Energy storage operation optimization method and system considering battery life loss

Abstract

The invention relates to the technical field of battery energy storage, and discloses an energy storage operation optimization method and system considering battery life loss, and the method comprises the steps: initializing battery energy storage electrical parameters, constructing a battery life loss model, and obtaining the health state change of a battery; constructing a battery operation cost model, defining a multi-objective optimization algorithm and constraint conditions, and optimizing the battery operation cost; and carrying out adaptive scheduling through a model prediction control and reinforcement learning algorithm, and determining an optimal charging and discharging strategy of the energy storage system. By constructing the battery life loss model and the multi-target optimization algorithm, economical operation of the energy storage system and prolonging of the battery life are achieved, the charging and discharging strategy of the energy storage system can be dynamically adjusted according to the power market cost fluctuation, the load requirement and the battery health state, and the operation cost of the energy storage system is reduced.

Description

Technical Field

[0001] The present invention relates to the field of battery energy storage technology, and in particular to an energy storage operation optimization method and system taking battery life loss into consideration. Background Art

[0002] As the proportion of renewable energy in the power system continues to increase, energy storage systems (ESS) are increasingly used in peak and frequency regulation, balancing supply and demand, and absorbing renewable energy. However, the battery charging and discharging process will cause the capacity to gradually decline, which directly affects the service life and economic benefits of the energy storage system. Traditional energy storage operation strategies often only focus on short-term economic benefits, such as electricity purchase costs, peak shaving and valley filling benefits, etc., while ignoring the impact of battery life loss on long-term economic efficiency, which leads to premature degradation of batteries under unreasonable charging and discharging strategies, increasing the maintenance and replacement costs of the system.

[0003] In the prior art, although some optimization methods involve battery charge and discharge control, they fail to effectively balance the battery life loss and system economy, and lack the ability to dynamically adjust the battery load. Therefore, an optimization method that comprehensively considers battery life and system economy is proposed, which can extend the battery life while achieving efficient operation of the energy storage system, which has important practical significance. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the above existing problems, the present invention is proposed. Therefore, the present invention provides an energy storage operation optimization method considering battery life loss to solve the above problems.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides an energy storage operation optimization method considering battery life loss, including: initializing battery energy storage electrical parameters, constructing a battery life loss model, and obtaining a battery health status change;

[0008] Based on the battery life loss model, a battery operation cost model is constructed, and a multi-objective optimization algorithm and constraint conditions are defined to optimize the battery operation cost;

[0009] Based on the optimization of battery cost, adaptive scheduling is performed through model predictive control and reinforcement learning algorithm to determine the optimal charging and discharging strategy of the energy storage system.

[0010] As a preferred solution of the energy storage operation optimization method considering battery life loss described in the present invention, the battery life loss is expressed as:

[0011]

[0012] Among them, SOH(t) represents the health state of the battery, SOH0 represents the initial health state, k and α are battery characteristic parameters, DoD(i) represents the depth of charge and discharge of the i-th time, and DoD ref Indicates the reference discharge depth.

[0013] As a preferred solution of the energy storage operation optimization method considering battery life loss described in the present invention, the battery operation cost model includes the electricity purchase cost and the battery life loss cost, and the battery life loss cost C degradation It is expressed as:

[0014] C degradation =β·(1-SOH(t))

[0015] Among them, β is the battery depreciation cost coefficient, and SOH(t) represents the battery health status at the current moment.

[0016] As a preferred solution of the energy storage operation optimization method considering battery life loss described in the present invention, the multi-objective optimization algorithm is expressed as:

[0017]

[0018] Among them, C buy (t) represents the electricity purchase cost at time t, λ1 and λ2 are weight coefficients used to balance the electricity purchase cost and battery loss cost, and T represents the total time of the optimization period.

