Operation control method and system of modular energy storage shelter

Abstract

The invention provides an operation control method and system for a modular energy storage shelter, and the method comprises the steps: obtaining comprehensive operation data through collecting the operation parameters of all energy storage modules, building an energy storage module health state evaluation model through a machine learning algorithm, and carrying out the operation control of the modular energy storage shelter. Meanwhile, real-time power demand data is obtained from an API interface of a power grid company, a user-side intelligent electric meter, historical data and current environment parameter analysis, a charging and discharging strategy of each energy storage module is dynamically adjusted by adopting a genetic algorithm to obtain a charging and discharging plan, and a power supply and demand change trend is predicted by combining a deep learning technology to generate a prediction result. An optimal energy storage module scheduling scheme is confirmed by adopting a mixed integer linear programming algorithm to obtain a scheduling instruction, a decision process is continuously optimized through online learning, an optimal control instruction is generated by utilizing a self-adaptive control strategy of reinforcement learning, and according to the technical scheme provided by the invention, energy waste is effectively reduced, the service life is prolonged, and maintenance and replacement are reduced; therefore, operation cost is reduced and economic benefits are improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of modular energy storage cabins, and in particular to an operation control method of a modular energy storage cabin. Background Art

[0002] With the widespread application of renewable energy and the continuous development of power systems, modular energy storage cabins are widely used as efficient energy storage solutions in the fields of grid peak regulation, smoothing renewable energy output, backup power supply, etc. Existing control methods rely on traditional scheduling strategies and simple optimization algorithms, including real-time collection of operating parameters, simple evaluation of health status, prediction of power demand based on historical data, generation of fixed scheduling schemes, and execution of charging and discharging operations. Although these methods can meet basic needs, they have problems such as inaccurate health status assessment, low accuracy of power demand prediction, single scheduling scheme and lack of flexibility, and lack of adaptive control capabilities. Therefore, a more intelligent and efficient control method is needed. Summary of the invention

[0003] The embodiment of the present invention provides an operation control method and system of a modular energy storage cabin, which is used to solve the problems in the prior art of inaccurate health status assessment, low power demand prediction accuracy, single scheduling scheme and lack of flexibility, and lack of adaptive control capability.

[0004] In a first aspect, an embodiment of the present invention provides an operation control method of a modular energy storage cabin, comprising:

[0005] Collect the operating parameters of each energy storage module in real time to obtain comprehensive operating data, wherein the operating parameters include: battery temperature, state of charge, internal resistance, voltage, current and external environmental parameters;

[0006] Based on the comprehensive operation data, a health status assessment model for the energy storage module is established through a machine learning algorithm to obtain a health index, and real-time power demand data is obtained from the grid company API interface, user-side smart meters, historical data, and current environmental parameter analysis;

[0007] Based on the health index and the real-time power demand data, a genetic algorithm is used to dynamically adjust the charging and discharging strategies of each energy storage module to obtain a charging and discharging plan. The charging and discharging plan is used in combination with deep learning technology to predict the changing trend of power supply and demand within a preset time range to generate a power demand forecast result;

[0008] Based on the power demand forecast result, a mixed integer linear programming algorithm is used to confirm the optimal energy storage module scheduling scheme to obtain a scheduling instruction for the energy storage module;

[0009] The dispatching instructions of the energy storage module are implemented, the decision-making process is continuously optimized through online learning, and the adaptive control strategy of reinforcement learning is used to generate the optimal control instructions.

[0010] Optionally, it is characterized in that, based on the power demand forecast result, a mixed integer linear programming algorithm is used to confirm the optimal energy storage module scheduling scheme to obtain the scheduling instruction of the energy storage module, including:

[0011] Using the power demand forecast results, combined with the current health status of the energy storage cabin, energy storage capacity, and charge and discharge rate limits, a multi-objective optimization model is constructed;

[0012] Using the multi-objective optimization model, a variety of preset target scenarios are generated through Monte Carlo simulation to obtain scheduling plan risk assessment results under various scenarios;

[0013] Based on the risk assessment results of the scheduling scheme, a mixed integer linear programming algorithm is used to solve the multi-objective optimization model to generate an initial energy storage module scheduling scheme;

[0014] The initial energy storage module scheduling scheme is used to conduct a comprehensive evaluation through the analytic hierarchy process to determine the optimal energy storage module scheduling scheme.

[0015] Optionally, it is characterized in that, based on the risk assessment result of the scheduling scheme, a mixed integer linear programming algorithm is used to solve a multi-objective optimization model to generate an initial energy storage module scheduling scheme, including:

[0016] Based on the risk assessment results of the scheduling scheme, the physical constraints and operation rules of the energy storage cabin are integrated to obtain a multi-objective optimization model under constraints;

[0017] By using the multi-objective optimization model and introducing a time window rolling optimization mechanism, the scheduling plan is optimized and calculated in stages to obtain a staged scheduling plan;

[0018] According to the phased scheduling plan, a mixed integer linear programming algorithm is used to combine the historical operation data and real-time operation status of the energy storage cabin to perform multi-objective optimization and generate a preliminary energy storage module scheduling plan;

[0019] Based on comprehensive operating data, a health status assessment model for energy storage modules is established through machine learning algorithms to obtain health status assessment results;

[0020] Using the preliminary energy storage module scheduling plan in combination with the health status assessment result, the preliminary energy storage module scheduling plan is revised to obtain a revised energy storage module scheduling plan;

[0021] The revised energy storage module scheduling plan is used to verify the scheduling plan through simulation technology, adjust infeasible scheduling instructions, and generate an initial energy storage module scheduling plan.

