Data analysis method and device of energy storage equipment, equipment and medium

Abstract

The invention provides a data analysis method, device and equipment of energy storage equipment and a medium, and relates to the technical field of transportation. The method is applied to an upper computer, and comprises the following steps: receiving original communication data sent by energy storage equipment under the condition of establishing communication connection with multiple pieces of energy storage equipment; identifying a communication protocol type adopted by the energy storage equipment according to the original communication data; converting the original communication data into operation data in a preset format according to the communication protocol type; the preset format is a protocol type adopted by the upper computer; and analyzing the operation states of the plurality of energy storage devices according to the operation data. A standardized data format can be adopted for analysis, a large amount of data can be rapidly processed, and the response speed is increased.

Description

Technical Field

[0001] The present invention relates to the field of transportation technology, and in particular to a data analysis method, device, equipment and medium for energy storage equipment. Background Art

[0002] With the widespread application of renewable energy and the demand for intelligent power systems, the deployment scale of energy storage equipment continues to expand.

[0003] Currently, most energy storage device monitoring systems use decentralized local controllers. However, these controllers cannot quickly process large amounts of data, which can lead to response delays and make centralized monitoring difficult. Summary of the Invention

[0004] The present invention provides a data analysis method, apparatus, device and medium for energy storage equipment, aiming to solve the problem that response delays are easily caused and centralized monitoring is difficult to achieve.

[0005] A first aspect of the present invention provides a data analysis method for an energy storage device, which is applied to a host computer, and the method comprises:

[0006] When establishing communication connections with multiple energy storage devices, receiving original communication data sent by the energy storage devices;

[0007] Identifying a communication protocol type used by the energy storage device based on the original communication data;

[0008] According to the communication protocol type, the original communication data is converted into operation data in a preset format; the preset format is the protocol type adopted by the host computer;

[0009] Analyze the operating status of the multiple energy storage devices based on the operating data.

[0010] Optionally, identifying, based on the original communication data, types of communication protocols adopted by the multiple energy storage devices includes:

[0011] Determining protocol characteristics of the communication protocol used by the plurality of energy storage devices based on the original communication data; the protocol characteristics include data frame structure, interface type, and transmission characteristics;

[0012] The communication protocol types adopted by the multiple energy storage devices are identified according to the data frame structure, the interface type, and the transmission characteristics.

[0013] Optionally, analyzing the operating status of the plurality of energy storage devices according to the operating data includes:

[0014] The operating data is input into a pre-trained neural network model to obtain anomaly detection results and fault prediction results output by the neural network model.

[0015] Optionally, after inputting the operating data into a pre-trained neural network model to obtain anomaly detection results and fault prediction results output by the neural network model, the method further includes:

[0016] Determining an identification of an abnormal energy storage device or a potential fault energy storage device based on the abnormality detection result or the fault prediction result;

[0017] Generate and output alarm information based on the identifier, the abnormality detection result, and the fault prediction result;

[0018] Send a shutdown instruction to the abnormal energy storage device or the potential fault energy storage device.

[0019] Optionally, after converting the original communication data into operation data in a preset format according to the target protocol type, the method further includes:

[0020] determining a label of the operating data in a field of the operating data;

[0021] According to the labels of the operating data, the operating data are classified and stored in data tables in a database, and different data tables store operating data with different labels.

[0022] Optionally, the method further includes:

[0023] Determine the label of the operation data to be called according to the control task to be executed; the control task to be executed is obtained according to the control instruction sent by the server or the control operation on the display interface of the host computer;

[0024] According to the label of the running data to be called, determining a target data table corresponding to the label from multiple data tables;

[0025] The operation data is obtained from the target data table, and the target task is executed according to the operation data.

[0026] Optionally, the operating data includes load data, and the method further includes:

[0027] Generate charge and discharge capacity allocation results based on load data and output forecast values ​​of multiple energy storage devices;

[0028] The charge and discharge capacity allocation result is sent to the multiple energy storage devices.

[0029] A second aspect of the present invention provides a data analysis device for an energy storage device, applied to a host computer, the device comprising:

[0030] A receiving module, configured to receive original communication data sent by the energy storage devices when establishing communication connections with the plurality of energy storage devices;

[0031] an identification module, configured to identify a type of communication protocol used by the energy storage device based on the original communication data;

[0032] A conversion module, configured to convert the original communication data into operation data in a preset format according to the communication protocol type; the preset format is the protocol type adopted by the host computer;

[0033] An analysis module is used to analyze the operating status of the multiple energy storage devices based on the operating data.

[0034] According to a third aspect of the present invention, an electronic device is provided, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a data analysis method for an energy storage device as described above is implemented.

[0035] A fourth aspect of the present invention provides a readable storage medium, which, when instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute any of the aforementioned data analysis methods for energy storage devices.

[0036] In the present invention, protocols are automatically identified and data is converted, eliminating the need to develop independent interfaces for different devices. This solves the problem of protocol incompatibility among multiple energy storage devices and facilitates centralized monitoring of multiple energy storage devices. The use of standardized data formats for analysis enables rapid processing of large amounts of data, improving response speed and providing a data foundation for efficient operation and intelligent optimization of energy storage systems. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0038] Figure 1 A flowchart showing the steps of a data analysis method for energy storage equipment in an embodiment of the present invention is shown.

[0039] Figure 2 A flowchart showing the specific steps of a data analysis method for energy storage equipment in an embodiment of the present invention is shown.

[0040] Figure 3 A schematic diagram of a display interface of a host computer in an embodiment of the present invention is shown.

[0041] Figure 4 A schematic diagram of a data analysis system for energy storage equipment in an embodiment of the present invention is shown.

[0042] Figure 5 A schematic diagram showing a data table stored in a database in an embodiment of the present invention is shown.

