Energy storage configuration optimization method, system, device and medium based on deep learning

Abstract

This invention discloses a method, system, device, and medium for optimizing energy storage configuration based on deep learning, relating to the field of energy storage optimization technology. The method includes: performing charging and discharging tests on energy storage devices to obtain charging and discharging optimization parameters; performing initial optimization on the energy storage devices; establishing and training a deep learning model; and using the trained deep learning model to perform real-time optimization of the energy storage devices. This invention addresses the problem that existing energy storage configuration optimization methods cannot effectively optimize the selection of charging and discharging efficiency for energy storage devices. Furthermore, when the battery has different remaining energy, the optimal charging or discharging rate cannot be used, resulting in a low lower limit of charging and discharging efficiency for the energy storage device during both charging and discharging.

Description

Technical Field

[0001] This invention relates to the field of energy storage optimization technology, specifically to a method, system, device, and medium for optimizing energy storage configuration based on deep learning. Background Technology

[0002] Energy storage configuration includes battery energy storage, mechanical energy storage, chemical energy storage, and superconducting energy storage. Energy storage configuration optimization refers to a technical means of improving the overall efficiency and economy of an energy storage system by optimizing and adjusting parameters such as battery capacity, energy storage efficiency, and output power. Specifically, energy storage configuration optimization uses software simulation, experiments, and other methods to achieve optimal energy storage efficiency and economy based on grid conditions and energy storage system performance parameters.

[0003] Existing methods for optimizing energy storage configurations typically involve establishing analytical models based on users' electricity cost calculation rules. These models then determine the return on investment for different users, leading to suitable energy storage configurations that meet their actual energy storage needs while minimizing operational losses. While this approach can reduce user costs through energy storage scheduling, it lacks effective optimization in selecting the charging and discharging efficiency of energy storage devices. This results in lower lower limits for charging and discharging efficiency due to varying battery levels, hindering efficient energy storage scheduling. For example, patent application CN110717259A discloses a method for optimizing energy storage configurations... The user-side battery energy storage configuration and operation optimization method involves constructing an energy storage configuration optimization model that combines demand defense and peak shaving / valley filling. For different users, it can use return on investment assessment to select the most suitable energy storage configuration, thereby reducing user electricity costs. Other improvements for energy storage configuration optimization typically focus on increasing the lifespan of energy storage devices. However, this approach does not effectively optimize the selection of charging and discharging efficiency for energy storage devices. Even when considering charging and discharging power based on total revenue and cost, the energy storage device cannot utilize the optimal charging or discharging rate when the battery has varying remaining energy. This results in a low lower limit for charging and discharging efficiency, leading to lower energy storage efficiency and a higher lower limit for charging and discharging costs. Therefore, it is necessary to improve existing optimization methods for energy storage configuration. Summary of the Invention

[0004] This invention aims to at least partially solve one of the technical problems in the prior art. By proposing a deep learning-based energy storage configuration optimization method, system, device, and medium, it addresses the issue that existing optimization methods for energy storage configuration cannot effectively optimize the selection of charging and discharging efficiency for energy storage devices. This results in the energy storage device being unable to use the optimal charging or discharging rate when the battery has different remaining energy, leading to a low lower limit of charging and discharging efficiency during both charging and discharging. Consequently, the energy storage efficiency is low, affecting the user's energy storage scheduling and resulting in a high lower limit of charging and discharging costs.

[0005] To achieve the above objectives, firstly, this application provides a deep learning-based method for optimizing energy storage configuration, comprising the following steps:

[0006] Multiple charging rates capable of charging the energy storage device are obtained, and charging tests are conducted on the energy storage device based on these multiple charging rates; based on the results of the charging tests, charging optimization parameters for each energy storage unit in the energy storage device are obtained.

[0007] A discharge test is established based on the method of obtaining charging optimization parameters, and a discharge test is conducted on the energy storage device based on all discharge rates that can discharge the energy storage unit. The discharge optimization parameters of each energy storage unit in the energy storage device are obtained based on the results of the discharge test.

[0008] The configuration of the energy storage device is initially optimized based on charging and discharging optimization parameters.

[0009] A deep learning model is established and trained based on the acquisition of charging optimization parameters and discharging optimization parameters. The trained deep learning model is then used to optimize the energy storage device in real time.

[0010] Furthermore, charging tests are conducted on the energy storage device at multiple charging rates; based on the results of the charging tests, the charging optimization parameters for each energy storage unit in the energy storage device are obtained, including:

[0011] Each individual energy storage unit in the energy storage device is designated as energy storage unit CN1 to energy storage unit CN1 in ascending order based on the electrical energy it can store. v For any energy storage unit CN z , will the energy storage unit CN z The maximum electrical energy that can be stored is denoted as the total electrical energy, where z is a positive integer less than or equal to v and greater than or equal to 1;

[0012] For energy storage unit CN z A charging test was conducted, which involved testing the energy storage unit CN. z The charging rates, from smallest to largest, are denoted as Rechargeable Rate CS1 to Rechargeable Rate CS. n .

[0013] Furthermore, charging tests are conducted on the energy storage device at multiple charging rates; based on the results of the charging tests, the charging optimization parameters for each energy storage unit in the energy storage device are obtained, including:

[0014] Empty energy storage unit CN z The electrical energy in the storage unit CN is charged at a rate of CS1. z Charging is initiated; a Cartesian coordinate system is established, denoted as the charging test coordinate system, where the X-axis represents time and the Y-axis represents electrical energy; when charging begins, based on the energy storage unit CN... z The internal electrical energy is plotted on the charging test coordinate system to obtain the corresponding curve, until the energy storage unit CN is reached. z The battery is fully charged, and the resulting curve is denoted as the charging curve CQ1.

[0015] energy storage unit CN z The internal electrical energy is emptied, and the energy is transferred to the energy storage unit CN using the rechargeable rate CS2. z Charging is performed, and charging curve CQ2 is obtained based on the method used to obtain charging curve CQ1, and so on, until charging curve CQ is obtained. n .

