Energy storage battery charging and discharging method, system and medium based on deep learning algorithm

Abstract

The present invention relates to the field of battery management technology, and specifically to a method, system and medium for charging and discharging an energy storage battery based on a deep learning algorithm, comprising the following steps: solving the charging and discharging control parameters of the energy storage battery using a multi-objective optimization algorithm to obtain the optimal charging control parameters and the optimal discharging control parameters; encapsulating the mapping relationship between the optimal charging control parameters and the optimal discharging control parameters using a neural network to obtain a charging and discharging balance control model for determining the optimal discharging control parameters according to the optimal charging control parameters; determining the optimal charging parameters and the optimal discharging parameters of the energy storage battery by combining the multi-objective optimization algorithm with the charging and discharging balance control model, and optimizing the charging and discharging management of the energy storage battery. The present invention reduces the large and complicated workload of optimizing the analysis of the control parameters of the charging and discharging process, thereby ensuring the efficiency of the charging and discharging planning and meeting the timeliness of the charging and discharging planning.

Description

Technical Field

[0001] The present invention relates to the field of battery control technology, and in particular to a method, system and medium for charging and discharging an energy storage battery based on a deep learning algorithm. Background Art

[0002] The charging and discharging of energy storage batteries are adjusted and controlled by the battery management system (BMS) and the power conversion system (PCS). The charging and discharging process can be adjusted according to different needs and situations, including adjusting the charging rate and discharge power to achieve control and management of the charging and discharging process of the energy storage battery.

[0003] In the prior art, it is necessary to optimize and solve the optimal control parameters one by one during the charging and discharging process. The workload of optimizing and analyzing the control parameters of the charging and discharging process is large and complicated, so the required charging and discharging process control analysis time is also long, resulting in the efficiency of the charging and discharging planning not being guaranteed, and it is difficult to meet the timeliness requirements of the battery charging and discharging planning. Summary of the invention

[0004] The purpose of the present invention is to provide a method, system and medium for charging and discharging an energy storage battery based on a deep learning algorithm, so as to solve the technical problems in the prior art that the workload of optimizing and analyzing the control parameters of the charging and discharging process is large and complicated, and the time required for the control and analysis of the charging and discharging process is also long, resulting in the efficiency of the charging and discharging planning not being guaranteed.

[0005] In order to solve the above technical problems, the present invention specifically provides the following technical solutions:

[0006] A method for charging and discharging an energy storage battery based on a deep learning algorithm comprises the following steps:

[0007] The multi-objective optimization algorithm is used to solve the charging and discharging control parameters of the energy storage battery to obtain the optimal charging control parameters and the optimal discharging control parameters;

[0008] A neural network is used to encapsulate the mapping relationship between the optimal charging control parameter and the optimal discharging control parameter, and a charging and discharging balancing control model is obtained for determining the optimal discharging control parameter according to the optimal charging control parameter.

[0009] By utilizing a multi-objective optimization algorithm combined with a charge-discharge balance control model, the optimal charging parameters and optimal discharging parameters of the energy storage battery are determined, and the charge and discharge of the energy storage battery are optimized.

[0010] As a preferred solution of the present invention, the process of solving the optimal charging control parameters includes:

[0011] Obtain system parameters of the energy storage system;

[0012] The stability target and the economic target are constructed as the optimization target of the energy storage battery charging control, and the energy storage battery charging optimization objective function is obtained. The energy storage battery charging optimization objective function is:

[0013]

[0014] Where Gc is the energy storage battery charging optimization objective function, min is the minimization operator, and Pc t and PC t+1 are the charging powers at the tth charging moment and the t+1th charging moment in the charging process, Mc t is the unit price of electricity at the tth charging time in the charging process, Tc is the total charging time of the charging process, The stability target of energy storage battery charging control, The economic goal of energy storage battery charging control.

[0015] Taking the system parameters of the energy storage system as constraints, the energy storage battery charging optimization objective function is solved to obtain the optimal charging control parameters of the energy storage battery in the energy storage system.