[0043] Figure 6 A schematic diagram of a data analysis device for energy storage equipment in an embodiment of the present invention is shown.

[0044] Figure 7 This is a block diagram of an electronic device provided in an embodiment of the present application.

[0045] Figure 8 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0047] First, an application scenario of the present invention is described.

[0048] With the widespread adoption of renewable energy and the demand for intelligent power systems, the deployment of energy storage equipment is expanding. Existing energy storage power plants typically use an Energy Management System (EMS) to monitor and collect operating data from the Battery Management System (BMS), which is then processed by a local controller.

[0049] However, this method has the following problems due to the large amount of data processing: 1. The communication protocols of energy storage devices of different brands or models are not unified, making centralized monitoring difficult; 2. The computing power of the local controller is limited and cannot quickly process large amounts of data, resulting in delayed abnormal responses; 3. When adding new equipment or functions, the hardware needs to be reconfigured, which is costly and time-consuming; 4. Traditional systems only implement basic data collection and do not combine algorithms for energy efficiency optimization or fault prediction.

[0050] Therefore, in order to solve the above problems, the present invention develops a data analysis method for energy storage devices. The data analysis method for energy storage devices provided by the present invention is described in detail below.

[0051] The present invention provides a data analysis method for energy storage equipment, referring to Figure 1 , the data analysis method of the energy storage device may include the following steps.

[0052] Step 101: When establishing communication connections with multiple energy storage devices, receive original communication data sent by the energy storage devices.

[0053] It should be noted that multiple energy storage devices can be different subsystems in the same energy storage power station, or they can be different subsystems in different energy storage power stations. The subsystems of an energy storage power station include BMS, power conversion system (PCS), EMS, and supervisory control and data acquisition (SCADA).

[0054] In a possible implementation, different subsystems support different communication interfaces, and establishing communication connections with multiple energy storage devices may be establishing communication connections with the multiple energy storage devices through different communication interfaces.

[0055] Exemplarily, energy storage devices include lithium battery packs, supercapacitors, and the like.

[0056] Step 102: Identify the type of communication protocol used by the energy storage device based on the original communication data.

[0057] In the present application, a communication protocol is the rules and standards followed when transmitting data between different devices in a computer network. They ensure that data can be transmitted accurately and efficiently within the network. The communication protocol type is the type of communication protocol used during data transmission.

[0058] Exemplarily, the communication protocol types may include Message Queuing Telemetry Transport (MQTT), Modbus RTU, CAN, Modbus TCP, etc.

[0059] In one possible implementation, the type of communication protocol used by the energy storage device is identified based on the data frame structure of the original communication data; wherein the data frame structure includes at least the position and length of the frame header, address segment, function code, data segment, and check code.

[0060] Exemplarily, the data frame structure of the original communication data is: slave address (1B) + function code (1B) + data start address (2B) + data length (2B) + data content (nB) + CRC check (2B), then the communication protocol type is identified as ModbusRTU.

[0061] In another possible implementation, the type of communication protocol used by the energy storage device is identified based on the transmission medium of the original communication data; wherein the transmission medium includes the physical layer type.

[0062] For example, when the transmission medium is RS-485, the communication protocol type is identified as Modbus RTU; when the transmission medium is CAN bus, the communication protocol type is identified as CAN; when the transmission medium is Ethernet, the communication protocol type is identified as Modbus TCP.

[0063] Step 103: Convert the original communication data into operation data in a preset format according to the communication protocol type.

[0064] In the embodiments of the present application, the preset format is the protocol type used by the host computer. The host computer is an important component of an industrial control system or computer application system, usually referring to a computer or software platform located in the upper layer of the system hierarchy, responsible for human-computer interaction, data processing, command transmission, and system monitoring.

[0065] For example, the host computer can be an industrial personal computer (IPC), a programmable logic controller (PLC), or a cloud platform server. The host computer must be equipped with a communication interface module, such as a serial port card, a network port card, or a controller area network (CAN) interface card.

[0066] In the embodiment of the present application, the energy storage power station operation data includes the temperature, power, power, current, voltage, battery state of charge (SOC) and battery health status (SOH) of the battery cells in the battery packs in each energy storage container.

[0067] In some embodiments, the gateway receives each original communication data in real time, converts the original communication data into operation data in a preset format according to the communication protocol type, and sends the operation data to the host computer so that the host computer stores the operation data in a pre-created message queue and analyzes the operating status of multiple energy storage devices based on the operation data.

[0068] In some embodiments, before step 103, the data analysis method for the energy storage device may further include: filtering noise data; and filling missing values. For example, filtering transient sensor interference and filling missing values ​​using linear interpolation or historical mean values.

[0069] Step 104: Analyze the operating status of the multiple energy storage devices based on the operating data.

[0070] In some embodiments, step 104 may include: analyzing, based on the operating data, whether the operating status of the plurality of energy storage devices is in an abnormal state.

[0071] In other embodiments, step 104 may include: analyzing, based on the operating data, whether the operating status of the plurality of energy storage devices is in a potential fault occurrence state.

[0072] In a possible implementation, the operating data includes battery cell data of multiple energy storage devices and alarm information of the energy storage power station. The operating status of the energy storage power station is monitored based on the battery cell data of the multiple energy storage devices and the alarm information of the energy storage power station.

[0073] In the present invention, protocols are automatically identified and data is converted, eliminating the need to develop independent interfaces for different devices. This solves the problem of protocol incompatibility among multiple energy storage devices and facilitates centralized monitoring of multiple energy storage devices. The use of standardized data formats for analysis enables rapid processing of large amounts of data, improving response speed and providing a data foundation for efficient operation and intelligent optimization of energy storage systems.

[0074] The present invention provides a data analysis method for energy storage equipment, referring to Figure 2 The data analysis method of the energy storage device may specifically include the following steps.