[0016] Furthermore, charging tests are conducted on the energy storage device at multiple charging rates; obtaining the charging optimization parameters for each energy storage unit in the energy storage device based on the results of the charging tests also includes:

[0017] Place all charging curves CQ within the same charging test coordinate system. Record the point with the largest x-coordinate among the rightmost points of all charging curves CQ as the rightmost charging point. Divide the coordinate system from the origin to X = rightmost charging point into k equal parts using a straight line parallel to the Y-axis. Label each part from left to right as the charging horizontal interval CH1 to the charging horizontal interval CH. k For any charging lateral interval CH j The charging lateral section CH j The point with the steepest slope among all curves is denoted as the charging transverse interval CH. j Find the interval charging peak points; obtain the interval charging peak points of all horizontal charging intervals CH, where j is a positive integer less than or equal to k and greater than or equal to 1;

[0018] Divide the coordinate system from the origin to the Y-axis into k equal parts using a straight line parallel to the X-axis. Then, label each part from bottom to top as the charging longitudinal interval CZ1 to the charging longitudinal interval CZ. k For any charging longitudinal interval CZ j When the charging longitudinal range CZ jWhen the number of interval charging peaks in all curves is greater than 1, the interval charging peak with the largest slope among all interval charging peaks is recorded as the preferred charging peak; when the charging longitudinal interval CZ j When the number of charging peaks in all curves within a given interval is equal to 1, the charging longitudinal interval CZ is... j The charging peak point within the interval is denoted as the preferred charging peak point; when the charging longitudinal interval CZ j When the number of charging peaks in all curves within a given interval is equal to 0, the charging longitudinal interval CZ is... j The point with the steepest slope among all curves is designated as the preferred charging peak.

[0019] Obtain the preferred charging peak points corresponding to all charging longitudinal intervals CZ; denote all charging longitudinal intervals CZ and their preferred charging peak points as energy storage units CN. z Optimized charging parameters.

[0020] Furthermore, a discharge test is established based on the method for obtaining charging optimization parameters, and a discharge test is performed on the energy storage device based on all discharge rates capable of discharging the energy storage unit. Based on the results of the discharge test, the discharge optimization parameters for each energy storage unit in the energy storage device are obtained, including:

[0021] For energy storage unit CN z Discharge tests are conducted. The discharge test is as follows: based on the charging test, all discharge rates that can discharge the energy storage unit CN are obtained. After the energy storage unit CN is fully charged, all discharge rates are used to discharge the charging unit CN in sequence. A Cartesian coordinate system is established to obtain the curves corresponding to all discharge rates.

[0022] Based on the method of obtaining charging optimization parameters, the curves corresponding to all discharge rates are analyzed. The interval obtained by the straight line parallel to the X-axis is denoted as the longitudinal discharge interval FZ, and the point obtained based on the preferred charging peak point is denoted as the preferred discharge peak point. All longitudinal discharge intervals FZ and their preferred discharge peak points are denoted as energy storage unit CN. z Optimized discharge parameters;

[0023] Obtain the charging optimization parameters and discharging optimization parameters for all energy storage units CN.

[0024] Furthermore, the initial optimization of the energy storage device configuration based on charging and discharging optimization parameters includes:

[0025] The initial optimizations include: when charging the energy storage battery, real-time acquisition of the electrical energy of each energy storage unit CN within the energy storage battery; for any energy storage unit CN that is not fully charged... z Obtain the charging unit CN z The charging optimization parameters will be used to optimize the energy storage unit CN. zThe longitudinal charging interval CZ in which the electrical energy is located is denoted as the preferred charging interval, and the energy storage unit CN in the preferred charging interval is... z The rechargeable rate CS corresponding to the curve where the preferred charging peak point is located is denoted as the preferred charging rate. The preferred charging rate is used to evaluate the energy storage unit CN. z Charge;

[0026] When the energy storage battery is discharged, the electrical energy of each energy storage unit CN within the battery is acquired in real time; for any energy storage unit CN that is not fully discharged... z Obtain the charging unit CN z The discharge optimization parameters will be used to optimize the energy storage unit CN. z The longitudinal discharge interval FZ in which the electrical energy is located is denoted as the preferred discharge interval, and the energy storage unit CN in the preferred discharge interval is... z The discharge rate corresponding to the curve where the preferred discharge peak point is located is denoted as the preferred discharge rate. The preferred discharge rate is used to evaluate the energy storage unit CN. z Discharge is performed.

[0027] Furthermore, a deep learning model is established, and trained based on the obtained charging and discharging optimization parameters. The trained deep learning model is then used to perform real-time optimization of the energy storage device, including:

[0028] A deep learning model is established, and the charging and discharging data of the energy storage battery after initial optimization is stored in the deep learning model. The input unit of the deep learning model is used to input the power consumption type and the remaining power, and the output unit of the deep learning model is used to output the charging and discharging rate. The power consumption type includes charging and discharging, and the charging and discharging rate includes the charging rate and the discharging rate.

[0029] The charging and discharging optimization parameters of each energy storage unit CN are optimized in real time based on the charging and discharging data of the energy storage battery stored in the deep learning model. The optimization method is as follows:

[0030] When the energy storage unit CN is charging or discharging, the power consumption type and remaining energy of the energy storage unit CN are input into the deep learning model. Based on the simulation of all charging or discharging rates, the fastest charging or discharging rate when the energy storage unit CN is fully charged or discharged from the remaining energy is obtained and output by the unit at the output end.

[0031] When the output of the deep learning model is the same as the preferred charging rate or preferred discharging rate obtained by the initial optimization, the charging optimization parameters and discharging optimization parameters of the energy storage unit CN are not optimized.

[0032] When the output of the deep learning model differs from the preferred charging or discharging rate obtained from the initial optimization, an optimization selection algorithm is used to obtain an optimization judgment value. The optimization selection algorithm is as follows: Where G is the optimization judgment value, f0 is the output result of the deep learning model, and when the output result of the deep learning is the rechargeable rate, g is the number of preferred charging rates obtained by the energy storage unit CN from the initial optimization, and f i Let f be the i-th preferred charging rate obtained by the energy storage unit CN in the initial optimization; when the output of deep learning is the discharge rate, g is the number of preferred discharge rates obtained by the energy storage unit CN in the initial optimization, and f is the number of preferred discharge rates obtained by the energy storage unit CN in the initial optimization. i The i-th preferred discharge rate of the energy storage unit CN obtained from the initial optimization;

[0033] When the optimization judgment value is greater than 0, the output result of the deep learning model will replace the preferred charging rate or preferred discharging rate of the energy storage unit CN.

[0034] When the optimization judgment value is less than or equal to 0, the charging optimization parameters and discharging optimization parameters of the energy storage unit CN are not optimized.