[0016] As a preferred solution of the present invention, the process of solving the optimal discharge control parameters includes:

[0017] Obtain system parameters of the energy storage system;

[0018] The stability target and the economic target are constructed as the optimization target of the energy storage battery discharge control, and the energy storage battery discharge optimization objective function is obtained. The energy storage battery discharge optimization objective function is:

[0019]

[0020] In the formula, Gf is the energy storage battery discharge optimization objective function, min is the minimization operator, max is the maximization operator, Pf t and Pf t+1 are the discharge powers at the tth discharge moment and the t+1th discharge moment in the discharge process, Mf t is the unit price of electricity at the tth discharge time in the discharge process, Tf is the total discharge duration of the discharge process, For the stability target of energy storage battery discharge control, It is the economic goal of energy storage battery discharge control.

[0021] Taking the system parameters of the energy storage system as constraints, the energy storage battery discharge optimization objective function is solved to obtain the optimal discharge control parameters of the energy storage battery in the energy storage system.

[0022] As a preferred solution of the present invention, the system parameters of the energy storage system include the power generation power of the power generation system, the power supply power of the power grid system, the power consumption of the load device, and the charging power and discharging power of the new energy equipment.

[0023] As a preferred solution of the present invention, the method for constructing the charge-discharge balance control model includes:

[0024] Selecting a plurality of time intervals including two adjacent time periods, obtaining an optimal charging control parameter by a multi-objective optimization algorithm in a leading time period of each time interval, and obtaining an optimal discharging control parameter by a multi-objective optimization algorithm in a trailing time period of each time interval;

[0025] The optimal charging control parameter at the leading time period of the time interval is used as an input item of the neural network, and the optimal discharging control parameter at the leading time period of the time interval is used as an output item of the neural network;

[0026] Constructing a loss function, using a neural network to train the input items and output items of the neural network, and obtaining a charge-discharge balance control model that characterizes the mapping relationship between the optimal charge control parameters and the optimal discharge control parameters;

[0027] The charge and discharge balance control model is:

[0028] [Pf t |t∈(1,Tf)]=BP([Pc t |t∈(1,Tc)]);

[0029] In the formula, [Pf t |t∈(1,Tf)] is the optimal discharge control parameter in the discharge process, [Pc t |t∈(1,Tc)] is the optimal charging control parameter during the charging process, Pf t is the discharge power at the tth discharge moment in the discharge process, Tf is the total discharge duration of the discharge process, Pc t is the charging power at the tth charging moment in the charging process, Tc is the total charging time of the charging process, and BP is the neural network;

[0030] The loss function is: loss = MSE ([Pf t |t∈(1,Tf)] BP ,[Pf t |t∈(1,Tf)] OR );

[0031] In the formula, loss is the loss function value, [Pf t |t∈(1,Tf)] BPis the optimal discharge control parameter output by the charge-discharge balance control model, [Pf t |t∈(1,Tf)] OR It is the optimal discharge control parameter solved by the multi-objective optimization algorithm, and MSE is the mean square error.

[0032] As a preferred embodiment of the present invention, a method for optimizing the charge and discharge management of an energy storage battery includes:

[0033] Combine a charging process and a discharging process into one management cycle;

[0034] Use a multi-objective optimization algorithm to plan the charging of the energy storage battery during the charging process of the management cycle, and obtain the optimal charging control parameters of the energy storage battery during the charging process;

[0035] The optimal charging control parameters of the energy storage battery are input into the charge-discharge balance control model to obtain the optimal discharge control parameters of the energy storage battery during the discharge process;

[0036] The charging and discharging operations of the energy storage battery are controlled sequentially with the optimal charging control parameters and the optimal discharging control parameters during the management cycle.

[0037] As a preferred solution of the present invention, the operation data in the multi-objective optimization algorithm and the charge-discharge balance control model are normalized.

[0038] As a preferred solution of the present invention, the discharge control parameter and the charge control parameter are discharge power and charge power respectively.

