Battery energy storage system monitoring resource configuration method, device, equipment, medium and program product

Abstract

The present invention discloses a method, device, equipment, medium and program product for monitoring resource configuration of a battery energy storage system. The method comprises: obtaining a multidimensional power disaster data set, and constructing a disaster event database based on the multidimensional power disaster data set; obtaining the spatiotemporal distribution information of faults of the battery energy storage system according to the disaster event database; constructing a situation awareness zoning map of the battery energy storage system based on the spatiotemporal distribution information of faults, generating a resource coordination configuration strategy according to the situation awareness zoning map, and performing monitoring resource configuration for each monitoring area in the battery energy storage system based on the resource coordination configuration strategy; because the present invention processes and analyzes data collected from multiple dimensions, thereby improving the monitoring range and monitoring accuracy, avoiding the problem of monitoring blind spots, and performing monitoring resource configuration based on the situation awareness zoning map, thereby effectively improving the monitoring efficiency, reducing the operation and maintenance cost of the battery energy storage system, and improving the system stability and reliability.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and in particular to a method, device, equipment, medium and program product for monitoring resource configuration of a battery energy storage system. Background Art

[0002] With the rapid development of technology, the current battery energy storage system faces many challenges: traditional monitoring methods are mostly single-level or local area perception, with spatial blind spots and data islands; lack of a multi-dimensional collaborative monitoring system from macro to micro, from environment to equipment, making it difficult to achieve full-domain perception; insufficient data fusion and analysis capabilities, making it difficult to extract key information from multi-source heterogeneous data and use it efficiently; imperfect risk perception and dynamic resource allocation mechanisms in operational safety, making it difficult to cope with diverse needs in complex operating environments, unreasonable resource allocation leading to increased monitoring costs, and low monitoring efficiency and accuracy, making it impossible to timely perceive the risks of battery energy storage systems. These problems have become technical bottlenecks for the further development of battery energy storage systems. Summary of the invention

[0003] The main purpose of the present invention is to provide a method, device, equipment, medium and program product for monitoring resource configuration of a battery energy storage system, aiming to solve the technical problems in the prior art that unreasonable resource configuration leads to increased monitoring costs, as well as low monitoring efficiency and accuracy, and cannot timely perceive the risks of the battery energy storage system.

[0004] To achieve the above object, the present invention provides a method for configuring monitoring resources of a battery energy storage system, wherein the battery energy storage system includes a plurality of energy storage power stations, and the method includes the following steps:

[0005] Acquire a multidimensional power disaster data set collected by a data acquisition system, and construct a disaster event database based on the multidimensional power disaster data set, wherein the data acquisition system includes a space-based data acquisition module, an air-based data acquisition module, and a ground-based data acquisition module;

[0006] Acquire the fault spatiotemporal distribution information of the battery energy storage system according to the disaster event database;

[0007] Constructing a situation awareness zoning map of the battery energy storage system based on the fault spatiotemporal distribution information, wherein the situation awareness zoning map includes each monitoring area of ​​the battery energy storage system and a risk level corresponding to each monitoring area, and the monitoring area includes at least one of the energy storage power stations;

[0008] A resource coordination configuration strategy is generated according to the situation awareness zoning map, and monitoring resources are configured for each monitoring area in the battery energy storage system based on the resource coordination configuration strategy.

[0009] Optionally, acquiring the fault spatiotemporal distribution information of the battery energy storage system according to the disaster event database includes:

[0010] Obtaining fault time series distribution information of the disaster event database;

[0011] Generate an importance threshold corresponding to each time period based on an importance measurement condition and the fault time series distribution information, wherein the importance measurement condition includes multi-dimensional measurement conditions, and the multi-dimensional conditions include support, confidence, promotion, conviction, and leverage;

[0012] Filtering target characteristic factors from characteristic factors in the disaster event database according to the importance threshold;

[0013] quantifying the effects of the target characteristic factors based on the structural importance assessment information of the battery energy storage system, and obtaining risk impact information corresponding to each target characteristic factor;

[0014] The fault spatiotemporal distribution information of the battery energy storage system is obtained according to the target characteristic factor and the risk impact information.

[0015] Optionally, the step of selecting a target characteristic factor from characteristic factors in the disaster event database according to the importance threshold comprises:

[0016] Classifying the characteristic factors based on the characteristic types of each characteristic factor in the disaster event database, and determining continuous characteristic factors and discrete characteristic factors among the characteristic factors;

[0017] Obtain the significance distribution information of each continuous characteristic factor;

[0018] Acquire fuzzy risk distribution information based on the saliency distribution information;

[0019] Acquire associated risk distribution information according to the numerical probability distribution information of the discrete characteristic factors;

[0020] Calculating the importance score of each characteristic factor based on the fuzzy risk distribution information and the associated risk distribution information;

[0021] A target characteristic factor is screened out from the characteristic factors according to the importance score and the importance threshold.

[0022] Optionally, the acquiring of a multidimensional power disaster data set collected by a data collection system, and building a disaster event database based on the multidimensional power disaster data set, includes:

[0023] Acquire multi-dimensional data collected by a data acquisition system;

[0024] Filtering out power disaster data from the multidimensional data, and marking event labels on the power disaster data;

[0025] Constructing an original data set based on the power disaster data and the event labels;

[0026] Preprocessing the original data set to obtain a target data set;

[0027] Performing feature extraction on the target data set to obtain multimodal feature data;

[0028] A disaster event database is constructed based on the multimodal feature data and the event labels.

[0029] Optionally, preprocessing the original data set to obtain a target data set includes:

[0030] Performing noise reduction processing on the original data set;

[0031] Perform abnormal data detection and missing data filling on the original data set after noise reduction to obtain a candidate data set;

[0032] Aligning the time information of the candidate data sets according to the timestamp information of each candidate data in the candidate data sets;

[0033] Based on the geographic coordinate information of each candidate data in the candidate data set, spatial information alignment is performed on the candidate data set after the time information alignment to obtain a target data set.

[0034] Optionally, the extracting features from the target data set to obtain multimodal feature data includes:

[0035] Extracting features from each target data according to the data type of each target data in the target data set to obtain an initial feature data set;

[0036] Performing standardization processing on the initial feature data set to obtain a standardized feature data set;

[0037] Obtaining weight information of a data acquisition module corresponding to each standardized data in the standardized feature data set;

[0038] Constructing a weighted fusion model based on the weight information;

[0039] The standardized feature data set is input into the weighted fusion model for weighted fusion to obtain multimodal feature data.

