Remote data interaction method and system of photovoltaic energy storage equipment

Abstract

The invention provides a remote data interaction method and system for photovoltaic energy storage equipment. The remote data interaction method of the photovoltaic energy storage equipment comprises the following steps: S1, data acquisition and transmission: (1) the photovoltaic energy storage equipment acquires various operation data of the equipment through a built-in sensor, such as battery electric quantity, voltage, current and temperature; (2) transmitting the data to a cloud data processing platform through a wireless communication module, such as Wi-Fi, LoRa and NB-IoT; s2, data storage and processing: (1) after receiving the transmitted data, the cloud data processing platform stores, cleans and preprocesses the data; and (2) analyzing the data based on a machine learning algorithm, and identifying the operation state of the equipment. The remote data interaction method and system for the photovoltaic energy storage equipment have the advantages that the equipment management efficiency can be remarkably improved, the fault response time is shortened, and the overall reliability and stability of the system are improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of photovoltaic energy storage, and particularly relates to a remote data interaction method and system for photovoltaic energy storage devices. Background Art

[0002] With the continuous growth of global energy demand and the improvement of environmental awareness, solar energy, as a clean and renewable energy source, has received extensive attention and application. As one of the important means of solar energy utilization, the photovoltaic energy storage system can effectively store solar energy and release energy when needed, providing users with stable and continuous power supply. However, with the continuous expansion of the scale of photovoltaic energy storage devices, how to efficiently monitor, manage, and maintain these devices has become an urgent problem to be solved.

[0003] Traditional photovoltaic energy storage device monitoring systems mostly rely on local monitoring and manual inspections, and there are the following problems: First, the monitoring information cannot be transmitted in real time, making it difficult to timely grasp the faults and operating states of the devices; second, the fault diagnosis process of device operation is cumbersome, and maintenance personnel need to go to the site for inspection, reducing work efficiency; third, there is a lack of systematic energy scheduling and management means, and the collaborative work between devices cannot be achieved. Therefore, how to achieve remote real-time monitoring and data interaction of photovoltaic energy storage devices has become an urgent problem to be solved in the current photovoltaic energy storage field.

[0004] Therefore, it is necessary to provide a new remote data interaction method and system for photovoltaic energy storage devices to solve the above technical problems. Summary of the Invention

[0005] The technical problem solved by the present invention is to provide a remote data interaction method and system for photovoltaic energy storage devices that can significantly improve the device management efficiency, reduce the fault response time, and enhance the overall reliability and stability of the system.

[0006] To solve the above technical problems, the remote data interaction method for photovoltaic energy storage devices provided by the present invention includes the following steps:

[0007] S1. Data acquisition and transmission:

[0008] (1). The photovoltaic energy storage device collects various operating data of the device through built-in sensors, such as battery power, voltage, current, and temperature;

[0009] (2). These data are transmitted to the cloud data processing platform through a wireless communication module, such as Wi-Fi, LoRa, NB-IoT;

[0010] S2. Data storage and processing:

[0011] (1) After the cloud data processing platform receives the transmitted data, it stores, cleans, and preprocesses the data;

[0012] (2) Analyze the data based on machine learning algorithms to identify the operating status of the device, predict possible faults or performance degradation of the device, and generate relevant diagnostic reports;

[0013] S3. Remote monitoring and alarm:

[0014] (1) Users or device maintenance personnel can view the operating data and status of the device in real time through mobile applications such as APPs or PC platforms, and control and schedule the device as needed;

[0015] (2) Based on the platform, it can automatically issue fault alarms or performance anomaly prompts according to the data analysis results to remind maintenance personnel to take timely measures;

[0016] S4. Scheduling and management:

[0017] (1) Based on the real-time data of the device, the system can automatically optimize energy management, perform load scheduling and battery charge and discharge strategy adjustment to ensure the maximum energy utilization efficiency of the device;

[0018] (2) The system can also realize the collaborative work between devices based on the data of multiple photovoltaic energy storage devices, balance energy supply and demand, and improve the operating efficiency of the overall system.