[0022] Optionally, the multi-objective optimization model is used to introduce a time window rolling optimization mechanism to perform phased optimization calculations on the scheduling plan to obtain a phased scheduling plan, including:

[0023] Using the multi-objective optimization model, combined with the real-time operating status of the energy storage cabin and the power demand forecast results within a preset time, a series of time windows are defined to obtain a time window sequence;

[0024] Using the time window sequence, according to the current health status of the energy storage cabin, energy storage capacity, charge and discharge rate limit and external environmental parameters, the scheduling plan in each time window is locally optimized and calculated to obtain the local optimal scheduling plan for each time window;

[0025] The local optimal scheduling scheme of each time window is used for integrated processing to form a phased scheduling scheme covering the entire preset time range;

[0026] Using the phased scheduling scheme and combining the historical operation data of the energy storage shelter, the performance change trend of each energy storage module in each time window is predicted through a machine learning algorithm to obtain a performance prediction result;

[0027] Dynamically adjusting the phased scheduling plan using the performance prediction results to obtain a dynamic phased scheduling plan;

[0028] The dynamic phased scheduling scheme is used in combination with the real-time operation data of the energy storage cabin, and the scheduling instructions are dynamically adjusted through a rolling optimization mechanism to generate a target phased scheduling scheme.

[0029] Optionally, according to the phased scheduling plan, a mixed integer linear programming algorithm is used to combine the historical operation data and real-time operation status of the energy storage cabin to perform multi-objective optimization and generate a preliminary energy storage module scheduling plan, including:

[0030] Utilizing the phased scheduling scheme, combined with the historical operation data and real-time operation status of the energy storage cabin, the operation characteristics of the energy storage cabin are analyzed to obtain the operation characteristics analysis results;

[0031] Using the operation characteristic analysis results, a customized design of the objective function of the mixed integer linear programming algorithm is performed to obtain a customized multi-objective optimization model;

[0032] Using the customized multi-objective optimization model, combined with the time window in the phased scheduling plan, multi-objective optimization is solved to generate preliminary multi-objective optimization results;

[0033] Using the preliminary multi-objective optimization results and combining them with the health status assessment results of the energy storage cabin, the optimization results are refined to obtain a refined multi-objective optimization result;

[0034] Based on the refined multi-objective optimization results, a plurality of preliminary scheduling schemes are comprehensively evaluated by using a hierarchical analysis method to obtain a preliminary scheduling scheme after evaluation;

[0035] The evaluated preliminary scheduling plan is used in combination with the real-time operation data of the energy storage cabin to perform dynamic adjustments and generate a preliminary energy storage module scheduling plan.

[0036] Optionally, it is characterized in that, based on the health index and the real-time power demand data, a genetic algorithm is used to dynamically adjust the charging and discharging strategy of each energy storage module to obtain a charging and discharging plan, and the charging and discharging plan is used in combination with deep learning technology to predict the power supply and demand change trend within a preset time range to generate a power demand forecast result, including:

[0037] Using the health index and the real-time power demand data, dynamically adjusting the charging and discharging strategies of each energy storage module through a genetic algorithm to obtain a preliminary charging and discharging plan;

[0038] Using the preliminary charging and discharging plan, combined with the real-time operating status and historical operating data of the energy storage shelter, the power supply and demand change trend within a preset time range is predicted through deep learning technology to obtain preliminary power demand forecast results;

[0039] Utilizing the preliminary power demand forecast result, optimizing the preliminary charging and discharging plan to obtain an optimized charging and discharging plan;

[0040] Utilizing the optimized charging and discharging plan, the changing trend of electricity supply and demand within a preset time range is predicted again through deep learning technology to generate a target electricity demand forecast result.

[0041] Optionally, the dispatching instructions of the energy storage module are implemented, the decision-making process is continuously optimized through online learning, and the adaptive control strategy of reinforcement learning is used to generate the optimal control instructions, including:

[0042] Using the dispatching instruction of the energy storage module to start the charging and discharging operation of the energy storage cabin, and at the same time collecting the real-time operation data of the energy storage cabin during the execution of the dispatching instruction to obtain real-time operation feedback data;

[0043] Based on the real-time operation feedback data and the historical operation data of the energy storage cabin, the current decision-making process is evaluated through an online learning algorithm to obtain a decision evaluation result;

[0044] Using the decision evaluation results, a reinforcement learning environment is designed, a reward function is defined, and a reinforcement learning model is constructed. Meanwhile, the reinforcement learning model is trained by simulating different charging and discharging strategies and energy storage module scheduling schemes to obtain an enhanced reinforcement learning model.

