducing the risk of failures and improving the safety and stability of the power grid. Through this comprehensive evaluation based on discharge depth, frequency and instability, the monitoring platform can make resource allocation and maintenance decisions more effectively to ensure the reliability of power system operation.

[0039] In one implementation, the benefits of analyzing the discharge influence coefficient of each power plant group for abnormal detection results of the monitoring platform for the virtual power plant energy storage equipment are: by calculating the discharge influence coefficient, the monitoring platform can give priority to detecting these devices before potential failures occur, so as to perform maintenance or adjustments before the equipment fails or performance declines; this method can not only reduce system risks and avoid power supply interruptions caused by energy storage equipment failures, but also extend the service life of equipment and reduce maintenance and replacement costs by identifying problem equipment in advance; by closely linking detection priority with discharge conditions, the monitoring platform can concentrate resources on the equipment that needs the most attention, improve the maintenance efficiency and reliability of the entire power system, and ultimately ensure the stability and security of the power grid.

[0040] In one embodiment, the step of calculating the priority detection coefficient of each power plant group according to the weighted total abnormal value and the discharge influence coefficient of each power plant group is: ; In the formula, For each power plant group, the priority detection coefficient, , are the weighted total abnormal value and discharge influence coefficient of each power plant group, They are , The preset scaling factor of All are greater than 0; It should be noted that It is set by professionals according to the actual situation. Generally, The sum of is 1, for example They can be 0.3, 0.7, or other numbers respectively, and are not specifically limited.

[0041] In one embodiment, the monitoring platform performs anomaly detection on the energy storage devices of each power plant group in the order of priority detection coefficient from large to small. By calculating the priority detection coefficient according to the weighted total anomaly value and the discharge influence coefficient of each power plant group, the monitoring platform can accurately and preferentially identify those energy storage devices that may have higher risks and perform timely anomaly detection; the weighted total anomaly value can reflect the potential problems and failure frequency of the equipment in operation, while the discharge influence coefficient measures the use pressure and possible health risks of the energy storage equipment. When these two indicators are combined, it is possible to effectively identify those devices that have both a history of anomaly detection and frequently experience high-load discharge. These devices are prone to performance degradation or failure due to long-term high-frequency discharge and unstable discharge depth. Therefore, prioritizing the detection of these devices can help avoid potential systemic risks and fault expansion, thereby ensuring the stable operation of the power grid; at the same time, the method of sorting priority detection coefficients from large to small can optimize resource allocation, so that the monitoring platform can focus on the power plant groups that need the most attention, improve detection efficiency, avoid invalid detection, improve the accuracy and response speed of abnormal detection, and reduce confusion or misjudgment of abnormal detection results, thereby ensuring the safety and stability of power supply to the greatest extent.

[0042] It should be noted that the monitoring platform usually relies on a series of comprehensive data analysis and real-time monitoring technologies when performing abnormal detection on the energy storage equipment in the virtual power plant of each power plant group in the order of priority detection coefficient from large to small. First, the platform will monitor the energy storage equipment in real time and collect various key indicators, such as battery voltage, current, load, output power, etc. These data will be transmitted to the platform's analysis system and compared with historical data to identify possible abnormal patterns of the equipment; for example, abnormal voltage fluctuations, increased load, large output power fluctuations, etc., may all be signals of impending equipment failure; the monitoring platform will first perform detailed health checks on equipment with higher weighted abnormal total values ​​and higher discharge frequencies according to the order of priority detection coefficients; these devices are usually set as high-risk targets first, and the platform will start more sophisticated diagnostic mechanisms, such as predictive maintenance algorithms, machine learning models, etc., to further analyze the abnormal trends of the equipment and predict potential failures; based on the detection results, the platform will automatically generate a detailed diagnostic report and automatically execute corresponding emergency response strategies according to the severity of the detection, such as shutdown inspection, adjustment of operating parameters or arrangement of maintenance, so as to effectively prevent the impact of equipment failure on the power grid.