[0035] Secondly, this application also provides a deep learning-based energy storage configuration optimization system, including a charging optimization analysis module, a discharging optimization analysis module, and a deep optimization module;

[0036] The charging optimization analysis module is used to obtain multiple charging rates that can charge the energy storage device, and to conduct charging tests on the energy storage device based on the multiple charging rates; based on the results of the charging tests, the charging optimization parameters of each energy storage unit in the energy storage device are obtained.

[0037] The discharge optimization analysis module is used to establish a discharge test based on the method of obtaining the charging optimization parameters, and to conduct a discharge test on the energy storage device based on all discharge rates that can discharge the energy storage unit. Based on the results of the discharge test, the discharge optimization parameters of each energy storage unit in the energy storage device are obtained.

[0038] The configuration of the energy storage device is initially optimized based on charging and discharging optimization parameters.

[0039] The deep optimization module is used to build a deep learning model and train the deep learning model based on the obtained charging optimization parameters and discharging optimization parameters. The trained deep learning model is then used to optimize the energy storage device in real time.

[0040] Thirdly, this application provides an electronic device including a processor and a memory, the memory storing computer-readable instructions, which, when executed by the processor, perform the steps of the method described above.

[0041] Fourthly, this application provides a storage medium having a computer program stored thereon, which, when executed by a processor, performs the steps of the method described above.

[0042] The beneficial effects of this invention are as follows: This application first obtains multiple charging rates that can charge the energy storage device, and performs charging tests on the energy storage device based on the multiple charging rates; based on the results of the charging tests, it obtains the charging optimization parameters for each energy storage unit in the energy storage device; then, it performs a discharge test based on the method of obtaining the charging optimization parameters, and obtains the discharge optimization parameters for each energy storage unit in the energy storage device based on the results of the discharge test. The advantage of this is that by performing charging and discharging tests and obtaining the charging and discharging optimization parameters, it is possible to obtain the optimal charging rate and discharging of the energy storage device's battery when there is different remaining energy. This ensures that in subsequent management, even considering charging and discharging costs and user scheduling, the lower limit of charging and discharging costs will be reduced and the user's energy storage scheduling efficiency will be improved with high charging and discharging efficiency.

[0043] This application also performs initial optimization of the energy storage device configuration based on charging and discharging optimization parameters; finally, a deep learning model is established and trained based on the obtained charging and discharging optimization parameters. The trained deep learning model is then used to optimize the energy storage device in real time. The advantage of this approach is that by performing initial optimization of the energy storage device and establishing a deep learning model to update the charging and discharging optimization parameters in real time, the charging and discharging optimization parameters can be applied while being updated in real time based on the real-time status of the energy storage device. This ensures that the charging and discharging optimization parameters used are the optimal parameters that conform to the current operating state of the energy storage device. Attached Figure Description

[0044] Figure 1 This is a schematic diagram of the system of the present invention;

[0045] Figure 2 This is a flowchart illustrating the steps of the method of the present invention;

[0046] Figure 3 This is a schematic diagram of the charging test coordinate system of the present invention;

[0047] Figure 4 This is a schematic diagram of the deep learning model of the present invention;

[0048] Figure 5 This is a schematic diagram of the electronic device of the present invention. Detailed Implementation

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] Example 1, please refer to Figure 1 As shown, this application provides a deep learning-based energy storage configuration optimization system, including a charging optimization analysis module, a discharging optimization analysis module, and a deep optimization module;

[0051] The charging optimization analysis module is used to obtain multiple charging rates that can charge the energy storage device, and to conduct charging tests on the energy storage device based on the multiple charging rates; based on the results of the charging tests, the charging optimization parameters of each energy storage unit in the energy storage device are obtained.

[0052] The charging optimization analysis module includes a charging parameter analysis unit, which is configured with charging parameter analysis strategies. These strategies include:

[0053] Each individual energy storage unit in the energy storage device is designated as energy storage unit CN1 to energy storage unit CN1 in ascending order based on the electrical energy it can store. v For any energy storage unit CN z , will the energy storage unit CN z The maximum electrical energy that can be stored is denoted as the total electrical energy, where z is a positive integer less than or equal to v and greater than or equal to 1;

[0054] In specific implementation, such as in practical applications, if the energy storage device is a battery pack composed of multiple connected batteries, then the energy storage unit can be multiple independent batteries in the energy storage device.

[0055] For energy storage unit CN z A charging test was conducted, which involved testing the energy storage unit CN. z The charging rates, from smallest to largest, are denoted as Rechargeable Rate CS1 to Rechargeable Rate CS. n ;

[0056] In a specific implementation process, for example, in a single data processing step, if the charging rates of the energy storage unit CN are obtained as 0.25C, 0.5C, 1C, and 2C, then the rechargeable rates CS1 to CS4 can be recorded as 0.25C, 0.5C, 1C, and 2C respectively. By obtaining the rechargeable rate CS, multiple charging rates of the energy storage unit CN can be acquired, thereby providing data support for subsequent analysis.

[0057] Empty energy storage unit CNz The electrical energy in the storage unit CN is charged at a rate of CS1. z Charging is initiated; a Cartesian coordinate system is established, denoted as the charging test coordinate system, where the X-axis represents time and the Y-axis represents electrical energy; when charging begins, based on the energy storage unit CN... z The internal electrical energy is plotted on the charging test coordinate system to obtain the corresponding curve, until the energy storage unit CN is reached. z The battery is fully charged, and the resulting curve is denoted as the charging curve CQ1.

[0058] energy storage unit CN z The internal electrical energy is emptied, and the energy is transferred to the energy storage unit CN using the rechargeable rate CS2. z Charging is performed, and charging curve CQ2 is obtained based on the method used to obtain charging curve CQ1, and so on, until charging curve CQ is obtained. n ;

[0059] Place all charging curves CQ within the same charging test coordinate system. Record the point with the largest x-coordinate among the rightmost points of all charging curves CQ as the rightmost charging point. Divide the coordinate system from the origin to X = rightmost charging point into k equal parts using a straight line parallel to the Y-axis. Label each part from left to right as the charging horizontal interval CH1 to the charging horizontal interval CH. k For any charging lateral interval CH j The charging lateral section CH j The point with the steepest slope among all curves is denoted as the charging transverse interval CH. j Find the interval charging peak points; obtain the interval charging peak points of all horizontal charging intervals CH, where j is a positive integer less than or equal to k and greater than or equal to 1;

[0060] In the specific implementation process, the value of k can be set according to the actual amount of data that can be analyzed. The larger the value of k, the more data needs to be processed and the more accurate the analysis data is. In this embodiment, the value of k is set to 5 for analysis.