[0045] The enhanced reinforcement learning model is used to optimize the control instructions of the energy storage module, generate new control instructions, and obtain optimized control instructions;

[0046] By utilizing the optimized control instructions and combining the real-time operating status and environmental parameters of the energy storage cabin, the charging and discharging strategy is dynamically adjusted to generate the optimal control instructions.

[0047] In a second aspect, an embodiment of the present application provides an operation control system of a modular energy storage cabin, including:

[0048] The acquisition module is used to collect the operating parameters of each energy storage module in real time to obtain comprehensive operating data, wherein the operating parameters include: battery temperature, state of charge, internal resistance, voltage, current and external environmental parameters;

[0049] A construction module is used to build a health status assessment model for energy storage modules based on comprehensive operation data through machine learning algorithms to obtain a health index. At the same time, it obtains real-time power demand data from the grid company API interface, user-side smart meters, historical data, and current environmental parameter analysis;

[0050] A prediction module is used to dynamically adjust the charging and discharging strategies of each energy storage module based on the health index and real-time power demand data by using a genetic algorithm to obtain a charging and discharging plan. The charging and discharging plan is used in combination with deep learning technology to predict the changing trend of power supply and demand within a preset time range to generate a power demand prediction result;

[0051] A confirmation module, used to confirm the optimal energy storage module scheduling scheme based on the power demand forecast result by using a mixed integer linear programming algorithm to obtain a scheduling instruction for the energy storage module;

[0052] The optimization module is used to implement the dispatching instructions of the energy storage module, optimize the decision-making process through online learning, and generate the best control instructions using the adaptive control strategy of reinforcement learning.

[0053] In a third aspect, an embodiment of the present invention provides a computing device, including a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute an operation control method of a modular energy storage cabin as described in any one of the first aspects.

[0054] In a fourth aspect, an embodiment of the present invention provides a computer storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement an operation control method of a modular energy storage cabin as described in any one of the first aspects.

[0055] In an embodiment of the present invention, the operating parameters of each energy storage module are collected in real time to obtain comprehensive operating data, wherein: based on the comprehensive operating data, a health status assessment model of the energy storage module is established through a machine learning algorithm to obtain a health index, and real-time power demand data is obtained from the power grid company API interface, the user-side smart meter, and historical data and current environmental parameter analysis; based on the health index and the real-time power demand data, a genetic algorithm is used to dynamically adjust the charging and discharging strategy of each energy storage module to obtain a charging and discharging plan, and the charging and discharging plan is used in combination with deep learning technology to predict the changing trend of power supply and demand within a preset time range to generate a power demand forecast result; based on the power demand forecast result, a mixed integer linear programming algorithm is used to confirm the optimal energy storage module scheduling plan to obtain the scheduling instructions of the energy storage module; the scheduling instructions of the energy storage module are implemented, the decision-making process is continuously optimized through online learning, and the adaptive control strategy of reinforcement learning is used to generate the best control instructions. The technical solution provided by the present invention improves the accuracy of health status assessment, improves the accuracy of power demand forecasting, optimizes the charging and discharging strategy, generates the optimal scheduling plan, and realizes adaptive control, enhances the flexibility and scalability of the system, and ultimately improves the overall operating efficiency and economic benefits;

[0056] Furthermore, by combining the current health status of the energy storage cabin, energy storage capacity, and charging and discharging rate limits, a multi-objective optimization model is constructed to ensure that the scheduling plan is feasible in actual operation and avoid infeasible plans caused by ignoring actual limitations; by generating a variety of preset target scenarios through Monte Carlo simulation and conducting risk assessment, various possible situations can be fully considered to improve the robustness of the scheduling plan, so that it can remain stable and efficient in the face of uncertainty and changes; the mixed integer linear programming algorithm is used to solve the multi-objective optimization model, which can find the optimal balance point between multiple objectives, ensuring that the scheduling plan achieves the best performance while meeting multiple constraints, improving The overall efficiency and economy of the system, and the performance of the scheduling scheme are optimized; the use of hierarchical analysis method to comprehensively evaluate the initial energy storage module scheduling scheme can systematically weigh the importance of various factors, ensure that the final selected scheduling scheme is optimal in all aspects, and improve the scientificity and rationality of decision-making; by comprehensively considering multiple factors and scenarios, the generated scheduling scheme can better cope with various operating conditions and external environmental changes, improve the reliability and stability of the system, and reduce failures and downtime; the optimized scheduling scheme can effectively reduce unnecessary energy waste, extend the service life of energy storage modules, and reduce maintenance and replacement costs, thereby significantly reducing operating costs and improving economic benefits.