[0043] Based on the same inventive concept, the embodiment of the present invention also provides a virtual power plant abnormality detection system. Figure 2 , Figure 2A framework diagram of a virtual power plant anomaly detection system provided by an embodiment of the present invention, the system comprising: Similarity module: For the energy storage equipment of each virtual power plant, the device type and working environment of the energy storage equipment in every two virtual power plants are obtained, and the similarity coefficient of the corresponding two virtual power plants is calculated based on the device type and working environment; Grouping module: grouping the energy storage devices in the virtual power plant according to the similarity coefficients of every two virtual power plants to obtain power plant groups; and the difference in similarity coefficients between any two virtual power plant energy storage devices in each power plant group is less than a preset maximum difference; Priority detection module: For each power plant group, the historical abnormal number and historical discharge number of energy storage equipment in each virtual power plant in each power plant group are obtained to calculate the priority detection coefficient of each power plant group; Abnormal detection module: The monitoring platform performs abnormal detection on the energy storage equipment of each power plant group in the order of priority detection coefficient from large to small.

[0044] Based on a virtual power plant anomaly detection system provided by an embodiment of the present invention, through the above-mentioned method, when the operating data of the energy storage equipment in the virtual power plant is detected for anomalies through the monitoring platform, the operating data of each virtual power plant energy storage device can be reasonably detected for anomalies in sequence, thereby reducing the complexity of detection, reducing the impact of confusion or misjudgment of the abnormal detection results of the virtual power plant energy storage equipment by the monitoring platform, and ensuring the accuracy of the abnormal detection results of the monitoring platform.

[0045] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be used to artificially limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A virtual power plant anomaly detection method, characterized in that: The following steps are involved: For the energy storage equipment of each virtual power plant, obtain the equipment type and working environment of the energy storage equipment in every two virtual power plants, and calculate the similarity coefficient of the corresponding two virtual power plants based on the equipment type and working environment; The energy storage devices in the virtual power plant are grouped according to the similarity coefficients of every two virtual power plants to obtain a number of power plant groups; and the difference in similarity coefficients between any two virtual power plant energy storage devices in each power plant group is less than a preset maximum difference; For each power plant group, the historical abnormal times and historical discharge times of the energy storage equipment in each virtual power plant in each power plant group are obtained to calculate the priority detection coefficient of each power plant group; The monitoring platform performs abnormal detection on the energy storage equipment of each power plant group in the order of priority detection coefficient from large to small.

2. A virtual power plant anomaly detection method according to claim 1, characterized in that: The steps for obtaining the equipment type and working environment of the energy storage equipment in each of the two virtual power plants and calculating the similarity value of the corresponding two virtual power plants according to the equipment type and working environment are as follows: Obtain the type of equipment type of the energy storage equipment in each virtual power plant, and collect the equipment type set of the corresponding energy storage equipment; And the Jaccard similarity between the two virtual power plants is calculated based on the device type set of energy storage devices in the two virtual power plants; The types of equipment with the same type in the equipment type set of the energy storage equipment in the two virtual power plants are recorded as common types, and the minimum number of the equipment in the energy storage equipment of the two virtual power plants corresponding to each common type is recorded as the common number of the common type; Add up the common categories of all categories, and divide the sum by the total number of energy storage devices in the two virtual power plants to obtain the quantity similarity between the two virtual power plants; According to the Jaccard similarity and quantity similarity between the two virtual power plants, the equipment similarity values ​​of the two virtual power plants are obtained: The similarity coefficients of the two virtual power plants are calculated based on the equipment similarity values ​​and working environment.

3. A virtual power plant anomaly detection method according to claim 2, characterized in that: The steps to calculate the similarity coefficients of the two virtual power plants according to the equipment similarity values ​​and the working environment are as follows: For the energy storage devices in the two virtual power plants, environmental data of the environments in which the two energy storage devices are located within a preset time period are obtained, and the environmental data of the environments in which the energy storage devices in the two virtual power plants are located are preprocessed; Construct a distance matrix, in which each element is the distance between an environmental data point of the environment in which the energy storage device in one virtual power plant is located and an environmental data point of the environment in which the energy storage device in another virtual power plant is located; A dynamic programming algorithm is used to calculate the shortest path in the distance matrix to find the best match between the environmental data sequences of the environments where the energy storage devices in the two virtual power plants are located; Based on the calculated shortest path, the environmental data sequences of the environments where the energy storage devices in the two virtual power plants are located are aligned; According to the aligned environmental data sequences of the environments in which the energy storage devices in the two virtual power plants are located, the similarity between them is calculated, and the calculated similarity is used as the environmental similarity value of the energy storage devices in the corresponding two virtual power plants; The similarity coefficients of the two virtual power plants are calculated based on the equipment similarity values ​​and the environment similarity values.