[0040] In addition, to achieve the above-mentioned purpose, the present invention further proposes a battery energy storage system monitoring resource configuration device, wherein the battery energy storage system includes a plurality of energy storage power stations, and the battery energy storage system monitoring resource configuration device includes:

[0041] A multidimensional data processing module, used to obtain a multidimensional power disaster data set collected by a data acquisition system, and to construct a disaster event database based on the multidimensional power disaster data set, wherein the data acquisition system includes a space-based data acquisition module, an air-based data acquisition module, and a ground-based data acquisition module;

[0042] A fault distribution analysis module, used to obtain the fault spatiotemporal distribution information of the battery energy storage system according to the disaster event database;

[0043] A situation awareness zoning module, used to construct a situation awareness zoning map of the battery energy storage system based on the fault spatiotemporal distribution information, wherein the situation awareness zoning map includes each monitoring area of ​​the battery energy storage system and the risk level corresponding to each monitoring area, and the monitoring area includes at least one of the energy storage power stations;

[0044] A monitoring resource configuration module is used to generate a resource coordination configuration strategy according to the situation awareness zoning map, and perform monitoring resource configuration for each monitoring area in the battery energy storage system based on the resource coordination configuration strategy.

[0045] In addition, to achieve the above-mentioned purpose, the present application also proposes a battery energy storage system monitoring resource configuration device, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the battery energy storage system monitoring resource configuration method as described above.

[0046] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the battery energy storage system monitoring resource configuration method as described above are implemented.

[0047] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the battery energy storage system monitoring resource configuration method as described above.

[0048] The present invention obtains a multidimensional power disaster data set and constructs a disaster event database based on the multidimensional power disaster data set; obtains the fault spatiotemporal distribution information of the battery energy storage system according to the disaster event database; constructs a situation awareness zoning map of the battery energy storage system based on the fault spatiotemporal distribution information, the situation awareness zoning map includes each monitoring area of ​​the battery energy storage system and the risk level corresponding to each monitoring area, the monitoring area includes at least one energy storage power station, generates a resource coordination configuration strategy according to the situation awareness zoning map, and performs monitoring resource configuration for each monitoring area in the battery energy storage system based on the resource coordination configuration strategy; because the present invention processes and analyzes data collected in multiple dimensions, The fault spatiotemporal distribution information of the battery energy storage system is obtained, and the fault distribution is analyzed from the time dimension and the space dimension, thereby improving the monitoring range and monitoring accuracy, avoiding the problems of monitoring blind spots and data islands, and constructing a situation awareness zoning map of the battery energy storage system based on the fault spatiotemporal distribution information, thereby realizing the division of monitoring areas and risk rating of each monitoring area, and configuring monitoring resources based on the situation awareness zoning map to meet the dynamic monitoring needs of the battery energy storage system, enhance the system's adaptability to dynamic environmental changes, and effectively improve the monitoring efficiency. By reasonably configuring monitoring resources, the operation and maintenance costs of the battery energy storage system are effectively reduced, and the system stability and reliability are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings herein are incorporated in and constitute a part of the specification, illustrate embodiments consistent with the present application, and together with the description, are used to explain the principles of the present application.

[0050] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0051] Figure 1 It is a structural diagram of a battery energy storage system monitoring resource configuration device in a hardware operating environment involved in an embodiment of the present invention;

[0052] Figure 2 A schematic diagram of a flow chart of a first embodiment of a method for configuring monitoring resources for a battery energy storage system according to the present invention;

[0053] Figure 3 A schematic diagram of a flow chart of a second embodiment of a method for configuring monitoring resources for a battery energy storage system according to the present invention;

[0054] Figure 4 This is a structural block diagram of the first embodiment of the device for monitoring resource allocation of a battery energy storage system according to the present invention.

[0055] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0056] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0057] Reference Figure 1 , Figure 1 A schematic diagram of the structure of a battery energy storage system monitoring resource configuration device in the hardware operating environment involved in an embodiment of the present invention.

[0058] like Figure 1 As shown, the battery energy storage system monitoring resource configuration device may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display screen (Display), an input unit such as a keyboard (Keyboard), and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (Wireless-Fidelity, WI-FI) interface). The memory 1005 may be a high-speed random access memory (Random Access Memory, RAM), or a stable non-volatile memory (Non-Volatile Memory, NVM), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0059] Those skilled in the art will understand that Figure 1 The structure shown in does not constitute a limitation on the battery energy storage system monitoring resource configuration device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0060] like Figure 1 As shown, the memory 1005 as a computer-readable storage medium may include an operating system, a network communication module, a user interface module, and a battery energy storage system monitoring resource configuration program.

[0061] exist Figure 1In the battery energy storage system monitoring resource configuration device shown, the network interface 1004 is mainly used for data communication with the network server; the user interface 1003 is mainly used for data interaction with the user; the processor 1001 and the memory 1005 in the battery energy storage system monitoring resource configuration device of the present invention can be set in the battery energy storage system monitoring resource configuration device, and the battery energy storage system monitoring resource configuration device calls the battery energy storage system monitoring resource configuration program stored in the memory 1005 through the processor 1001, and executes the battery energy storage system monitoring resource configuration method provided in the embodiment of the present invention.

[0062] The embodiment of the present invention provides a method for configuring monitoring resources of a battery energy storage system, referring to Figure 2 , Figure 2 It is a flowchart of the first embodiment of the method for configuring monitoring resources of a battery energy storage system according to the present invention.

[0063] In this embodiment, the battery energy storage system monitoring resource configuration method includes the following steps:

[0064] Step S10: Acquire a multidimensional power disaster data set collected by a data collection system, and construct a disaster event database based on the multidimensional power disaster data set.

[0065] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or a terminal electronic device capable of realizing the above functions, etc. The following takes a battery energy storage system monitoring resource configuration device (hereinafter referred to as monitoring device) as an example to illustrate this embodiment and the following embodiments.

[0066] It should be noted that the data acquisition system includes a space-based data acquisition module, an air-based data acquisition module and a ground-based data acquisition module.

[0067] In some embodiments, the data acquisition system can be a sky-ground system or a satellite-ground global system. The above-mentioned space-based data acquisition module can be a satellite observation unit, such as a low-altitude orbit satellite, etc.; the above-mentioned air-based data acquisition module can be a high-altitude inspection unit, such as a drone, an aircraft, etc.; the above-mentioned ground-based data acquisition module can be a ground perception unit, such as a sensor network of a battery energy storage system, etc.