[0061] For example, in a single data processing step, the obtained charging test coordinate system is as follows: Figure 3As shown, curves CQ1 to CQ4 represent the charging curves CQ1 to CQ4, respectively. Analysis reveals that point JY is the rightmost charging point, and the peak charging points in the horizontal charging intervals CH1 to CH5 are points FD1 to FD5. By obtaining these peak charging points, we can identify the points with the fastest charging rates in different time intervals after the start of charging the energy storage unit CN. This provides valuable data for selecting optimal charging peak points in subsequent analyses. Furthermore, considering the discrepancy between the actual and expected charging rates of the energy storage unit CN due to the duration of charging, obtaining the points with the fastest charging rates in different time intervals allows for analysis based on the actual charging situation of the energy storage unit CN, ensuring that the obtained data aligns with real-world application scenarios.

[0062] Divide the coordinate system from the origin to the Y-axis into k equal parts using a straight line parallel to the X-axis. Then, label each part from bottom to top as the charging longitudinal interval CZ1 to the charging longitudinal interval CZ. k For any charging longitudinal interval CZ j When the charging longitudinal range CZ j When the number of interval charging peaks in all curves is greater than 1, the interval charging peak with the largest slope among all interval charging peaks is recorded as the preferred charging peak; when the charging longitudinal interval CZ j When the number of charging peaks in all curves within a given interval is equal to 1, the charging longitudinal interval CZ is... j The charging peak point within the interval is denoted as the preferred charging peak point; when the charging longitudinal interval CZ j When the number of charging peaks in all curves within a given interval is equal to 0, the charging longitudinal interval CZ is... j The point with the steepest slope among all curves is designated as the preferred charging peak.

[0063] In this embodiment, the purpose of obtaining interval charging peaks in multiple intervals is to uniformly obtain the fastest charging rate within each charging time period during the charging process. Therefore, whether the end of an interval is steep or not does not affect the acquisition of interval charging peaks. At the same time, the selection of the optimal charging curve is also obtained by the interval charging peaks or the point with the largest slope in the longitudinal charging interval. Therefore, there is no need to worry about the impact of the steep end of a certain transverse charging interval on the acquisition of the optimal charging curve. If the slope of the curve in a certain interval is fixed, the position of the charging peak can be set by itself, or the transverse charging interval with a fixed curve slope can be calibrated, and in the subsequent analysis of the longitudinal charging interval, all points in the curve in the calibrated transverse charging interval are recorded as interval charging peaks and the optimal charging peaks are selected.

[0064] Different charging curves for the same energy storage unit CN are obtained at different charging rates, "which will enable the energy storage unit CN..." zThe charging rates, from smallest to largest, are denoted as Rechargeable Rate CS1 to Rechargeable Rate CS. n "When charging begins, based on the energy storage unit CN..." z The internal electrical energy is plotted on the charging test coordinate system to obtain the corresponding curve, until the energy storage unit CN is reached. z The energy storage unit CN is fully charged, and the resulting curve is denoted as the charging curve CQ1; z The internal electrical energy is emptied, and the energy is transferred to the energy storage unit CN using the rechargeable rate CS2. z Charging is performed, and charging curve CQ2 is obtained based on the method used to obtain charging curve CQ1, and so on, until charging curve CQ is obtained. n "Because for different charging curves, the conditions other than the charging rate, such as the configuration environment of the energy storage unit itself or the external environment, are the same, there is comparability between different charging curves."

[0065] In the specific implementation process, by obtaining the optimal charging peak point, the optimal charging rate of the energy storage unit CN when there is different remaining electrical energy can be obtained. This helps to use the most efficient charging rate when charging the remaining unused energy storage unit CN, thereby increasing the upper limit of charging efficiency.

[0066] Obtain the preferred charging peak points corresponding to all charging longitudinal intervals CZ; denote all charging longitudinal intervals CZ and their preferred charging peak points as energy storage units CN. z Optimized charging parameters.

[0067] The discharge optimization analysis module is used to establish a discharge test based on the method of obtaining the charging optimization parameters, and to conduct a discharge test on the energy storage device based on all discharge rates that can discharge the energy storage unit. Based on the results of the discharge test, the discharge optimization parameters of each energy storage unit in the energy storage device are obtained.

[0068] The configuration of the energy storage device is initially optimized based on charging and discharging optimization parameters.

[0069] The discharge optimization analysis module includes a discharge parameter analysis unit, which is configured with discharge parameter analysis strategies, including:

[0070] For energy storage unit CN z Discharge tests are conducted. The discharge test is as follows: based on the charging test, all discharge rates that can discharge the energy storage unit CN are obtained. After the energy storage unit CN is fully charged, all discharge rates are used to discharge the charging unit CN in sequence. A Cartesian coordinate system is established to obtain the curves corresponding to all discharge rates.

[0071] Based on the method of obtaining charging optimization parameters, the curves corresponding to all discharge rates are analyzed. The interval obtained by the straight line parallel to the X-axis is denoted as the longitudinal discharge interval FZ, and the point obtained based on the preferred charging peak point is denoted as the preferred discharge peak point. All longitudinal discharge intervals FZ and their preferred discharge peak points are denoted as energy storage unit CN. z Optimized discharge parameters;

[0072] In the specific implementation process, the method of using multiple chargeable rates CS and obtaining charging curves in charging tests can be referenced. Based on the discharge rate, the corresponding curve can be obtained, and all discharge rates can be placed in the same coordinate system. The analysis method based on charging tests uses straight lines parallel to the Y-axis and parallel to the X-axis to perform analysis in sequence, and the discharge longitudinal interval FZ and its preferred discharge peak point corresponding to the discharge test can be obtained based on the analysis results. The purpose is to obtain the optimal discharge rate of the energy storage unit CN when there is different remaining electrical energy, which helps to use the most efficient discharge rate when discharging the remaining unused energy storage unit CN, so as to improve the upper limit of discharge efficiency.

