A photovoltaic energy storage management system based on big data

Abstract

The present invention discloses a photovoltaic energy storage management system based on big data, which specifically relates to the field of photovoltaic energy storage technology, including a photovoltaic storage device data collection module, a data sorting module, a neural network module, a database, an evaluation module, and a photovoltaic storage device management module; the photovoltaic storage device management module is respectively connected with the photovoltaic storage device data collection module, the data sorting module, the neural network module, the database, and the evaluation module; the photovoltaic storage device data collection module is used to collect the main body operation information, charging line information, discharge line information and external environment information of the photovoltaic storage device, and transmit the main body operation information, charging line information, discharge line information and external environment information of the photovoltaic storage device to the data sorting module; the present invention can realize real-time monitoring and management of photovoltaic storage devices, improve the operation safety and stability of photovoltaic storage devices, reduce operation and maintenance costs, and improve energy utilization efficiency.

Description

Technical Field

[0001] The present invention relates to the field of photovoltaic energy storage technology, and more specifically, to a photovoltaic energy storage management system based on big data. Background Art

[0002] With the intensification of the global energy crisis and the increasing severity of environmental pollution, solar energy as a clean and renewable energy source has attracted more and more attention. The photovoltaic storage system is a system that converts solar energy into electrical energy and stores it for emergency use. The photovoltaic power generation system refers to a power generation system that directly converts light energy into electrical energy without going through a thermal process. The main components of the photovoltaic power generation system are solar cells, batteries, controllers and inverters. The battery is also a photovoltaic energy storage system. The battery is used to store the direct current converted by solar cells and is the energy storage center. The existing photovoltaic energy storage system is easily affected by natural factors such as light and temperature. Its output power is unstable and intermittent, and there is an unbalanced power supply. The natural loss of the battery caused by use and the abnormal loss caused by abnormal conditions cannot be well understood through conventional methods. At the same time, the staff cannot understand the battery life and replace the battery in time, which affects the normal operation of the photovoltaic system. In order to solve the above problems, a photovoltaic energy storage management system based on big data is designed to facilitate the staff to control the operating safety and stability of the photovoltaic storage equipment.

[0003] Invention Project

[0004] To achieve the above object, the present invention provides the following technical solutions:

[0005] A photovoltaic energy storage management system based on big data, comprising a photovoltaic equipment data collection module, a data sorting module, a neural network module, a database, an evaluation module, and a photovoltaic equipment management module; the photovoltaic equipment management module is respectively connected to the photovoltaic equipment data collection module, the data sorting module, the neural network module, the database, and the evaluation module;

[0006] The optical storage device data collection module is used to collect the main body operation information, charging line information, discharging line information and external environment information of the optical storage device, and transmit the main body operation information, charging line information, discharging line information and external environment information of the optical storage device to the data sorting module;

[0007] A threshold table is pre-stored in the database;

[0008] The data sorting module is used to sort the main body operation information, charging line information, discharging line information and external environment information of the optical storage device, and transmit the data sorting results to the neural network module and the evaluation module respectively;

[0009] The neural network module is used to predict the operation risk of the optical storage equipment based on the data sorting results, and send the prediction results to the evaluation module;

[0010] The evaluation module is used to evaluate the optical storage device according to the pre-stored threshold table, prediction results, and data sorting results in the database, and send the evaluation results to the optical storage device management module;

[0011] The optical storage device management module executes management strategies on the optical storage device according to the evaluation results.

[0012] In a preferred embodiment, the big data-based photovoltaic energy storage management system also includes a display and adjustment terminal, which is used to display all operation records of the big data-based photovoltaic energy storage management system, and to update and adjust the threshold forms pre-stored in the database and the management strategies in the photovoltaic storage device management module.

[0013] In a preferred embodiment, the main operating information of the photovoltaic storage device includes the charging and discharging status data of the photovoltaic storage device, the real-time capacity percentage data of the photovoltaic storage device, the real-time temperature data of the photovoltaic storage device, and the difference data between the terminal voltage values ​​at both ends of the photovoltaic storage device.