[0068] In some embodiments, the satellite observation unit uses microwave imaging and satellite-borne lidar technology to conduct wide-area scans of the area where the energy storage system is located and its surrounding environment, focusing on monitoring climate change, terrain features and macro-anomalies; the high-altitude inspection unit uses drones as the core to conduct flexible and high-precision close-range detection of the equipment operating status of the energy storage site; the ground perception unit relies on the sensor network to focus on the key operating parameters of the internal equipment of the energy storage system, providing accurate and real-time data support for fault identification and operation optimization.

[0069] In some embodiments, the monitoring equipment can perform time synchronization, space synchronization and information synchronization on the multi-dimensional power disaster data set based on the time-space information coordination mechanism to obtain standardized data, and build a disaster event database based on the standardized data.

[0070] It should be noted that the specific content of the space-time information coordinated monitoring mechanism can be the time synchronization, space synchronization and data fusion of the multi-dimensional data collected by satellite, air-based and ground-based modules. The core purpose of this process is to optimize the coordination and integration of monitoring data in different dimensions to improve the state perception and dynamic monitoring capabilities of the battery energy storage system.

[0071] In some embodiments, the space-time information collaborative monitoring mechanism may include:

[0072] In terms of time response, the global coverage and periodic observation of the space-based module, the flexible response and short-term dynamic compensation of the air-based module, and the real-time update and detailed monitoring of the ground-based module are combined to build a coordinated response mechanism in the time dimension.

[0073] In terms of spatial coverage, the wide-area coverage of the space-based module provides macro-environmental perception, the local monitoring of the air-based module strengthens the dynamic perception of the surrounding area of ​​the site, and the close-range and refined observation of the ground-based module builds a hierarchical coordination mechanism in the spatial dimension;

[0074] In terms of information depth, it integrates space-based macro-monitoring, air-based dynamic capture and ground-based fine perception to build a collaborative fusion mechanism in information dimensions.

[0075] In some embodiments, the monitoring equipment can extract features from multidimensional power disaster data sets to obtain multidimensional feature data, perform feature fusion based on the multidimensional feature data to obtain multimodal feature data, and build a disaster event database based on the multimodal feature data.

[0076] Step S20: Acquire the fault spatiotemporal distribution information of the battery energy storage system according to the disaster event database.

[0077] It should be noted that the fault spatiotemporal distribution information may be the distribution information of power disasters and power faults in the time dimension and the space dimension.

[0078] In some embodiments, the monitoring device may perform time distribution analysis and space distribution analysis on each disaster event in the disaster event database to determine the time and space distribution information of each disaster event.

[0079] Furthermore, in order to accurately analyze the time dimension distribution information and space dimension distribution information of the battery energy storage system fault, the above step S20 may include:

[0080] Step S201: obtaining fault time series distribution information of the disaster event database;

[0081] Step S202: Generate importance thresholds corresponding to each time period based on importance measurement conditions and the fault time series distribution information;

[0082] Step S203: selecting target characteristic factors from the characteristic factors in the disaster event database according to the importance threshold;

[0083] Step S204: quantifying the effects of the target characteristic factors based on the structural importance assessment information of the battery energy storage system, and obtaining risk impact information corresponding to each target characteristic factor;

[0084] Step S205: Acquire the fault spatiotemporal distribution information of the battery energy storage system according to the target characteristic factor and the risk impact information.

[0085] It should be noted that the importance measurement condition includes multi-dimensional measurement conditions, and the multi-dimensional conditions include support, confidence, promotion, conviction and leverage.

[0086] In some embodiments, the monitoring device can set five conditional threshold setting methods based on five importance measurement criteria (support, confidence, enhancement, conviction and leverage), driven by the fault timing distribution within each benchmark time unit, to match the respective optimal thresholds for different time periods, fully considering the impact of rare and high-risk fault characteristics.

[0087] In some embodiments, the monitoring device may extract characteristic factors (i.e., target characteristic factors) that are strongly correlated with the battery energy storage system failure safety warning under the data bias distribution in the disaster event database.

[0088] In some embodiments, the monitoring device can construct a risk factor weight measurement framework to quantify the effect of the battery energy storage system fault characteristic factors under data coupling distribution, thereby quantifying the effect of the target characteristic factors.

[0089] It should be noted that in order to quantify the degree of influence of characteristic factors related to the safety risk of energy storage battery systems, the overall failure risk of the system is described based on the system risk structure theory. Combined with the structural importance assessment (SIM), the structural function of the risk coefficient calculation model is constructed according to the path type B structural importance measure to characterize the impact of characteristic factors on the system.

[0090] Furthermore, in order to accurately screen out the target characteristic factors, the above step S203 may include:

[0091] Step S2031: classifying the characteristic factors based on the characteristic types of the characteristic factors in the disaster event database, and determining continuous characteristic factors and discrete characteristic factors in the characteristic factors;

[0092] Step S2032: Obtaining significance distribution information of each continuous feature factor;

[0093] Step S2033: acquiring fuzzy risk distribution information based on the saliency distribution information;

[0094] Step S2034: acquiring associated risk distribution information according to the numerical probability distribution information of the discrete characteristic factors;

[0095] Step S2035: calculating the importance score of each characteristic factor based on the fuzzy risk distribution information and the associated risk distribution information;

[0096] Step S2036: Filter out target characteristic factors from the characteristic factors according to the importance score and the importance threshold.

[0097] It should be noted that the continuous characteristic factors can be continuous variables and discrete variables in the disaster event database.

[0098] It should be noted that discrete characteristic factors can be characteristic information of transient states, such as animal activities, etc. The above-mentioned continuous characteristic factors can be characteristic information of persistent and continuous states, such as continuous data such as wind speed and rainfall, which are continuous characteristics.

[0099] It can be understood that this embodiment sets different importance score calculation methods for continuous variables and discrete variables, where continuous variables are based on the improvement potential (IP) theory, first solving the significance distribution function of each continuous feature and dividing the significance interval, and then constructing the corresponding significance membership function through numerical probability and significance distribution characteristics, and finally designing a hierarchical fuzzy structure and calculating the fuzzy risk distribution. Discrete variables are driven by numerical probability distribution and calculate the corresponding associated risk distribution; finally, if the importance score of the feature factor is greater than the threshold, it is a feature factor that is strongly related to the safety risk of the energy storage power station system.