[0073] Obtain the charging optimization parameters and discharging optimization parameters for all energy storage units CN;

[0074] The initial optimizations include: when charging the energy storage battery, real-time acquisition of the electrical energy of each energy storage unit CN within the energy storage battery; for any energy storage unit CN that is not fully charged... z Obtain the charging unit CN z The charging optimization parameters will be used to optimize the energy storage unit CN. z The longitudinal charging interval CZ in which the electrical energy is located is denoted as the preferred charging interval, and the energy storage unit CN in the preferred charging interval is... z The rechargeable rate CS corresponding to the curve where the preferred charging peak point is located is denoted as the preferred charging rate. The preferred charging rate is used to evaluate the energy storage unit CN. z Charge;

[0075] When the energy storage battery is discharged, the electrical energy of each energy storage unit CN within the battery is acquired in real time; for any energy storage unit CN that is not fully discharged... z Obtain the charging unit CN z The discharge optimization parameters will be used to optimize the energy storage unit CN. z The longitudinal discharge interval FZ in which the electrical energy is located is denoted as the preferred discharge interval, and the energy storage unit CN in the preferred discharge interval is... z The discharge rate corresponding to the curve where the preferred discharge peak point is located is denoted as the preferred discharge rate. The preferred discharge rate is used to evaluate the energy storage unit CN. z Discharge is performed.

[0076] The deep optimization module is used to build a deep learning model and train the deep learning model based on the obtained charging optimization parameters and discharging optimization parameters. The trained deep learning model is then used to optimize the energy storage device in real time.

[0077] The deep optimization module includes a deep real-time optimization unit, which is configured with deep real-time optimization strategies, including:

[0078] A deep learning model is established, storing the initially optimized charging and discharging data of the energy storage battery. The input unit of the deep learning model is used to input the power consumption type and remaining energy, while the output unit outputs the charging and discharging rate. The power consumption type includes charging and discharging, and the charging and discharging rate includes the charging rate and the discharging rate. In specific implementation, the structure of the deep learning model in this embodiment can be referred to... Figure 4 As shown;

[0079] The charging and discharging optimization parameters of each energy storage unit CN are optimized in real time based on the charging and discharging data of the energy storage battery stored in the deep learning model. The optimization method is as follows:

[0080] When the energy storage unit CN is charging or discharging, the power consumption type and remaining energy of the energy storage unit CN are input into the deep learning model. Based on the simulation of all charging or discharging rates, the fastest charging or discharging rate when the energy storage unit CN is fully charged or discharged from the remaining energy is obtained and output by the unit at the output end.

[0081] When the output of the deep learning model is the same as the preferred charging rate or preferred discharging rate obtained by the initial optimization, the charging optimization parameters and discharging optimization parameters of the energy storage unit CN are not optimized.

[0082] When the output of the deep learning model differs from the preferred charging or discharging rate obtained from the initial optimization, an optimization selection algorithm is used to obtain an optimization judgment value. The optimization selection algorithm is as follows: Where G is the optimization judgment value, f0 is the output result of the deep learning model, when the output result of the deep learning is the charging rate, g is the number of preferred charging rates obtained by the energy storage unit CN from the initial optimization, and fi is the i-th preferred charging rate obtained by the energy storage unit CN from the initial optimization; when the output result of the deep learning is the discharge rate, g is the number of preferred discharge rates obtained by the energy storage unit CN from the initial optimization, and fi is the i-th preferred discharge rate obtained by the energy storage unit CN from the initial optimization.

[0083] In a specific implementation process, for example, during a data processing session, the deep learning output result is that the rechargeable rate is 2C. The number of preferred charging rates obtained by the energy storage unit CN from the initial optimization is 5. The preferred charging rates obtained by the energy storage unit CN from the initial optimization are 1C, 2C, 2C, 2C and 1C respectively. Then, through calculation, it can be found that the optimization judgment value is 2, that is, the optimization judgment value is greater than 0. This means that the charging rate obtained by the deep learning model is more efficient than the preferred charging rate obtained from the initial optimization when charging the energy storage unit CN. Therefore, 2C can be used to replace the preferred charging rate of the energy storage unit CN to achieve higher charging efficiency for the energy storage unit CN.

[0084] When the optimization judgment value is greater than 0, the output result of the deep learning model will replace the preferred charging rate or preferred discharging rate of the energy storage unit CN.

[0085] When the optimization judgment value is less than or equal to 0, the charging optimization parameters and discharging optimization parameters of the energy storage unit CN are not optimized.

[0086] Example 2, please refer to Figure 2 As shown, this application also provides a deep learning-based energy storage configuration optimization method, including the following steps:

[0087] Step S1: Obtain multiple charging rates that can charge the energy storage device, and conduct charging tests on the energy storage device based on the multiple charging rates; obtain the charging optimization parameters for each energy storage unit in the energy storage device based on the results of the charging tests.

[0088] Step S1 includes: Step S101, each independent energy storage unit in the energy storage device is named from smallest to largest energy storage unit CN1 to energy storage unit CNv based on the electrical energy that can be stored; for any energy storage unit CNz, the maximum electrical energy that energy storage unit CNz can store is recorded as the total electrical energy, where z is a positive integer less than or equal to v and greater than or equal to 1.

[0089] Step S102: Perform a charging test on the energy storage unit CNz. The charging test is as follows: the charging rates that can charge the energy storage unit CNz are recorded in ascending order as the chargeable rates CS1 to CSn.

[0090] Step S103: Empty the electrical energy in the energy storage unit CNz and charge the energy storage unit CNz using the rechargeable rate CS1; establish a Cartesian coordinate system, denoted as the charging test coordinate system, where the X-axis of the charging test coordinate system is in units of time and the Y-axis is in units of electrical energy; when charging begins, plot the corresponding curve in the charging test coordinate system based on the electrical energy in the energy storage unit CNz until the energy storage unit CNz is fully charged, and record the resulting curve as the charging curve CQ1;

[0091] Step S104: Empty the energy in the energy storage unit CNz, charge the energy storage unit CNz using the rechargeable rate CS2, and obtain the charging curve CQ2 based on the method of obtaining the charging curve CQ1, and so on, until the charging curve CQn is obtained.

[0092] Step S105: Place all charging curves CQ into the same charging test coordinate system, and record the point with the largest x-coordinate among the rightmost points of all charging curves CQ as the charging rightmost point; use a straight line parallel to the Y-axis to divide the coordinate origin to X = charging rightmost point into k equal parts, and record each part as charging horizontal interval CH1 to charging horizontal interval CHk from left to right; for any charging horizontal interval CHj, record the point with the largest slope among all curves in the charging horizontal interval CHj as the interval charging peak point of the charging horizontal interval CHj; obtain the interval charging peak points of all charging horizontal intervals CH, where j is a positive integer less than or equal to k and greater than or equal to 1.