[0019] As a further solution of the present invention, the method for the photovoltaic energy storage device to collect various operating data through built-in sensors and transmit these data to the cloud data processing platform is as follows:

[0020] (1) Sensor deployment: Deploy multiple sensors on photovoltaic energy storage devices such as photovoltaic panels, battery energy storage systems, and inverters, so as to monitor the operating parameters of the devices in real time. The sensors are as follows:

[0021] 1) Battery voltage sensor: Measure the battery voltage to ensure that the battery operates within a reasonable range;

[0022] 2) Battery current sensor: Measure the charge and discharge current to monitor the charge and discharge efficiency of the battery;

[0023] 3) Temperature sensor: Measure the operating temperature of the device, especially the battery temperature, to prevent overheating;

[0024] 4) Battery SOC (State of Charge) sensor: Evaluate the remaining battery charge;

[0025] 5) Power / energy sensor: Measure the power output of the system or the energy flow of the energy storage system;

[0026] (2). Data collection period and frequency: According to the operating characteristics and data transmission capabilities of the device, set a reasonable data collection frequency. For the key operating parameters of the device, a higher sampling frequency can be set, such as once per second, while for relatively stable parameters, such as the health status of the battery, a lower sampling frequency can be set;

[0027] (3). Data formatting and preprocessing: Preprocess the collected raw data, such as unit conversion, missing data filling, and preliminary anomaly detection, so as to ensure the accuracy and consistency of the data.

[0028] As a further solution of the present invention, the wireless communication module can select a suitable communication protocol according to the requirements of the application scenario, such as the number of devices, data volume, and distance, as follows:

[0029] (1). Wi-Fi: Suitable for situations where the device distance is relatively close and the network environment is good. Wi-Fi is suitable for high-speed data transmission;

[0030] (2). LoRa (Long Range): Suitable for large-scale and low-power scenarios. LoRa can achieve remote communication of low-power devices and is suitable for periodic data upload;

[0031] (3). NB-IoT (Narrowband IoT): Suitable for low-power and low-data-rate Internet of Things devices in wide area networks. NB-IoT has stronger network coverage capabilities and can provide stable data transmission;

[0032] (4). Encryption technology should be adopted during the transmission process, such as using the TLS / SSL protocol for data encryption to prevent data from being stolen or tampered with during transmission.

[0033] As a further solution of the present invention, the data reception and transmission to the cloud are as follows:

[0034] (1). Data transmission: Configure the parameters for data transmission on the wireless communication module at the device end and establish a communication channel with the cloud data processing platform. According to the selected communication protocol, such as Wi-Fi, LoRa, or NB-IoT, the device transmits the collected data to the cloud through the adapted gateway;

[0035] (2). Data format and protocol: The data sent by the device end should conform to the standard data format, such as JSON, XML, Protobuf, and select a suitable communication protocol according to needs, such as HTTP, MQTT, CoAP for transmission;

[0036] (3). Cloud data reception and processing:

[0037] Data reception and storage: After the cloud platform receives the data transmitted from the device side, the data is stored in the database. When storing, the following aspects need to be considered:

[0038] Data timestamp: Record the data collection time for time series analysis;

[0039] Data partitioning and indexing: Partition and index the stored data to improve query efficiency and data processing speed;

[0040] Data cleaning and preprocessing: Further data cleaning is performed on the cloud side, including outlier detection, data missing value processing, and denoising. At this time, data deduplication, formatting, and standardization can also be performed on the data;

[0041] Data storage and structuring: Structurally store the data uploaded by the device for subsequent data query, analysis, and report generation;

[0042] (4). Cloud data analysis and processing:

[0043] 1). Data analysis and monitoring: The cloud platform can perform real-time monitoring and analysis on the received data. For example, the battery power, voltage, current, and temperature data of the device can be displayed through charts, dashboards, etc., to help the operation and maintenance personnel monitor the device status in real time;

[0044] 2). Fault detection and warning: Based on the device operation data, the cloud platform can use machine learning or rule engines to analyze whether the device is in a fault state. For example, if the battery temperature exceeds the threshold or the current is abnormal, a fault warning is triggered

[0045] (5). Data display and report generation:

[0046] 1). Real-time data visualization: The cloud platform displays the real-time data of the device through a visualization interface to help the operation and maintenance personnel intuitively understand the device operation status. For example, charts can display the battery power change, voltage fluctuation, and charge and discharge efficiency parameters;

[0047] 2). Fault report and alarm: The system generates a device fault report or alarm notification according to the analysis results, and timely notifies the user or operation and maintenance personnel of the device operation abnormality, supporting notification methods such as email, SMS, or APP push.