[0039] As a preferred embodiment of the present invention, the present invention provides a storage battery charging and discharging system based on a deep learning algorithm, which is applied to the storage battery charging and discharging method based on a deep learning algorithm, and the system includes:

[0040] An optimization operation unit, used to solve the charge and discharge control parameters of the energy storage battery using a multi-objective optimization algorithm to obtain optimal charge control parameters and optimal discharge control parameters;

[0041] A model building unit, used to encapsulate the mapping relationship between the optimal charging control parameter and the optimal discharging control parameter by using a neural network, so as to obtain a charge-discharge balance control model for determining the optimal discharging control parameter according to the optimal charging control parameter;

[0042] The balancing management unit is used to determine the optimal charging parameters and optimal discharging parameters of the energy storage battery through the battery management device BMS using a multi-objective optimization algorithm combined with a charge and discharge balancing control model, and then use the power conversion system PCS to optimize the charge and discharge management of the energy storage battery to balance the charge and discharge of the energy storage battery.

[0043] As a preferred embodiment of the present invention, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions. When a processor executes the computer-executable instructions, a method for balanced charging and discharging of an energy storage battery is implemented.

[0044] Compared with the prior art, the present invention has the following beneficial effects:

[0045] The present invention utilizes a neural network to encapsulate the mapping relationship between the optimal charging control parameters and the optimal discharging control parameters to construct a charging and discharging balance control model, thereby realizing the determination of the optimal discharging control parameters according to the optimal charging control parameters; there is no need to optimize and solve the optimal control parameters one by one during the charging and discharging process, thereby reducing the workload of optimizing and analyzing the control parameters of the charging and discharging process, which is large and complicated, and ensures the efficiency of the charging and discharging planning, and meets the timeliness of the charging and discharging planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0047] Figure 1 A flow chart of a method for balanced charging and discharging of an energy storage battery provided by an embodiment of the present invention;

[0048] Figure 2 A block diagram of a balanced charging and discharging system for an energy storage battery provided by an embodiment of the present invention;

[0049] Figure 3 A block diagram of an energy storage system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] 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.

[0051] like Figure 1 As shown, the present invention provides a method for charging and discharging an energy storage battery based on a deep learning algorithm, comprising the following steps:

[0052] The multi-objective optimization algorithm is used to solve the charging and discharging control parameters of the energy storage battery to obtain the optimal charging control parameters and the optimal discharging control parameters;

[0053] A neural network is used to encapsulate the mapping relationship between the optimal charging control parameter and the optimal discharging control parameter, and a charging and discharging balancing control model is obtained for determining the optimal discharging control parameter according to the optimal charging control parameter.

[0054] By utilizing a multi-objective optimization algorithm combined with a charge-discharge balance control model, the optimal charging parameters and optimal discharging parameters of the energy storage battery are determined, and the charge and discharge of the energy storage battery are optimized.

[0055] In order to improve the planning efficiency of the charging and discharging process of the energy storage battery, that is, to obtain the optimal control parameters (optimal charging control parameters and optimal discharging control parameters) of the energy storage battery with high efficiency, the present invention constructs a charging and discharging balance control model, which can determine the optimal discharging control parameters according to the optimal charging control parameters, and replaces the multi-objective optimization solution process in the discharging process. Therefore, in the planning of the charging and discharging process of the energy storage battery, the multi-objective optimization solution in the charging and discharging process is simplified to the multi-objective optimization solution only in the charging process, which simplifies the analysis and solution workload in the planning process and improves the efficiency of battery charging and discharging planning.

[0056] In the present invention, a charge and discharge balance control model is constructed, and the difference between the optimal discharge control parameters output by the charge and discharge balance control model and the optimal discharge control parameters solved by the multi-objective optimization algorithm is used as the loss function, so that the trained charge and discharge balance control model can output data results consistent with those solved by the multi-objective optimization algorithm, thereby ensuring that the results output by the charge and discharge balance control model can achieve optimal discharge control, and realize the stability and economy of battery discharge in the control. Maximization.

[0057] The multi-objective optimization algorithm in the present invention takes stability and economy as optimization objectives for energy storage battery charging control, so that the solved charging control parameters and discharging control parameters can maintain the stability of the energy storage battery during the charging and discharging process, will not generate abnormal charging and discharging power, and ensure the safety of the energy storage battery. At the same time, the solved charging control parameters and discharging control parameters can maintain the economy of the energy storage battery during the charging and discharging process, that is, the cost is minimized during the charging process and the benefit is maximized during the discharging process.