[0014] In a preferred embodiment, the charging circuit information includes real-time current data and real-time voltage data of the charging circuit; the discharging circuit information includes real-time current data and real-time voltage data of the discharging circuit.

[0015] In a preferred embodiment, the external environment information includes temperature data of the external environment, humidity data of the external environment, and atmospheric pressure data of the external environment.

[0016] In a preferred embodiment, the data sorting module is used to sort the data of the main body operation information, charging line information, discharging line information and external environment information of the optical storage device, which means:

[0017] Step A1, dividing the collected time period T1, marking the average value of the real-time temperature data of the photovoltaic storage device in the charging state in the time period T1 as GW1i, and marking the average value of the difference data between the terminal voltage values ​​at both ends of the photovoltaic storage device as GY1i; marking the average value of the real-time temperature data of the photovoltaic storage device in the discharging state as GW2i, and marking the average value of the difference data between the terminal voltage values ​​at both ends of the photovoltaic storage device as GY2i;

[0018] Step A2, according to the collected time period T1, the real-time current data average value of the charging circuit is marked as CDi, the real-time voltage data average value of the charging circuit is marked as CYi; the real-time current data average value of the discharge circuit is marked as FDi, and the real-time voltage data average value of the discharge circuit is marked as FYi;

[0019] Step A3, dividing the collected time period T1, marking the average value of the temperature data of the external environment as HWi, the average value of the humidity data of the external environment as HSi, and the average value of the atmospheric pressure data of the external environment as HYi;

[0020] Step A4, marking the real-time capacity percentage data of the optical storage device as SRi;

[0021] Step A5: Summarize the results of steps A1, A2, A3 and A4.

[0022] In a preferred embodiment, the neural network module is used to predict the operation risk of the optical storage device according to the data sorting result, and send the prediction result to the evaluation module, which means:

[0023] Step B1: Obtain the charging safety factor C1 of the solar energy storage device through the formula. The calculation formula is C1= ;

[0024] Step B2: Obtain the discharge safety factor C2 of the photovoltaic storage device through the formula, and the calculation formula is C2= ;

[0025] Step B3: Obtain the environmental safety factor C3 of the photovoltaic storage device through the formula, and the calculation formula is C3= , , , , All are specific proportional coefficients;

[0026] Step B4: Obtain the abnormal operation coefficient C4 of the optical storage device through the formula, and the calculation formula is C4=f1 C1+f2 C2+f3 C3, f1, f2, and f3 are all specific proportional coefficients;

[0027] Step B5, the neural network module uses the charging safety factor C1 of the photovoltaic storage device, the discharging safety factor C2 of the photovoltaic storage device, the environmental safety factor C3 of the photovoltaic storage device, and the corresponding data acquisition time as input data for neural network model training, uses the operation abnormality coefficient C4 of the photovoltaic storage device as output data for neural network model training, and assigns it to 0 or 1 to train the model, wherein 0 indicates that the operation abnormality coefficient C4 of the photovoltaic storage device is less than or equal to the set threshold, and 1 indicates that the operation abnormality coefficient C4 of the photovoltaic storage device is greater than the set threshold;

[0028] Step B6: Use the collected data of the latest m time periods T1 as the input data of the neural network model. When the output data of the neural network model is 0, use the collected data of the latest m time periods T1 as the training data of the model to perform secondary training on the model. When the output data of the model is 1, use the collected data of the latest m time periods T1 as the training data of the model to perform secondary training on the model while sending the output data 1 to the evaluation module.

