An automatic battery replacement fault prediction system and method based on edge collaborative computing

Abstract

This invention discloses an automatic battery swapping fault prediction system and method based on edge collaborative computing. The system includes: a cloud, a master device, and slave devices. The cloud includes a presentation layer and a service layer. The master device includes a scheduling layer, a computing layer, and a hardware layer. The slave device includes a computing layer and a hardware layer. The presentation layer sends tasks to be processed to the scheduling layer of the master device through the service layer, infers the task status during task execution, and displays the execution results after task completion. The service layer defines the input and output of service requirements and interacts with the scheduling layer. The scheduling layer manages the master and slave devices, decomposes, orchestrates, and schedules tasks, and performs load balancing for the devices. The computing layer executes corresponding tasks according to the scheduling layer and reports the task execution results to the scheduling layer. The hardware layer collects the basic data required by the computing layer of the device to execute tasks and reports it to the computing layer of the device.

Description

Technical Field

[0001] This invention relates to the field of new energy vehicle technology, and in particular to an automatic battery swapping fault prediction system and method based on edge collaborative computing. Background Technology

[0002] Fault detection and reporting are crucial components of automatic battery swapping systems. However, we usually only report and issue warnings after a fault occurs. Early detection of potential faults is an important research topic.

[0003] As the company's hardware equipment becomes more diverse and sophisticated, these devices, while belonging to the same ecosystem, still exist as information silos. However, the diverse and multi-point collected data often holds potential value, such as battery connector temperature warnings, battery swapping process quality assessments, and driver behavior analysis. Therefore, breaking down these barriers and leveraging the value of the equipment ecosystem to predict automatic battery swapping system failures is a pressing technical challenge in this field. Summary of the Invention

[0004] The purpose of this invention is to provide an automatic battery swapping fault prediction system and method based on edge collaborative computing, which can solve the above-mentioned problems existing in the prior art.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: This invention provides an automatic battery swapping fault prediction system based on edge collaborative computing. The system includes: a cloud, a master device, and slave devices; the cloud includes a presentation layer and a service layer; the master device includes a scheduling layer, a computing layer, and a hardware layer; and the slave device includes a computing layer and a hardware layer. The presentation layer is used to send the task to be processed to the scheduling layer of the main device through the business layer, infer the task status during task execution, and display the execution result after the task is completed. The business layer is used to define the input and output of business requirements and to interact with the scheduling layer. The scheduling layer is used for master and slave device management, task breakdown, orchestration and scheduling, and load balancing of devices; The computing layer is used to schedule and execute corresponding tasks according to the scheduling layer, and to report the task execution results to the scheduling layer. The hardware layer is used to collect the basic data required by the computing layer of the device to perform tasks, and to report it to the computing layer of the device.

[0006] Optionally, the service layer includes: a first edge computing service module, and a battery swapping station security module, an equipment fault analysis module, a driving behavior analysis module, and a battery cell or connector temperature abnormality early warning module that interact with the first edge computing service module; The edge computing service module is equipped with a unified interface to receive feedback results from the battery swapping station security module, equipment fault analysis module, driving behavior analysis module, and battery cell or connector temperature anomaly early warning module, and aggregates the feedback results.

[0007] Optionally, the scheduling layer includes: a node monitoring and health assessment module, an automatic orchestration module, a device management module, a load balancing module, and a task scheduling module.

[0008] Optionally, the device management module is used to manage master devices and slave devices, wherein the management of devices includes: device registration, device heartbeat monitoring, and device capability query; The automatic orchestration module is used for task orchestration; The task scheduling module is used for task breakdown and scheduling; The node monitoring health assessment module is used to assess the health status of the managed devices and send the assessment results to the load balancing module. The load balancing module is used for load balancing and allocation of equipment.

[0009] Optionally, the computing layer includes: a second edge computing service module and an algorithm module that interacts with the second edge computing service module; The algorithm module includes: a pattern recognition unit, an image recognition unit, a deep learning unit, a natural language processing unit, and a noise reduction and filtering unit; The second computing service module is used to send computing tasks to the algorithm module, and aggregate the processing results of each unit in the algorithm module before reporting them to the scheduling layer; The algorithm module is used to perform the corresponding computational tasks.

[0010] Optionally, the hardware layer of the main device includes: a video image acquisition module, an audio acquisition module, a connector temperature data acquisition module, and a gyroscope data acquisition module.