[0058] In the present invention, a multi-objective optimization algorithm is combined with a charge-discharge balance control model to determine the optimal charging parameters and optimal discharging parameters of the energy storage battery, which can efficiently calculate the optimal charging parameters and optimal discharging parameters with battery stability / safety and economic profitability, and at the same time achieve the three-way optimization of efficiency, stability and economy.

[0059] In the present invention, the charging and discharging process is regarded as a battery management cycle, so that the multi-objective optimization algorithm can be used to control the charging process. On the basis of the control plan of the charging process, the charge and discharge balance control model is used to obtain the control plan of the discharge process, so that the control plan of the discharge process is completed on the premise of the control plan of the charging process, and the charging process and the discharge process are associated, and the charging and discharging generated by the multi-objective optimization solution in the two processes are not independent of each other. Therefore, the control parameters of the discharge process obtained can make the discharge process of the battery discharge according to the charging characteristics of the charging process, avoid the separation of the charging process and the discharge process, resulting in jump discharge after charging is completed, ensure the consistency of the charging and discharging process, and finally further improve the charging and discharging safety of the energy storage battery.

[0060] The multi-objective optimization algorithm of the present invention takes stability and economy as optimization objectives of energy storage battery charging control, so that the solved charging control parameters and discharging control parameters can maintain the stability of the energy storage battery during the charging and discharging process, and will not generate abnormal charging and discharging power, thereby ensuring the safety of the energy storage battery. At the same time, the solved charging control parameters and discharging control parameters can maintain the economy of the energy storage battery during the charging and discharging process, that is, the cost is minimized during the charging process and the benefit is maximized during the discharging process, as follows:

[0061] The process of solving the optimal charging control parameters includes:

[0062] Obtain energy storage systems (such as Figure 3 System parameters shown in

[0063] The stability target and the economic target are constructed as the optimization target of the energy storage battery charging control, and the energy storage battery charging optimization objective function is obtained. The energy storage battery charging optimization objective function is:

[0064]

[0065] Where Gc is the energy storage battery charging optimization objective function, min is the minimization operator, and Pc t and PC t+1 are the charging powers at the tth charging moment and the t+1th charging moment in the charging process, Mc t is the unit price of electricity at the tth charging time in the charging process, Tc is the total charging time of the charging process, The stability target of energy storage battery charging control, The economic goal of energy storage battery charging control.

[0066] Taking the system parameters of the energy storage system as constraints, the energy storage battery charging optimization objective function is solved to obtain the optimal charging control parameters of the energy storage battery in the energy storage system.

[0067] The process of solving the optimal discharge control parameters includes:

[0068] Obtain system parameters of the energy storage system;

[0069] The stability target and the economic target are constructed as the optimization target of the energy storage battery discharge control, and the energy storage battery discharge optimization objective function is obtained. The energy storage battery discharge optimization objective function is:

[0070]

[0071] In the formula, Gf is the energy storage battery discharge optimization objective function, min is the minimization operator, max is the maximization operator, Pf t and Pf t+1 are the discharge powers at the tth discharge moment and the t+1th discharge moment in the discharge process, Mf t is the unit price of electricity at the tth discharge time in the discharge process, Tf is the total discharge duration of the discharge process, For the stability target of energy storage battery discharge control, It is the economic goal of energy storage battery discharge control.

[0072] Taking the system parameters of the energy storage system as constraints, the energy storage battery discharge optimization objective function is solved to obtain the optimal discharge control parameters of the energy storage battery in the energy storage system.

[0073] The system parameters of the energy storage system include the power generation power of the power generation system (photovoltaic power generation, wind power generation, etc.), the power supply power of the power grid system, the power consumption of the load device, and the charging power and discharging power of new energy equipment (new energy electric vehicles, etc.).