[0029] In a preferred embodiment, the evaluation module is used to evaluate the optical storage device according to the pre-stored threshold table, prediction results, and data sorting results in the database, which means:

[0030] Step 1: Divide the data into time periods T1, and based on the comparison results between the collected data and the pre-stored threshold table in the database, mark the number of abnormalities of the optical storage device in n consecutive time periods T1 as YC1i, the number of abnormalities of the charging circuit as YC2i, the number of abnormalities of the discharge circuit as YC3i, and the number of abnormalities of the external environment as YC4i;

[0031] Step 2: Divide by time period T2, and count the number of times YC5i that the evaluation module receives the output data 1 result of the neural network module in time period T2. Time period T2 is a time interval composed of integer multiples of time period T1, n=T2 / T1, n is a positive integer;

[0032] Step 3: Calculate the evaluation value PG of the optical storage device, PG=k1 (YC1i+YC2i+YC3i)+k2 YC4i+k3 YC5i, compares the evaluation value PG of the optical storage device with the standard evaluation threshold interval in the pre-stored threshold table in the database For comparison, if PG Standard evaluation threshold interval , it is determined that the optical storage device is in a low-risk operating state and generates a second-class operating instruction; if PG , it is determined that the optical storage device is in a safe operating state and generates a type of operating instruction; if PG , it is determined that the optical storage equipment is in a high-risk operating state and three types of operating instructions are generated.

[0033] Technical effects and advantages of the present invention:

[0034] The present invention can collect the main body operation information, charging line information, discharging line information and external environment information of the photoelectric storage device in real time, and perform data processing through the data sorting module, and transmit the processing results to the neural network module and the evaluation module. The neural network module predicts the operation risk of the photoelectric storage device according to the data sorting result, and sends the prediction result to the evaluation module; the evaluation module evaluates the photoelectric storage device according to the pre-stored threshold table, prediction result and data sorting result in the database, and sends the evaluation result to the photoelectric storage device management module. The photoelectric storage device management module executes the management strategy for the photoelectric storage device according to the evaluation result, so as to realize real-time monitoring and management of the photoelectric storage device, improve the operation safety and stability of the photoelectric storage device, reduce the operation and maintenance cost, and improve the energy utilization efficiency.

[0035] In the present invention, the neural network module uses the charging safety factor C1 of the photovoltaic storage device, the discharging safety factor C2 of the photovoltaic storage device, the environmental safety factor C3 of the photovoltaic storage device and the corresponding data acquisition time as the input data of the neural network model training, and uses the operation abnormality coefficient C4 of the photovoltaic storage device as the output data of the neural network model training. By constructing a prediction model, the overall prediction accuracy of the system can be improved, and the control accuracy of the operation safety and stability of the equipment can be further ensured. A display and adjustment terminal is also added to display all operation records of the photovoltaic energy management system based on big data, as well as to update and adjust the threshold tables pre-stored in the database and the management strategies in the photovoltaic storage device management module, so that users can make timely strategy adjustments according to actual usage. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0037] Figure 1 This is a schematic diagram of a big data-based optical energy storage management system in the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] Example 1

[0040] A photovoltaic energy storage management system based on big data, comprising a photovoltaic equipment data collection module, a data sorting module, a neural network module, a database, an evaluation module, and a photovoltaic equipment management module; the photovoltaic equipment management module is respectively connected to the photovoltaic equipment data collection module, the data sorting module, the neural network module, the database, and the evaluation module;

[0041] The photoelectric storage device data collection module is used to collect the main body operation information, charging circuit information, discharging circuit information and external environment information of the photoelectric storage device, and transmit the main body operation information, charging circuit information, discharging circuit information and external environment information of the photoelectric storage device to the data sorting module; the main body operation information of the photoelectric storage device includes the charging and discharging state data of the photoelectric storage device, the real-time capacity percentage data of the photoelectric storage device, the real-time temperature data of the photoelectric storage device, and the difference data between the terminal voltage values ​​at both ends of the photoelectric storage device; the charging circuit information includes the real-time current data of the charging circuit and the real-time voltage data of the charging circuit; the discharging circuit information includes the real-time current data of the discharging circuit and the real-time voltage data of the discharging circuit; the external environment information includes the temperature data of the external environment, the humidity data of the external environment, and the atmospheric pressure data of the external environment;

[0042] A threshold table is pre-stored in the database;

[0043] The data sorting module is used to sort the main body operation information, charging line information, discharging line information and external environment information of the optical storage device, and transmit the data sorting results to the neural network module and the evaluation module respectively;

[0044] The neural network module is used to predict the operation risk of the optical storage equipment based on the data sorting results, and send the prediction results to the evaluation module;

[0045] The evaluation module is used to evaluate the optical storage device according to the pre-stored threshold table, prediction results, and data sorting results in the database, and send the evaluation results to the optical storage device management module;

[0046] The optical storage device management module executes management strategies on the optical storage device according to the evaluation results.