[0011] Optionally, the hardware layer of the slave device includes: a cell voltage data acquisition module, a video image acquisition module, an audio acquisition module, a connector temperature data acquisition module, and a gyroscope data acquisition module.

[0012] This invention also provides an automatic battery swapping fault prediction method based on edge collaborative computing. The method is applied to an automatic battery swapping fault prediction system based on edge collaborative computing, the system comprising: a cloud, a master device, and slave devices; the cloud includes a presentation layer and a service layer; the master device includes a scheduling layer, a computing layer, and a hardware layer; the slave device includes a computing layer and a hardware layer; the method includes: The presentation layer sends the tasks to be processed to the scheduling layer of the main device through the business layer, infers the task status during task execution, and displays the execution results after the task is completed. The business layer defines the input and output of business requirements and interacts with the scheduling layer. The scheduling layer breaks down, orchestrates, and schedules tasks, and allocates equipment to execute tasks based on the load balancing of the equipment. The hardware layer collects the basic data required by the computing layer of the device to execute tasks, and reports it to the computing layer of the device so that the computing layer can execute the corresponding tasks. The computing layer of the allocated equipment executes the corresponding task based on the basic data reported by the scheduling layer and the hardware layer, and reports the task execution result to the scheduling layer. The scheduling layer reports the execution results to the presentation layer through the business layer, and the presentation layer displays the execution results after the task is completed.

[0013] Optionally, the service layer includes: a first edge computing service module, and a battery swapping station security module, an equipment fault analysis module, a driving behavior analysis module, and a battery cell or connector temperature abnormality early warning module that interact with the first edge computing service module; The edge computing service module is equipped with a unified interface to receive feedback results from the battery swapping station security module, equipment fault analysis module, driving behavior analysis module, and battery cell or connector temperature anomaly early warning module, and aggregates the feedback results.

[0014] Optionally, the scheduling layer includes: a node monitoring and health assessment module, an automatic orchestration module, a device management module, a load balancing module, and a task scheduling module. The scheduling layer performs task decomposition, orchestration, and scheduling, and allocates devices to execute tasks based on the load balancing of the devices, including the following steps: The device management module is invoked to manage master and slave devices, including device registration, device heartbeat monitoring, and device capability query. The automatic orchestration module is invoked to perform task orchestration. The task scheduling module is invoked to perform task breakdown and scheduling; The node monitoring and health assessment module is invoked to assess the health status of the managed devices, and the assessment results are sent to the load balancing module. The load balancing module is invoked to perform load balancing on the devices.

[0015] The automatic battery swapping fault prediction system based on edge collaborative computing provided in this invention includes a cloud, a master device, and slave devices. The cloud includes a presentation layer and a business layer. The master device includes a scheduling layer, a computing layer, and a hardware layer. The slave device includes a computing layer and a hardware layer. The presentation layer is used to send tasks to be processed to the scheduling layer of the master device through the business layer, infer the task status during task execution, and display the execution results after the task is completed. The business layer is used to define the input and output of business requirements and to interact with the scheduling layer. The scheduling layer is used to manage the master and slave devices, decompose, orchestrate, and schedule tasks, and perform load balancing of the devices. The computing layer is used to execute the corresponding tasks according to the scheduling layer and report the task execution results to the scheduling layer. The hardware layer is used to collect the basic data required by the computing layer of the device to execute tasks and report it to the computing layer of the device. The solution provided in this application, firstly, abstracts hardware devices with different architectures and capabilities into unified "computing nodes," "storage nodes," and "communication nodes," hiding the underlying complexity from upper-layer services and applications, exhibiting good adaptability, and predicting faults in the automatic battery swapping system based on information shared between devices; secondly, it can dynamically allocate and schedule computing subtasks according to task requirements, current device status, and data localization attributes; thirdly, it provides capabilities to the service layer through a set of defined API interfaces using RPC channels, enabling services to utilize the entire edge cluster as if calling a submodule; and fourthly, it completes task processing and data processing at the edge, i.e., from the device side, uploading only necessary results or aggregated data to the cloud service layer, thereby reducing latency and bandwidth consumption. Attached Figure Description

[0016] Figure 1 This is a structural block diagram illustrating an automatic battery swapping fault prediction system based on edge collaborative computing, according to an embodiment of this application. Figure 2 This is a structural block diagram illustrating an automatic battery swapping fault prediction system based on edge collaborative computing, according to an embodiment of this application. Figure 3 This is a schematic diagram of a device ecosystem; Figure 4 This is a flowchart illustrating the steps of the automatic battery swapping fault prediction method based on edge collaborative computing according to an embodiment of this application. Detailed Implementation

[0017] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0018] The following description, in conjunction with the accompanying drawings, details the automatic battery swapping fault prediction scheme based on edge collaborative computing provided in this application through specific embodiments and application scenarios.