[0100] In some embodiments, in order to adapt to the distribution characteristics of different data types (discrete and continuous feature data types exist in the form of distinct sets and fuzzy sets respectively) and reduce the potential subjective uncertainty in a single model method, an integrated path solution for different historical experience models is studied. Based on the integrated learning theory, the two sub-historical experience models of the relevant pattern recognition model and the fuzzy risk reasoning system are integrated to extract and quantify the risks of discrete and continuous features respectively. By collecting historical data, a historical experience model is constructed based on history, and the importance of feature factors is scored based on the historical experience model.

[0101] Step S30: constructing a situation awareness zoning map of the battery energy storage system based on the fault spatiotemporal distribution information.

[0102] It should be noted that the situation awareness zoning map includes each monitoring area of ​​the battery energy storage system and the risk level corresponding to each monitoring area, and the monitoring area includes at least one of the energy storage power stations.

[0103] It can be understood that the monitoring equipment can divide the battery energy storage system into monitoring areas based on the temporal and spatial distribution information of faults, and conduct risk rating for each monitoring area, determine the safety risk level of each monitoring area, collect multi-dimensional data of each monitoring area through the sky-ground system, and construct a situational awareness zoning map based on the multi-dimensional data, safety risk level and regional information of each monitoring area.

[0104] It should be noted that the monitoring equipment can determine the risk distribution of equipment, environment and operating status in the battery energy storage system based on the situational awareness zoning map; combined with the characteristics of different risk areas, a satellite-air-ground multi-level resource collaborative configuration strategy is proposed to achieve dynamic allocation and optimal configuration of resources in the energy storage system in multi-task scenarios and complex operating environments, effectively improving the system's safety protection capabilities and stable operation efficiency.

[0105] Step S40: Generate a resource coordination configuration strategy according to the situation awareness zoning map, and perform monitoring resource configuration for each monitoring area in the battery energy storage system based on the resource coordination configuration strategy.

[0106] It should be noted that the resource coordination configuration strategy may be to implement corresponding monitoring resource configuration for monitoring areas of different risk levels.

[0107] It should be noted that monitoring equipment can be combined with situational awareness zoning maps to intuitively present the intensity and distribution differences of fault events in geographical space. The characteristics of different risk areas are related to the risk level of the area, and resources are allocated according to different risk areas and their related fault characteristics.

[0108] In the specific implementation, the monitoring equipment can determine the regional characteristics corresponding to the low-risk areas, medium-risk areas and high-risk areas based on the situational awareness zoning map, reasonably configure monitoring resources based on the regional characteristics, and conduct dynamic status monitoring.

[0109] In some embodiments, low-risk areas are mainly based on satellite observation units, combined with basic perception functions to achieve full coverage and wide-area monitoring; medium-risk areas are based on high-altitude inspection units and ground perception units, focusing on refined monitoring of key points; high-risk areas have a comprehensive satellite-ground full-area detection network, combined with communication capabilities, to achieve comprehensive life cycle precision monitoring and dynamic risk control.

[0110] In some embodiments, the resource collaborative configuration strategy may include: resource allocation strategy, multi-level monitoring strategy, optimization configuration strategy and operation and maintenance strategy.

[0111] Resource allocation: Dynamically allocate different data collection, monitoring and response resources according to risk levels.

[0112] Multi-level monitoring: Conduct hierarchical monitoring based on the risk characteristics of different areas to ensure that key areas receive adequate monitoring support.

[0113] Optimized configuration: When resources are limited, intelligent optimization algorithms are used to schedule and configure monitoring resources to ensure stable and efficient operation of the system.

[0114] Operation and maintenance: By dividing different areas into different risk levels, human resources and resources can be deployed in key risk areas.

[0115] In some embodiments, the monitoring equipment can build a cloud-edge integrated big data hierarchical management system for the battery energy storage system. Through data collaboration and functional integration between the cloud system and the edge system, it provides comprehensive support for the digital operation and maintenance of the battery energy storage system throughout its life cycle, including:

[0116] Construct a big data hierarchical management system for battery energy storage systems, which consists of an energy management system (EMS), a edge data system (DMS), and a cloud network system (CMS). Among them, EMS provides monitoring and scheduling functions for energy storage power station equipment and batteries, with strong real-time performance; DMS is a hardware and software integrated system deployed locally in large independent energy storage power stations, providing a data-driven energy storage brain and a data center based on full data on top of EMS; CMS is a set of energy storage systems based on a cloud platform, responsible for collecting underlying necessary data and key data, and realizing unified management of multi-power station clusters.

[0117] Taking into account the different scales and needs of energy storage battery systems, with CMS as the core and combining the functional advantages of EMS and DMS, a cloud-edge integrated big data hierarchical management system for energy storage batteries is constructed with CMS-EMS direct deployment and CMS-DMS collaborative deployment.

[0118] The cloud-edge integrated big data hierarchical management system is as follows:

[0119] CMS-EMS direct connection deployment directly connects CMS to EMS, uploads single-station data to the cloud for power station big data management, and is suitable for distributed energy storage power stations or new energy storage power stations with small capacity, dispersed locations, and low single-station data volume. This method is lightweight and flexible, and can effectively reduce the digitalization cost of power stations while meeting basic big data management needs.

[0120] CMS-DMS collaborative deployment achieves seamless connection with the cloud platform through DMS, which is suitable for large-scale energy storage power stations with large capacity and data cloud conditions. DMS is responsible for the local storage of massive data at a single station and the sinking of computing tasks to the edge, effectively reducing the burden of cloud bandwidth and improving data stability and quality; CMS is responsible for the integration and in-depth analysis of regional multi-site data, providing strong technical support for safe operation, energy optimization, equipment life cycle management and intelligent operation and maintenance for energy storage battery systems.

[0121] In some embodiments, the monitoring equipment can build a multi-module safety risk perception architecture for the battery energy storage system, covering a multi-source data fusion module, a safety risk perception module, and a resource collaborative configuration module, to conduct all-round situational awareness and status inspection, and help achieve active safety in energy storage power stations.

[0122] The conditions for transferring data to the cloud refer to the premise and requirements for transferring the data of the battery energy storage system from the local to the cloud platform, which specifically include the following aspects:

[0123] Stability of network bandwidth: Data uploading requires a reliable network connection, especially for large-scale energy storage systems, ensuring that the network bandwidth is sufficient and stable to support real-time or periodic data transmission.