[0047] The data sorting module is used to sort the data of the main body operation information, charging line information, discharging line information and external environment information of the optical storage device, which refers to:

[0048] Step A1, dividing the collected time period T1, marking the average value of the real-time temperature data of the photovoltaic storage device in the charging state in the time period T1 as GW1i, and marking the average value of the difference data between the terminal voltage values ​​at both ends of the photovoltaic storage device as GY1i; marking the average value of the real-time temperature data of the photovoltaic storage device in the discharging state as GW2i, and marking the average value of the difference data between the terminal voltage values ​​at both ends of the photovoltaic storage device as GY2i; i represents the project number, which does not involve the specific meaning and will not be repeated below;

[0049] Step A2, dividing the collected time period T1, marking the average value of the real-time current data of the charging circuit as CDi, and the average value of the real-time voltage data of the charging circuit as CYi; marking the average value of the real-time current data of the discharging circuit as FDi, and the average value of the real-time voltage data of the discharging circuit as FYi; the average value is determined according to the average value calculation formula, which is a calculation method well known to those skilled in the art and will not be described in detail below;

[0050] Step A3, dividing the collected time period T1, marking the average value of the temperature data of the external environment as HWi, the average value of the humidity data of the external environment as HSi, and the average value of the atmospheric pressure data of the external environment as HYi;

[0051] Step A4, marking the real-time capacity percentage data of the optical storage device as SRi;

[0052] Step A5: Summarize the results of steps A1, A2, A3 and A4.

[0053] The neural network module is used to predict the operation risk of the optical storage equipment based on the data collation results and send the prediction results to the evaluation module:

[0054] Step B1: Obtain the charging safety factor C1 of the solar energy storage device through the formula. The calculation formula is C1= ;

[0055] Step B2: Obtain the discharge safety factor C2 of the photovoltaic storage device through the formula, and the calculation formula is C2= ;

[0056] Step B3: Obtain the environmental safety factor C3 of the photovoltaic storage device through the formula, and the calculation formula is C3= , , , , All are specific proportional coefficients;

[0057] Step B4: Obtain the abnormal operation coefficient C4 of the optical storage device through the formula, and the calculation formula is C4=f1 C1+f2 C2+f3 C3, f1, f2, and f3 are all specific proportional coefficients;

[0058] Step B5, the neural network module uses the charging safety factor C1 of the photovoltaic storage device, the discharging safety factor C2 of the photovoltaic storage device, the environmental safety factor C3 of the photovoltaic storage device, and the corresponding data acquisition time as input data for neural network model training, uses the operation abnormality coefficient C4 of the photovoltaic storage device as output data for neural network model training, and assigns it to 0 or 1 to train the model, wherein 0 indicates that the operation abnormality coefficient C4 of the photovoltaic storage device is less than or equal to the set threshold, and 1 indicates that the operation abnormality coefficient C4 of the photovoltaic storage device is greater than the set threshold;

[0059] Step B6: Use the collected data of the latest m time periods T1 as the input data of the neural network model. When the output data of the neural network model is 0, use the collected data of the latest m time periods T1 as the training data of the model to perform secondary training on the model. When the output data of the model is 1, use the collected data of the latest m time periods T1 as the training data of the model to perform secondary training on the model while sending the output data 1 to the evaluation module.

