Intelligent battery management method based on edge-cloud collaboration and related device

Abstract

The invention discloses a battery intelligent management method based on edge-cloud collaboration and a related device, and the method comprises the steps: obtaining the real-time data of each battery cluster through each cluster-level edge controller in an edge layer, carrying out the preprocessing of the real-time data of each battery cluster, and obtaining the real-time data of each battery cluster; calculating the real-time SOC, the state of health SOH and the maximum chargeable / dischargeable power of each battery cluster according to the preprocessed real-time data of the battery clusters; and at the cloud, correcting the calculated real-time SOC, SOH and maximum chargeable / dischargeable power of each battery cluster, generating a control power instruction of each battery cluster according to a correction result, an economical efficiency target and service life attenuation cost, and respectively issuing the control power instruction to a cluster-level edge controller of each battery cluster for execution. The method and the related device can improve the safety of the battery system.

Description

Technical Field

[0001] This invention belongs to the field of energy storage battery management technology, and relates to a battery intelligent management method and related devices based on edge-cloud collaboration. Background Technology

[0002] With the rapid development of large-scale energy storage systems, the capacity, voltage level, and complexity of battery systems are constantly increasing. Existing technologies mainly suffer from the following drawbacks: **Communication silos:** Battery Management System (BMS), Power Conversion System (PCS), and Energy Management System (EMS) often use independent buses, resulting in large information transmission delays, inconsistent protocols, and difficulty in achieving millisecond-level collaborative control. **Information fragmentation:** State monitoring data (voltage, current, temperature, SOC / SOH) and fault protection data (insulation, thermal runaway, overcurrent) are transmitted separately, leading to data redundancy, wasted bandwidth, and difficulty in making fusion decisions on the same time scale. **Control-protection misalignment:** Traditional solutions classify "battery balancing / power scheduling" as the control layer and "overvoltage / overtemperature / overcurrent" as the protection layer. These two layers operate independently, easily leading to protection actions preceding control actions or conflicts between control commands and protection thresholds, causing system oscillations or false shutdowns, thereby reducing the safety of the battery system. Summary of the Invention

[0003] The purpose of this invention is to overcome the shortcomings of the prior art and provide a battery intelligent management method and related device based on edge-cloud collaboration, which can improve the safety of battery systems.

[0004] To achieve the above objectives, this invention discloses a battery intelligent management method based on edge-cloud collaboration, comprising: At the edge layer, real-time data of each battery cluster is obtained through each cluster-level edge controller. The real-time data of each battery cluster is preprocessed, and the real-time SOC, state of health (SOH), and maximum charge / discharge power of each battery cluster are calculated based on the preprocessed real-time data. In the cloud, the calculated real-time SOC, SOH, and maximum charge / discharge power of each battery cluster are corrected. Based on the correction results, economic objectives, and lifespan degradation costs, control power commands for each battery cluster are generated and sent to the cluster-level edge controller of each battery cluster for execution.

[0005] Furthermore, the process of preprocessing the real-time data of each battery cluster is as follows: A lightweight IOAA-AUKF fusion algorithm is used to perform spatiotemporal alignment and outlier data point removal on the real-time data of each battery cluster.

[0006] Furthermore, the process of correcting the calculated real-time SOC, SOH, and maximum charge / discharge power of each battery cluster is as follows: The real-time SOC, state of health (SOH), and maximum charge / discharge power of each battery cluster are corrected using a full life cycle parameter model.

[0007] Furthermore, the process of generating control power commands for each battery cluster based on the correction results, economic objectives, and lifespan degradation costs is as follows: Based on the correction results, economic objectives, and lifetime degradation costs, a non-uniform power allocation strategy is adopted to generate control power commands for each battery cluster.

[0008] Furthermore, the process of executing the control power command sent to each battery cluster by the cluster-level edge controller is as follows: each cluster-level edge controller receives the control power command sent from the cloud, converts the power command into the charging and discharging current setting value of its own battery cluster, and sends it to the corresponding battery cluster for execution via the CAN bus.

[0009] Furthermore, it also includes: When the real-time data of any battery cluster becomes abnormal, the dynamic reconstruction algorithm is activated to control the MOSFET matrix switch within that battery cluster and switch the battery cluster to bypass.