4. A virtual power plant anomaly detection method according to claim 3, characterized in that: The steps for calculating the similarity coefficients of the two virtual power plants according to the equipment similarity value and the environment similarity value are as follows: ; In the formula, is the similarity coefficient of the two virtual power plants, , are the device similarity value and the environment similarity value respectively, They are , The preset scaling factor of Both are greater than 0.

5. The method for detecting anomalies in a virtual power plant according to claim 1, characterized in that: For each power plant group, the steps of obtaining the historical abnormal times and historical discharge times of the energy storage equipment in each virtual power plant in each power plant group and calculating the priority detection coefficient of each power plant group are as follows: Obtain the total number of abnormalities detected in the historical detection records of each virtual power plant energy storage device in each power plant group, and divide the total number of abnormalities by the total working time of the energy storage device to obtain the abnormal frequency of the energy storage device; Obtain the capacity of the energy storage device in each virtual power plant, and multiply the capacity of the energy storage device by the corresponding abnormal frequency to obtain the weighted abnormal value of the energy storage device in the corresponding virtual power plant; add the weighted abnormal values ​​of the energy storage device in each virtual power plant in each power plant group to obtain the total weighted abnormal value of the corresponding power plant group; The priority detection coefficient of each power plant group is calculated based on the weighted total abnormal value of each power plant group and the historical discharge times of the energy storage equipment in each virtual power plant.

6. A virtual power plant anomaly detection method according to claim 5, characterized in that: The steps for calculating the priority detection coefficient of each power plant group according to the total weighted abnormal value of each power plant group and the historical discharge times of the energy storage equipment in each virtual power plant are as follows: Obtain the historical discharge times of the energy storage device in each virtual power plant of each power plant group, and obtain the actual discharge capacitance and the capacitance before discharge during each discharge, and divide the actual discharge capacitance by the capacitance before discharge to obtain the discharge depth; And calculate the mean discharge depth of the energy storage equipment in each virtual power plant as the average discharge depth; According to the discharge depth of each energy storage device in each virtual power plant, the standard deviation of the corresponding discharge depth is calculated, and the standard deviation is used as the unstable value of the discharge depth of the energy storage device in each virtual power plant; The discharge frequency of the energy storage equipment in each virtual power plant is obtained, and the discharge frequency is normalized to obtain the discharge frequency value. The discharge influence coefficient of each power plant group is calculated according to the discharge frequency value, average discharge depth and discharge depth instability value. The calculation formula is: , where is the discharge influence coefficient of the power plant group, Indicates the order number of the energy storage equipment in the virtual power plant in the power plant group. Indicates the total number of energy storage devices in the virtual power plant in the power plant group; , and They represent the average discharge depth, the unstable value of discharge depth and the discharge frequency value respectively; , , They are , and Preset weight values, and , , All are greater than 0; The priority detection coefficient of each power plant group is calculated based on the weighted total abnormal value and discharge influence coefficient of each power plant group.

7. A virtual power plant anomaly detection method according to claim 6, characterized in that: The steps for calculating the priority detection coefficient of each power plant group according to the weighted total abnormal value and discharge influence coefficient of each power plant group are: In the formula, For each power plant group, the priority detection coefficient, , are the weighted total abnormal value and discharge influence coefficient of each power plant group, They are , The preset scaling factor of Both are greater than 0.

8. A virtual power plant anomaly detection system, used to implement a virtual power plant anomaly detection method according to any one of claims 1 to 7, characterized in that: The system comprises: Similarity module: For the energy storage equipment of each virtual power plant, the device type and working environment of the energy storage equipment in every two virtual power plants are obtained, and the similarity coefficient of the corresponding two virtual power plants is calculated based on the device type and working environment; Grouping module: grouping the energy storage devices in the virtual power plant according to the similarity coefficients of every two virtual power plants to obtain power plant groups; and the difference in similarity coefficients between any two virtual power plant energy storage devices in each power plant group is less than a preset maximum difference; Priority detection module: For each power plant group, the historical abnormal number and historical discharge number of energy storage equipment in each virtual power plant in each power plant group are obtained to calculate the priority detection coefficient of each power plant group; Abnormal detection module: The monitoring platform performs abnormal detection on the energy storage equipment of each power plant group in the order of priority detection coefficient from large to small.

Images