[0093] Step S106: Divide the coordinate origin to Y = total electrical energy into k equal parts using a straight line parallel to the X-axis, and label each part as charging longitudinal interval CZ1 to charging longitudinal interval CZk from bottom to top; for any charging longitudinal interval CZj, when the number of interval charging peaks in all curves within the charging longitudinal interval CZj is greater than 1, the interval charging peak with the largest slope among all interval charging peaks is labeled as the preferred charging peak; when the number of interval charging peaks in all curves within the charging longitudinal interval CZj is equal to 1, the interval charging peak in the charging longitudinal interval CZj is labeled as the preferred charging peak; when the number of interval charging peaks in all curves within the charging longitudinal interval CZj is equal to 0, the point with the largest slope among all curves within the charging longitudinal interval CZj is labeled as the preferred charging peak.

[0094] Step S107: Obtain the preferred charging peak points corresponding to all charging longitudinal intervals CZ; record all charging longitudinal intervals CZ and their preferred charging peak points as the charging optimization parameters of the energy storage unit CNz.

[0095] Step S2: Establish a discharge test based on the method of obtaining charging optimization parameters, and conduct a discharge test on the energy storage device based on all discharge rates that can discharge the energy storage unit. Based on the results of the discharge test, obtain the discharge optimization parameters of each energy storage unit in the energy storage device.

[0096] The configuration of the energy storage device is initially optimized based on charging and discharging optimization parameters.

[0097] Step S2 includes: Step S201, performing a discharge test on the energy storage unit CNz. The discharge test is as follows: based on the charging test, all discharge rates that can discharge the energy storage unit CN are obtained. After the energy storage unit CN is fully charged, all discharge rates are used to discharge the charging unit CN in sequence, and a plane rectangular coordinate system is established to obtain the curves corresponding to all discharge rates.

[0098] Step S202: Based on the method of obtaining the charging optimization parameters, analyze the curves corresponding to all discharge rates, and denote the interval obtained by the straight line parallel to the X-axis as the discharge longitudinal interval FZ, and denote the point obtained based on the preferred charging peak point as the preferred discharge peak point; denote all the discharge longitudinal intervals FZ and their preferred discharge peak points as the discharge optimization parameters of the energy storage unit CNz.

[0099] Step S203: Obtain the charging optimization parameters and discharging optimization parameters of all energy storage units CN;

[0100] Step S204, initial optimization includes: Step S2041, when charging the energy storage battery, the electrical energy of each energy storage unit CN in the energy storage battery is obtained in real time; for any energy storage unit CNz that is not fully charged, the charging optimization parameters of the charging unit CNz are obtained, the charging vertical interval CZ in which the electrical energy in the energy storage unit CNz is located is recorded as the preferred charging interval, the rechargeable rate CS corresponding to the curve where the preferred charging peak point of the energy storage unit CNz in the preferred charging interval is recorded as the preferred charging rate, and the energy storage unit CNz is charged using the preferred charging rate;

[0101] Step S2042: When discharging the energy storage battery, the electrical energy of each energy storage unit CN in the energy storage battery is acquired in real time; for any energy storage unit CNz that is not fully charged, the discharge optimization parameters of the charging unit CNz are acquired, the discharge longitudinal interval FZ in which the electrical energy in the energy storage unit CNz is located is recorded as the preferred discharge interval, the discharge rate corresponding to the curve where the preferred discharge peak point of the energy storage unit CNz in the preferred discharge interval is recorded as the preferred discharge rate, and the energy storage unit CNz is discharged using the preferred discharge rate.

[0102] Step S3: Establish a deep learning model and train the deep learning model based on the obtained charging optimization parameters and discharging optimization parameters. Use the trained deep learning model to optimize the energy storage device in real time.

[0103] Step S3 includes: Step S301, establishing a deep learning model, storing the initial optimized charging and discharging data of the energy storage battery in the deep learning model, the input unit of the deep learning model is used to input the power consumption type and the remaining power, and the output unit of the deep learning model is used to output the charging and discharging rate, wherein the power consumption type includes charging and discharging, and the charging and discharging rate includes the charging rate and the discharging rate.

[0104] Step S302: Based on the charging and discharging data of the energy storage battery stored in the deep learning model, the charging optimization parameters and discharging optimization parameters of each energy storage unit CN are optimized in real time. The optimization method is as follows:

[0105] Step S303: When the energy storage unit CN is charging or discharging, the power consumption type and remaining energy of the energy storage unit CN are input into the deep learning model. Based on the simulation of all charging or discharging rates, the fastest charging or discharging rate of the energy storage unit CN when it is fully charged or discharged from the remaining energy is obtained and output by the unit at the output end.

[0106] Step S304: When the output of the deep learning model is the same as the preferred charging rate or preferred discharging rate obtained by the initial optimization, the charging optimization parameters and discharging optimization parameters of the energy storage unit CN are not optimized.

[0107] Step S305: When the output of the deep learning model differs from the preferred charging rate or preferred discharging rate obtained from the initial optimization, an optimization selection algorithm is used to obtain an optimization judgment value. The optimization selection algorithm is as follows: Where G is the optimization judgment value, f0 is the output result of the deep learning model, and when the output result of the deep learning is the rechargeable rate, g is the number of preferred charging rates obtained by the energy storage unit CN from the initial optimization, and f i Let f be the i-th preferred charging rate obtained by the energy storage unit CN in the initial optimization; when the output of deep learning is the discharge rate, g is the number of preferred discharge rates obtained by the energy storage unit CN in the initial optimization, and f is the number of preferred discharge rates obtained by the energy storage unit CN in the initial optimization. i The i-th preferred discharge rate of the energy storage unit CN obtained from the initial optimization;

[0108] Step S306: When the optimization judgment value is greater than 0, the output result of the deep learning model is used to replace the preferred charging rate or preferred discharging rate of the energy storage unit CN.

[0109] Step S307: When the optimization judgment value is less than or equal to 0, the charging optimization parameters and discharging optimization parameters of the energy storage unit CN are not optimized.