[0057] These and other aspects of the present invention will become more apparent from the following description of the embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0059] Figure 1 A flowchart of an operation control method of a modular energy storage cabin provided by an embodiment of the present invention;

[0060] Figure 2 A schematic diagram of the structure of an operation control system of a modular energy storage cabin provided by an embodiment of the present invention;

[0061] Figure 3 A schematic diagram of the structure of a computing device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0062] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0063] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0064] 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0065] Since existing control methods rely on traditional scheduling strategies and simple optimization algorithms, including real-time collection of operating parameters, simple health status assessment, power demand prediction based on historical data, generation of fixed scheduling plans and execution of charging and discharging operations. Although these methods can meet basic needs, they have problems such as inaccurate health status assessment, low power demand prediction accuracy, single scheduling plan and lack of flexibility, and lack of adaptive control capabilities. Based on this, the present invention provides an operation control method for a modular energy storage cabin, such as Figure 1 ,include:

[0066] Step 101: collecting operating parameters of each energy storage module in real time to obtain comprehensive operating data, wherein the operating parameters include: battery temperature, state of charge, internal resistance, voltage, current and external environmental parameters;

[0067] In this step, the key operating parameters of each energy storage module are collected in real time through sensors and monitoring equipment, including battery temperature, state of charge (SOC), internal resistance, voltage, current and external environmental parameters (such as temperature, humidity, etc.);

[0068] The various operating parameters collected are integrated to form comprehensive operating data, which reflects the operating status and external environmental conditions of the energy storage module at the current moment.

[0069] Step 102: Based on the comprehensive operation data, a health status assessment model of the energy storage module is established through a machine learning algorithm to obtain a health index, and real-time power demand data is obtained from the grid company API interface, user-side smart meters, historical data, and current environmental parameter analysis;

[0070] In this step, a health status assessment model is trained based on comprehensive operating data using machine learning algorithms (such as support vector machines, random forests, neural networks, etc.). The model can predict the health status of the energy storage module based on the input operating parameters and generate a health index;

[0071] Real-time power demand data is obtained from the grid company's API interface. At the same time, data analysis is performed based on the data from the user's smart meter, historical data, and current environmental parameters (such as weather forecasts, holiday effects, etc.) to generate real-time power demand data.

[0072] Step 103: Based on the health index and the real-time power demand data, a genetic algorithm is used to dynamically adjust the charge and discharge strategy of each energy storage module to obtain a charge and discharge plan. The charge and discharge plan is used in combination with deep learning technology to predict the power supply and demand change trend within a preset time range to generate a power demand forecast result.

[0073] In this step, based on the health index and real-time power demand data, a genetic algorithm is used to dynamically adjust the charging and discharging strategies of each energy storage module. The genetic algorithm optimizes the charging and discharging strategies by simulating natural selection and genetic mechanisms to achieve the best energy utilization efficiency.

[0074] Generate a specific charging and discharging plan based on the optimized charging and discharging strategy;

[0075] Using deep learning technology (such as recurrent neural network RNN, long short-term memory network LSTM, etc.), the trend of power supply and demand changes within a preset time range is predicted. Combined with the generated charging and discharging plan, a high-precision power demand forecast result is generated.

[0076] Step 104: Based on the power demand forecast result, a mixed integer linear programming algorithm is used to confirm the optimal energy storage module scheduling scheme to obtain a scheduling instruction for the energy storage module;

[0077] In this step, a multi-objective optimization model is constructed based on the power demand forecast results, combined with the current health status of the energy storage cabin, energy storage capacity, and charge and discharge rate limits;

[0078] The mixed integer linear programming algorithm (MI LP) is used to solve the multi-objective optimization model and generate the initial energy storage module scheduling plan. MI LP can find the optimal balance point between multiple objectives to ensure that the scheduling plan achieves the best performance while meeting multiple constraints.

[0079] According to the solution results, specific energy storage module scheduling instructions are generated to guide the charging and discharging operations of the energy storage modules.

[0080] Step 105: Implement the dispatching instructions of the energy storage module, continuously optimize the decision-making process through online learning, and generate the best control instructions using the adaptive control strategy of reinforcement learning;

[0081] In this step, the charging and discharging operations of the energy storage module are executed according to the generated scheduling instructions;

[0082] Through online learning methods (such as recursive neural networks, incremental learning, etc.), actual operation data is continuously collected, model parameters are updated, and the decision-making process is optimized;

[0083] Using the adaptive control strategy of reinforcement learning (such as Ql earning, DQN, etc.), the control strategy is dynamically adjusted according to the real-time operation data and environmental changes to generate the optimal control instructions. Reinforcement learning continuously learns and optimizes the control strategy through interaction with the environment, thereby improving the system's adaptability and overall performance.