[0074] In order to improve the planning efficiency of the charging and discharging process of the energy storage battery, that is, to obtain the optimal control parameters (optimal charging control parameters and optimal discharging control parameters) of the energy storage battery with high efficiency, the present invention constructs a charging and discharging balance control model, which can determine the optimal discharging control parameters according to the optimal charging control parameters, and replaces the multi-objective optimization solution process in the discharging process, so that in the planning of the charging and discharging process of the energy storage battery, the multi-objective optimization solution in the charging and discharging process is simplified to only need to perform multi-objective optimization solution in the charging process, simplifying the analysis and solution workload in the planning process, and improving the efficiency of battery charging and discharging planning, as follows:

[0075] The construction method of the charge and discharge balance control model includes:

[0076] Selecting a plurality of time intervals including two adjacent time periods, obtaining an optimal charging control parameter by a multi-objective optimization algorithm in a leading time period of each time interval, and obtaining an optimal discharging control parameter by a multi-objective optimization algorithm in a trailing time period of each time interval;

[0077] The optimal charging control parameter at the leading time period of the time interval is used as an input item of the neural network, and the optimal discharging control parameter at the leading time period of the time interval is used as an output item of the neural network;

[0078] Constructing a loss function, using a neural network to train the input items and output items of the neural network, and obtaining a charge-discharge balance control model that characterizes the mapping relationship between the optimal charge control parameters and the optimal discharge control parameters;

[0079] The charge and discharge balance control model is:

[0080] [Pf t |t∈(1,Tf)]=BP([Pc t |t∈(1,Tc)]);

[0081] In the formula, [Pf t |t∈(1,Tf)] is the optimal discharge control parameter in the discharge process, [Pc t |t∈(1,Tc)] is the optimal charging control parameter during the charging process, Pf t is the discharge power at the tth discharge moment in the discharge process, Tf is the total discharge duration of the discharge process, Pc t is the charging power at the tth charging moment in the charging process, Tc is the total charging time of the charging process, and BP is the neural network;

[0082] The loss function is: loss = MSE ([Pf t |t∈(1,Tf)] BP ,[Pf t |t∈(1,Tf)] OR );

[0083] In the formula, loss is the loss function value, [Pf t |t∈(1,Tf)] BP is the optimal discharge control parameter output by the charge-discharge balance control model, [Pf t |t∈(1,Tf)] OR It is the optimal discharge control parameter solved by the multi-objective optimization algorithm, and MSE is the mean square error.

[0084] Methods for optimizing the charge and discharge management of energy storage batteries include:

[0085] Combine a charging process and a discharging process into one management cycle;

[0086] Use a multi-objective optimization algorithm to plan the charging of the energy storage battery during the charging process of the management cycle, and obtain the optimal charging control parameters of the energy storage battery during the charging process;

[0087] The optimal charging control parameters of the energy storage battery are input into the charge-discharge balance control model to obtain the optimal discharge control parameters of the energy storage battery during the discharge process;

[0088] The charging and discharging operations of the energy storage battery are controlled sequentially with the optimal charging control parameters and the optimal discharging control parameters during the management cycle.

[0089] The calculation data in the multi-objective optimization algorithm and the charge-discharge balance control model are normalized.

[0090] The discharge control parameter and the charge control parameter are the discharge power and the charge power respectively.

[0091] In the present invention, a multi-objective optimization algorithm is combined with a charge-discharge balance control model to determine the optimal charging parameters and optimal discharging parameters of the energy storage battery, which can efficiently calculate the optimal charging parameters and optimal discharging parameters with battery stability / safety and economic profitability, and at the same time achieve the three-way optimization of efficiency, stability and economy.

[0092] In the present invention, the charging and discharging process is regarded as a battery management cycle, so that the multi-objective optimization algorithm can be used to control the charging process. On the basis of the control plan of the charging process, the charge and discharge balance control model is used to obtain the control plan of the discharge process, so that the control plan of the discharge process is completed on the premise of the control plan of the charging process, and the charging process and the discharge process are associated, and the charging and discharging generated by the multi-objective optimization solution in the two processes are not independent of each other. Therefore, the control parameters of the discharge process obtained can make the discharge process of the battery discharge according to the charging characteristics of the charging process, avoid the separation of the charging process and the discharge process, resulting in jump discharge after charging is completed, ensure the consistency of the charging and discharging process, and finally further improve the charging and discharging safety of the energy storage battery.