[0019] As a preferred solution of the energy storage operation optimization method considering battery life loss described in the present invention, the model predictive control includes:

[0020] Based on historical data and external information, the load demand and electricity price in the future are predicted to obtain the load and electricity price forecast values ​​in the next optimization cycle;

[0021] With the goal of minimizing the electricity purchase cost and battery life loss cost in the future time step, define the rolling optimization objective function and define the constraints of the rolling optimization process;

[0022] Based on the rolling optimization objective function, the optimal charging and discharging power at the current moment is solved, and the values ​​of the battery charging and discharging state and the battery energy storage state are updated.

[0023] As a preferred solution of the energy storage operation optimization method considering battery life loss described in the present invention, the rolling optimization objective function is expressed as:

[0024]

[0025] Among them, C degradation (t+i) represents the battery life loss cost at the future time, C buy (t+i) represents the electricity purchase cost at a future time. represents the electricity price in the future period, P storage (t+i) represents the optimal charge and discharge power at the future moment.

[0026] As a preferred solution of the energy storage operation optimization method considering battery life loss described in the present invention, the reinforcement learning algorithm includes:

[0027] Define the state, action and reward functions of the energy storage system;

[0028] Update the Q value according to the Q-learning algorithm and calculate the optimal strategy for the current state through the deep Q network;

[0029] The optimal charging and discharging power at the current moment is selected according to the ε-greedy strategy, and is integrated with the strategy of the model predictive control output to obtain the final charging and discharging instructions.

[0030] In a second aspect, the present invention provides an energy storage operation optimization system taking into account battery life loss, comprising:

[0031] The first building module is used to initialize the battery energy storage electrical parameters, build a battery life loss model, and obtain the health status change of the battery;

[0032] A second construction module is used to construct a battery operation cost model based on the battery life loss model, and define a multi-objective optimization algorithm and constraint conditions to optimize the battery operation cost;

[0033] The output module is used to perform adaptive scheduling based on the optimization of the battery cost and determine the optimal charging and discharging strategy of the energy storage system through model predictive control and reinforcement learning algorithm.

[0034] In a third aspect, the present invention provides an electronic device, comprising:

[0035] Memory and processor;

[0036] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the energy storage operation optimization method considering battery life loss are implemented.

[0037] In a fourth aspect, the present invention provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the energy storage operation optimization method taking into account battery life loss.

[0038] Compared with the prior art, the present invention has the following beneficial effects: the present invention realizes the economical operation of the energy storage system and the extension of the battery life by constructing a battery life loss model and a multi-objective optimization algorithm. It can dynamically adjust the charging and discharging strategy of the energy storage system according to the fluctuation of electricity market costs, load demand and battery health status, thereby reducing the operating cost of the energy storage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0040] Figure 1 The figure is a schematic diagram of the overall process of an energy storage operation optimization method taking into account battery life loss according to an embodiment of the present invention. DETAILED DESCRIPTION

[0041] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0043] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0044] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0045] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0046] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0047] Reference Figure 1 , which is an embodiment of the present invention, provides an energy storage operation optimization method considering battery life loss, comprising:

[0048] S101, initializing battery energy storage electrical parameters, building a battery life loss model, and obtaining changes in the battery's health status;

[0049] S102, based on the battery life loss model, construct a battery operation cost model, and define a multi-objective optimization algorithm and constraint conditions to optimize the battery operation cost;

[0050] S103, based on the optimization of battery cost, adaptive scheduling is performed through model predictive control and reinforcement learning algorithm to determine the optimal charging and discharging strategy of the energy storage system.

[0051] It should be noted that this embodiment incorporates battery life loss into the scheduling model of the energy storage system, and combines model predictive control (MPC) and reinforcement learning (RL) algorithms to optimize the multi-objective operation strategy of the energy storage system. When the market price is low, the system gives priority to charging, and when the market price is high, it chooses to discharge, thereby maximizing economic benefits while protecting battery life.

[0052] In a preferred embodiment, a battery state of health (SOH) model is constructed for factors such as the depth of battery charge and discharge (DoD), temperature, and number of cycles to evaluate the impact of different charge and discharge strategies on battery life;

[0053] Battery life loss is expressed as:

[0054]

[0055] Among them, SOH(t) represents the health state of the battery, SOH0 represents the initial health state, k and α are battery characteristic parameters, DoD(i) represents the depth of charge and discharge of the i-th time, and DoD ref Indicates the reference discharge depth.