[0010] This invention discloses a battery intelligent management system based on edge-cloud collaboration, comprising: The first data processing module is used to acquire real-time data of each battery cluster through each cluster-level edge controller at the edge layer, preprocess the real-time data of each battery cluster, and calculate the real-time SOC, state of health (SOH), and maximum charge / discharge power of each battery cluster based on the preprocessed real-time data of the battery cluster. The second data processing module is used to correct the calculated real-time SOC, SOH and maximum charge / discharge power of each battery cluster in the cloud. Based on the correction results, economic targets and life decay costs, it generates control power commands for each battery cluster and sends them to the cluster-level edge controller of each battery cluster for execution.

[0011] Furthermore, the process of preprocessing the real-time data of each battery cluster is as follows: A lightweight IOAA-AUKF fusion algorithm is used to perform spatiotemporal alignment and outlier data point removal on the real-time data of each battery cluster.

[0012] This invention discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the edge-cloud collaborative battery intelligent management method.

[0013] The present invention discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the edge-cloud collaborative battery intelligent management method.

[0014] The present invention has the following beneficial effects: The edge-cloud collaborative battery intelligent management method and related devices described in this invention, in practical operation, construct an edge-cloud collaborative layered processing architecture to offload high-frequency, high-real-time computing tasks (such as fault diagnosis and SOC estimation) to the edge side for processing. This reduces the generation and execution latency of control power commands from over 500ms in the traditional centralized system to less than 100ms, effectively avoiding control lag problems caused by communication delays, meeting the stringent real-time requirements of battery systems for safety control, and thus improving the safety of the battery system. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments of this application will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of the dual attention model in this invention; Figure 2 This is a structural diagram of the battery system; Figure 3 This is a flowchart of the IAOA-AUKF fusion algorithm. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] In the description of this invention, it should be understood that the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0019] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0020] It should also be further understood that the term "and / or" as used in this specification and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations. For example, A and / or B can represent three cases: A alone, A and B simultaneously, and B alone. Additionally, the character " / " in this invention generally indicates that the preceding and following objects have an "or" relationship.

[0021] It should be understood that although terms such as first, second, third, etc., may be used in the embodiments of the present invention to describe the preset range, these preset ranges should not be limited to these terms. These terms are only used to distinguish the preset ranges from one another. For example, without departing from the scope of the embodiments of the present invention, the first preset range may also be referred to as the second preset range, and similarly, the second preset range may also be referred to as the first preset range.

[0022] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0024] The accompanying drawings illustrate various structural schematic diagrams according to embodiments disclosed in this invention. These drawings are not to scale, and some details have been enlarged for clarity, and some details may have been omitted. The shapes of the various regions and layers shown in the drawings, as well as their relative sizes and positional relationships, are merely exemplary and may deviate from reality due to manufacturing tolerances or technical limitations. Furthermore, those skilled in the art can design regions / layers with different shapes, sizes, and relative positions as needed.

[0025] Example 1 refer to Figure 1 and Figure 2 The edge-cloud collaborative battery intelligent management method of the present invention includes the following steps: On the battery side, the entire energy storage system consists of 20 battery clusters connected in parallel. Each battery cluster has a rated voltage of 800V and a capacity of 200kWh. Each battery cluster contains 40 battery packs connected in series. Each battery pack has an integrated BMS slave control module based on STM32F4 and MAX17853 chips, which is responsible for real-time acquisition of the voltage, temperature, and total current of each cell at a frequency of 1Hz. Each battery cluster is equipped with a cluster-level edge coordination controller, which uses a more powerful NVIDIA Jetson Xavier NX module. The cluster-level edge coordination controller communicates with the 40 battery pack slave control modules within the cluster via a CAN bus to aggregate all data.

[0026] Communication network: Industrial-grade 5G base stations or gigabit Ethernet are deployed within the station. 20 cluster-level edge controllers are connected to the station's local area network via 5GCPE or Ethernet switches. The station's local area network is connected to the cloud server via fiber optic cable.

[0027] Cloud Platform: Deployed on the Alibaba Cloud IoT platform, a digital twin of the energy storage power station has been built. This twin not only includes a real-time status image of the energy storage battery system, but also accesses multi-source information such as grid dispatch instructions, local weather forecasts (ambient temperature), and historical electricity price data.