[0048] As a further solution of the present invention, the specific method steps for the cloud data processing platform to store, clean, and preprocess the data of the photovoltaic energy storage device, analyze the device operation status through machine learning algorithms, predict faults or performance degradation, and generate a diagnostic report are as follows:

[0049] (1). Data reception and storage:

[0050] 1). Data reception: The cloud platform receives data from the photovoltaic energy storage device through the communication module. These data include, but are not limited to, battery voltage, current, temperature, power generation, energy storage parameters;

[0051] 2). Data storage: The received raw data is stored in the cloud database. A relational database or a non-relational database can be selected for storage, and the appropriate database type is selected according to the data volume and storage requirements;

[0052] 3). Data storage strategy: For large data streams that are frequently updated, partitioned storage and timestamp marking are adopted for subsequent query and analysis;

[0053] (2). Data cleaning:

[0054] 1). Duplicate data removal: By verifying the timestamp and device ID, duplicate records are removed to ensure data uniqueness;

[0055] 2). Outlier detection: Based on the normal operating range of the device, statistical methods such as Z-score and IQR are used to detect outliers in the data. If a parameter, such as battery voltage, exceeds the normal range, it can be marked as abnormal data, and according to / normalization: **To enable effective comparison and processing of data on different scales in machine learning algorithms, standardization processing is performed on various parameters such as battery voltage and current, including Z-score standardization and Min-Max normalization;

[0056] 3). Time series data processing: The data is divided into windows, such as sliding windows, and a feature sequence is generated. Features such as moving average, rate of change, and amplitude of fluctuation can be extracted for further analysis.

[0057] As a further solution of the present invention, the machine learning-based analysis and fault prediction are as follows:

[0058] (1). Data labeling: According to the actual device fault records, the data is divided into "normal" and "fault" categories, or the device performance degradation is classified by level, such as mild, moderate, and severe;

[0059] (2). Selection of machine learning model: According to the nature of the problem, a suitable machine learning model is selected, such as including:

[0060] 1). Regression model: Used to predict the health status or performance degradation degree of the device;

[0061] 2). Classification model: Used to determine whether the device is in a fault state;

[0062] 3). Time series prediction model: used to predict the future operating status and battery life of the device;

[0063] 4). Clustering algorithm: used to identify abnormal patterns or categories of device operation;

[0064] (3). Training and validation model: trained using historical data, and the cross-validation method is adopted to evaluate the accuracy and robustness of the model.

[0065] As a further solution of the present invention, the fault diagnosis and performance report are generated as follows:

[0066] (1). Fault diagnosis: The system determines whether the device has a fault based on the analysis results. For faulty devices, the fault type can be further analyzed, such as battery damage, overheating, abnormal charge and discharge, etc., and possible fault causes are given;

[0067] (2). Performance report generation: The system automatically generates an operation report of the device, including the current status, predicted fault risk, and performance degradation trend. The report can include the following information:

[0068] 1). Device operating status: including key parameters such as battery power, temperature, and charge and discharge efficiency;

[0069] 2). Fault prediction: Based on the machine learning model, predict the probability and estimated time of fault occurrence;

[0070] 3). Performance evaluation: Based on historical data, evaluate the attenuation of the battery and give the estimated remaining life.

[0071] The present invention also provides a remote data interaction system for a photovoltaic energy storage device, including a data acquisition module, a communication module, a cloud data processing platform, and a user-side application.

[0072] As a further solution of the present invention, the data acquisition module includes multiple sensors and a data acquisition unit, which are used to collect the operation parameters of the photovoltaic energy storage device in real time and transmit the data to the communication module. The communication module is used to realize the remote transmission of data. The communication module supports multiple wireless communication protocols, such as Wi-Fi, LoRa, NB-IoT, to ensure that the device data can be stably and reliably transmitted to the cloud data processing platform.

[0073] As a further solution of the present invention, the cloud data processing platform is responsible for receiving and storing the data transmitted by the photovoltaic energy storage device, performing data analysis and fault diagnosis, generating a visual monitoring interface for users to perform remote monitoring. The platform is also responsible for performing energy optimization scheduling based on the data analysis results and providing intelligent decision-making support. The user-side application provides user interfaces for mobile (APP) and PC, and users can view the real-time status of the photovoltaic energy storage device, set control commands, receive alarm notifications, and manage and maintain the device according to the data and suggestions provided by the platform.