[0124] Data storage capacity: The cloud platform must have sufficient storage capacity to accommodate massive amounts of data from multiple power plants and support efficient data management and retrieval.

[0125] Data security: Data must be encrypted during upload and storage to prevent data leakage or tampering. A secure authentication and authorization mechanism must be in place during the cloud migration process.

[0126] Device compatibility: Local devices need to be compatible with the cloud platform and support standardized data formats and communication protocols to ensure seamless data connection.

[0127] This embodiment obtains a multidimensional power disaster data set and builds a disaster event database based on the multidimensional power disaster data set; obtains the spatiotemporal distribution information of the faults of the battery energy storage system according to the disaster event database; builds a situation awareness zoning map of the battery energy storage system based on the spatiotemporal distribution information of the faults, the situation awareness zoning map includes each monitoring area of ​​the battery energy storage system and the risk level corresponding to each monitoring area, the monitoring area includes at least one energy storage power station, generates a resource coordination configuration strategy according to the situation awareness zoning map, and performs monitoring resource configuration for each monitoring area in the battery energy storage system based on the resource coordination configuration strategy; since this embodiment processes and analyzes the data collected in multiple dimensions , obtain the spatiotemporal distribution information of faults in the battery energy storage system, analyze the fault distribution from the time dimension and space dimension, thereby improving the monitoring range and monitoring accuracy, avoiding the problems of monitoring blind spots and data islands, and constructing a situation awareness zoning map of the battery energy storage system based on the spatiotemporal distribution information of faults, thereby realizing the division of monitoring areas and risk rating of each monitoring area, and configuring monitoring resources based on the situation awareness zoning map to meet the dynamic monitoring needs of the battery energy storage system, enhance the system's adaptability to dynamic environmental changes, and effectively improve the monitoring efficiency. By reasonably configuring monitoring resources, the operation and maintenance costs of the battery energy storage system are effectively reduced, and the system stability and reliability are improved.

[0128] refer to Figure 3 , Figure 3 It is a flow chart of the second embodiment of the method for configuring monitoring resources of a battery energy storage system according to the present invention.

[0129] Based on the above first embodiment, in this embodiment, the step S10 further includes:

[0130] Step S101: Acquire multi-dimensional data collected by a data collection system.

[0131] It should be noted that multidimensional data can be data in three dimensions: space-based data, air-based data, and ground-based data.

[0132] In some embodiments, the data acquisition system can be a sky-ground system or a satellite-ground global system. The above-mentioned space-based data acquisition module can be a satellite observation unit, such as a low-altitude orbit satellite, etc.; the above-mentioned air-based data acquisition module can be a high-altitude inspection unit, such as a drone, an aircraft, etc.; the above-mentioned ground-based data acquisition module can be a ground perception unit, such as a sensor network of a battery energy storage system, etc.

[0133] In some embodiments, the satellite observation unit uses microwave imaging and satellite-borne lidar technology to conduct wide-area scans of the area where the energy storage system is located and its surrounding environment, focusing on monitoring climate change, terrain features and macro-anomalies; the high-altitude inspection unit uses drones as the core to conduct flexible and high-precision close-range detection of the equipment operating status of the energy storage site; the ground perception unit relies on the sensor network to focus on the key operating parameters of the internal equipment of the energy storage system, providing accurate and real-time data support for fault identification and operation optimization.

[0134] In some embodiments, the monitoring equipment can perform time synchronization, space synchronization and information synchronization on the multi-dimensional power disaster data set based on the time-space information coordination mechanism to obtain standardized data, and build a disaster event database based on the standardized data.

[0135] Step S102: Filter out power disaster data from the multidimensional data, and mark the power disaster data with event labels.

[0136] It should be noted that the event label may be a label of the fault type and / or disaster event corresponding to each power disaster data.

[0137] It can be understood that the monitoring equipment collects multi-dimensional data collected by the data acquisition system, and then selects power disaster data composed of modal data such as images, videos, texts, etc. in the disaster data, and marks the corresponding event labels for the fault data categories corresponding to each power disaster data.

[0138] Step S103: constructing an original data set based on the power disaster data and the event labels.

[0139] In some embodiments, the monitoring equipment can collect multi-dimensional data (such as images, videos, texts, sensor data, etc.) from the satellite-ground monitoring network, filter out disaster-related data sets, label each event (such as equipment failure, climate anomaly, etc.), and obtain the original data set.

[0140] Step S104: preprocessing the original data set to obtain a target data set.

[0141] It is understandable that the preprocessing may include denoising, outlier detection, missing value filling, standardization, etc. of the original data set.

[0142] Furthermore, in order to improve data quality and analysis efficiency, the above step S104 may include:

[0143] Step S1041: performing noise reduction processing on the original data set.

[0144] In some embodiments, the monitoring device may use filtering methods (such as median filtering, low-pass filtering, etc.) to remove noise from images and sensor data to ensure the smoothness and effectiveness of the data.

[0145] Step S1042: performing abnormal data detection and missing data filling on the original data set after the noise reduction process to obtain a candidate data set.

[0146] In some embodiments, the monitoring device may use statistical methods (such as Z-score, box plot analysis, etc.) to identify and eliminate data points that are significantly deviated from the normal range, detect abnormal data, and ensure the accuracy of the data.

[0147] In some embodiments, the monitoring device may use an interpolation method (such as linear interpolation, Lagrange interpolation) or a model-based filling method (such as K-nearest neighbor interpolation, regression filling) to fill in the missing data, thereby reducing the impact of data loss on the analysis results.

[0148] Step S1043: aligning the time information of the candidate data sets according to the timestamp information of each candidate data in the candidate data sets.

[0149] In some embodiments, the monitoring device may use different formats (such as image format, text format, and numerical format) for different data sources (satellites, drones, and ground sensors), which need to be unified into a processable format (such as converting images to standard resolution and text data to structured data).

[0150] In some embodiments, the monitoring device may align timestamps from different data sources, using time interpolation or an interpolation algorithm (such as linear interpolation) to ensure time synchronization of each data source and avoid data deviation caused by time misalignment.

[0151] In some embodiments, the monitoring device can align spatial information from different data sources according to geographic coordinates (such as latitude and longitude, three-dimensional spatial coordinates), and use geographic information system (GIS) methods to perform coordinate conversion and precise matching.