[0075] Step 201 : When establishing communication connections with multiple energy storage devices, receive original communication data sent by the energy storage devices.

[0076] Step 201 may refer to step 101 and will not be described again here to avoid repetition.

[0077] In some embodiments, step 201 may include: the intermediate computer of the energy storage device collects the original operating data of each energy storage device, preprocesses the original operating data, and obtains original communication data; the intermediate computer sends the original communication data to the gateway in real time through MQTT, so that the gateway identifies the communication protocol type adopted by the energy storage device based on the original communication data.

[0078] In one possible implementation, when the intermediate machine is a BMS, the original communication data includes battery cell and battery cluster data, cell voltage balancing status, battery cluster total voltage, total current, remaining capacity, charge and discharge cycle count, etc.

[0079] In a possible implementation, when the intermediate machine is a PCS, the original communication data includes: three-phase voltage, current, frequency, power factor, active power, reactive power, apparent power, harmonic content, etc.

[0080] In one possible implementation, when the intermediate machine is an EMS, the original communication data includes: charging and discharging instructions, grid dispatch signals, energy flow direction, real-time charging and discharging amount, energy storage system efficiency, operation mode switching records, etc.

[0081] In one possible implementation, when the intermediate computer is a SCADA system, the original communication data includes: temperature and humidity of the energy storage power station, fire protection system status, air conditioning operating parameters, communication status of each subsystem, communication logs between the upper computer and the intermediate computer, etc.

[0082] Step 202: Determine protocol characteristics of the communication protocols used by the plurality of energy storage devices based on the original communication data.

[0083] In the embodiment of the present application, the protocol features include data frame structure, interface type and transmission characteristics.

[0084] In a possible implementation, protocol characteristics of the communication protocols used by the multiple energy storage devices are determined based on the positions and lengths of the frame header, the address segment, the function code, the data segment, and the check code.

[0085] In a possible implementation, the interface types include RS-485, CAN bus, Ethernet (TCP / IP), Universal Serial Bus (USB), etc.

[0086] In a possible implementation, the protocol features of the communication protocols adopted by the multiple energy storage devices are determined based on the transmission rate, duplex mode, parity check mode, data bit length, and number of stop bits.

[0087] Step 203 : Identify the communication protocol types used by the multiple energy storage devices based on the data frame structure, interface type, and transmission characteristics.

[0088] In a possible implementation, the type of communication protocol used by the energy storage device is identified based on the data frame structure of the original communication data.

[0089] Exemplarily, the data frame structure of the original communication data is: slave address (1B) + function code (1B) + data start address (2B) + data length (2B) + data content (nB) + CRC check (2B), then the communication protocol type is identified as ModbusRTU.

[0090] In another possible implementation, the type of communication protocol used by the energy storage device is identified based on the transmission medium of the original communication data.

[0091] For example, when the transmission medium is RS-485, the communication protocol type is identified as Modbus RTU; when the transmission medium is CAN bus, the communication protocol type is identified as CAN; when the transmission medium is Ethernet, the communication protocol type is identified as Modbus TCP.

[0092] In another possible implementation, the type of communication protocol used by the energy storage device is identified based on the transmission rate.

[0093] For example, RS-232 generally uses asynchronous transmission, while Ethernet uses synchronous transmission and a fixed frame rate.

[0094] Through the above technical solution, the system can automatically adapt to multiple protocols without the need to develop separate interfaces for each device, reducing integration costs. When adding new energy storage devices, it is only necessary to identify their type through protocol characteristics without modifying the underlying code of the upper computer, which facilitates system expansion and upgrades.

[0095] Step 204: Convert the original communication data into operation data in a preset format according to the communication protocol type.

[0096] Step 204 may refer to step 103 and will not be described again here to avoid repetition.

[0097] In some embodiments, after step 204, the data analysis method for the energy storage device further includes:

[0098] Sub-step A1: determining a label of the operating data in a field of the operating data;

[0099] Sub-step A2: Classify the operation data according to the labels of the operation data and store them in a data table in the database.

[0100] In the embodiment of the present application, different data tables store the operating data of different tags.

[0101] In one possible implementation, labels in the running data are extracted through an LSTM model.

[0102] In a possible implementation, the label of the data table includes the primary key and fields of the data table.

[0103] For example, the data table includes an operation data table, and the labels of the operation data table include an operation data identifier (ID), a data acquisition time (Timestamp), voltage, current, temperature, SOC, SOH, and a data validity mark, wherein a data validity mark of 0 indicates normal, a data validity mark of 1 indicates noise, and a data validity mark of 2 indicates missing.

[0104] For another example, the data table includes a device information table, and the labels of the device information table include device ID, device name, type, installation location, communication protocol type, manufacturer information, commissioning date, etc.

[0105] In a possible implementation, the data table further includes a user and permission table and an algorithm parameter table.

[0106] For example, the tags of the user and permission table include user ID, user name, user role, permission JavaScript Object Notation (JSON), last login time, etc.; the tags of the algorithm parameter table include algorithm name, model parameter JSON, training data time range and model accuracy.

[0107] In a possible implementation, one energy storage device corresponds to multiple pieces of operating data, one energy storage device corresponds to multiple alarm trigger records, and one algorithm can serve multiple energy storage devices.

[0108] In a possible implementation, it is also possible to set up an intermediate table to record the processor and the operation.

[0109] In one possible implementation, multiple data tables can be linked by timestamps. For example, meteorological data at the same time point can be analyzed along with energy storage operating efficiency analysis during the same period.

[0110] Through the above technical solution, in a complex energy storage scenario with multiple devices and multiple indicators, when a new energy storage device is added, the operating data is stored in a tagged manner because the operating data adopts a standardized data format. This allows the operating data of energy storage devices with different communication protocols to be stored in a classified manner, and the complex operating data of the energy storage system to be converted into a structured, standardized data table. This ensures that data storage is not affected by the complex communication protocol format, thereby improving data management efficiency.