[0074] Compared with the related technologies, the remote data interaction method and system for the photovoltaic energy storage device provided by the present invention have the following beneficial effects:

[0075] 1. Through the remote data interaction technology, the present invention realizes the real-time monitoring, fault diagnosis and energy management of the photovoltaic energy storage device. Compared with the traditional local monitoring and manual inspection methods, the present invention can significantly improve the device management efficiency, reduce the fault response time, and enhance the overall reliability and stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0076] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the accompanying drawings.

[0077] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0078] Please refer to Figure 1 , wherein, Figure 1 It is a schematic diagram of the process of the present invention. The remote data interaction method for the photovoltaic energy storage device includes the following steps:

[0079] S1. Data acquisition and transmission:

[0080] (1). The photovoltaic energy storage device collects various operating data of the device, such as battery power, voltage, current, temperature, through built-in sensors;

[0081] (2). These data are transmitted to the cloud data processing platform through a wireless communication module, such as Wi-Fi, LoRa, NB-IoT;

[0082] S2. Data storage and processing:

[0083] (1). After receiving the transmitted data, the cloud data processing platform stores, cleans, and preprocesses the data;

[0084] (2). Based on machine learning algorithms, the data is analyzed to identify the operating state of the device, predict possible faults or performance degradation of the device, and generate relevant diagnostic reports;

[0085] S3. Remote Monitoring and Alarm:

[0086] (1). Users or equipment maintenance personnel can view the operation data and status of the equipment in real time through mobile applications such as APPs or PC platforms, and control and schedule the equipment as needed;

[0087] (2). Based on the platform, it can automatically send out fault alarms or performance anomaly prompts according to the data analysis results, reminding the maintenance personnel to take measures in a timely manner;

[0088] S4. Scheduling and Management:

[0089] (1). Based on the real-time data of the equipment, the system can automatically optimize energy management, perform load scheduling and battery charge and discharge strategy adjustment to ensure the maximization of the energy utilization efficiency of the equipment;

[0090] (2). The system can also achieve collaborative work among devices based on the data of multiple photovoltaic energy storage devices, balance energy supply and demand, and improve the operation efficiency of the overall system.

[0091] The method for the photovoltaic energy storage device to collect various operation data through built-in sensors and transmit these data to the cloud data processing platform is as follows:

[0092] (1). Sensor Deployment: Deploy multiple sensors on photovoltaic energy storage devices such as photovoltaic panels, battery energy storage systems, and inverters, so as to monitor the operation parameters of the devices in real time. The sensors are as follows:

[0093] 1). Battery Voltage Sensor: Measure the battery voltage to ensure that the battery operates within a reasonable range;

[0094] 2). Battery Current Sensor: Measure the charge and discharge current to monitor the battery charge and discharge efficiency;

[0095] 3). Temperature Sensor: Measure the working temperature of the device, especially the battery temperature, to prevent overheating;

[0096] 4). Battery SOC (State of Charge) Sensor: Evaluate the remaining battery charge;

[0097] 5). Power / Energy Sensor: Measure the power output of the system or the energy flow of the energy storage system;

[0098] (2). Data Acquisition Period and Frequency: Set a reasonable data acquisition frequency according to the operation characteristics and data transmission capabilities of the equipment. For the key operation parameters of the equipment, a higher sampling frequency can be set, such as once per second, while for relatively stable parameters such as the battery health status, a lower sampling frequency can be set;

[0099] (3). Data formatting and preprocessing: The collected raw data is preprocessed, such as unit conversion, missing data filling, and preliminary anomaly detection, so as to ensure the accuracy and consistency of the data.

[0100] The wireless communication module can select a suitable communication protocol according to the requirements of the application scenario, such as the number of devices, data volume, and distance, as follows:

[0101] (1). Wi-Fi: Suitable for situations where the device distance is relatively close and the network environment is good. Wi-Fi is suitable for high-speed data transmission;

[0102] (2). LoRa (Long Range): Suitable for large-scale and low-power scenarios. LoRa can achieve remote communication of low-power devices and is suitable for periodic data upload;

[0103] (3). NB-IoT (Narrowband IoT): Suitable for low-power and low-data-rate IoT devices in wide area networks. NB-IoT has stronger network coverage ability and can provide stable data transmission;

[0104] (4). Encryption technology should be adopted during the transmission process, such as using the TLS / SSL protocol for data encryption to prevent data from being stolen or tampered with during transmission.