[0019] In order to break down information silos between devices and leverage the value of the device ecosystem, the inventors of this application proposed introducing RPC (Remote Procedure Call) technology to break down barriers between devices. However, the following challenges remain: Challenge 1: Edge devices generate massive amounts of data, and uploading all of it to the cloud for processing leads to: Challenge 2: High bandwidth costs, especially for high-frequency data such as CAN messages, gyroscope data, temperature data, or video streams; Challenge 3: High latency, as network transmission time cannot meet real-time requirements; Challenge 4: Privacy and security risks, as it is impossible to ensure that sensitive data such as battery swapping-related data does not leave the site, making it difficult to meet the needs of customers with high security requirements.

[0020] The inventors designed an architecture that is compatible with diverse and heterogeneous hardware environments and capable of handling complex intelligent tasks. The diverse and heterogeneous hardware environments are mainly reflected in the vast differences in device form factors, computing power, power consumption, and instruction sets at the edge. The complex processing capability of intelligent tasks is mainly reflected in the ability to completely execute multiple stages such as data acquisition, preprocessing, inference, decision-making, and control, which is difficult for a single device to complete. This architecture maximizes overall efficiency through collaboration between master devices, slave devices, and the cloud, thereby predicting potential faults in the automatic battery swapping system.

[0021] Appendix Figure 1 This is a structural block diagram of an automatic battery swapping fault prediction system based on edge collaborative computing implemented in this application.

[0022] As attached Figure 1 As shown, the automatic battery swapping fault prediction system based on edge collaborative computing includes: a cloud 101, a master device 102, and a slave device 103; the cloud 101 includes a presentation layer 1011 and a business layer 1012; the master device 102 includes a scheduling layer 1021, a computing layer 1022, and a hardware layer 1023; the slave device 103 includes a computing layer 1031 and a hardware layer 1032. It should be noted that the functional modules contained in the computing layers of the master device and the slave device can be the same or different.

[0023] The presentation layer 1011 is used to send the tasks to be processed to the scheduling layer 1021 of the master device 102 through the business layer 1012, infer the task status during task execution, and display the execution result after the task is completed; that is, the presentation layer is responsible for the display of the final result and the configuration entry for manual scheduling.

[0024] The business layer 1012 is used to define the input and output of business requirements and to interact with the scheduling layer 1021. The scheduling layer 1021 is used for master and slave device management, task decomposition, orchestration and scheduling, and load balancing of devices; the scheduling layer is the core brain of the system.

[0025] The computation layer 1022 is used to execute corresponding tasks according to the scheduling layer and report the task execution results to the scheduling layer 1021; the computation layer is mainly responsible for the execution of tasks such as filtering, inference, and deep learning.

[0026] The hardware layer 1032 is used to collect the basic data required by the computing layer of the device to perform tasks, and report it to the computing layer 1022 of the device.

[0027] The hardware layer 1032 consists of actual physical devices, each with different computing capabilities and specializations.

[0028] It should be noted that the automatic battery swapping fault prediction system based on edge collaborative computing can include at least one slave device, and there is no specific limit to the number of slave devices. Each slave device can include the same functional modules, or the functional modules included in each slave device can differ. However, each slave device includes a computing layer and a hardware layer.

[0029] In one optional embodiment, the service layer includes: a first edge computing service module, and a battery swapping station safety prevention module, an equipment fault analysis module, a driving behavior analysis module, and a battery cell or connector temperature anomaly early warning module that interact with the first edge computing service module; the edge computing service module is provided with a unified interface to receive feedback results from the battery swapping station safety prevention module, the equipment fault analysis module, the driving behavior analysis module, and the battery cell or connector temperature anomaly early warning module, and to aggregate the feedback results.

[0030] The first edge computing service module includes a unified interface that can provide data transmission between the various functional modules in the business layer and the functional modules in the presentation layer. It should be noted that the functional modules included in the business layer are not limited to those listed above; those skilled in the art can add, delete, or replace one or more of these functional modules according to actual needs.