[0056] It should be noted that this model dynamically reflects the battery life loss under different charging and discharging strategies for use in optimizing scheduling strategies.

[0057] Furthermore, the battery energy storage electrical parameters are initialized, that is, the basic parameters of the energy storage system are initialized, including battery capacity, charge and discharge power, initial state of SOC and SOH, etc., the parameters required for model predictive control (MPC) and reinforcement learning (RL) are configured, and the real-time data interface is connected at the same time, so as to receive electricity price and load data in real time later.

[0058] In a preferred embodiment, the battery operation cost model includes the electricity purchase cost and the battery life loss cost. The battery life loss cost C degradation It is expressed as:

[0059] C degradation =β·(1-SOH(t))

[0060] Among them, β is the battery depreciation cost coefficient, and SOH(t) represents the battery health status at the current moment.

[0061] It should be noted that through the comprehensive expression of the life loss model and the electricity purchase cost, an overall operating cost model was established to provide a basis for the optimization target.

[0062] In a preferred embodiment, the multi-objective optimization algorithm is expressed as:

[0063]

[0064] Among them, C buy (t) represents the electricity purchase cost at time t, λ1 and λ2 are weight coefficients used to balance the electricity purchase cost and battery loss cost, and T represents the total time of the optimization period.

[0065] It should be noted that the multi-objective optimization algorithm model aims to balance the electricity purchase cost and battery life loss cost of the energy storage system. At the same time, constraints need to be added in the multi-objective optimization to ensure the feasibility of the system and the safe operation of the battery.

[0066] In an optional implementation, the constraints include:

[0067] Power balance constraint: The power output of the energy storage system must meet the load demand and the power balance of the electricity market, expressed as:

[0068] P load (t)+P storage (t) = P demand (t)

[0069] Battery power limit: To ensure safe operation of the battery, the charge and discharge power must be within the rated power range, expressed as:

[0070] -P max ≤P storage (t)≤P max

[0071] Battery SOC (State of Charge) constraint: The battery SOC must be kept within a safe range to avoid overcharging or over-discharging, expressed as:

[0072] SOC min ≤SOC(t)≤SOC max

[0073] Battery charge and discharge state constraints: To avoid frequent switching of charge and discharge states, set charge and discharge depth limits and charge and discharge cycle constraints, expressed as:

[0074] DoD min ≤SOC(t)≤DoD max

[0075] |P storage (t)-P storage (t-1)|≤ΔP threshold

[0076] Among them, SOC(t) is the battery charge and discharge state at time t, DoD min and DoD max To set the minimum and maximum depth limits, P storage (t) is the charge and discharge power at time t, ΔPthreshold It is the threshold value of charge and discharge power change, which is used to avoid frequent charge and discharge switching.

[0077] It should be noted that in step S103, an adaptive scheduling algorithm is designed by combining model predictive control (MPC) and reinforcement learning (RL) algorithms. Model predictive control (MPC) is a prediction-based optimal control method that ensures that the system achieves the optimal charging and discharging strategy under different market prices and load demand conditions by rolling optimization of control variables in multiple future time steps at each time step. The present invention applies MPC to the scheduling of battery energy storage systems.

[0078] In a preferred embodiment, the model predictive control includes:

[0079] Based on historical data and external information, the load demand and electricity price in the future are predicted to obtain the load and electricity price forecast values ​​in the next optimization cycle;

[0080] With the goal of minimizing the electricity purchase cost and battery life loss cost in the future time step, define the rolling optimization objective function and define the constraints of the rolling optimization process;

[0081] Based on the rolling optimization objective function, the optimal charging and discharging power at the current moment is solved, and the values ​​of the battery charging and discharging state and the battery energy storage state are updated.

[0082] In an optional implementation, predicting future electricity prices and load demands includes:

[0083] Based on historical data and external information (such as weather forecasts, load demand), predict the electricity price in the next N time steps and load demand It is expressed as:

[0084]

[0085] Among them, f price and f demand is a prediction function that can be implemented through a machine learning model (such as an LSTM neural network).