[0028] Specifically, the following steps are included: 1) Obtain the status information of each battery cluster; At the edge layer: Each cluster-level edge controller receives real-time data (approximately 5000 cell data points) uploaded by 40 battery packs within its cluster. The lightweight IAOA-AUKF fusion algorithm deployed within the cluster-level edge controller performs spatiotemporal alignment of the received data, removes outlier data points, and then calculates the real-time SOC, SOH, and maximum charge / discharge power (SOP) of its battery cluster, referencing... Figure 3 .

[0029] In the cloud: The cluster-level edge controller compresses the calculated cluster-level state results (such as SOC=65%, SOH=92%) and key raw data snapshots and uploads them to the cloud digital twin. The cloud uses a full lifecycle parameter model to verify and correct the calculation results of the edge layer, and then sends the corrected results to the cluster-level edge controller to achieve collaborative optimization of cloud training and edge inference, ensuring that the SOC estimation error of the entire site is consistently ≤1.5%.

[0030] 2) Optimize and coordinate control and protection; Cloud-based global optimization strategy generation: When the cloud-based digital twin receives a dispatch command from the power grid to discharge at maximum power within the next two hours, the cloud-based strategy engine is activated. Taking into account the state of the battery clusters, economic objectives, and lifetime degradation costs, a non-uniform power allocation strategy is adopted to generate control power commands for each battery cluster, which are then sent to the corresponding cluster-level edge controllers. The economic objective is that the current electricity price period offers the highest economic benefit from discharge; the lifetime degradation cost is that high-rate discharge accelerates battery aging. The cluster-level edge controller controls the corresponding battery clusters according to the power commands. For battery clusters with higher SOC, better SOH, and lower temperature (such as clusters #5 and #12), higher discharge power (e.g., 55kW) is allocated; for clusters in slightly worse condition (e.g., cluster #3, SOH=88%), lower power (e.g., 45kW) is allocated, aiming to complete the power plant operation commands with minimal overall lifetime degradation costs.

[0031] In addition, each cluster-level edge controller receives power commands from the cloud, converts the power commands into charging and discharging current settings for its own battery cluster, and then sends them to the corresponding battery cluster for execution via the CAN bus.

[0032] The cluster-level edge controller also compares the received power command with the real-time extreme safety status of the battery cluster (such as the highest temperature and the lowest voltage). Suppose that after receiving the 55kW command, a cooling fan of battery cluster #12 suddenly fails, causing its internal highest temperature to rise to 58°C within 10 seconds. Then the cluster-level edge controller immediately activates the outer loop protection. That is, it will not wait for the cloud response (which may be delayed by hundreds of milliseconds), but will autonomously reduce the discharge power from 55kW to 48kW according to local rules, and at the same time send an over-temperature derating alarm and operation log to the cloud.

[0033] After receiving the alert in the cloud, the digital twin simulates the operation and confirms that the derating operation is reasonable and does not affect the overall task. Then, it approves the instruction and re-optimizes the allocation of power to the remaining clusters to make up for the reduced power output of battery cluster #12 and ensure that the total output power remains stable at 1MW.

[0034] 3) Fault dynamic reconfiguration (control and protection optimization and coordination); Fault detection: During the discharge process, the cluster-level edge controller corresponding to battery cluster #7 detected an abnormal voltage drop in battery pack #25 (15% lower than the average voltage of other packs) and a continuous temperature rise through real-time data monitoring, indicating that battery cluster #7 has an internal short circuit fault risk.

[0035] The controller immediately initiates the dynamic reconfiguration algorithm, controlling the MOSFET matrix switch within the battery cluster to quickly bypass the faulty battery pack No. 25 from the main circuit within 80ms.

[0036] When a battery pack is lost, the total voltage of the battery cluster drops. The cluster-level edge controller adjusts the operating point of the DC / DC converter to ensure the output voltage of the battery cluster is stable, and immediately reports the status of "cluster output voltage change, temporary capacity reduction" to the cloud.

[0037] Upon receiving the fault reconstruction information, the cloud platform immediately updates the system topology in the digital twin and assesses the impact.