[0093] like Figure 2 As shown, the present invention provides an energy storage battery charging and discharging system based on a deep learning algorithm, which is applied to an energy storage battery charging and discharging method based on a deep learning algorithm. The system includes:

[0094] An optimization operation unit, used to solve the charge and discharge control parameters of the energy storage battery using a multi-objective optimization algorithm to obtain optimal charge control parameters and optimal discharge control parameters;

[0095] A model building unit, used to encapsulate the mapping relationship between the optimal charging control parameter and the optimal discharging control parameter by using a neural network, so as to obtain a charge-discharge balance control model for determining the optimal discharging control parameter according to the optimal charging control parameter;

[0096] The balancing management unit is used to manage the battery through the battery management device BMS (such as Figure 3 As shown in the figure, the optimal charging parameters and optimal discharging parameters of the energy storage battery are determined by combining the multi-objective optimization algorithm with the charge and discharge balance control model, and then the power conversion system PCS (as shown in the figure) is used to calculate the optimal charging parameters and optimal discharging parameters of the energy storage battery. Figure 3 As shown in the figure, the charging and discharging of the energy storage battery is optimized and managed to balance the charging and discharging of the energy storage battery.

[0097] The present invention provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, a method for balanced charging and discharging of an energy storage battery is implemented.

[0098] The present invention utilizes a neural network to encapsulate the mapping relationship between the optimal charging control parameters and the optimal discharging control parameters to construct a charging and discharging balance control model, thereby realizing the determination of the optimal discharging control parameters according to the optimal charging control parameters; there is no need to optimize and solve the optimal control parameters one by one during the charging and discharging process, thereby reducing the workload of optimizing and analyzing the control parameters of the charging and discharging process, which is large and complicated, and ensures the efficiency of the charging and discharging planning, and meets the timeliness of the charging and discharging planning.

[0099] The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art may make various modifications or equivalent substitutions to the present application within the essence and protection scope of the present application, and such modifications or equivalent substitutions shall also be deemed to fall within the protection scope of the present application.

Claims

1. A method for charging and discharging an energy storage battery based on a deep learning algorithm, characterized in that: The following steps are involved: The multi-objective optimization algorithm is used to solve the charging and discharging control parameters of the energy storage battery to obtain the optimal charging control parameters and the optimal discharging control parameters; A neural network is used to encapsulate the mapping relationship between the optimal charging control parameter and the optimal discharging control parameter, and a charging and discharging balancing control model is obtained for determining the optimal discharging control parameter according to the optimal charging control parameter. By using a multi-objective optimization algorithm combined with a charge-discharge balance control model, the optimal charging and discharging parameters of the energy storage battery are determined, and the charge and discharge of the energy storage battery are optimized. The construction method of the charge and discharge balance control model includes: Selecting a plurality of time intervals including two adjacent time periods, obtaining an optimal charging control parameter by a multi-objective optimization algorithm in a leading time period of each time interval, and obtaining an optimal discharging control parameter by a multi-objective optimization algorithm in a trailing time period of each time interval; The optimal charging control parameter at the leading time period of the time interval is used as an input item of the neural network, and the optimal discharging control parameter at the leading time period of the time interval is used as an output item of the neural network; Constructing a loss function, using a neural network to train the input items and output items of the neural network, and obtaining a charge-discharge balance control model that characterizes the mapping relationship between the optimal charge control parameters and the optimal discharge control parameters; The charge and discharge balance control model is: [Pf t |t∈(1,Tf)]=BP([Pc t |t∈(1,Tc)]); In the formula, [Pf t |t∈(1,Tf)] is the optimal discharge control parameter in the discharge process, [Pc t |t∈(1,Tc)] is the optimal charging control parameter during the charging process, Pf t is the discharge power at the tth discharge moment in the discharge process, Tf is the total discharge duration of the discharge process, Pc t is the charging power at the tth charging moment in the charging process, Tc is the total charging time of the charging process, and BP is the neural network; The loss function is: loss = MSE ([Pf t |t∈(1,Tf)] BP ,[Pf t |t∈(1,Tf)] OR ); Where loss is the loss function value, [Pf t |t∈(1,Tf)] BP is the optimal discharge control parameter output by the charge-discharge balance control model, [Pf t |t∈(1,Tf)] OR is the optimal discharge control parameter solved by the multi-objective optimization algorithm, and MSE is the mean square error; Methods for optimizing the charge and discharge management of energy storage batteries include: Combine a charging process and a discharging process into one management cycle; Use a multi-objective optimization algorithm to plan the charging of the energy storage battery during the charging process of the management cycle, and obtain the optimal charging control parameters of the energy storage battery during the charging process; The optimal charging control parameters of the energy storage battery are input into the charge-discharge balance control model to obtain the optimal discharge control parameters of the energy storage battery during the discharge process; The charging and discharging operations of the energy storage battery are controlled sequentially with the optimal charging control parameters and the optimal discharging control parameters during the management cycle.