[0086] In a preferred embodiment, the rolling optimization objective function is defined with the goal of minimizing the electricity purchase cost and battery life loss cost in the next N time steps, which is expressed as:

[0087]

[0088] Among them, C degradation (t+i) represents the battery life loss cost at the future time, C buy (t+i) represents the electricity purchase cost at a future time. represents the electricity price in the future period, P storage (t+i) represents the optimal charge and discharge power at the future moment.

[0089] Furthermore, during the rolling optimization process, it is ensured that the battery charging and discharging power and SOC meet the constraints, including the battery power constraint and the SOC constraint, which are expressed as:

[0090] -P max ≤P storage (t)≤P max

[0091] SOC min ≤SOC(t)≤SOC max

[0092] Among them, P storage (t) represents the optimal charging and discharging power at the current moment, -P max , P max Respectively represent the minimum and maximum values ​​of charge and discharge power, SOC min、 SOC max Represent the minimum and maximum SOC values ​​respectively.

[0093] In an optional implementation, solving the optimal charging and discharging strategy includes:

[0094] Use quadratic programming or other optimization algorithms to solve the optimal charge and discharge power sequence P for the next N steps based on the objective function and constraints. storage (t),P storage (t+1),...,P storage (t+N).

[0095] The optimal charging and discharging power P at the current moment storage (t) is used as the current control instruction, and the future prediction results are used as the input reference of RL.

[0096] In an optional implementation, the rolling optimization process includes:

[0097] At each time step t, solve the optimal charging and discharging power P at the current time t storage After (t), the charge and discharge operation is performed and the calculation is repeated at the next time t+1. During this process, the SOC and SOH values ​​of the system are updated, which are expressed as:

[0098]

[0099] Among them, C battery is the rated capacity of the battery, and Δt is the time step.

[0100] It should be noted that through the MPC method, the energy storage system can dynamically adapt to future changes in market prices and load demand to achieve optimal scheduling.

[0101] In a preferred embodiment, the reinforcement learning algorithm includes:

[0102] Define the state, action and reward functions of the energy storage system;

[0103] Update the Q value according to the Q-learning algorithm and calculate the optimal strategy for the current state through the deep Q network;

[0104] The optimal charging and discharging power at the current moment is selected according to the ε-greedy strategy and integrated with the strategy output by the model predictive control to obtain the final charging and discharging instructions.

[0105] It should be noted that reinforcement learning (RL) is used to adaptively optimize the operation strategy of the energy storage system in an uncertain market environment. RL enables the energy storage system to maximize long-term benefits in a complex market environment by continuously learning and updating strategies. This embodiment combines the deep Q network (DQN) algorithm and the battery life model to propose an adaptive charging and discharging strategy.

[0106] In an optional implementation, the state, action, and reward functions of the energy storage system are defined in RL:

[0107] Status: Status t Including market price P price (t), load demand P demand (t), battery SOC(t) and SOH(t);

[0108] Action: Charge and discharge power a t =P storage (t), where a t ∈[-P max ,P max ];

[0109] Reward function: Considering the battery life loss and electricity purchase cost, define the reward function R t , expressed as:

[0110] R t =-(C buy (t)+β·(1-SOH(t)))

[0111] Among them, β is the depreciation cost coefficient.

[0112] Update the Q value, including:

[0113] The RL model iteratively updates the Q value according to the Q-learning algorithm, optimizes the strategy, and uses the ε-greedy strategy to select the charging and discharging power action a t , expressed as:

[0114]

[0115] Among them, α is the learning rate, γ is the discount factor, reflecting the weight of future rewards, Represents the maximum expected reward at the next moment.

[0116] In the Q-learning update, if the maximum change between the two Q values ​​is less than 0.01, the strategy is considered to have converged.

[0117] According to the ε-greedy strategy, the optimal charging and discharging power P at the current moment is selected storage (t), and then merged with the strategy output by MPC to obtain the final charge and discharge instructions.