[0084] Based on this, the present invention provides a specific embodiment, wherein step 104, based on the power demand forecast result, uses a mixed integer linear programming algorithm to confirm the optimal energy storage module scheduling scheme to obtain the scheduling instructions of the energy storage module, specifically includes the following steps:

[0085] Step 201: Utilizing the power demand forecast results, combined with the current health status of the energy storage cabin, energy storage capacity, and charge and discharge rate limits, a multi-objective optimization model is constructed;

[0086] In this step, the power demand forecast result refers to the high-precision power demand forecast result obtained in step 103; the current health status of the energy storage cabin refers to the health index obtained in step 102; the energy storage capacity refers to the current available capacity of each energy storage module; the charge and discharge rate limit refers to the maximum charge and discharge rate of each energy storage module;

[0087] Define multiple optimization objectives, such as minimizing operating costs, maximizing system stability, minimizing energy storage module losses, etc.; constraints include energy storage capacity limitations, charge and discharge rate limitations, health status limitations, etc.; the model formula refers to converting the above objectives and constraints into mathematical expressions to form a multi-objective optimization model; generate multiple preset target scenarios through Monte Carlo simulation, each scenario represents different operating conditions and external environmental changes; the risk assessment results of the scheduling plan under each scenario refer to calculating the risk value of the scheduling plan under each scenario (such as cost, stability and loss).

[0088] Step 202: using the multi-objective optimization model, generating a variety of preset target scenarios through Monte Carlo simulation, and obtaining scheduling plan risk assessment results under the various scenarios;

[0089] In this step, a variety of possible operation scenarios are generated through random sampling methods. These scenarios take into account different power demand, weather conditions, holiday effects and other factors. Under each scenario, the risk assessment results of the scheduling scheme are calculated according to the multi-objective optimization model.

[0090] Calculate the performance of the scheduling plan in each scenario on different objectives, such as operating costs, system stability, energy storage module losses, etc.; generate a risk assessment report, including the risk value and corresponding scheduling plan for each scenario.

[0091] Step 203: Based on the risk assessment result of the scheduling scheme, a mixed integer linear programming algorithm is used to solve the multi-objective optimization model to generate an initial energy storage module scheduling scheme;

[0092] In this step, based on the risk assessment results in step 202, scenarios with lower risks and better performance are selected as references, and the data of these scenarios are input into the multi-objective optimization model;

[0093] The mixed integer linear programming (MILP) algorithm is used to solve the multi-objective optimization model. The MILP algorithm can handle multiple objectives and complex constraints, find the optimal scheduling plan, and generate the initial energy storage module scheduling plan, including the charging and discharging instructions of each energy storage module at different time points.

[0094] The initial energy storage module scheduling plan includes the charging and discharging plan of each energy storage module and the corresponding control parameters.

[0095] Step 204: using the initial energy storage module scheduling plan, a comprehensive evaluation is performed through the analytic hierarchy process to determine the optimal energy storage module scheduling plan;

[0096] In this step, the analytic hierarchy process (AHP) is used to define evaluation criteria, such as cost, stability, reliability, efficiency, etc. The evaluation criteria are sorted by importance to form a hierarchical structure diagram, and weights are assigned to each criterion through expert scoring or data analysis;

[0097] Evaluate the initial energy storage module scheduling schemes, calculate the scores of each scheme on each criterion, and calculate the comprehensive score of each scheme based on the hierarchy and weights;

[0098] The scheduling plan with the highest comprehensive score is selected as the final optimal energy storage module scheduling plan; the optimal scheduling plan is output, including detailed charging and discharging plans and control instructions.

[0099] Based on this, the present invention provides a specific embodiment, wherein step 203, based on the risk assessment result of the scheduling scheme, uses a mixed integer linear programming algorithm to solve a multi-objective optimization model to generate an initial energy storage module scheduling scheme, specifically comprising the following steps:

[0100] Step 301: Based on the risk assessment result of the scheduling scheme, the physical constraints and operation rules of the energy storage cabin are integrated to obtain a multi-objective optimization model under constraints;

[0101] In this step, physical constraints are integrated to determine the physical constraints of the energy storage cabin, such as the maximum charge and discharge rate, the upper and lower limits of energy storage capacity, and the battery temperature range. These physical constraints are integrated into the optimization model to ensure that the generated scheduling plan is feasible in actual operation.

[0102] Integrate operating rules and determine the operating rules of the energy storage cabin, such as charging and discharging time windows, minimum charging and discharging intervals, and safe operating procedures. Integrate these operating rules into the optimization model to ensure that the scheduling plan meets operating specifications and safety requirements.

[0103] Construct a multi-objective optimization model. After integrating physical constraints and operating rules, a multi-objective optimization model is constructed. The model will consider multiple optimization objectives, such as minimizing costs, maximizing system stability, minimizing energy storage module losses, etc. The model includes all the above constraints to ensure that the generated scheduling plan achieves optimal performance while meeting various constraints.

[0104] Step 302: using the multi-objective optimization model and introducing a time window rolling optimization mechanism, the scheduling scheme is optimized and calculated in stages to obtain a staged scheduling scheme;

[0105] In this step, the entire scheduling cycle is divided into multiple time windows (for example, every hour or every half hour); the scheduling scheme in each time window is optimized independently, while considering the connection between the previous and next time windows;

[0106] In each time window, a multi-objective optimization model is used to perform optimization calculations and generate a scheduling plan for that time period; the time window is gradually advanced, and the scheduling plan is continuously updated and optimized to form a complete phased scheduling plan;

[0107] Through the rolling optimization mechanism, a series of phased scheduling plans are eventually generated, covering the entire scheduling cycle; the scheduling plan for each stage takes into account the actual situation within the current time window and future forecast data to ensure the continuity and feasibility of the scheduling plan.