[0060] The evaluation module is used to evaluate the optical storage device according to the pre-stored threshold table, prediction results, and data sorting results in the database, which refers to:

[0061] Step 1: Divide the data into time periods T1, and based on the comparison results between the collected data and the pre-stored threshold table in the database, mark the number of abnormalities of the optical storage device in n consecutive time periods T1 as YC1i, the number of abnormalities of the charging circuit as YC2i, the number of abnormalities of the discharge circuit as YC3i, and the number of abnormalities of the external environment as YC4i;

[0062] Step 2: Divide by time period T2, and count the number of times YC5i that the evaluation module receives the output data 1 result of the neural network module in time period T2. Time period T2 is a time interval composed of integer multiples of time period T1, n=T2 / T1, n is a positive integer;

[0063] Step 3: Calculate the evaluation value PG of the optical storage device, PG=k1 (YC1i+YC2i+YC3i)+k2 YC4i+k3 YC5i, compares the evaluation value PG of the optical storage device with the standard evaluation threshold interval in the pre-stored threshold table in the database For comparison, if PG Standard evaluation threshold interval , it is determined that the optical storage device is in a low-risk operating state and generates a second-class operating instruction; if PG , it is determined that the optical storage device is in a safe operating state and generates a type of operating instruction; if PG , it is determined that the optical storage equipment is in a high-risk operating state and three types of operating instructions are generated.

[0064] Example 2

[0065] A photovoltaic energy storage management system based on big data comprises a photovoltaic device data collection module, a data sorting module, a neural network module, a database, an evaluation module and a photovoltaic device management module; the photovoltaic device management module is respectively connected to the photovoltaic device data collection module, the data sorting module, the neural network module, the database and the evaluation module; the photovoltaic energy storage management system based on big data also comprises a display and adjustment terminal, which is used to display all operation records of the photovoltaic energy storage management system based on big data, and to update and adjust the threshold value tables pre-stored in the database and the management strategies in the photovoltaic device management module.

[0066] The photoelectric storage device data collection module is used to collect the main operation information, charging circuit information, discharging circuit information and external environment information of the photoelectric storage device, and transmit the main operation information, charging circuit information, discharging circuit information and external environment information of the photoelectric storage device to the data sorting module; the main operation information of the photoelectric storage device includes the charging and discharging status data of the photoelectric storage device, the real-time capacity percentage data of the photoelectric storage device, the real-time temperature data of the photoelectric storage device, and the difference data between the terminal voltage values ​​at both ends of the photoelectric storage device.

[0067] The charging circuit information includes the real-time current data and the real-time voltage data of the charging circuit; the discharging circuit information includes the real-time current data and the real-time voltage data of the discharging circuit.

[0068] The external environment information includes temperature data of the external environment, humidity data of the external environment, and atmospheric pressure data of the external environment.

[0069] A threshold table is pre-stored in the database; the data sorting module is used to sort the data of the main body operation information, charging line information, discharging line information and external environment information of the photovoltaic storage device, and transmit the data sorting results to the neural network module and the evaluation module respectively; specifically: step A1, according to the collected time period T1, the average value of the real-time temperature data of the photovoltaic storage device in the charging state within the time period T1 is marked as GW1i, and the average value of the difference data between the terminal voltage values ​​at both ends of the photovoltaic storage device is marked as GY1i; the average value of the real-time temperature data of the photovoltaic storage device in the discharging state is marked as GW2i, and the average value of the difference data between the terminal voltage values ​​at both ends of the photovoltaic storage device is marked as GY2i;

[0070] Step A2, according to the collected time period T1, the real-time current data average value of the charging circuit is marked as CDi, the real-time voltage data average value of the charging circuit is marked as CYi; the real-time current data average value of the discharge circuit is marked as FDi, and the real-time voltage data average value of the discharge circuit is marked as FYi;

[0071] Step A3, dividing the collected time period T1, marking the average value of the temperature data of the external environment as HWi, the average value of the humidity data of the external environment as HSi, and the average value of the atmospheric pressure data of the external environment as HYi;

[0072] Step A4, marking the real-time capacity percentage data of the optical storage device as SRi;

[0073] Step A5: Summarize the results of steps A1, A2, A3 and A4.