[0111] In one possible implementation, the operating data is compressed and synchronized to a cloud server, so that the cloud server device generates a health assessment and maintenance plan.

[0112] In a possible implementation, the data source type, JSON or binary data, synchronization time and synchronization status with the cloud server are stored in an external data interface table.

[0113] Step 205: Input the operating data into the pre-trained neural network model to obtain the abnormality detection results and fault prediction results output by the neural network model.

[0114] In one possible implementation, anomalies such as voltage drops and excessively high temperatures are identified based on an isolation forest algorithm or a threshold rule base.

[0115] In one possible implementation, a long short-term memory (LSTM) network model is used to predict battery capacity attenuation or potential failure points.

[0116] In a possible implementation, the anomaly detection results and the fault prediction results are stored in an alarm event table. The labels of the alarm event table may include alarm trigger time, alarm type, alarm level, processing status, and processing operation log.

[0117] Through the above technical solution, since the operating data is obtained by converting the original communication data into the protocol type format used by the upper computer, the data input into the neural network model adopts the same format, which improves the accuracy of the abnormality detection results or fault prediction results and reduces the output time of the abnormality detection results or fault prediction results; further, by utilizing the strong feature extraction and prediction capabilities of the neural network model, the problems of abnormality detection lag, fault location difficulty, and high maintenance cost in the energy storage system are solved, and millisecond-level abnormal response and fault warning are achieved, thereby extending the life of the equipment.

[0118] In some embodiments, after step 205, the data analysis method for the energy storage device further includes:

[0119] Sub-step B1: determining the identifier of an abnormal energy storage device or a potential fault energy storage device based on the abnormality detection result or the fault prediction result;

[0120] Sub-step B2: generating and outputting alarm information based on the identification, abnormality detection results, and fault prediction results;

[0121] Sub-step B3: Send a shutdown instruction to the abnormal energy storage device or the potential fault energy storage device.

[0122] In one possible implementation, the anomaly detection result is associated with the basic device information table using a primary key. For example, if the anomaly detection result indicates "the battery temperature of device 007 exceeds the threshold," the database is queried using the device ID "007" to obtain the device's full name, "Battery Cluster No. 7, Area B, XX Power Station."

[0123] In one possible implementation, the alarm information may include device identification, anomaly type, severity level, timestamp, detailed description, and suggested measures.

[0124] For example, device identification: XX Energy Storage Power Station-PCS003, abnormality type: converter overcurrent fault, severity level: emergency (red alarm), timestamp: 2025-06-16 15:20:45, detailed description: the three-phase currents all exceed 120% of the rated value (phase A 156A, phase B 148A, phase C 162A), recommended measures: immediately shut down and check the IGBT module to eliminate short circuit hazards.

[0125] In one possible implementation, the alarm is output to the operation and maintenance personnel via SMS or email.

[0126] In a possible implementation, the shutdown command needs to be sent through an independent safety bus to avoid conflict with the normal data bus.

[0127] In a possible implementation, after sending a shutdown instruction to an abnormal energy storage device or a potential fault energy storage device, an execution result fed back by the energy storage device may also be received.

[0128] For example, when the temperature sensor detects that the temperature of a battery cell is >60°C, it indicates that the temperature of the lithium battery pack is abnormal. The host computer generates a shutdown command and sends it to the BMS where the temperature sensor is located. At the same time, it pushes an alarm to the operation and maintenance personnel's mobile phone, so that the BMS responds to the shutdown command and controls the energy storage equipment to shut down and cool down.

[0129] Through the above technical solution, since the operating data is obtained by converting the original communication data into the protocol type format used by the host computer, that is, the operating data adopts a standardized data format, the accuracy of the abnormality detection results or fault prediction results is improved, and the output time of the abnormality detection results or fault prediction results is reduced. In the case of an emergency abnormality in the energy storage device, the time spent in the entire process from detection to shutdown is reduced, thereby ensuring the safety of the energy storage device; further, through multi-dimensional data correlation judgment, the accurate positioning of the abnormal device can be achieved.

[0130] In some embodiments, after step 205, the data analysis method for the energy storage device further includes:

[0131] Sub-step 206: Determine the label of the operation data to be called according to the control task to be executed; the control task to be executed is obtained according to the control instruction sent by the server or the control operation on the display interface;

[0132] Sub-step 207: determining a target data table corresponding to the label from multiple data tables according to the label of the running data to be called;

[0133] Sub-step 208: Obtain the operating data from the target data table, and execute the target task according to the operating data.

[0134] In a possible implementation, the control task to be executed may include monitoring the operating status of the energy storage power station; the operating data to be called may include energy storage device cell data and alarm information of the energy storage power station.

[0135] In one possible implementation, the control task to be executed may include querying the SOC curve of a battery pack over a preset period of time in the past; the operating data to be called may include the SOC of the energy storage device at different times within the preset period of time.

[0136] For example, the preset duration is 24 hours. The energy storage device is located through the device information table, and the corresponding data table is directly retrieved by time partition, with a response time of <100ms.

[0137] In one possible implementation, when the user's control operation on the display interface is to click "Battery Pack 1", the control task to be executed is to view the real-time SOC curve; afterwards, the user finds an abnormal drop, and the control operation on the display interface is to click the "Forced Balancing" button, and the control task to be executed is load balancing. The host computer sends an instruction to the BMS to perform balancing, and "Balancing (Progress 80%)" is displayed on the display interface.

[0138] In some embodiments, the display interface of the host computer includes different functional partitions.