[0031] In one optional embodiment, the scheduling layer of the master device may include: a node monitoring and health assessment module, an automatic orchestration module, a device management module, a load balancing module, and a task scheduling module.

[0032] The automatic orchestration module can be connected to the battery swapping station safety prevention module, equipment fault analysis module, driving behavior analysis module, and cell or connector temperature abnormality early warning module in the business layer, respectively, so as to automatically orchestrate tasks according to the task requirements of each functional module and send the automatically orchestrated tasks to the task scheduling module in the scheduling layer.

[0033] The device management module is used to manage master and slave devices. Device management includes: device registration, device heartbeat monitoring, and device capability query. The automatic orchestration module is used for task orchestration. The task scheduling module is used for task breakdown and scheduling; The node monitoring and health assessment module is used to assess the health status of the managed devices and send the assessment results to the load balancing module. The load balancing module is used for load balancing and allocation of equipment.

[0034] This optional scheduling layer structure can reasonably orchestrate and schedule various types of tasks issued by the business layer, thereby ensuring the orderly and efficient execution of tasks.

[0035] In one optional embodiment, the computing layer includes: a second edge computing service module and an algorithm module that interacts with the second edge computing service module; the algorithm module includes: a pattern recognition unit, an image recognition unit, a deep learning unit, a natural language processing unit, and a noise reduction and filtering unit; The second computing service module is used to send computing tasks to the algorithm module and aggregate the processing results of each unit in the algorithm module before reporting them to the scheduling layer; the algorithm module is used to execute the corresponding computing tasks.

[0036] In one optional embodiment, the hardware layer of the master device may include: a video image acquisition module, an audio acquisition module, a connector temperature data acquisition module, and a gyroscope data acquisition module. The hardware layer of the slave device may include: a cell voltage data acquisition module, a video image acquisition module, an audio acquisition module, a connector temperature data acquisition module, and a gyroscope data acquisition module. A structural block diagram of a preferred automatic battery swapping fault prediction system based on edge collaborative computing is shown below. Figure 2 As shown.

[0037] It should be noted that the functional modules contained in the hardware layers of the master device and the slave device can be the same or different. The hardware layer of the master device can be directly connected to the second edge computing service module in the master device, and the hardware layer of the slave device can be directly connected to the second edge computing service module in the slave device.

[0038] The automatic battery swapping fault prediction system based on edge collaborative computing provided in this application includes a cloud, a master device, and slave devices. The cloud includes a presentation layer and a business layer. The master device includes a scheduling layer, a computing layer, and a hardware layer. The slave device includes a computing layer and a hardware layer. The presentation layer is used to send tasks to be processed to the scheduling layer of the master device through the business layer, infer the task status during task execution, and display the execution results after the task is completed. The business layer is used to define the input and output of business requirements and to interact with the scheduling layer. The scheduling layer is used to manage the master and slave devices, decompose, orchestrate, and schedule tasks, and perform load balancing of the devices. The computing layer is used to execute the corresponding tasks according to the scheduling layer and report the task execution results to the scheduling layer. The hardware layer is used to collect the basic data required by the computing layer of the device to execute tasks and report it to the computing layer of the device. The solution provided in this application, firstly, abstracts hardware devices with different architectures and capabilities into unified "computing nodes," "storage nodes," and "communication nodes," hiding the underlying complexity from upper-layer services and applications, exhibiting good adaptability, and predicting faults in the automatic battery swapping system based on information shared between devices; secondly, it can dynamically allocate and schedule computing subtasks according to task requirements, current device status, and data localization attributes; thirdly, it provides capabilities to the service layer through a set of defined API interfaces using RPC channels, enabling services to utilize the entire edge cluster as if calling a submodule; and fourthly, it completes task processing and data processing at the edge, i.e., from the device side, uploading only necessary results or aggregated data to the cloud service layer, thereby reducing latency and bandwidth consumption.

[0039] The following is combined Figure 3 The device ecosystem diagram shown illustrates the automatic battery swapping fault prediction method based on edge collaborative computing.

[0040] Figure 3 This system integrates equipment such as station control, vehicle battery swapping controller, battery operation controller, station control intelligent video inference engine, and cloud computing into an ecosystem. By merging data within this ecosystem, applications can proactively detect battery swapping faults. The station control system acts as the master device, while the vehicle battery swapping controller, battery operation controller, and vehicle battery swapping controller function as slave devices.