[0108] Step 303: According to the phased scheduling plan, a mixed integer linear programming algorithm is used to combine the historical operation data and real-time operation status of the energy storage cabin to perform multi-objective optimization and generate a preliminary energy storage module scheduling plan;

[0109] In this step, the historical operation data of the energy storage cabin is collected, including past charging and discharging records, health status, environmental parameters, etc.; the current real-time operation status is obtained, including the current state of charge, battery temperature, external environmental parameters, etc.;

[0110] The mixed integer linear programming (MILP) algorithm is used to further optimize the phased scheduling scheme by combining historical operation data and real-time operation status. The MILP algorithm can handle multiple objectives and complex constraints to find the optimal scheduling scheme.

[0111] Based on the optimization results, a preliminary energy storage module scheduling plan is generated, including the charging and discharging instructions for each energy storage module at different time points; the plan takes into account historical data and real-time status to ensure the feasibility and efficiency of the scheduling plan in actual operation.

[0112] Step 304: Based on the comprehensive operation data, a health status assessment model of the energy storage module is established by a machine learning algorithm to obtain a health status assessment result;

[0113] In this step, comprehensive operating data is collected, including battery temperature, state of charge, internal resistance, voltage, current and external environmental parameters; a health status assessment model is trained using machine learning algorithms (such as support vector machines, random forests, neural networks, etc.), and the training data includes historical operating data and known health status labels; the current comprehensive operating data is input into the trained health status assessment model to obtain the health status assessment results of each energy storage module.

[0114] Step 305: using the preliminary energy storage module scheduling plan in combination with the health status assessment result, the preliminary energy storage module scheduling plan is revised to obtain a revised energy storage module scheduling plan;

[0115] In this step, the preliminary energy storage module scheduling plan is combined with the health status assessment results to revise the scheduling plan. If the health status of some energy storage modules is not good, their charging and discharging loads are reduced, or the charging and discharging strategies of other energy storage modules are adjusted to ensure the stability and reliability of the overall system. After the revision, a revised energy storage module scheduling plan is generated to ensure that the best scheduling effect is achieved while meeting the health status requirements.

[0116] Step 306: using the revised energy storage module scheduling plan, verifying the scheduling plan through simulation technology, adjusting infeasible scheduling instructions, and generating an initial energy storage module scheduling plan;

[0117] In this step, simulation technology (such as MATLAB / Simu link, Python simulation library, etc.) is used to simulate and test the revised energy storage module scheduling plan. During the simulation process, various possible operating conditions and external environmental changes are simulated; during the simulation process, the feasibility of the scheduling plan is checked, and infeasible scheduling instructions are identified and adjusted. For example, if the charge and discharge rate of a certain energy storage module exceeds its physical limit in a certain time period, the charge and discharge plan for that time period needs to be adjusted; after simulation verification and adjustment, the initial energy storage module scheduling plan is generated, which has high feasibility and reliability in actual operation.

[0118] Based on this, the present invention provides a specific embodiment, wherein step 302 utilizes the multi-objective optimization model and introduces a time window rolling optimization mechanism to perform phased optimization calculations on the scheduling scheme to obtain a phased scheduling scheme, specifically including the following steps:

[0119] Step 401: using the multi-objective optimization model, combining the real-time operating status of the energy storage cabin and the power demand forecast result within a preset time, a series of time windows are defined to obtain a time window sequence;

[0120] In this step, the entire time range is divided into a series of time windows according to a preset time range (e.g., 24 hours). Each time window can be fixed (e.g., every hour or every half hour); the current operating status of the energy storage cabin is considered, including battery temperature, state of charge, internal resistance, voltage, current, etc.; the power demand forecast result generated in step 103 is used to provide power demand data for each time window; based on the above information, a series of time windows are defined to form a time window sequence. Each time window has its specific power demand and operating status.

[0121] Step 402: Using the time window sequence, according to the current health status of the energy storage cabin, energy storage capacity, charge and discharge rate limit and external environmental parameters, the scheduling plan in each time window is locally optimized and calculated to obtain the local optimal scheduling plan for each time window;

[0122] In this step, local optimization refers to using a multi-objective optimization model to perform local optimization calculations for each time window; considering the health status refers to combining the current health status of the energy storage cabin to ensure that the scheduling plan does not cause excessive loss to the energy storage module; considering the energy storage capacity refers to ensuring that the scheduling plan in each time window is within the energy storage capacity range; considering the charge and discharge rate limit refers to ensuring that the scheduling plan meets the maximum charge and discharge rate limit of the energy storage module; considering external environmental parameters refers to combining external environmental parameters (such as temperature, humidity, etc.) to ensure the feasibility of the scheduling plan under actual operating conditions; generating a local optimal plan refers to generating a local optimal scheduling plan for each time window through local optimization calculations;