[0139] For example, see Figure 3 The host computer's display interface consists of a top navigation bar, a center main display area, a left panel, a right panel, and a bottom status bar. The top navigation bar displays the system name and functional module switching controls (for example, the system name is "Energy Storage Equipment Intelligent Monitoring Platform"). Functional module switching controls include: real-time monitoring, historical data, alarm management, energy efficiency reports, and system settings. The center main display area displays a real-time data dashboard, for example, showing real-time values ​​and dynamic curves for voltage, current, temperature, and SOC, annotating the energy storage device location, and allowing users to jump to detailed information by clicking. The left panel displays a device tree and device status overview, displaying energy storage devices by geographic location or logical grouping, and color-coding device status. For example, "PV Energy Storage Station A - Battery Pack 1" has green for normal, yellow for warning, and red for fault. The right panel displays alarm information and control command controls. Alarm notifications include the latest alarm list, alarm processing status, and notification method. For example, the latest alarm list may include time, device name, alarm type, and level. Control command controls include start and stop controls. The status bar at the bottom is used to display the system time, network status, and data synchronization progress, such as "Cloud synchronization completed."

[0140] Through the above technical solution, the label of the operating data to be called is obtained according to the control task to be executed. Since the operating data with different labels are classified and stored in the database, the operating data with different labels are obtained for energy storage devices using different communication protocol types. The operating data is obtained from the target data table according to the label, which improves the calling speed of the operating data, reduces the time of calling the operating data, and thus improves the execution efficiency of the control task.

[0141] In some embodiments, after step 205, the data analysis method for the energy storage device further includes:

[0142] Sub-step 209: generating a charge and discharge capacity allocation result based on the load data and output prediction values ​​of the multiple energy storage devices;

[0143] Sub-step 210: Send the charge and discharge capacity allocation result to multiple energy storage devices.

[0144] In the embodiment of the present application, the output prediction value may be a predicted value of the output power of the energy storage device, or may be the active output power of the energy storage device.

[0145] In one possible implementation, the storage limit and transmission limit of the load in the energy storage device are obtained, wherein the storage limit is used to indicate the storage limit of the load's discharged electricity in the energy storage device, and the transmission limit is used to indicate the limit on the amount of electricity transmitted between the energy storage device and the load; based on the storage limit and the transmission limit, the output forecast value and the load data are randomly allocated to obtain a charge and discharge capacity distribution result.

[0146] In a possible implementation, the energy storage device is configured to provide charging power to a load corresponding to the power supply while receiving the discharged power from the power supply.

[0147] In a possible implementation, the charge and discharge capacity allocation result includes an initial allocation result of providing charging capacity to a load corresponding to the power supply and an initial allocation result of receiving discharging capacity from the power supply.

[0148] In a possible implementation, the storage limit is used to indicate the storage limit of the discharged power of the load in the energy storage device.

[0149] In a possible implementation, the transmission limit is used to indicate a limit on the amount of power transmitted between the energy storage device and the load.

[0150] Through the above technical solution, the charge and discharge distribution results are adjusted according to the load data of different energy storage devices, thereby achieving systematic optimization of the user's power distribution and making the user's power usage plan more flexible; and because the load data is obtained by converting the original communication data into the protocol type format used by the host computer, that is, the load data adopts a standardized data format, the response speed of adjusting the charge and discharge distribution results is improved.

[0151] In some embodiments, after step 205, the data analysis method for energy storage devices further includes: generating energy efficiency report information of the plurality of energy storage devices based on the operating data.

[0152] In some embodiments, after step 205 , the data analysis method for energy storage devices further includes: sub-step 211 , determining a charge and discharge strategy for any energy storage device based on the historical operating data and electricity price curve of the energy storage device.

[0153] In the embodiment of the present application, the electricity price curve may include historical time-of-use electricity prices. Through the electricity price curve, peak, valley and normal period electricity prices, real-time market electricity prices, and electricity price fluctuation patterns can be obtained.

[0154] In the embodiment of the present application, historical operation data may include the energy storage station's historical charge and discharge power, SOC changes, equipment efficiency curves, fault records, etc. Historical operation data may also include: grid load curves, renewable energy output data, weather data, etc.

[0155] In one possible implementation, the charging and discharging strategy of the energy storage device includes: charging during off-peak hours and discharging during peak hours, and making profits by utilizing the price difference of electricity.

[0156] For example, when historical operating data indicates a sudden increase in grid load during a certain period, charging in advance during off-peak hours and discharging during peak load periods can alleviate grid pressure and obtain high-price profits.

[0157] For example, when historical operating data indicates that there is power curtailment during peak photovoltaic output periods, the battery can be charged using low-cost or free curtailed power and discharged when the photovoltaic output decreases.

[0158] In the present invention, first, by dynamically loading protocol plug-ins, it supports mixed networking of new and old equipment, reducing the cost of system upgrades. Secondly, it uses anomaly detection (such as the isolation forest algorithm) and fault prediction (LSTM neural network) based on time series data. Thirdly, it combines grid electricity prices and load demand to optimize the charging and discharging strategies of energy storage equipment. Finally, the host computer and cloud server are linked to process real-time control tasks locally, and perform long-term energy efficiency analysis in the cloud.

[0159] This application also provides a data analysis system for energy storage equipment, referring to Figure 4 ,The data analysis system of energy storage equipment includes energy ,storage equipment, intermediate computer, communication layer, host computer, database, application layer, and cloud ,server.

[0160] In some embodiments, the energy storage device includes multiple energy storage units (such as lithium battery packs, supercapacitors), sensors (voltage, current, temperature) and a battery management unit (BMS).

[0161] In a possible implementation, the energy storage device may also be referred to as a "slave computer".

[0162] In some embodiments, the communication layer includes an industrial gateway (supporting Modbus TCP, CAN, MQTT and other protocols), which is responsible for two-way communication between the device layer and the host computer.

[0163] In some embodiments, the host computer includes a protocol parsing engine for dynamically loading protocol plug-ins. The host computer is also used for real-time data processing, anomaly detection and fault prediction, and generation of control strategies such as charge and discharge optimization and balancing management.