[0041] For example, when the charger in the station control system is charging the battery, it is found that the extreme voltage or temperature of the battery cell fluctuates more than that of other batteries, but does not exceed the critical value. If the power data provided by the SMES (Site Energy Management System) shows no power abnormality and the charger's operating temperature is normal, then the battery is suspected to be a problem battery.

[0042] For example, when a battery is transferred from a battery swapping station to a vehicle, the battery swapping station transmits data to the vehicle's battery swapping controller via the RPC (Remote Procedure Call Protocol). When the battery is discharging, the vehicle's battery swapping controller focuses on the extreme values ​​of the cell voltage or temperature. If it finds that this battery also has fluctuation problems compared to other batteries, it will report a cell failure.

[0043] As attached Figure 4 As shown, the automatic battery swapping fault prediction method based on edge collaborative computing in this application includes the following steps: Step 401: The presentation layer sends the task to be processed to the scheduling layer of the main device through the business layer, infers the task status during task execution, and displays the execution result after the task is completed.

[0044] The automatic battery swapping fault prediction method based on edge collaborative computing provided in this application is applied to an automatic battery swapping fault prediction system based on edge collaborative computing, such as... Figure 1 As shown, the system includes: a cloud, a master device, and slave devices; the cloud includes a presentation layer and a business layer; the master device includes a scheduling layer, a computing layer, and a hardware layer; and the slave devices include a computing layer and a hardware layer. For the specific structure of each device and the operating logic of each functional module in the edge collaborative computing-based automatic battery swapping fault prediction system, please refer to the relevant descriptions in the aforementioned system embodiments, and they will not be repeated here.

[0045] Step 402: The business layer defines the input and output of business requirements and interacts with the scheduling layer.

[0046] In one optional embodiment, the service layer includes: a first edge computing service module, and a battery swapping station safety prevention module, an equipment fault analysis module, a driving behavior analysis module, and a battery cell or connector temperature anomaly early warning module that interact with the first edge computing service module; the edge computing service module is provided with a unified interface to receive feedback results from the battery swapping station safety prevention module, the equipment fault analysis module, the driving behavior analysis module, and the battery cell or connector temperature anomaly early warning module, and to aggregate the feedback results.

[0047] Step 403: The scheduling layer breaks down, orchestrates, and schedules tasks, and allocates equipment to execute tasks based on the load balancing of the equipment.

[0048] In one optional embodiment, the scheduling layer includes: a node monitoring and health assessment module, an automatic orchestration module, a device management module, a load balancing module, and a task scheduling module. When the scheduling layer decomposes, orchestrates, and schedules tasks, and allocates devices to execute tasks based on the load balancing of the devices, it can perform the following specific process: The device management module is invoked to manage master and slave devices. Device management includes: device registration, device heartbeat monitoring, and device capability query. Call the automatic orchestration module to orchestrate tasks; Call the task scheduling module to break down and schedule tasks; The node monitoring and health assessment module is invoked to assess the health status of the managed devices and the assessment results are sent to the load balancing module. The load balancing module is invoked to perform load balancing on the devices.

[0049] Step 404: The hardware layer collects the basic data required by the computing layer of the device to execute the task, and reports it to the computing layer of the device so that the computing layer can execute the corresponding task.

[0050] Step 405: The computing layer of the allocated device executes the corresponding task based on the basic data reported by the scheduling layer and the hardware layer, and reports the task execution result to the scheduling layer.

[0051] Step 406: The scheduling layer reports the execution result to the presentation layer through the business layer. The presentation layer displays the execution result after the task is completed.

[0052] The embodiments provided in this application Figure 1 The automatic battery swapping fault prediction system shown can achieve... Figure 4 The various processes implemented in the method implementation examples will not be described again here to avoid repetition.

[0053] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0054] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. An automatic battery swapping fault prediction system based on edge collaborative computing, characterized in that, The system includes: a cloud, a master device, and slave devices; the cloud includes a presentation layer and a business layer; the master device includes a scheduling layer, a computing layer, and a hardware layer; the slave device includes a computing layer and a hardware layer. The presentation layer is used to send the task to be processed to the scheduling layer of the main device through the business layer, infer the task status during task execution, and display the execution result after the task is completed. The business layer is used to define the input and output of business requirements and to interact with the scheduling layer. The scheduling layer is used for master and slave device management, task breakdown, orchestration and scheduling, and load balancing of devices; The computing layer is used to schedule and execute corresponding tasks according to the scheduling layer, and to report the task execution results to the scheduling layer. The hardware layer is used to collect the basic data required by the computing layer of the device to perform tasks, and to report it to the computing layer of the device.