[0110] Example 3, please refer to Figure 5 As shown, Figure 5A schematic diagram of an electronic device is provided, which may include a processor, a communication interface, a memory, and a communication bus. The processor, communication interface, and memory communicate with each other via the communication bus. The memory stores computer-readable instructions, and the processor can call the instructions in the memory. When the computer-readable instructions are executed by the processor, steps such as those in the deep learning-based energy storage configuration optimization method are performed to achieve the following functions: First, multiple charging rates capable of charging the energy storage device are obtained, and charging tests are conducted on the energy storage device based on these multiple charging rates. Based on the results of the charging tests, charging optimization parameters for each energy storage unit in the energy storage device are obtained. Then, discharge tests are conducted based on the method used to obtain the charging optimization parameters, and discharge optimization parameters for each energy storage unit in the energy storage device are obtained based on the results of the discharge tests. The configuration of the energy storage device is initially optimized based on the charging optimization parameters and the discharge optimization parameters. Finally, a deep learning model is established, and the deep learning model is trained based on the obtained charging optimization parameters and the discharge optimization parameters. The trained deep learning model is then used to optimize the energy storage device in real time.

[0111] Furthermore, when the logical instructions in the aforementioned memory can be implemented as 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 this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0112] Example 4: This application also provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, it performs the steps of the deep learning-based energy storage configuration optimization method described above to achieve the following functions: First, it acquires multiple charging rates capable of charging the energy storage device and performs charging tests on the energy storage device based on the multiple charging rates; based on the results of the charging tests, it acquires charging optimization parameters for each energy storage unit in the energy storage device; then, it performs a discharge test based on the acquisition method of the charging optimization parameters and acquires discharge optimization parameters for each energy storage unit in the energy storage device based on the results of the discharge test; and performs initial optimization of the configuration of the energy storage device based on the charging optimization parameters and the discharge optimization parameters; finally, it establishes a deep learning model and trains the deep learning model based on the acquisition of the charging optimization parameters and the discharge optimization parameters, and uses the trained deep learning model to optimize the energy storage device in real time.

[0113] Based on the above description of the embodiments, the embodiments of the present invention can be provided as methods, systems, or computer program products. Based on this understanding, the above technical solutions, in essence or in terms of their contribution to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or certain parts of the embodiments.

[0114] In the embodiments provided in this application, it should be understood that the disclosed system or method can be implemented in other ways. The embodiments described above are merely illustrative. For example, the division of modules or units is only a logical functional division, and there may be other division methods in actual implementation. Furthermore, multiple modules or units may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces. The indirect coupling or communication connection between systems, modules, and units may be electrical, mechanical, or other forms.

[0115] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A deep learning-based energy storage configuration optimization method, characterized in that, Includes the following steps: Multiple charging rates capable of charging the energy storage device are obtained, and charging tests are conducted on the energy storage device based on these multiple charging rates; based on the results of the charging tests, charging optimization parameters for each energy storage unit in the energy storage device are obtained. A discharge test is established based on the method of obtaining charging optimization parameters, and a discharge test is conducted on the energy storage device based on all discharge rates that can discharge the energy storage unit. The discharge optimization parameters of each energy storage unit in the energy storage device are obtained based on the results of the discharge test. The configuration of the energy storage device is initially optimized based on charging and discharging optimization parameters. A deep learning model is established and trained based on the acquisition of charging optimization parameters and discharging optimization parameters. The trained deep learning model is then used to optimize the energy storage device in real time. A deep learning model is established and trained based on the obtained charging and discharging optimization parameters. The trained deep learning model is then used to optimize the energy storage device in real time, including: A deep learning model is established, and the charging and discharging data of the energy storage battery after initial optimization is stored in the deep learning model. The input unit of the deep learning model is used to input the power consumption type and the remaining power, and the output unit of the deep learning model is used to output the charging and discharging rate. The power consumption type includes charging and discharging, and the charging and discharging rate includes the charging rate and the discharging rate. The charging and discharging optimization parameters of each energy storage unit CN are optimized in real time based on the charging and discharging data of the energy storage battery stored in the deep learning model. The optimization method is as follows: When the energy storage unit CN is charging or discharging, the power consumption type and remaining energy of the energy storage unit CN are input into the deep learning model. Based on the simulation of all charging or discharging rates, the fastest charging or discharging rate when the energy storage unit CN is fully charged or discharged from the remaining energy is obtained and output by the unit at the output end. When the output of the deep learning model is the same as the preferred charging rate or preferred discharging rate obtained by the initial optimization, the charging optimization parameters and discharging optimization parameters of the energy storage unit CN are not optimized. When the output of the deep learning model differs from the preferred charging or discharging rate obtained from the initial optimization, an optimization selection algorithm is used to obtain an optimization judgment value. The optimization selection algorithm is as follows: Where G is the optimization judgment value, f0 is the output result of the deep learning model, and when the output result of the deep learning is the rechargeable rate, g is the number of preferred charging rates obtained by the energy storage unit CN from the initial optimization, and f i Let f be the i-th preferred charging rate obtained by the energy storage unit CN in the initial optimization; when the output of deep learning is the discharge rate, g is the number of preferred discharge rates obtained by the energy storage unit CN in the initial optimization, and f is the number of preferred discharge rates obtained by the energy storage unit CN in the initial optimization. i The i-th preferred discharge rate of the energy storage unit CN obtained from the initial optimization; When the optimization judgment value is greater than 0, the output result of the deep learning model will replace the preferred charging rate or preferred discharging rate of the energy storage unit CN. When the optimization judgment value is less than or equal to 0, the charging optimization parameters and discharging optimization parameters of the energy storage unit CN are not optimized.

2. The energy storage configuration optimization method based on deep learning according to claim 1, characterized in that, Charging tests were conducted on energy storage devices based on multiple charging rates. The charging optimization parameters for each energy storage unit in the energy storage device, obtained based on the results of charging tests, include: Each individual energy storage unit in the energy storage device is designated as energy storage unit CN1 to energy storage unit CN1 in ascending order based on the electrical energy it can store. v For any energy storage unit CN z , will the energy storage unit CN z The maximum electrical energy that can be stored is denoted as the total electrical energy, where z is a positive integer less than or equal to v and greater than or equal to 1; For energy storage unit CN z A charging test was conducted, which involved testing the energy storage unit CN. z The charging rates, from smallest to largest, are denoted as Rechargeable Rate CS1 to Rechargeable Rate CS. n .