[0074] The neural network module is used to predict the operating risk of the photovoltaic storage device based on the data collation results, and send the prediction results to the evaluation module; specifically, step B1, obtain the charging safety factor C1 of the photovoltaic storage device through the formula, and the calculation formula is C1= ;

[0075] Step B2: Obtain the discharge safety factor C2 of the photovoltaic storage device through the formula, and the calculation formula is C2= ;

[0076] Step B3: Obtain the environmental safety factor C3 of the photovoltaic storage device through the formula, and the calculation formula is C3= , , , , All are specific proportional coefficients;

[0077] Step B4: Obtain the abnormal operation coefficient C4 of the optical storage device through the formula, and the calculation formula is C4=f1 C1+f2 C2+f3 C3, f1, f2, and f3 are all specific proportional coefficients;

[0078] Step B5, the neural network module uses the charging safety factor C1 of the photovoltaic storage device, the discharging safety factor C2 of the photovoltaic storage device, the environmental safety factor C3 of the photovoltaic storage device, and the corresponding data acquisition time as input data for neural network model training, uses the operation abnormality coefficient C4 of the photovoltaic storage device as output data for neural network model training, and assigns it to 0 or 1 to train the model, wherein 0 indicates that the operation abnormality coefficient C4 of the photovoltaic storage device is less than or equal to the set threshold, and 1 indicates that the operation abnormality coefficient C4 of the photovoltaic storage device is greater than the set threshold;

[0079] Step B6: Use the collected data of the latest m time periods T1 as the input data of the neural network model. When the output data of the neural network model is 0, use the collected data of the latest m time periods T1 as the training data of the model to perform secondary training on the model. When the output data of the model is 1, use the collected data of the latest m time periods T1 as the training data of the model to perform secondary training on the model while sending the output data 1 to the evaluation module, where m is a positive integer.

[0080] The evaluation module is used to evaluate the photovoltaic storage device according to the pre-stored threshold table, prediction results, and data sorting results in the database, and send the evaluation results to the photovoltaic storage device management module; specifically: Step 1, divide according to the time period T1, and according to the comparison results of the collected data with the pre-stored threshold table in the database, mark the number of abnormalities of the photovoltaic storage device in n consecutive time periods T1 as YC1i, the number of abnormalities of the charging circuit as YC2i, the number of abnormalities of the discharge circuit as YC3i, and the number of abnormalities of the external environment as YC4i; the pre-stored threshold table stores the standard threshold of the average value of the real-time temperature data of the photovoltaic storage device in the charging state, the standard threshold of the average value of the difference data between the terminal voltage values ​​at both ends of the photovoltaic storage device, the standard threshold of the average value of the real-time temperature data of the photovoltaic storage device in the discharging state, the standard threshold of the average value of the difference data between the terminal voltage values ​​at both ends of the photovoltaic storage device, the standard threshold of the average value of the real-time current data of the charging circuit, and the standard threshold of the average value of the real-time voltage data of the charging circuit. ; The standard threshold of the average value of the real-time current data of the discharge circuit, the standard threshold of the average value of the real-time voltage data of the discharge circuit, the standard threshold interval of the average value of the temperature data of the external environment, the standard threshold interval of the average value of the humidity data of the external environment, and the standard threshold interval of the average value of the atmospheric pressure data of the external environment. If any of the data exceeds the standard threshold or is not in the corresponding standard threshold interval, it is determined that the data is abnormal. Taking the number of times the photovoltaic storage device is abnormal as YC1i as an example, the average value of the real-time temperature data of the photovoltaic storage device in the charging state within the time period T1 is marked as GW1i, the average value of the difference data between the terminal voltage values ​​at both ends of the photovoltaic storage device is marked as GY1i, the average value of the real-time temperature data of the photovoltaic storage device in the discharge state is marked as GW2i, and the average value of the difference data between the terminal voltage values ​​at both ends of the photovoltaic storage device is marked as GY2i, a total of four data. If any of the data is abnormal, it is determined that the photovoltaic storage device is abnormal. If multiple data are abnormal within the same time period T1, the number of times is also recorded as once;