2. The system according to claim 1, characterized in that, The business layer includes: a first edge computing service module, and a battery swapping station security module, an equipment fault analysis module, a driving behavior analysis module, and a battery cell or connector temperature abnormality early warning module that interact with the first edge computing service module. The edge computing service module is equipped with a unified interface to receive feedback results from the battery swapping station security module, equipment fault analysis module, driving behavior analysis module, and battery cell or connector temperature anomaly early warning module, and aggregates the feedback results.

3. The system according to claim 1, characterized in that, The scheduling layer includes: a node monitoring and health assessment module, an automatic orchestration module, a device management module, a load balancing module, and a task scheduling module.

4. The system according to claim 3, characterized in that: The device management module is used to manage master devices and slave devices. The device management includes: device registration, device heartbeat monitoring, and device capability query. The automatic orchestration module is used for task orchestration; The task scheduling module is used for task breakdown and scheduling; The node monitoring health assessment module is used to assess the health status of the managed devices and send the assessment results to the load balancing module. The load balancing module is used for load balancing and allocation of equipment.

5. The system according to claim 1, characterized in that, The computing layer includes: a second edge computing service module and an algorithm module that interacts with the second edge computing service module; The algorithm module includes: a pattern recognition unit, an image recognition unit, a deep learning unit, a natural language processing unit, and a noise reduction and filtering unit; The second computing service module is used to send computing tasks to the algorithm module, and aggregate the processing results of each unit in the algorithm module before reporting them to the scheduling layer; The algorithm module is used to perform the corresponding computational tasks.

6. The system according to claim 1, characterized in that, The hardware layer of the main device includes: a video image acquisition module, an audio acquisition module, a connector temperature data acquisition module, and a gyroscope data acquisition module.

7. The system according to claim 1, characterized in that, The hardware layer of the slave device includes: a cell voltage data acquisition module, a video image acquisition module, an audio acquisition module, a connector temperature data acquisition module, and a gyroscope data acquisition module.

8. A method for predicting automatic battery swapping faults based on edge collaborative computing, characterized in that, The method is applied to an automatic battery swapping fault prediction system based on edge collaborative computing. The system includes: a cloud, a master device, and slave devices; the cloud includes a presentation layer and a service layer; the master device includes a scheduling layer, a computing layer, and a hardware layer; the slave device includes a computing layer and a hardware layer; the method includes: The presentation layer sends the tasks to be processed to the scheduling layer of the main device through the business layer, infers the task status during task execution, and displays the execution results after the task is completed. The business layer defines the input and output of business requirements and interacts with the scheduling layer. The scheduling layer breaks down, orchestrates, and schedules tasks, and allocates equipment to execute tasks based on the load balancing of the equipment. The hardware layer collects the basic data required by the computing layer of the device to execute tasks, and reports it to the computing layer of the device so that the computing layer can execute the corresponding tasks. The computing layer of the allocated equipment executes the corresponding task based on the basic data reported by the scheduling layer and the hardware layer, and reports the task execution result to the scheduling layer. The scheduling layer reports the execution results to the presentation layer through the business layer, and the presentation layer displays the execution results after the task is completed.

9. The method according to claim 8, characterized in that, The business layer includes: a first edge computing service module, and a battery swapping station security module, an equipment fault analysis module, a driving behavior analysis module, and a battery cell or connector temperature abnormality early warning module that interact with the first edge computing service module. The edge computing service module is equipped with a unified interface to receive feedback results from the battery swapping station security module, equipment fault analysis module, driving behavior analysis module, and battery cell or connector temperature anomaly early warning module, and aggregates the feedback results.

10. The method according to claim 8, characterized in that, The scheduling layer includes: a node monitoring and health assessment module, an automatic orchestration module, a device management module, a load balancing module, and a task scheduling module. The scheduling layer performs task decomposition, orchestration, and scheduling, and allocates devices to execute tasks based on the load balancing of the devices, including the following steps: The device management module is invoked to manage master and slave devices, including device registration, device heartbeat monitoring, and device capability query. The automatic orchestration module is invoked to perform task orchestration. The task scheduling module is invoked to perform task breakdown and scheduling; The node monitoring and health assessment module is invoked to assess the health status of the managed devices, and the assessment results are sent to the load balancing module. The load balancing module is invoked to perform load balancing on the devices.

Images