[0123] Among them, the optimal charge and discharge power Optimal_Charge(t) within the time window t is calculated by the following formula:

[0124]

[0125] Among them, Optimal_Charge(t) is the optimal charge and discharge power; P demand (t) is the power demand forecast value within time window t, H(t) is the health status assessment value of the energy storage module within time window t, E(t) is the external environmental parameter within time window t, T(t) is the current temperature within time window t, C(t) is the charging and discharging cost within time window t, D(t) is the grid stability index within time window t, F(t) is the future power demand fluctuation forecast within time window t, and α, β, γ, λ, δ, η, θ, φ are weight coefficients.

[0126] Step 403: using the local optimal scheduling scheme of each time window, performing integration processing to form a phased scheduling scheme covering the entire preset time range;

[0127] In this step, the local optimal scheduling plans of each time window are integrated to form a phased scheduling plan covering the entire preset time range; ensure smooth transition of scheduling plans between adjacent time windows to avoid system instability caused by sudden changes; and finally generate a complete phased scheduling plan covering all time windows to ensure that the scheduling plan within the entire preset time range is coherent and consistent.

[0128] Step 404: using the phased scheduling scheme and combining the historical operation data of the energy storage shelter, predicting the performance change trend of each energy storage module in each time window through a machine learning algorithm, and obtaining a performance prediction result;

[0129] In this step, the historical operation data of the energy storage cabin is collected, including battery temperature, state of charge, internal resistance, voltage, current, etc.; machine learning algorithms (such as random forest, support vector machine, neural network, etc.) are used to predict the performance change trend of each energy storage module in each time window based on the historical operation data and the current phased scheduling plan; the performance prediction results of each energy storage module in different time windows are output, including health status, charging and discharging efficiency, etc.

[0130] Step 405: dynamically adjusting the phased scheduling plan using the performance prediction result to obtain a dynamic phased scheduling plan;

[0131] In this step, the phased scheduling plan is dynamically adjusted according to the performance prediction results. If it is predicted that the performance of some energy storage modules will decline in a certain time window in the future, the scheduling instructions in the time window will be adjusted to reduce the burden on these modules; the adjusted scheduling plan should ensure that the stability and reliability of the system are maintained while meeting the power demand; after dynamic adjustment, a new dynamic phased scheduling plan is generated to ensure that the best scheduling effect can be achieved in each time window.

[0132] Step 406: using the dynamic phased scheduling scheme, combined with the real-time operation data of the energy storage cabin, dynamically adjusting the scheduling instructions through a rolling optimization mechanism, and generating a target phased scheduling scheme;

[0133] In this step, the real-time operation data of the energy storage cabin is continuously collected, including battery temperature, state of charge, internal resistance, voltage, current, etc.; a rolling optimization mechanism is adopted to gradually advance the time window according to the real-time operation data and dynamic phased scheduling plan, and each time window is optimized and adjusted; within each time window, the scheduling instructions are dynamically adjusted according to the latest real-time data to ensure that the scheduling plan is always optimal; after rolling optimization and dynamic adjustment, the final target phased scheduling plan is generated. This plan has high feasibility and reliability in actual operation and can cope with changing operating conditions and power demand.

[0134] Based on this, the present invention provides a specific embodiment, wherein step 303, according to the phased scheduling plan, adopts a mixed integer linear programming algorithm, combines the historical operation data and real-time operation status of the energy storage cabin, performs multi-objective optimization solution, and generates a preliminary energy storage module scheduling plan, which specifically includes the following steps:

[0135] Step 501: Analyze the operating characteristics of the energy storage cabin using the phased scheduling scheme in combination with the historical operating data and real-time operating status of the energy storage cabin to obtain an operating characteristics analysis result;

[0136] In this step, the phased scheduling plan refers to the scheduling plan covering the entire preset time range, which is divided into multiple time windows; the historical operation data refers to the operation records of the energy storage cabin in the past period of time, including battery temperature, state of charge, internal resistance, voltage, current, etc.; the real-time operation status refers to the current operation parameters of the energy storage cabin, reflecting its immediate working status; the operation characteristic analysis results refer to the performance characteristics and behavior patterns of the energy storage cabin under different conditions obtained through data analysis;

[0137] The phased scheduling plan, historical operation data and real-time operation status data are integrated together, and data analysis tools (such as statistical analysis, cluster analysis, etc.) are used to extract the key operating characteristics of the energy storage cabin, such as charging and discharging efficiency, response speed, stability, etc. Based on the above analysis, detailed operation characteristic analysis results are generated to provide a basis for subsequent optimization.