[0164] In some embodiments, the host computer stores the received raw communication data, analysis results, and device parameters in a database.

[0165] In some embodiments, the application layer includes a human-computer interaction interface for providing visual monitoring, alarm management, and report generation. For example, the human-computer interaction interface can be a web applet or a desktop app.

[0166] In some embodiments, the application layer interacts with a cloud server, and the cloud server can receive electricity price signals and load instructions from a power grid dispatching system.

[0167] For example, the data flow direction for uplink data can be: device layer sensor / BMS → communication layer protocol analysis → host computer data processing → database storage → application layer display / cloud synchronization. The data flow direction for downlink instructions can be: application layer user instructions / cloud strategy → host computer control logic generation → communication layer issuance → device layer execution (such as charge and discharge control).

[0168] In one possible implementation, the sensor / BMS collects parameters such as voltage, current, temperature, SOC, and SOH of the energy storage device in real time; the data is transmitted to the host computer through a communication module (CAN / Modbus and other protocols).

[0169] In a possible implementation, the protocol parsing engine of the host computer dynamically loads the protocol plug-in of the corresponding device to convert the original data into a unified format.

[0170] In one possible implementation, the host computer filters out noisy data (such as transient interference from sensors) and fills in missing values ​​(using linear interpolation or historical mean filling).

[0171] In one possible implementation, the host computer identifies anomalies such as voltage drops and excessive temperatures based on an isolation forest algorithm or a threshold rule library; and predicts battery capacity degradation or potential failure points through an LSTM model.

[0172] In one possible implementation, the host computer generates real-time alarm information and outputs it via SMS or email notification; the host computer sends control instructions such as load reduction and shutdown to the energy storage device.

[0173] In one possible implementation, the host computer combines historical data with electricity price curves to formulate charging and discharging strategies.

[0174] In one possible implementation, the host computer will compress the received data and synchronize it to the cloud for equipment health assessment and maintenance plan generation.

[0175] In a possible implementation, the host computer sends control instructions to the energy storage device through the communication module; wherein the control instructions include charge and discharge start and stop, and balancing strategy.

[0176] In one possible implementation, the energy storage device executes the control instructions issued by the host computer and feeds back the execution results to the host computer, forming a closed-loop verification.

[0177] For example, the temperature of a lithium battery pack is abnormal, and the temperature sensor detects that the temperature of a battery cell is >60°C; the processing process is: protocol analysis → abnormality detection (threshold exceeded) → generation of shutdown command → sending to BMS; result: the equipment is shut down for cooling, and an alarm is pushed to the operation and maintenance personnel's mobile phone.

[0178] In some embodiments, a database stores multiple data tables. Figure 5 The data tables include device information table (Device_Info), operation data table (Operation_Data), alarm event table (Alarm_Events), user and permission table (User_Access), algorithm parameter table (Algorithm_Params) and external data interface table (External_Data).

[0179] In one possible implementation, the primary key of the device information table is Device_ID (device unique identifier, such as UUID), and the fields of the device information table include: Device_Name (device name, such as "lithium battery pack A1"), Device_Type (type, such as lithium battery / supercapacitor), Install_Location (installation location, longitude and latitude or logical partition), Protocol_Type (communication protocol type, such as Modbus / CAN), Manufacturer (manufacturer information), and Commissioning_Date (commissioning date).

[0180] In one possible implementation, the primary key of the operation data table is Data_ID (auto-increment ID), and the fields of the operation data table include: Device_ID (foreign key, associated with the Device_Info table), Timestamp (data acquisition time, accurate to milliseconds), Voltage (voltage, unit V), Current (current, unit A), Temperature (temperature, unit ℃), SOC (state of charge, percentage), SOH (state of health, percentage), Data_Status (data validity mark, such as 0-normal / 1-noise / 2-missing).

[0181] In one possible implementation, the primary key of the alarm event table is Alarm_ID (auto-increment ID), and the fields of the alarm event table include: Device_ID (foreign key, associated with the Device_Info table), Alarm_Time (alarm trigger time), Alarm_Type (type, such as overvoltage / high temperature / low SOC), Alarm_Level (level, such as emergency / warning / prompt), Status (processing status, such as unconfirmed / processed), Action_Log (processing operation log, such as "User Zhang San executes shutdown").

[0182] In one possible implementation, the primary key of the user and permission table is User_ID, and the fields of the user and permission table include: User_Name (user name), Role (role, such as administrator / operator / guest), Permissions (permission JSON, such as {"control":true,"alarm_ack":false}), and Last_Login (last login time).

[0183] In one possible implementation, the primary key of the algorithm parameter table is Algorithm_ID, and the fields of the algorithm parameter table include: Model_Name (algorithm name, such as "LSTM_FaultPrediction_v1"), Parameters (model parameter JSON, such as the number of hidden layers, learning rate), Training_Data_Range (training data time range), and Accuracy (model accuracy, updated regularly).

[0184] In one possible implementation, the primary key of the external data interface table is the primary key: External_ID, and the fields of the external data interface table include: Source_Type (data source type, such as grid electricity price / meteorological data / third-party EMS), Data_Content (JSON or binary data), Sync_Time (synchronization time), Status (synchronization status, success / failure).

[0185] In some embodiments, the primary key of the device information table and the foreign key of the operation data table are one-to-many, indicating that one energy storage device corresponds to multiple operation data; the primary key of the device information table and the foreign key of the alarm event table are one-to-many, indicating that one energy storage device corresponds to multiple alarm information.

[0186] In some embodiments, the primary key of the alarm event table and the primary key of the user and authority table can be used to set up an intermediate table (Alarm_Action) to record the handler and the operation.