[0038] Due to the temporary reduction in capacity of battery cluster #7, the cloud adjusts its subsequent charging and discharging power commands and appropriately increases the power of other healthy clusters to maintain the system's total energy throughput capacity.

[0039] At the same time, a maintenance alert is generated in the cloud to notify staff to replace the faulty battery pack as soon as possible.

[0040] This invention constructs an edge-cloud collaborative layered processing architecture, offloading high-frequency, high-real-time computing tasks (such as fault diagnosis and SOC estimation) to the edge for processing. It reduces the generation and execution latency of critical control commands from over 500ms in traditional centralized systems to less than 100ms, effectively avoiding control lag caused by communication delays and meeting the stringent real-time requirements of battery systems for safety control. Significantly improving the accuracy and robustness of battery state estimation, this invention innovatively adopts a mechanism-data hybrid driving model and the IOA-AUKF joint algorithm, integrating multi-source heterogeneous data (electrical, thermal, and operating condition data). It achieves an SOC estimation error ≤1.5% and a SOH prediction error ≤2% across the entire temperature range, far exceeding the accuracy of traditional single models (error >5%), providing a solid and reliable data foundation for deep optimization control of batteries. Through collaborative innovation in architecture, algorithms, and hardware, this invention systematically solves the core pain points of battery management in terms of real-time performance, accuracy, reliability, and economy, providing a high-performance, high-reliability solution for battery systems in large-scale energy storage power stations.

[0041] Example 2 The edge-cloud collaborative battery intelligent management system of the present invention includes: The first data processing module is used to acquire real-time data of each battery cluster through each cluster-level edge controller at the edge layer, preprocess the real-time data of each battery cluster, and calculate the real-time SOC, state of health (SOH), and maximum charge / discharge power of each battery cluster based on the preprocessed real-time data of the battery cluster. The second data processing module is used to correct the calculated real-time SOC, SOH and maximum charge / discharge power of each battery cluster in the cloud. Based on the correction results, economic targets and life decay costs, it generates control power commands for each battery cluster and sends them to the cluster-level edge controller of each battery cluster for execution.

[0042] In this embodiment, the process of preprocessing the real-time data of each battery cluster is as follows: A lightweight IOAA-AUKF fusion algorithm is used to perform spatiotemporal alignment and outlier data point removal on the real-time data of each battery cluster.

[0043] The photovoltaic panel is moved according to the offset, so that the offset is within a preset range.

[0044] The module division in this embodiment is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in each embodiment of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0045] Example 3 A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the edge-cloud collaborative battery intelligent management method. For example, the method includes: at the edge layer, acquiring real-time data of each battery cluster through each cluster-level edge controller; preprocessing the real-time data of each battery cluster; and calculating the real-time SOC, state of health (SOH), and maximum charge / discharge power of each battery cluster based on the preprocessed real-time data; at the cloud layer, correcting the calculated real-time SOC, SOH, and maximum charge / discharge power of each battery cluster; and generating control power commands for each battery cluster based on the correction results, economic objectives, and lifespan degradation costs, and sending these commands to the cluster-level edge controllers of each battery cluster for execution. The memory may include main memory, such as high-speed random access memory (RAM), or non-volatile memory, such as at least one disk storage device. The processor, network interface, and memory are interconnected via an internal bus, which may be an industry-standard architecture bus, a peripheral component interconnection standard bus, or an extended industry-standard architecture bus. The bus can be categorized as an address bus, data bus, or control bus. The memory stores programs; specifically, the program may include program code, which includes computer operation instructions. The memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0046] Example 4 A computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the edge-cloud collaborative battery intelligent management method. For example, the method includes: at the edge layer, acquiring real-time data of each battery cluster through each cluster-level edge controller; preprocessing the real-time data of each battery cluster; and calculating the real-time SOC, state of health (SOH), and maximum charge / discharge power of each battery cluster based on the preprocessed real-time data; at the cloud layer, correcting the calculated real-time SOC, SOH, and maximum charge / discharge power of each battery cluster; generating control power commands for each battery cluster based on the correction results, economic objectives, and lifetime degradation costs; and issuing these commands to the cluster-level edge controllers of each battery cluster for execution. Specifically, the computer-readable storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. The volatile memory may include random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include read-only memory (ROM), hard disk, flash memory, optical disk, magnetic disk, etc.