[0105] The data reception and transmission to the cloud are as follows:

[0106] (1). Data transmission: Configure the data transmission parameters on the wireless communication module at the device end, establish a communication channel with the cloud data processing platform, and according to the selected communication protocol, such as Wi-Fi, LoRa, or NB-IoT, the device transmits the collected data to the cloud through the adapted gateway;

[0107] (2). Data format and protocol: The data sent from the device end should conform to the standard data format, such as JSON, XML, Protobuf, and select a suitable communication protocol according to needs, such as HTTP, MQTT, CoAP, for transmission;

[0108] (3). Cloud data reception and processing:

[0109] Data reception and storage: After the cloud platform receives the data transmitted from the device end, the data is stored in the database. When storing, the following need to be considered:

[0110] Data timestamp: Record the time of data collection for time series analysis;

[0111] Data Partitioning and Indexing: Partition and index the stored data to improve query efficiency and data processing speed;

[0112] Data Cleaning and Preprocessing: Further data cleaning is performed in the cloud, including outlier detection, handling of missing data, and denoising. At this time, data deduplication, formatting, and standardization can also be carried out on the data;

[0113] Data Storage and Structuring: Structurally store the data uploaded by the device for subsequent data querying, analysis, and report generation;

[0114] (4). Cloud Data Analysis and Processing:

[0115] 1). Data Analysis and Monitoring: The cloud platform can perform real-time monitoring and analysis on the received data. For example, the battery power, voltage, current, and temperature data of the device can be displayed through charts, dashboards, etc., to help the operation and maintenance personnel monitor the device status in real time;

[0116] 2). Fault Detection and Warning: Based on the operation data of the device, the cloud platform can use machine learning or rule engines to analyze whether the device is in a fault state. For example, if the battery temperature exceeds the threshold or the current is abnormal, a fault warning is triggered

[0117] (5). Data Presentation and Report Generation:

[0118] 1). Real-time Data Visualization: The cloud platform displays the real-time data of the device through a visualization interface to help the operation and maintenance personnel intuitively understand the device operation status. For example, charts can display the battery power change, voltage fluctuation, and charge and discharge efficiency parameters;

[0119] 2). Fault Report and Alarm: The system generates a device fault report or alarm notification according to the analysis results, and timely notifies the user or operation and maintenance personnel of the device operation anomaly, supporting notification methods such as email, SMS, or APP push.

[0120] The specific method steps for the cloud data processing platform to store, clean, preprocess the data of the photovoltaic energy storage device, analyze the device operation status through machine learning algorithms, predict faults or performance degradation, and generate a diagnostic report are as follows:

[0121] (1). Data Reception and Storage:

[0122] 1). Data Reception: The cloud platform receives data from the photovoltaic energy storage device through the communication module. These data include but are not limited to battery voltage, current, temperature, power generation, and energy storage parameters;

[0123] (2). Data storage: The received original data is stored in a cloud database. You can choose a relational database or a non-relational database for storage, and specifically select a suitable database type according to the data volume and storage requirements.

[0124] (3). Data storage strategy: For large data streams that are frequently updated, use partition storage and timestamp marking for easy subsequent querying and analysis.

[0125] (2). Data cleaning:

[0126] (1). Removing duplicate data: By verifying timestamps and device IDs, remove duplicate records to ensure data uniqueness.

[0127] (2). Outlier detection: Based on the normal operating range of the device, use statistical methods such as Z-score and IQR to detect outliers in the data. If a parameter, such as battery voltage, exceeds the normal range, it can be marked as abnormal data, and according to / normalization: **To enable effective comparison and processing of data on different scales in machine learning algorithms, standardize various parameters such as battery voltage and current, including Z-score standardization and Min-Max normalization.

[0128] (3). Time series data processing: Divide the data into windows, such as sliding windows, and generate feature sequences. Features such as moving average, rate of change, and fluctuation amplitude can be extracted for further analysis.

[0129] The machine learning-based analysis and fault prediction are as follows:

[0130] (1). Data labeling: According to actual device fault records, divide the data into "normal" and "fault" categories, or classify device performance degradation by level, such as mild, moderate, and severe.

[0131] (2). Selecting a machine learning model: According to the nature of the problem, select a suitable machine learning model, such as including:

[0132] (1). Regression model: Used to predict the health state or performance degradation degree of the device.

[0133] (2). Classification model: Used to determine whether the device is in a fault state.