[0187] In some embodiments, the primary key of the algorithm parameter table and the primary key of the device information table have a many-to-many relationship, indicating that one algorithm can be applied to multiple energy storage devices, and one energy storage device can be configured with multiple algorithms. The primary key of the algorithm parameter table and the primary key of the device information table can be associated through an intermediate table (Device_Algorithm_Mapping).

[0188] In some embodiments, the primary key of the external data interface table is associated with the operation data table through a timestamp, indicating that time-related operations can be performed, such as analysis of meteorological data and energy storage operation efficiency during the same period.

[0189] In the present invention, first, by dynamically loading protocol plug-ins, it supports mixed networking of new and old equipment, reducing the cost of system upgrades. Secondly, it uses anomaly detection (such as the isolation forest algorithm) and fault prediction (LSTM neural network) based on time series data. Thirdly, it combines grid electricity prices and load demand to optimize the charging and discharging strategies of energy storage equipment. Finally, the host computer and cloud server are linked to process real-time control tasks locally, and perform long-term energy efficiency analysis in the cloud.

[0190] This application also provides a data analysis device for energy storage equipment, referring to Figure 6 The data analysis device of the energy storage device is applied to a host computer, and the data analysis device 500 of the energy storage device may include the following modules.

[0191] The receiving module 501 is used to receive original communication data sent by the energy storage device when establishing communication connections with multiple energy storage devices;

[0192] Identification module 502, used to identify the type of communication protocol used by the energy storage device based on the original communication data;

[0193] The conversion module 503 is used to convert the original communication data into operation data in a preset format according to the communication protocol type; the preset format is the protocol type adopted by the host computer;

[0194] The analysis module 504 is configured to analyze the operating status of the plurality of energy storage devices based on the operating data.

[0195] Optionally, the identification module 502 includes:

[0196] A first determination submodule is configured to determine protocol features of the communication protocols used by the plurality of energy storage devices based on the original communication data; the protocol features include data frame structure, interface type, and transmission characteristics;

[0197] The first identification submodule is used to identify the type of communication protocol used by the energy storage device according to the data frame structure, interface type and transmission characteristics.

[0198] Optionally, the analysis module 504 includes:

[0199] The first model application submodule is used to input the operating data into the pre-trained neural network model to obtain the abnormality detection results and fault prediction results output by the neural network model.

[0200] Optionally, the data analysis device 500 for the energy storage device further includes:

[0201] A first determination module is configured to determine an identifier of an abnormal energy storage device or a potential fault energy storage device based on an abnormality detection result or a fault prediction result;

[0202] The first generation module is used to generate and output alarm information based on the identification, abnormality detection results and fault prediction results;

[0203] The first sending module is used to send a shutdown instruction to an abnormal energy storage device or a potential fault energy storage device.

[0204] Optionally, the data analysis device 500 for the energy storage device further includes:

[0205] A second determining module is used to determine a label of the operating data in a field of the operating data;

[0206] The storage module is used to classify and store the operation data into data tables in the database according to the labels of the operation data, and different data tables store operation data with different labels.

[0207] Optionally, the data analysis device 500 for the energy storage device further includes:

[0208] The third determining module is used to determine the label of the operation data to be called according to the control task to be executed; the control task to be executed is obtained according to the control instruction sent by the server or the control operation on the display interface of the host computer;

[0209] A fourth determining module is configured to determine a target data table corresponding to the tag from multiple data tables according to the tag of the running data to be called;

[0210] The execution module is used to obtain the operation data from the target data table and execute the target task according to the operation data.

[0211] Optionally, the data analysis device 500 for the energy storage device further includes:

[0212] A second generating module is used to generate a charge and discharge capacity allocation result based on the load data and output prediction values ​​of the multiple energy storage devices;

[0213] The second sending module is used to send the charge and discharge capacity allocation result to multiple energy storage devices.

[0214] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0215] like Figure 7 As shown, an embodiment of the present application further provides an electronic device 600, including a processor 601 and a memory 602, wherein the memory 602 stores a program or instruction that can be run on the processor 601, and when the program or instruction is executed by the processor 601, the various steps of the data analysis method embodiment of the above-mentioned energy storage device are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0216] It should be noted that the electronic devices in the embodiments of the present application include the mobile electronic devices and non-mobile electronic devices mentioned above.

[0217] Figure 8 A schematic diagram of the hardware structure of an electronic device implementing an embodiment of the present application.

[0218] The electronic device 700 includes but is not limited to components such as a radio frequency unit 701 , a network module 702 , an audio output unit 703 , an input unit 704 , a sensor 705 , a display unit 706 , a user input unit 707 , an interface unit 708 , a memory 709 , and a processor 710 .

[0219] Those skilled in the art will understand that the electronic device 700 may also include a power source (such as a battery) to power each component, and the power source may be logically connected to the processor 710 through a power management system, thereby implementing functions such as charging, discharging, and power consumption management through the power management system. Figure 8 The electronic device structure shown in the figure does not constitute a limitation on the electronic device. The electronic device may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently, which will not be repeated here.

[0220] The processor 710 is configured to obtain the original video and video parameter information of the video recording; and process the original video based on the video parameter information when the video recording is completed and the target conditions are met.

[0221] In an embodiment of the present application, the original video and video parameter information of the video recording are obtained; after the video recording is completed and the target conditions are met, the original video is processed based on the video parameter information. In this way, when a video recorded by an electronic device is obtained, it can be determined that the video recording of the electronic device is completed and the target conditions are met, and an audio playback operation is performed on the original video based on the video parameter information. In this way, the problem of video freeze and frame loss caused by forcibly performing audio playback when the status parameters of the electronic device are not good can be avoided, thereby improving the display effect of the recorded video.