[0118] Strategy optimization and training process. During the training process, the RL algorithm continuously updates the Q value by sampling the energy storage system's charging and discharging history data and market data, optimizing the charging and discharging strategy to maximize the energy storage system's revenue and lifespan. The specific training process is as follows:

[0119] Initially set up the Q network and adopt a random strategy;

[0120] Select the charge and discharge power a at each time step t , and record the corresponding status and rewards;

[0121] Update the Q value to maximize the benefits and extend the life of the energy storage system in the long term.

[0122] Finally, DQN training and prediction are applied to complete the charging and discharging execution and state update. According to the comprehensive results of MPC and RL, the charging and discharging operation at the current moment is performed, and the actual charging and discharging power is P storage (t), after charging and discharging, the SOC and SOH status of the battery are updated, and the current electricity price, load demand, charging and discharging power, SOC and SOH are stored as input data for the next moment to provide feedback data for subsequent MPC and RL optimization.

[0123] It should be noted that this embodiment uses a deep Q network (DQN) to fit the Q value to improve the learning ability of the algorithm. DQN simulates the Q function through a deep neural network and implements random sampling of samples through a replay memory pool (ReplayBuffer) to avoid correlation problems during the strategy update process.

[0124] The multi-objective optimization problem of this embodiment can be solved by mixed integer linear programming (MILP), where the decision variables include the charge and discharge power and the operating state of the battery. In each optimization cycle, the optimization algorithm solves the optimal solution through the following steps:

[0125] Determine the battery charging and discharging requirements based on current market prices and load requirements;

[0126] Calculate the life loss cost of the charging and discharging scheme according to the battery life loss model;

[0127] Through the multi-objective optimization model, the balance point between economy and life loss is solved, and the optimal charging and discharging strategy is output.

[0128] The energy storage operation optimization method considering battery life loss provided by the present invention can significantly extend the battery life, reduce long-term operation costs, and maximize the economic benefits of the energy storage system. Compared with traditional scheduling algorithms, this method, while considering the battery loss cost, can flexibly respond to market price changes and load fluctuations through multi-objective optimization and intelligent scheduling technology, thereby improving the operating efficiency of the energy storage system.

[0129] This embodiment achieves economical operation of the energy storage system and extended battery life by constructing a battery life loss model and a multi-objective optimization algorithm. The method can dynamically adjust the charging and discharging strategy of the energy storage system according to price fluctuations in the electricity market, load demand, and battery health status, thereby reducing the operating cost of the energy storage system.

[0130] The above is a schematic scheme of an energy storage operation optimization method considering battery life loss in this embodiment. It should be noted that the technical scheme of the energy storage operation optimization system considering battery life loss and the technical scheme of the energy storage operation optimization method considering battery life loss belong to the same concept, and the details not described in detail in the technical scheme of the energy storage operation optimization system considering battery life loss in this embodiment can be referred to the description of the technical scheme of the energy storage operation optimization method considering battery life loss.

[0131] The energy storage operation optimization system considering battery life loss in this embodiment includes:

[0132] The first building module is used to initialize the battery energy storage electrical parameters, build a battery life loss model, and obtain the health status change of the battery;

[0133] The second building module is used to build a battery operation cost model based on the battery life loss model, and define a multi-objective optimization algorithm and constraints to optimize the battery operation cost;

[0134] The output module is used to optimize the battery cost and perform adaptive scheduling through model predictive control and reinforcement learning algorithms to determine the optimal charging and discharging strategy of the energy storage system.

[0135] This embodiment further provides an electronic device, which is applicable to the case of optimizing energy storage operation in consideration of battery life loss, and includes:

[0136] Memory and processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to implement the energy storage operation optimization method considering battery life loss as proposed in the above embodiment.

[0137] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, the energy storage operation optimization method considering battery life loss as proposed in the above embodiment is implemented.