[0081] Step 2: Divide according to time period T2, and count the number of times YC5i that the evaluation module receives the output data 1 result of the neural network module in time period T2. Time period T2 is a time interval composed of integer multiples of time period T1, n=T2 / T1, n is a positive integer; it should be mentioned that the start time of time period T2 is the start time of the first time period T1, and the end time of time period T2 is the end time of the last time period T1;

[0082] Step 3: Calculate the evaluation value PG of the optical storage device, PG=k1 (YC1i+YC2i+YC3i)+k2 YC4i+k3 YC5i, compares the evaluation value PG of the optical storage device with the standard evaluation threshold interval in the pre-stored threshold table in the database For comparison, if PG Standard evaluation threshold interval , it is determined that the optical storage device is in a low-risk operating state and generates a second-class operating instruction; if PG , it is determined that the optical storage device is in a safe operating state and generates a type of operating instruction; if PG , it is determined that the optical storage equipment is in a high-risk operating state and three types of operating instructions are generated.

[0083] The optical storage device management module executes management strategies for the optical storage device based on the evaluation results. Specific examples are as follows: when the optical storage device management module receives a Class I operating instruction, no measures need to be taken for the optical storage device, and the optical storage device operates normally; when the optical storage device management module receives a Class II operating instruction, measures need to be taken for the optical storage device, and the optical storage device operates with low risk; when the optical storage device management module receives a Class III operating instruction, measures need to be taken for the optical storage device, and the optical storage device operates with high risk. The measures taken include but are not limited to disconnecting the charging circuit, discharging circuit, inspection by maintenance personnel, replacement and maintenance of the optical storage device, and other operations.