[0134] (3). Time series prediction model: Used to predict the future operating state and battery life of the device.

[0135] (4). Clustering algorithm: Used to identify abnormal patterns or categories of device operation.

[0136] (3). Training and validating the model: Use historical data for training and adopt the cross-validation method to evaluate the accuracy and robustness of the model.

[0137] The fault diagnosis and performance report are generated as follows:

[0138] (1). Fault diagnosis: The system determines whether the device has a fault based on the analysis results. For faulty devices, the fault type can be further analyzed, such as battery damage, overheating, abnormal charging and discharging, etc., and possible fault causes are given;

[0139] (2). Performance report generation: The system automatically generates an operation report of the device, including the current status, predicted fault risk, and performance degradation trend. The following information can be included in the report:

[0140] 1). Device operation status: Includes key parameters such as battery power, temperature, and charge and discharge efficiency;

[0141] 2). Fault prediction: Based on the machine learning model, predict the probability and estimated time of fault occurrence;

[0142] 3). Performance evaluation: Based on historical data, evaluate the attenuation of the battery and give the estimated remaining life.

[0143] The present invention also provides a remote data interaction system for a photovoltaic energy storage device, including a data acquisition module, a communication module, a cloud data processing platform, and a user-side application.

[0144] The data acquisition module includes multiple sensors and a data acquisition unit, which are used to collect the operation parameters of the photovoltaic energy storage device in real time and transmit the data to the communication module. The communication module is used to realize the remote transmission of data. The communication module supports multiple wireless communication protocols, such as Wi-Fi, LoRa, NB-IoT, to ensure that the device data can be stably and reliably transmitted to the cloud data processing platform.

[0145] The cloud data processing platform is responsible for receiving and storing the data transmitted by the photovoltaic energy storage device, performing data analysis and fault diagnosis, generating a visual monitoring interface for users to perform remote monitoring. The platform is also responsible for performing energy optimization scheduling based on the data analysis results and providing intelligent decision-making support. The user-side application provides user interfaces for the mobile end (APP) and the PC end. Users can view the real-time status of the photovoltaic energy storage device through these interfaces, set control instructions, receive alarm notifications, and manage and maintain the device according to the data and suggestions provided by the platform.

[0146] Through the remote data interaction technology, the present invention realizes the real-time monitoring, fault diagnosis and energy management of photovoltaic energy storage devices. Compared with the traditional local monitoring and manual inspection methods, the present invention can significantly improve the equipment management efficiency, reduce the fault response time, and enhance the overall reliability and stability of the system.

[0147] The above are only the preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention, according to the technical solution and inventive concept of the present invention, making equivalent substitutions or changes, should be covered within the protection scope of the present invention.

Claims

1. A remote data interaction method for photovoltaic energy storage equipment, characterized in that: The following steps are involved: S1.Data collection and transmission: (1) Photovoltaic energy storage equipment collects various operating data of the equipment through built-in sensors, such as battery power, voltage, current, and temperature; (2) Transmit these data to the cloud data processing platform through wireless communication modules such as Wi-Fi, LoRa, and NB-IoT; S2. Data storage and processing: (1) After receiving the transmitted data, the cloud data processing platform stores, cleans and pre-processes the data; (2) Analyze data based on machine learning algorithms, identify the operating status of the equipment, predict possible equipment failures or performance degradation, and generate relevant diagnostic reports; S3. Remote monitoring and alarm: (1) Users or equipment maintenance personnel can view the equipment's operating data and status in real time through mobile applications such as APP or PC platforms, and control and dispatch the equipment as needed; (2) Based on the data analysis results, the platform can automatically issue fault alarms or performance abnormality prompts to remind maintenance personnel to take timely measures; S4. Scheduling and Management: (1) Based on the real-time data of the equipment, the system can automatically optimize energy management, perform load scheduling and adjust battery charging and discharging strategies to ensure the maximum energy utilization efficiency of the equipment; (2) The system can also achieve collaborative work between devices based on the data of multiple photovoltaic energy storage devices, balance energy supply and demand, and improve the operating efficiency of the overall system.