[0152] Step S1044: performing spatial information alignment on the candidate data sets after the time information alignment based on the geographic coordinate information of each candidate data in the candidate data sets to obtain a target data set.

[0153] It is understandable that the raw data collected by the monitoring equipment can be preprocessed, including denoising, outlier detection and missing value filling. Due to the heterogeneity of different data sources, format unification, time synchronization and coordinate alignment are required to ensure that the data is compared and integrated under the same standard, and finally the cleaned data is obtained.

[0154] Step S105: extracting features from the target data set to obtain multimodal feature data.

[0155] It can be understood that since the target data set includes data collected in multiple dimensions, such as images, audio, text and other data, the monitoring equipment can extract features based on the data type of each target data in the target data set, and then fuse the extracted feature data to obtain multimodal feature data.

[0156] Furthermore, in order to ensure data consistency and reduce the impact of different types of data on analysis, the above step S105 may include:

[0157] Step S1051: extracting features from each target data according to the data type of each target data in the target data set to obtain an initial feature data set;

[0158] Step S1052: performing standardization processing on the initial feature data set to obtain a standardized feature data set;

[0159] Step S1053: Obtaining weight information of the data acquisition module corresponding to each standardized data in the standardized feature data set;

[0160] Step S1054: constructing a weighted fusion model based on the weight information;

[0161] Step S1055: input the standardized feature data set into the weighted fusion model for weighted fusion to obtain multimodal feature data.

[0162] In some embodiments, the monitoring device can extract key features from data of different modalities through training models of various data sources or task-specific feature extraction models. For example, object detection features are extracted from images, dynamic features are extracted from videos, and key information is extracted from text. All extracted features need to be standardized to ensure that features of different modalities are fused at a unified scale. For example:

[0163] In some embodiments, when the monitoring device normalizes the image data, it is usually processed based on the pixel value, using Z-score normalization (mean is 0, standard deviation is 1) or Min-Max normalization (normalizing the pixel value to the range of [0, 1]). This can eliminate the impact of different image sizes and brightness differences.

[0164] In some embodiments, the normalization of video data is generally performed based on frame features, such as optical flow, motion direction, speed, etc. A normalization method such as Z-score can be used to process each feature to ensure that the amplitude of dynamic features in the video data is consistent and avoid deviations in the time dimension.

[0165] In some embodiments, the standardization of text data is often processed through word vectors (such as Word2Vec, BERT, etc.) or TF-IDF features. After different text features are processed by standardization (such as mean 0, variance 1), the consistency of text data in the feature space is ensured, reducing the impact of differences in length or frequency of different texts.

[0166] In some embodiments, the monitoring device may use a weighted fusion model to fuse the standardized feature data according to the weights of different modalities to obtain a unified multimodal feature representation. This weighting strategy can be dynamically adjusted according to the importance of each modality in the current task to obtain fused multimodal feature data.

[0167] In some embodiments, the monitoring device may use a weighted fusion model to fuse data from different modalities (macro, dynamic, and fine features) into a unified multimodal feature. This process may be weighted according to the importance or credibility of each modality. The purpose of weighted fusion is to maximize the role of each data source in a specific situation.

[0168] It should be noted that the input of the weighted model is data features from different modes, and the output is the fused multi-modal features. This output represents the comprehensive information of each modal feature, and can also be regarded as various status information of the energy storage system when a fault event occurs.

[0169] In some embodiments, the monitoring device can continuously optimize the data integration effect of real-time data streams and monitoring feedback through a dynamic update mechanism. With the arrival of new data, the system can adaptively adjust the weighting strategy and feature extraction model to ensure the accuracy and relevance of real-time data. For example, if a data source shows higher accuracy in the current situation, the system will increase its weight accordingly, or retrain a certain modality's deep learning model with the arrival of new data to improve its feature extraction capabilities, etc.

[0170] Step S106: constructing a disaster event database based on the multimodal feature data and the event labels.

[0171] It is understandable that the monitoring equipment can combine the fused multimodal feature data with the corresponding fault event labels to build a comprehensive disaster event database.

[0172] In some embodiments, the monitoring device may use training models of various data sources or feature extraction models for specific tasks to extract key features from each modal data, and then further fuse them to obtain a fusion representation of multimodal features, and finally integrate them into a disaster event database of multimodal fusion features and corresponding fault events.

[0173] This embodiment obtains multidimensional data collected by a data acquisition system, filters out power disaster data from the multidimensional data, and marks event labels on the power disaster data, constructs an original data set based on the power disaster data and the event labels, preprocesses the original data set to obtain a target data set, extracts features from the target data set to obtain multimodal feature data, and constructs a disaster event database based on the multimodal feature data and the event labels.

[0174] In addition, an embodiment of the present invention further proposes a computer-readable storage medium, on which a battery energy storage system monitoring resource configuration program is stored. When the battery energy storage system monitoring resource configuration program is executed by a processor, the steps of the battery energy storage system monitoring resource configuration method described above are implemented.

[0175] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0176] The computer-readable storage medium may be included in the battery energy storage system monitoring resource configuration device; or may exist independently without being assembled into the battery energy storage system monitoring resource configuration device.

[0177] In addition, an embodiment of the present invention further proposes a computer program product, including a battery energy storage system monitoring resource configuration program, which implements the steps of the battery energy storage system monitoring resource configuration method as described above when executed by a processor.

[0178] The specific implementation manner of the computer program product of the present invention is basically the same as the various embodiments of the above-mentioned battery energy storage system monitoring resource configuration method, and will not be repeated here.

[0179] Reference Figure 4 , Figure 4 This is a structural block diagram of the first embodiment of the device for monitoring resource allocation of a battery energy storage system according to the present invention.

[0180] like Figure 4 As shown, the battery energy storage system monitoring resource configuration device proposed in the embodiment of the present invention includes: a multi-dimensional data processing module 10, a fault distribution analysis module 20, a situation awareness zoning module 30 and a monitoring resource configuration module 40. The battery energy storage system in this embodiment includes multiple energy storage power stations;

[0181] The multidimensional data processing module 10 is used to obtain a multidimensional power disaster data set collected by a data acquisition system, and to construct a disaster event database based on the multidimensional power disaster data set. The data acquisition system includes a space-based data acquisition module, an air-based data acquisition module, and a ground-based data acquisition module.