2. The energy storage battery charging and discharging method based on a deep learning algorithm according to claim 1, characterized in that: The process of solving the optimal charging control parameters includes: Obtain system parameters of the energy storage system; The stability target and the economic target are constructed as the optimization target of the energy storage battery charging control, and the energy storage battery charging optimization objective function is obtained. The energy storage battery charging optimization objective function is: Where Gc is the energy storage battery charging optimization objective function, min is the minimization operator, and Pc t and PC t+1 are the charging powers at the tth charging moment and the t+1th charging moment in the charging process, Mc t is the unit price of electricity at the tth charging time in the charging process, Tc is the total charging time of the charging process, The stability target of energy storage battery charging control, Economical target for energy storage battery charging control; Taking the system parameters of the energy storage system as constraints, the energy storage battery charging optimization objective function is solved to obtain the optimal charging control parameters of the energy storage battery in the energy storage system.

3. The energy storage battery charging and discharging method based on deep learning algorithm according to claim 2, characterized in that: The process of solving the optimal discharge control parameters includes: Obtain system parameters of the energy storage system; The stability target and the economic target are constructed as the optimization target of the energy storage battery discharge control, and the energy storage battery discharge optimization objective function is obtained. The energy storage battery discharge optimization objective function is: In the formula, Gf is the energy storage battery discharge optimization objective function, min is the minimization operator, max is the maximization operator, Pf t and Pf t+1 are the discharge powers at the tth discharge moment and the t+1th discharge moment in the discharge process, Mf t is the unit price of electricity at the tth discharge time in the discharge process, Tf is the total discharge duration of the discharge process, For the stability target of energy storage battery discharge control, To achieve the economic goal of energy storage battery discharge control; Taking the system parameters of the energy storage system as constraints, the energy storage battery discharge optimization objective function is solved to obtain the optimal discharge control parameters of the energy storage battery in the energy storage system.

4. The energy storage battery charging and discharging method based on a deep learning algorithm according to claim 3, characterized in that: The system parameters of the energy storage system include the power generation power of the power generation system, the power supply power of the power grid system, the power consumption of the load device, and the charging power and discharging power of the new energy equipment.

5. The energy storage battery charging and discharging method based on deep learning algorithm according to claim 1, characterized in that: The calculation data in the multi-objective optimization algorithm and the charge-discharge balance control model are normalized.

6. The energy storage battery charging and discharging method based on a deep learning algorithm according to claim 1, characterized in that: The discharge control parameter and the charge control parameter are discharge power and charge power respectively.

7. A storage battery charging and discharging system based on a deep learning algorithm, characterized in that: According to a method for charging and discharging an energy storage battery based on a deep learning algorithm according to any one of claims 1 to 6, the system comprises: An optimization operation unit, used to solve the charge and discharge control parameters of the energy storage battery using a multi-objective optimization algorithm to obtain optimal charge control parameters and optimal discharge control parameters; A model building unit, used to encapsulate the mapping relationship between the optimal charging control parameter and the optimal discharging control parameter by using a neural network, so as to obtain a charge-discharge balance control model for determining the optimal discharging control parameter according to the optimal charging control parameter; The balancing management unit is used to determine the optimal charging parameters and optimal discharging parameters of the energy storage battery through the battery management device BMS using a multi-objective optimization algorithm combined with a charge and discharge balancing control model, and then use the power conversion system PCS to optimize the charge and discharge management of the energy storage battery to balance the charge and discharge of the energy storage battery.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the processor executes the computer-executable instructions, the method according to any one of claims 1 to 6 is implemented.

Images