2. The remote data interaction method of photovoltaic energy storage equipment according to claim 1, characterized in that: The method of the photovoltaic energy storage device collecting various operating data through built-in sensors and transmitting the data to the cloud data processing platform through the wireless communication module is as follows: (1) Sensor deployment: Multiple sensors are deployed on photovoltaic energy storage equipment, such as photovoltaic panels, battery energy storage systems, and inverters, to monitor the operating parameters of the equipment in real time. The sensors are as follows: 1). Battery voltage sensor: measures the battery voltage to ensure that the battery operates within a reasonable range; 2). Battery current sensor: measures the charge and discharge current and monitors the battery charge and discharge efficiency; 3). Temperature sensor: measures the operating temperature of the device, especially the battery temperature, to prevent overheating; 4). Battery SOC (State of Charge) sensor: evaluates the remaining battery power; 5) Power / Energy Sensor: measures the power output of the system or the energy flow of the energy storage system; (2) Data collection cycle and frequency: According to the operating characteristics and data transmission capacity of the equipment, set a reasonable data collection frequency. For the key operating parameters of the equipment, you can set a higher sampling frequency, such as collecting data once per second, while for more stable parameters, such as the health status of the battery, you can set a lower sampling frequency; (3) Data formatting and preprocessing: The collected raw data is preprocessed, such as unit conversion, missing data filling and preliminary anomaly detection, to ensure the accuracy and consistency of the data.

3. The remote data interaction method of photovoltaic energy storage equipment according to claim 1, characterized in that: The wireless communication module can select a suitable communication protocol according to the requirements of the application scenario, such as the number of devices, data volume, and distance, as follows: (1) Wi-Fi: Applicable to situations where the devices are close and the network environment is good. Wi-Fi is suitable for high-speed data transmission; (2) LoRa (Long Range): Suitable for large-scale, low-power scenarios. LoRa can achieve long-distance communication of low-power devices and is suitable for periodic data upload; (3) NB-IoT (Narrowband IoT): Low-power, low-data-rate IoT devices suitable for wide area networks. NB-IoT has stronger network coverage and can provide stable data transmission. (4) Encryption technology should be used during the transmission process, such as TLS / SSL protocol for data encryption to prevent data from being stolen or tampered with during transmission.

4. The remote data interaction method of photovoltaic energy storage equipment according to claim 1, characterized in that: The data is received and transmitted to the cloud as follows: (1) Data transmission: Configure the data transmission parameters on the wireless communication module on the device side and establish a communication channel with the cloud data processing platform. According to the selected communication protocol, such as Wi-Fi, LoRa or NB-IoT, the device transmits the collected data to the cloud through the adapted gateway; (2) Data format and protocol: The data sent by the device should conform to the standard data format, such as JSON, XML, Protobuf, and select the appropriate communication protocol as needed, such as HTTP, MQTT, CoAP for transmission; (3) Cloud data reception and processing: Data reception and storage: After the cloud platform receives the data transmitted by the device, it stores the data in the database. When storing the data, the following should be considered: Data timestamp: records the time of data collection for timing analysis; Data partitioning and indexing: Partition and index the stored data to improve query efficiency and data processing speed; Data cleaning and preprocessing: Further data cleaning is performed in the cloud, including outlier detection, data missing processing, and denoising. At this point, the data can also be deduplicated, formatted, and standardized. Data storage and structuring: Data uploaded by the device is stored in a structured manner for subsequent data query, analysis and report generation; (4) Cloud data analysis and processing: 1) Data analysis and monitoring: The cloud platform can monitor and analyze the received data in real time. For example, the battery power, voltage, current, and temperature data of the equipment can be displayed through charts, dashboards, etc., to help operation and maintenance personnel monitor the equipment status in real time; 2) Fault detection and early warning: Based on the operating data of the device, the cloud platform can use machine learning or rule engines to analyze whether the device is in a fault state. For example, if the battery temperature exceeds the threshold or the current is abnormal, a fault early warning is triggered. (5) Data display and report generation: 1) Real-time data visualization: The cloud platform displays the real-time data of the equipment through a visual interface, helping operation and maintenance personnel to intuitively understand the operating status of the equipment. For example, the chart can show the battery power change, voltage fluctuation, and charging and discharging efficiency parameters; 2) Fault reporting and alarming: The system generates equipment fault reports or alarm notifications based on the analysis results, and promptly notifies users or operation and maintenance personnel of equipment operating abnormalities. Notifications can be sent by email, SMS or APP push.