[0182] The fault distribution analysis module 20 is used to obtain the fault spatiotemporal distribution information of the battery energy storage system according to the disaster event database;

[0183] The situation awareness zoning module 30 is used to construct a situation awareness zoning map of the battery energy storage system based on the fault spatiotemporal distribution information, wherein the situation awareness zoning map includes each monitoring area of ​​the battery energy storage system and the risk level corresponding to each monitoring area, and the monitoring area includes at least one of the energy storage power stations;

[0184] The monitoring resource configuration module 40 is used to generate a resource coordination configuration strategy according to the situation awareness zoning map, and perform monitoring resource configuration for each monitoring area in the battery energy storage system based on the resource coordination configuration strategy.

[0185] Furthermore, the fault distribution analysis module 20 is also used to obtain the fault time series distribution information of the disaster event database; generate the importance threshold corresponding to each time period based on the importance measurement condition and the fault time series distribution information, the importance measurement condition includes multi-dimensional measurement conditions, and the multi-dimensionality includes support, confidence, promotion, conviction and leverage; select the target characteristic factor from the characteristic factors of the disaster event database according to the importance threshold; quantify the effect of the target characteristic factor based on the structural importance evaluation information of the battery energy storage system, and obtain the risk impact information corresponding to each target characteristic factor; obtain the fault spatiotemporal distribution information of the battery energy storage system according to the target characteristic factor and the risk impact information.

[0186] Furthermore, the fault distribution analysis module 20 is also used to classify the characteristic factors based on the characteristic types of each characteristic factor in the disaster event database, determine the continuous characteristic factors and discrete characteristic factors among the characteristic factors; obtain the significance distribution information of each continuous characteristic factor; obtain fuzzy risk distribution information based on the significance distribution information; obtain associated risk distribution information according to the numerical probability distribution information of the discrete characteristic factors; calculate the importance score of each characteristic factor based on the fuzzy risk distribution information and the associated risk distribution information; and screen out the target characteristic factors from the characteristic factors according to the importance score and the importance threshold.

[0187] Furthermore, the multidimensional data processing module 10 is also used to obtain multidimensional data collected by the data acquisition system; filter out power disaster data from the multidimensional data, and mark the power disaster data with event labels; construct an original data set based on the power disaster data and the event labels; preprocess the original data set to obtain a target data set; perform feature extraction on the target data set to obtain multimodal feature data; and construct a disaster event database based on the multimodal feature data and the event labels.

[0188] Furthermore, the multidimensional data processing module 10 is also used to perform noise reduction processing on the original data set; perform abnormal data detection and missing data filling on the original data set after noise reduction processing to obtain a candidate data set; perform time information alignment on the candidate data sets according to the timestamp information of each candidate data in the candidate data set; perform spatial information alignment on the candidate data sets after time information alignment based on the geographic coordinate information of each candidate data in the candidate data set to obtain a target data set.

[0189] Furthermore, the multidimensional data processing module 10 is also used to extract features from each target data according to the data type of each target data in the target data set to obtain an initial feature data set; standardize the initial feature data set to obtain a standardized feature data set; obtain weight information of the data acquisition module corresponding to each standardized data in the standardized feature data set; construct a weighted fusion model based on the weight information; input the standardized feature data set into the weighted fusion model for weighted fusion to obtain multimodal feature data.

[0190] This embodiment obtains a multidimensional power disaster data set and builds a disaster event database based on the multidimensional power disaster data set; obtains the spatiotemporal distribution information of the faults of the battery energy storage system according to the disaster event database; builds a situation awareness zoning map of the battery energy storage system based on the spatiotemporal distribution information of the faults, the situation awareness zoning map includes each monitoring area of ​​the battery energy storage system and the risk level corresponding to each monitoring area, the monitoring area includes at least one energy storage power station, generates a resource coordination configuration strategy according to the situation awareness zoning map, and performs monitoring resource configuration for each monitoring area in the battery energy storage system based on the resource coordination configuration strategy; since this embodiment processes and analyzes the data collected in multiple dimensions , obtain the spatiotemporal distribution information of faults in the battery energy storage system, analyze the fault distribution from the time dimension and space dimension, thereby improving the monitoring range and monitoring accuracy, avoiding the problems of monitoring blind spots and data islands, and constructing a situation awareness zoning map of the battery energy storage system based on the spatiotemporal distribution information of faults, thereby realizing the division of monitoring areas and risk rating of each monitoring area, and configuring monitoring resources based on the situation awareness zoning map to meet the dynamic monitoring needs of the battery energy storage system, enhance the system's adaptability to dynamic environmental changes, and effectively improve the monitoring efficiency. By reasonably configuring monitoring resources, the operation and maintenance costs of the battery energy storage system are effectively reduced, and the system stability and reliability are improved.

[0191] The battery energy storage system monitoring resource configuration device provided in the present application adopts the battery energy storage system monitoring resource configuration method in the above-mentioned embodiment, which can solve the technical problem of battery energy storage system monitoring resource configuration. Compared with the prior art, the beneficial effects of the battery energy storage system monitoring resource configuration device provided in the present application are the same as the beneficial effects of the battery energy storage system monitoring resource configuration method provided in the above-mentioned embodiment, and other technical features in the battery energy storage system monitoring resource configuration device are the same as the features disclosed in the above-mentioned embodiment method, which will not be repeated here.

[0192] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0193] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0194] In addition, for technical details not fully described in this embodiment, reference may be made to the battery energy storage system monitoring resource configuration method provided in any embodiment of the present invention, which will not be described in detail here.