[0084] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0085] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0086] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0087] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0088] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0089] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0090] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A light energy storage management system based on big data, characterized in that: It includes a light storage device data collection module, a data sorting module, a neural network module, a database, an evaluation module, and a light storage device management module; the light storage device management module is connected to the light storage device data collection module, the data sorting module, the neural network module, the database, and the evaluation module respectively; The optical storage device data collection module is used to collect the main body operation information, charging line information, discharging line information and external environment information of the optical storage device, and transmit the main body operation information, charging line information, discharging line information and external environment information of the optical storage device to the data sorting module; A threshold table is pre-stored in the database; The data sorting module is used to sort the main body operation information, charging line information, discharging line information and external environment information of the optical storage device, and transmit the data sorting results to the neural network module and the evaluation module respectively; The neural network module is used to predict the operation risk of the optical storage equipment based on the data sorting results, and send the prediction results to the evaluation module; The evaluation module is used to evaluate the optical storage device according to the pre-stored threshold table, prediction results, and data sorting results in the database, and send the evaluation results to the optical storage device management module; The optical storage device management module executes a management strategy on the optical storage device according to the evaluation result; The optical storage energy management system based on big data also includes a display and adjustment terminal, which is used to display all operation records of the optical storage energy management system based on big data, and to update and adjust the threshold value table pre-stored in the database and the management strategy in the optical storage device management module; The main operation information of the photovoltaic storage device includes the charging and discharging state data of the photovoltaic storage device, the real-time capacity percentage data of the photovoltaic storage device, the real-time temperature data of the photovoltaic storage device, and the difference data between the terminal voltage values ​​at both ends of the photovoltaic storage device; The charging circuit information includes the real-time current data and the real-time voltage data of the charging circuit; the discharging circuit information includes the real-time current data and the real-time voltage data of the discharging circuit; The external environment information includes the temperature data of the external environment, the humidity data of the external environment, and the atmospheric pressure data of the external environment; The data sorting module is used to sort the data of the main body operation information, charging line information, discharging line information and external environment information of the optical storage device, which refers to: Step A1, dividing the collected time period T1, marking the average value of the real-time temperature data of the photovoltaic storage device in the charging state in the time period T1 as GW1i, and marking the average value of the difference data between the terminal voltage values ​​at both ends of the photovoltaic storage device as GY1i; marking the average value of the real-time temperature data of the photovoltaic storage device in the discharging state as GW2i, and marking the average value of the difference data between the terminal voltage values ​​at both ends of the photovoltaic storage device as GY2i; Step A2, according to the collected time period T1, the real-time current data average value of the charging circuit is marked as CDi, the real-time voltage data average value of the charging circuit is marked as CYi; the real-time current data average value of the discharge circuit is marked as FDi, and the real-time voltage data average value of the discharge circuit is marked as FYi; Step A3, dividing the collected time period T1, marking the average value of the temperature data of the external environment as HWi, the average value of the humidity data of the external environment as HSi, and the average value of the atmospheric pressure data of the external environment as HYi; Step A4, marking the real-time capacity percentage data of the optical storage device as SRi; Step A5, summarizing the results of step A1, step A2, step A3, and step A4; The neural network module is used to predict the operation risk of the optical storage equipment based on the data collation results and send the prediction results to the evaluation module: Step B1: Obtain the charging safety factor C1 of the solar energy storage device through the formula. The calculation formula is C1= ; Step B2: Obtain the discharge safety factor C2 of the photovoltaic storage device through the formula, and the calculation formula is C2= ; Step B3: Obtain the environmental safety factor C3 of the photovoltaic storage device through the formula, and the calculation formula is C3= , , , , All are specific proportional coefficients; Step B4: Obtain the abnormal operation coefficient C4 of the optical storage device through the formula, and the calculation formula is C4=f1 C1+f2 C2+f3 C3, f1, f2, and f3 are all specific proportional coefficients; Step B5, the neural network module uses the charging safety factor C1 of the photovoltaic storage device, the discharging safety factor C2 of the photovoltaic storage device, the environmental safety factor C3 of the photovoltaic storage device, and the corresponding data acquisition time as input data for neural network model training, uses the operation abnormality coefficient C4 of the photovoltaic storage device as output data for neural network model training, and assigns it to 0 or 1 to train the model, wherein 0 indicates that the operation abnormality coefficient C4 of the photovoltaic storage device is less than or equal to the set threshold, and 1 indicates that the operation abnormality coefficient C4 of the photovoltaic storage device is greater than the set threshold; Step B6: Use the data collected in the latest m time periods T1 as the input data of the neural network model. When the output data of the neural network model is 0, use the data collected in the latest m time periods T1 as the training data of the model to perform secondary training on the model. When the output data of the model is 1, use the data collected in the latest m time periods T1 as the training data of the model to perform secondary training on the model and send the output data 1 to the evaluation module. The evaluation module is used to evaluate the optical storage device according to the pre-stored threshold table, prediction results, and data sorting results in the database, which refers to: Step 1: Divide the data into time periods T1, and based on the comparison results between the collected data and the pre-stored threshold table in the database, mark the number of abnormalities of the optical storage device in n consecutive time periods T1 as YC1i, the number of abnormalities of the charging circuit as YC2i, the number of abnormalities of the discharge circuit as YC3i, and the number of abnormalities of the external environment as YC4i; Step 2: Divide by time period T2, and count the number of times YC5i that the evaluation module receives the output data 1 result of the neural network module in time period T2. Time period T2 is a time interval composed of integer multiples of time period T1, n=T2 / T1, n is a positive integer; Step 3: Calculate the evaluation value PG of the optical storage device, PG=k1 (YC1i+YC2i+YC3i)+k2 YC4i+k3 YC5i, compares the evaluation value PG of the optical storage device with the standard evaluation threshold interval in the pre-stored threshold table in the database For comparison, if PG Standard evaluation threshold interval , it is determined that the optical storage device is in a low-risk operating state and generates a second-class operating instruction; if PG , it is determined that the optical storage device is in a safe operating state and generates a type of operating instruction; if PG , it is determined that the optical storage equipment is in a high-risk operating state and three types of operating instructions are generated.

Images