[0138] The storage medium proposed in this embodiment and the energy storage operation optimization method considering battery life loss proposed in the above embodiment belong to the same inventive concept. The technical details not fully described in this embodiment can be referred to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0139] Through the above description of the implementation methods, the technicians in the relevant field can clearly understand that the present invention can be implemented by means of software and necessary general hardware, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ReadOnly, Memory, ROM), random access memory (RandomAccess Memory, RAM), flash memory (FLASH), hard disk or optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform the methods of various embodiments of the present invention.

[0140] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for optimizing energy storage operation considering battery life loss, characterized in that: include: Initialize battery energy storage parameters, build a battery life loss model, and obtain changes in battery health status; Based on the battery life loss model, a battery operation cost model is constructed, and a multi-objective optimization algorithm and constraint conditions are defined to optimize the battery operation cost; Based on the optimization of battery cost, adaptive scheduling is performed through model predictive control and reinforcement learning algorithm to determine the optimal charging and discharging strategy of the energy storage system.

2. The energy storage operation optimization method considering battery life loss as claimed in claim 1, characterized in that: The battery life loss is expressed as: Among them, SOH(t) represents the health state of the battery, SOH0 represents the initial health state, k and α are battery characteristic parameters, DoD(i) represents the depth of charge and discharge of the i-th time, and DoD ref Indicates the reference discharge depth.

3. The energy storage operation optimization method considering battery life loss according to claim 1 or 2, characterized in that: The battery operation cost model includes the electricity purchase cost and the battery life loss cost. The battery life loss cost C degradation It is expressed as: C degradation =β·(1-SOH(t)) Among them, β is the battery depreciation cost coefficient, and SOH(t) represents the battery health status at the current moment.

4. The energy storage operation optimization method considering battery life loss as claimed in claim 3 is characterized in that: The multi-objective optimization algorithm is expressed as: Among them, C buy (t) represents the electricity purchase cost at time t, λ1 and λ2 are weight coefficients used to balance the electricity purchase cost and battery loss cost, and T represents the total time of the optimization period.

5. The energy storage operation optimization method considering battery life loss as claimed in claim 1 or 4, characterized in that: The model predictive control includes: Based on historical data and external information, the load demand and electricity price in the future are predicted to obtain the load and electricity price forecast values ​​in the next optimization cycle; With the goal of minimizing the electricity purchase cost and battery life loss cost in the future time step, define the rolling optimization objective function and define the constraints of the rolling optimization process; Based on the rolling optimization objective function, the optimal charging and discharging power at the current moment is solved, and the values ​​of the battery charging and discharging state and the battery energy storage state are updated.

6. The energy storage operation optimization method considering battery life loss as claimed in claim 5, characterized in that: The rolling optimization objective function is expressed as: Among them, C degradation (t+i) represents the battery life loss cost at the future time, C buy (t+i) represents the electricity purchase cost at a future time. represents the electricity price in the future period, P storage (t+i) represents the optimal charge and discharge power at the future moment.

7. The energy storage operation optimization method considering battery life loss as claimed in claim 5, characterized in that: The reinforcement learning algorithm includes: Define the state, action and reward functions of the energy storage system; Update the Q value according to the Q-learning algorithm and calculate the optimal strategy for the current state through the deep Q network; The optimal charging and discharging power at the current moment is selected according to the ε-greedy strategy, and is integrated with the strategy of the model predictive control output to obtain the final charging and discharging instructions.

8. An energy storage operation optimization system considering battery life loss, characterized in that: include, The first building module is used to initialize the battery energy storage electrical parameters, build a battery life loss model, and obtain the health status change of the battery; A second construction module is used to construct a battery operation cost model based on the battery life loss model, and define a multi-objective optimization algorithm and constraint conditions to optimize the battery operation cost; The output module is used to perform adaptive scheduling based on the optimization of the battery cost and determine the optimal charging and discharging strategy of the energy storage system through model predictive control and reinforcement learning algorithm.

9. An electronic device, characterized in that: include: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the energy storage operation optimization method considering battery life loss as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: It stores computer executable instructions, which, when executed by a processor, implement the steps of the energy storage operation optimization method taking into account battery life loss as described in any one of claims 1 to 7.

Images