[0195] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0196] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0197] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory / random access memory, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0198] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for monitoring resource configuration of a battery energy storage system, characterized in that: The battery energy storage system includes a plurality of energy storage power stations, and the battery energy storage system monitoring resource configuration method includes: Acquire a multidimensional power disaster data set collected by a data acquisition system, and construct a disaster event database based on the multidimensional power disaster data set, wherein the data acquisition system includes a space-based data acquisition module, an air-based data acquisition module, and a ground-based data acquisition module; Acquire the fault spatiotemporal distribution information of the battery energy storage system according to the disaster event database; Constructing a situation awareness zoning map of the battery energy storage system based on the fault spatiotemporal distribution information, wherein the situation awareness zoning map includes each monitoring area of ​​the battery energy storage system and a risk level corresponding to each monitoring area, and the monitoring area includes at least one of the energy storage power stations; Generate a resource coordination configuration strategy according to the situation awareness zoning map, and perform monitoring resource configuration for each monitoring area in the battery energy storage system based on the resource coordination configuration strategy; The acquiring the fault spatiotemporal distribution information of the battery energy storage system according to the disaster event database includes: Obtaining fault time series distribution information of the disaster event database; Generate an importance threshold corresponding to each time period based on an importance measurement condition and the fault time series distribution information, wherein the importance measurement condition includes multi-dimensional measurement conditions, and the multi-dimensional conditions include support, confidence, promotion, conviction, and leverage; Filtering target characteristic factors from characteristic factors in the disaster event database according to the importance threshold; quantifying the effects of the target characteristic factors based on the structural importance assessment information of the battery energy storage system, and obtaining risk impact information corresponding to each target characteristic factor; Acquire fault spatiotemporal distribution information of the battery energy storage system according to the target characteristic factor and the risk impact information; The step of selecting target characteristic factors from characteristic factors in the disaster event database according to the importance threshold comprises: Classifying the characteristic factors based on the characteristic types of each characteristic factor in the disaster event database, and determining continuous characteristic factors and discrete characteristic factors in the characteristic factors; Obtain the significance distribution information of each continuous characteristic factor; Acquire fuzzy risk distribution information based on the saliency distribution information; Acquire associated risk distribution information according to the numerical probability distribution information of the discrete characteristic factors; Calculating the importance score of each characteristic factor based on the fuzzy risk distribution information and the associated risk distribution information; A target characteristic factor is screened out from the characteristic factors according to the importance score and the importance threshold.

2. The method for configuring monitoring resources of a battery energy storage system according to claim 1, characterized in that: The method of acquiring a multidimensional power disaster data set collected by a data collection system and constructing a disaster event database based on the multidimensional power disaster data set includes: Acquire multi-dimensional data collected by a data acquisition system; Filtering out power disaster data from the multidimensional data, and marking event labels on the power disaster data; Constructing an original data set based on the power disaster data and the event labels; Preprocessing the original data set to obtain a target data set; Performing feature extraction on the target data set to obtain multimodal feature data; A disaster event database is constructed based on the multimodal feature data and the event labels.

3. The method for configuring monitoring resources of a battery energy storage system according to claim 2, characterized in that: The preprocessing of the original data set to obtain the target data set includes: Performing noise reduction processing on the original data set; Perform abnormal data detection and missing data filling on the original data set after noise reduction to obtain a candidate data set; Aligning the time information of the candidate data sets according to the timestamp information of each candidate data in the candidate data sets; Based on the geographic coordinate information of each candidate data in the candidate data set, spatial information alignment is performed on the candidate data set after the time information alignment to obtain a target data set.

4. The method for configuring monitoring resources of a battery energy storage system according to claim 3, characterized in that: The extracting features of the target data set to obtain multimodal feature data includes: Extracting features from each target data according to the data type of each target data in the target data set to obtain an initial feature data set; Performing standardization processing on the initial feature data set to obtain a standardized feature data set; Obtaining weight information of a data acquisition module corresponding to each standardized data in the standardized feature data set; Constructing a weighted fusion model based on the weight information; The standardized feature data set is input into the weighted fusion model for weighted fusion to obtain multimodal feature data.

5. A battery energy storage system monitoring resource configuration device, characterized in that: The battery energy storage system includes a plurality of energy storage power stations, and the battery energy storage system monitoring resource configuration device includes: A multidimensional data processing module, used to obtain a multidimensional power disaster data set collected by a data acquisition system, and to construct a disaster event database based on the multidimensional power disaster data set, wherein the data acquisition system includes a space-based data acquisition module, an air-based data acquisition module, and a ground-based data acquisition module; A fault distribution analysis module, used to obtain the fault spatiotemporal distribution information of the battery energy storage system according to the disaster event database; A situation awareness zoning module, used to construct a situation awareness zoning map of the battery energy storage system based on the fault spatiotemporal distribution information, wherein the situation awareness zoning map includes each monitoring area of ​​the battery energy storage system and the risk level corresponding to each monitoring area, and the monitoring area includes at least one of the energy storage power stations; A monitoring resource configuration module, used to generate a resource coordination configuration strategy according to the situation awareness zoning map, and perform monitoring resource configuration for each monitoring area in the battery energy storage system based on the resource coordination configuration strategy; The fault distribution analysis module is also used to obtain the fault time series distribution information of the disaster event database; generate the importance threshold corresponding to each time period based on the importance measurement condition and the fault time series distribution information, the importance measurement condition includes multi-dimensional measurement conditions, and the multi-dimensionality includes support, confidence, promotion, conviction and leverage; select the target characteristic factor from the characteristic factors of the disaster event database according to the importance threshold; quantify the effect of the target characteristic factor based on the structural importance evaluation information of the battery energy storage system, and obtain the risk impact information corresponding to each target characteristic factor; obtain the fault spatiotemporal distribution information of the battery energy storage system according to the target characteristic factor and the risk impact information; The fault distribution analysis module is also used to classify the characteristic factors based on the characteristic types of each characteristic factor in the disaster event database, determine the continuous characteristic factors and discrete characteristic factors among the characteristic factors; obtain the significance distribution information of each continuous characteristic factor; obtain fuzzy risk distribution information based on the significance distribution information; obtain associated risk distribution information according to the numerical probability distribution information of the discrete characteristic factors; calculate the importance score of each characteristic factor based on the fuzzy risk distribution information and the associated risk distribution information; and screen out the target characteristic factors from the characteristic factors according to the importance score and the importance threshold.

6. A battery energy storage system monitoring resource configuration device, characterized in that: The battery energy storage system monitoring resource configuration device includes: a memory, a processor, and a battery energy storage system monitoring resource configuration program stored in the memory and executable on the processor, wherein the battery energy storage system monitoring resource configuration program is configured to implement the battery energy storage system monitoring resource configuration method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a battery energy storage system monitoring resource configuration program, and when the battery energy storage system monitoring resource configuration program is executed by the processor, the battery energy storage system monitoring resource configuration method according to any one of claims 1 to 4 is implemented.

8. A computer program product, characterized in that The computer program product includes a battery energy storage system monitoring resource configuration program, and when the battery energy storage system monitoring resource configuration program is executed by a processor, the steps of the battery energy storage system monitoring resource configuration method according to any one of claims 1 to 4 are implemented.

Images