5. The remote data interaction method of photovoltaic energy storage equipment according to claim 1, characterized in that: The cloud data processing platform stores, cleans, and preprocesses the data of photovoltaic energy storage equipment, and uses machine learning algorithms to analyze the operating status of the equipment, predict failures or performance degradation, and generate a diagnostic report. The specific steps are as follows: (1) Data reception and storage: 1). Data reception: The cloud platform receives data from the photovoltaic energy storage device through the communication module. These data include but are not limited to battery voltage, current, temperature, power generation, and energy storage parameters; 2). Data storage: The received raw data is stored in the cloud database. You can choose a relational database or a non-relational database for storage. The appropriate database type is selected based on the data volume and storage requirements. 3) Data storage strategy: For frequently updated large data streams, partition storage and timestamp marking are used to facilitate subsequent query and analysis; (2) Data cleaning: 1) Remove duplicate data: By verifying the timestamp and device ID, remove duplicate records to ensure the uniqueness of the data; 2). Outlier detection: Based on the normal operating range of the equipment, use statistical methods such as Z-score and IQR to detect outliers in the data. If a parameter, such as battery voltage, exceeds the normal range, it can be marked as abnormal data and normalized according to / normalization: **In order to enable data of different scales to be effectively compared and processed in machine learning algorithms, various parameters such as battery voltage and current are standardized, such as Z-score normalization and Min-Max normalization; 3) Time series data processing: Divide the data into windows, such as sliding windows, and generate feature sequences. Features such as moving average, rate of change, and fluctuation range can be extracted for further analysis.

6. The remote data interaction method of photovoltaic energy storage equipment according to claim 1, characterized in that: The analysis and fault prediction based on machine learning are as follows: (1) Data labeling: Based on actual equipment failure records, data is divided into "normal" and "fault" categories, or equipment performance degradation is classified into levels, such as mild, moderate, and severe; (2) Select a machine learning model: Select a suitable machine learning model based on the nature of the problem, such as: 1). Regression model: used to predict the health status or performance degradation of equipment; 2). Classification model: used to determine whether the equipment is in a fault state; 3). Time series prediction model: used to predict the future operating status and battery life of the device; 4) Clustering algorithm: used to identify abnormal patterns or categories of equipment operation; (3) Training and validating the model: Use historical data for training and use cross-validation method to evaluate the accuracy and robustness of the model.

7. The remote data interaction method and system of photovoltaic energy storage equipment according to claim 1, characterized in that: The fault diagnosis and performance report is generated as follows: (1) Fault diagnosis: The system determines whether the device has a fault based on the analysis results. For faulty devices, the system can further analyze the fault type, such as battery damage, overheating, abnormal charging and discharging, etc., and give possible fault causes; (2) Performance report generation: The system automatically generates an operation report of the equipment, including the current status, predicted failure risk, and performance degradation trend. The report can include the following information: 1). Equipment operating status: including key parameters such as battery power, temperature, and charging and discharging efficiency; 2) Fault prediction: predict the probability and estimated time of fault occurrence based on machine learning models; 3) Performance evaluation: Based on historical data, evaluate the battery degradation and give an estimated remaining life.

8. A remote data interaction system for photovoltaic energy storage equipment, characterized in that: It includes the remote data interaction method and data acquisition module, communication module, cloud data processing platform and user-end application of the photovoltaic energy storage device as claimed in claim 1.

9. The remote data interaction system of photovoltaic energy storage equipment according to claim 8, characterized in that: The data acquisition module includes multiple sensors and data acquisition units, which are used to collect the operating parameters of the photovoltaic energy storage equipment in real time and transmit the data to the communication module. The communication module is used to realize remote transmission of data. The communication module supports multiple wireless communication protocols, such as Wi-Fi, LoRa, and NB-IoT, to ensure that the device data can be stably and reliably transmitted to the cloud data processing platform.

10. The remote data interaction system of photovoltaic energy storage equipment according to claim 8, characterized in that: The cloud data processing platform is responsible for receiving and storing data transmitted by photovoltaic energy storage equipment, performing data analysis and fault diagnosis, and generating a visual monitoring interface for users to conduct remote monitoring. The platform is also responsible for optimizing energy scheduling based on data analysis results and providing intelligent decision support. The user-side application provides user interfaces for mobile terminals (APP) and PC terminals. Users can use these interfaces to view the real-time status of photovoltaic energy storage equipment, set control instructions, receive alarm notifications, and manage and maintain the equipment based on the data and suggestions provided by the platform.

Images