[0047] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0048] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0049] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0050] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0051] Other embodiments of the invention will readily occur to those skilled in the art upon consideration of the specification and disclosure of the invention. This application is intended to cover any variations, uses, or adaptations of the invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of the invention are indicated by the following claims.

[0052] It should be understood that the present invention is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of the invention is limited only by the appended claims.

[0053] The above description is merely a preferred embodiment of the present invention and does not constitute any limitation on the present invention. Any simple modifications, alterations, or equivalent structural changes made to the above embodiments based on the technical essence of the present invention shall still fall within the protection scope of the present invention.

Claims

1. A battery intelligent management method based on edge-cloud collaboration, characterized in that, The method comprises the following steps of: In the edge layer, real-time data of each battery cluster is acquired by each cluster-level edge controller, the real-time data of each battery cluster is preprocessed, real-time SOC, health state SOH and maximum chargeable / dischargable power of each battery cluster are calculated according to the preprocessed real-time data of each battery cluster; In the cloud, the calculated real-time SOC, health state SOH and maximum chargeable / dischargable power of each battery cluster are corrected, control power instructions of each battery cluster are generated according to the correction results, economic targets and life attenuation costs, and the control power instructions are respectively sent to the cluster-level edge controllers of each battery cluster for execution. 2.The edge-cloud collaborative based battery intelligent management method of claim 1, wherein, The process of preprocessing the real-time data of each battery cluster comprises the following steps of: The real-time data of each battery cluster is aligned in time and space and abnormal data points are removed by using a lightweight IAOA-AUKF fusion algorithm. 3.The edge-cloud collaborative based battery intelligent management method of claim 1, wherein, The process of correcting the calculated real-time SOC, health state SOH and maximum chargeable / dischargable power of each battery cluster comprises the following steps of: The calculated real-time SOC, health state SOH and maximum chargeable / dischargable power of each battery cluster are corrected by using a full life cycle parameter model. 4.The edge-cloud collaborative based battery intelligent management method of claim 1, wherein, The process of generating the control power instructions of each battery cluster according to the correction results, economic targets and life attenuation costs comprises the following steps of: The control power instructions of each battery cluster are generated by using a non-uniform power distribution strategy according to the correction results, economic targets and life attenuation costs. 5.The edge-cloud collaborative based battery intelligent management method of claim 1, wherein, The process of respectively sending the control power instructions to the cluster-level edge controllers of each battery cluster for execution comprises the following steps of: each cluster-level edge controller receives the control power instructions sent by the cloud, converts the power instructions into charge / discharge current set values of the battery cluster, and sends the charge / discharge current set values to the corresponding battery cluster for execution through a CAN bus. 6.The edge-cloud collaborative based battery intelligent management method according to claim 1, wherein, The method further comprises the following steps of: When the real-time data of any battery cluster is abnormal, a dynamic reconstruction algorithm is started to control MOSFET matrix switches in the battery cluster, and the battery cluster is switched to bypass.

7. A battery intelligent management system based on edge-cloud collaboration, characterized in that, The method comprises the following steps of: A first data processing module is configured to acquire real-time data of each battery cluster by each cluster-level edge controller in the edge layer, preprocess the real-time data of each battery cluster, and calculate real-time SOC, health state SOH and maximum chargeable / dischargable power of each battery cluster according to the preprocessed real-time data of each battery cluster; A second data processing module is configured to correct the calculated real-time SOC, health state SOH and maximum chargeable / dischargable power of each battery cluster in the cloud, generate control power instructions of each battery cluster according to the correction results, economic targets and life attenuation costs, and respectively send the control power instructions to the cluster-level edge controllers of each battery cluster for execution. 8.The edge-cloud collaborative based battery intelligent management system according to claim 7, wherein, The process of preprocessing the real-time data of each battery cluster comprises the following steps of: The real-time data of each battery cluster is aligned in time and space and abnormal data points are removed by using a lightweight IAOA-AUKF fusion algorithm.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the steps of the battery intelligent management method based on edge-cloud collaboration according to any one of claims 1-6.

10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to realize the steps of the battery intelligent management method based on edge-cloud collaboration according to any one of claims 1-6.

Images