[0222] It should be understood that in an embodiment of the present application, the input unit 704 may include a graphics processing unit (GPU) 7041 and a microphone 7042, and the graphics processor 7041 processes the image data of a static picture or video obtained by an image capture device (such as a camera) in a video capture mode or an image capture mode. The display unit 706 may include a display panel 7061, and the display panel 7061 may be configured in the form of a liquid crystal display, an organic light emitting diode, etc. The user input unit 707 includes a touch panel 7071 and at least one of other input devices 7072. The touch panel 7071 is also called a touch screen. The touch panel 7071 may include two parts: a touch detection device and a touch controller. Other input devices 7072 may include, but are not limited to, a physical keyboard, function keys (such as volume control keys, switch keys, etc.), a trackball, a mouse, and an operating stick, which will not be repeated here.

[0223] Memory 709 can be used to store software programs and various data. Memory 709 may primarily include a first storage area for storing programs or instructions and a second storage area for storing data. The first storage area may store an operating system, applications or instructions required for functions (such as sound playback and image playback), and the like. Furthermore, memory 709 may include volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct RAM bus random access memory (DRRAM). The memory 709 in the embodiment of the present application includes but is not limited to these and any other suitable types of memory.

[0224] Processor 710 may include one or more processing units. Optionally, processor 710 integrates an application processor and a modem processor. The application processor primarily handles operations related to the operating system, user interface, and application programs, while the modem processor primarily processes wireless communication signals, such as a baseband processor. It is understood that the modem processor may not be integrated into processor 710.

[0225] An embodiment of the present application also provides a readable storage medium, on which a program or instruction is stored. When the program or instruction is executed by a processor, the various processes of the data analysis method embodiment of the above-mentioned energy storage device are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0226] The processor is the processor in the electronic device described in the above embodiment. The readable storage medium includes a computer-readable storage medium, such as a computer read-only memory (ROM), random access memory (RAM), a magnetic disk, or an optical disk.

[0227] An embodiment of the present application further provides a chip, which includes a processor and a communication interface, wherein the communication interface is coupled to the processor, and the processor is used to run programs or instructions to implement the various processes of the data analysis method embodiment of the above-mentioned energy storage device, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0228] It should be understood that the chip mentioned in the embodiments of the present application may also be referred to as a system-on-chip, a system-on-chip, a chip system, or a system-on-chip chip. The present invention also provides a readable storage medium, which, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to perform the steps of the above-mentioned energy storage device data analysis method.

[0229] The present invention also provides a computer program product, comprising a computer program, which implements the steps of the aforementioned data analysis method for energy storage devices when executed by a processor.

[0230] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0231] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better embodiment. Based on this 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 ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for enabling a terminal (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present invention.

[0232] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are protected by the present invention.

Claims

1. A data analysis method for energy storage equipment, characterized in that: Applied to a host computer, the method includes: When establishing communication connections with multiple energy storage devices, receiving original communication data sent by the energy storage devices; Identifying a communication protocol type used by the energy storage device based on the original communication data; According to the communication protocol type, the original communication data is converted into operation data in a preset format; the preset format is the protocol type adopted by the host computer; Analyze the operating status of the multiple energy storage devices based on the operating data.

2. The method according to claim 1, characterized in that The step of identifying the communication protocol types used by the plurality of energy storage devices based on the original communication data includes: Determining protocol characteristics of the communication protocol used by the plurality of energy storage devices based on the original communication data; the protocol characteristics include data frame structure, interface type, and transmission characteristics; The communication protocol types adopted by the multiple energy storage devices are identified according to the data frame structure, the interface type, and the transmission characteristics.

3. The method according to claim 1, characterized in that Analyzing the operating status of the plurality of energy storage devices according to the operating data includes: The operating data is input into a pre-trained neural network model to obtain anomaly detection results and fault prediction results output by the neural network model.

4. The method according to claim 3, characterized in that After inputting the operating data into a pre-trained neural network model and obtaining anomaly detection results and fault prediction results output by the neural network model, the method further includes: Determining an identification of an abnormal energy storage device or a potential fault energy storage device based on the abnormality detection result or the fault prediction result; Generate and output alarm information based on the identifier, the abnormality detection result, and the fault prediction result; Send a shutdown instruction to the abnormal energy storage device or the potential fault energy storage device.

5. The method according to claim 1, wherein After converting the original communication data into operation data in a preset format according to the communication protocol type, the method further includes: Determine a label of the operating data in a field of the operating data; According to the labels of the operating data, the operating data are classified and stored in data tables in a database, and different data tables store operating data with different labels.

6. The method according to claim 1, characterized in that The method further comprises: Determine the label of the operation data to be called according to the control task to be executed; the control task to be executed is obtained according to the control instruction sent by the server or the control operation on the display interface of the host computer; According to the label of the running data to be called, determining a target data table corresponding to the label from multiple data tables; The operation data is obtained from the target data table, and the target task is executed according to the operation data.

7. The method according to any one of claims 1 to 6, characterized in that The operation data includes load data, and the method further includes: Generate charge and discharge capacity allocation results based on load data and output forecast values ​​of multiple energy storage devices; The charge and discharge capacity allocation result is sent to the multiple energy storage devices.

8. A data analysis device for energy storage equipment, characterized in that: Applied to a host computer, the device includes: A receiving module, configured to receive original communication data sent by the energy storage devices when establishing communication connections with the plurality of energy storage devices; an identification module, configured to identify a type of communication protocol used by the energy storage device based on the original communication data; A conversion module, configured to convert the original communication data into operation data in a preset format according to the communication protocol type; the preset format is the protocol type adopted by the host computer; An analysis module is used to analyze the operating status of the multiple energy storage devices based on the operating data.

9. An electronic device, characterized in that: include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the data analysis method for an energy storage device according to any one of claims 1 to 7 when executing the program.

10. A readable storage medium, characterized in that: When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the data analysis method for an energy storage device according to any one of claims 1 to 7.

Images