3. The energy storage configuration optimization method based on deep learning according to claim 2, characterized in that, Charging tests were conducted on energy storage devices based on multiple charging rates. The charging optimization parameters for each energy storage unit in the energy storage device, obtained based on the results of charging tests, include: Empty energy storage unit CN z The electrical energy in the storage unit CN is charged at a rate of CS1. z Charging is initiated; a Cartesian coordinate system is established, denoted as the charging test coordinate system, where the X-axis represents time and the Y-axis represents electrical energy; when charging begins, based on the energy storage unit CN... z The internal electrical energy is plotted on the charging test coordinate system to obtain the corresponding curve, until the energy storage unit CN is reached. z The battery is fully charged, and the resulting curve is denoted as the charging curve CQ1. energy storage unit CN z The internal electrical energy is emptied, and the energy is transferred to the energy storage unit CN using the rechargeable rate CS2. z Charging is performed, and charging curve CQ2 is obtained based on the method used to obtain charging curve CQ1, and so on, until charging curve CQ is obtained. n .

4. The energy storage configuration optimization method based on deep learning according to claim 3, characterized in that, Charging tests were conducted on energy storage devices based on multiple charging rates. Obtaining the optimal charging parameters for each energy storage unit in the energy storage device based on the results of charging tests also includes: Place all charging curves CQ within the same charging test coordinate system. Record the point with the largest x-coordinate among the rightmost points of all charging curves CQ as the rightmost charging point. Divide the coordinate system from the origin to X = rightmost charging point into k equal parts using a straight line parallel to the Y-axis. Label each part from left to right as the charging horizontal interval CH1 to the charging horizontal interval CH. k For any charging lateral interval CH j The charging lateral section CH j The point with the steepest slope among all curves is denoted as the charging transverse interval CH. j Find the interval charging peak points; obtain the interval charging peak points of all horizontal charging intervals CH, where j is a positive integer less than or equal to k and greater than or equal to 1; Divide the coordinate system from the origin to the Y-axis into k equal parts using a straight line parallel to the X-axis. Then, label each part from bottom to top as the charging longitudinal interval CZ1 to the charging longitudinal interval CZ. k For any charging longitudinal interval CZ j When the charging longitudinal range CZ j When the number of interval charging peaks in all curves is greater than 1, the interval charging peak with the largest slope among all interval charging peaks is recorded as the preferred charging peak; when the charging longitudinal interval CZ j When the number of charging peaks in all curves within a given interval is equal to 1, the charging longitudinal interval CZ is... j The charging peak point within the interval is denoted as the preferred charging peak point; when the charging longitudinal interval CZ j When the number of charging peaks in all curves within a given interval is equal to 0, the charging longitudinal interval CZ is... j The point with the steepest slope among all curves is designated as the preferred charging peak. Obtain the preferred charging peak points corresponding to all charging longitudinal intervals CZ; denote all charging longitudinal intervals CZ and their preferred charging peak points as energy storage units CN. z Optimized charging parameters.

5. The energy storage configuration optimization method based on deep learning according to claim 4, characterized in that, A discharge test is established based on the method of obtaining charging optimization parameters, and a discharge test is conducted on the energy storage device based on all discharge rates that can discharge the energy storage unit. The discharge optimization parameters for each energy storage unit in the energy storage device are obtained based on the results of the discharge test, including: For energy storage unit CN z Discharge tests are conducted. The discharge test is as follows: based on the charging test, all discharge rates that can discharge the energy storage unit CN are obtained. After the energy storage unit CN is fully charged, all discharge rates are used to discharge the charging unit CN in sequence. A Cartesian coordinate system is established to obtain the curves corresponding to all discharge rates. Based on the method of obtaining charging optimization parameters, the curves corresponding to all discharge rates are analyzed. The interval obtained by the straight line parallel to the X-axis is denoted as the longitudinal discharge interval FZ, and the point obtained based on the preferred charging peak point is denoted as the preferred discharge peak point. All longitudinal discharge intervals FZ and their preferred discharge peak points are denoted as energy storage unit CN. z Optimized discharge parameters; Obtain the charging optimization parameters and discharging optimization parameters for all energy storage units CN.

6. The energy storage configuration optimization method based on deep learning according to claim 5, characterized in that, The initial optimization of the energy storage device configuration based on charging and discharging optimization parameters includes: The initial optimizations include: when charging the energy storage battery, real-time acquisition of the electrical energy of each energy storage unit CN within the energy storage battery; for any energy storage unit CN that is not fully charged... z Obtain the charging unit CN z The charging optimization parameters will be used to optimize the energy storage unit CN. z The longitudinal charging interval CZ in which the electrical energy is located is denoted as the preferred charging interval, and the energy storage unit CN in the preferred charging interval is... z The rechargeable rate CS corresponding to the curve where the preferred charging peak point is located is denoted as the preferred charging rate. The preferred charging rate is used to evaluate the energy storage unit CN. z Charge; When the energy storage battery is discharged, the electrical energy of each energy storage unit CN within the battery is acquired in real time; for any energy storage unit CN that is not fully discharged... z Obtain the charging unit CN z The discharge optimization parameters will be used to optimize the energy storage unit CN. z The longitudinal discharge interval FZ in which the electrical energy is located is denoted as the preferred discharge interval, and the energy storage unit CN in the preferred discharge interval is... z The discharge rate corresponding to the curve where the preferred discharge peak point is located is denoted as the preferred discharge rate. The preferred discharge rate is used to evaluate the energy storage unit CN. z Discharge is performed.

7. A deep learning-based energy storage configuration optimization system, used to implement the deep learning-based energy storage configuration optimization method according to any one of claims 1-6, characterized in that, It includes a charging optimization analysis module, a discharging optimization analysis module, and a deep optimization module; The charging optimization analysis module is used to obtain multiple charging rates that can charge the energy storage device, and to perform charging tests on the energy storage device based on the multiple charging rates. Based on the results of charging tests, the charging optimization parameters for each energy storage unit in the energy storage device are obtained; The discharge optimization analysis module is used to establish a discharge test based on the method of obtaining the charging optimization parameters, and to conduct a discharge test on the energy storage device based on all discharge rates that can discharge the energy storage unit. Based on the results of the discharge test, the discharge optimization parameters of each energy storage unit in the energy storage device are obtained. The configuration of the energy storage device is initially optimized based on charging and discharging optimization parameters. The deep optimization module is used to build a deep learning model and train the deep learning model based on the obtained charging optimization parameters and discharging optimization parameters. The trained deep learning model is then used to optimize the energy storage device in real time.

8. An electronic device, characterized in that, It includes a processor and a memory, the memory storing computer-readable instructions that, when executed by the processor, perform the steps of the method as described in any one of claims 1-6.

9. A storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it performs the steps of the method as described in any one of claims 1-6.

Images