[0138] Step 502: using the operation characteristic analysis result to customize the objective function of the mixed integer linear programming algorithm to obtain a customized multi-objective optimization model;

[0139] In this step, the operation characteristic analysis result refers to the performance characteristics and behavior patterns of the energy storage cabin obtained in step 501; the mixed integer linear programming algorithm refers to an optimization algorithm that can process discrete variables and continuous variables and is suitable for multi-objective optimization problems under complex constraints; the customized multi-objective optimization model refers to an optimization model adjusted according to the actual operation characteristics of the energy storage cabin, which is more in line with actual needs;

[0140] Based on the results of the operating characteristics analysis, redefine the objective function of the optimization model. For example, if the analysis results show that system stability is particularly important during certain time periods, the weight of stability can be increased. According to the operating characteristics, adjust the constraints in the model to ensure that the optimization results are more in line with the actual situation. After customization is completed, build a new multi-objective optimization model and prepare it for solving.

[0141] Step 503: Utilize the customized multi-objective optimization model and the time window in the phased scheduling scheme to perform multi-objective optimization and generate preliminary multi-objective optimization results;

[0142] In this step, the customized multi-objective optimization model refers to the optimization model adjusted according to the operating characteristics of the energy storage cabin; the time window refers to the time period divided in the phased scheduling plan; the preliminary multi-objective optimization result refers to the preliminary scheduling plan obtained after the optimization calculation; phased optimization: for each time window, a customized multi-objective optimization model is used to perform local optimization calculations.

[0143] The optimization results of each time window are summarized to form a preliminary multi-objective optimization result covering the entire preset time range, and a preliminary multi-objective optimization result is generated as the basis for subsequent refinement.

[0144] Step 504: using the preliminary multi-objective optimization result and combining it with the health status assessment result of the energy storage cabin, the optimization result is refined to obtain a refined multi-objective optimization result;

[0145] In this step, the preliminary multi-objective optimization result refers to the preliminary scheduling plan generated in step 503; the health status assessment result refers to the health status information of the energy storage module obtained by the machine learning algorithm; the refined multi-objective optimization result refers to the detailed optimization result after considering the health status;

[0146] Combine the preliminary multi-objective optimization results with the health status assessment results to ensure that the scheduling plan does not place excessive burden on modules with poor health status. According to the health status assessment results, correct the preliminary multi-objective optimization results, adjust the charging and discharging strategies of each energy storage module, and generate refined multi-objective optimization results to ensure that the best scheduling effect is achieved while meeting the health status requirements.

[0147] Step 505: Based on the refined multi-objective optimization result, a plurality of preliminary scheduling schemes are comprehensively evaluated by using a hierarchical analysis method to obtain an evaluated preliminary scheduling scheme;

[0148] In this step, the refined multi-objective optimization result refers to the detailed optimization result generated in step 504; the analytic hierarchy process refers to a decision analysis method that constructs a hierarchical structure, ranks the importance of multiple criteria, and finally determines the optimal solution; the evaluated preliminary scheduling solution refers to the best scheduling solution selected after comprehensive evaluation;

[0149] Define evaluation criteria, such as cost, stability, reliability, efficiency, etc., and sort them by importance to form a hierarchical diagram. Comprehensively evaluate multiple preliminary scheduling plans, calculate the score of each plan on each criterion, and select the scheduling plan with the highest comprehensive score as the preliminary scheduling plan after evaluation based on the hierarchy and weight.

[0150] Step 506: Using the evaluated preliminary scheduling plan and combining it with the real-time operation data of the energy storage cabin, a dynamic adjustment is performed to generate a preliminary energy storage module scheduling plan;

[0151] In this step, the evaluated preliminary scheduling plan refers to the best scheduling plan selected in step 505; the real-time operation data refers to the current operation parameters of the energy storage cabin; the preliminary energy storage module scheduling plan refers to the finally generated scheduling instructions;

[0152] Continuously collect real-time operating data of the energy storage cabin, including battery temperature, state of charge, internal resistance, voltage, current, etc., and dynamically adjust the initial scheduling plan after evaluation based on the real-time operating data to ensure that the scheduling plan is always optimal. After dynamic adjustment, generate a preliminary energy storage module scheduling plan to guide the specific charging and discharging operations of the energy storage module.

[0153] The embodiments of the present invention improve the operating efficiency, reliability and economy of the energy storage cabin through the above steps, which not only solves the defects in the prior art, but also provides an effective solution for the intelligent management of the energy storage system, and promotes the effective use of renewable energy and the sustainable development of the power system.

[0154] Based on this, the present invention provides a specific embodiment, wherein the step 103, based on the health index and the real-time power demand data, uses a genetic algorithm to dynamically adjust the charge and discharge strategy of each energy storage module to obtain a charge and discharge plan, and uses the charge and discharge plan in combination with deep learning technology to predict the power supply and demand change trend within a preset time range to generate a power demand forecast result, specifically including the following steps:

[0155] Step 601: using the health index and the real-time power demand data, dynamically adjusting the charging and discharging strategies of each energy storage module through a genetic algorithm to obtain a preliminary charging and discharging plan;

[0156] In this step, the health index of the energy storage module is first combined with the real-time power demand data obtained from the grid company API interface, the user-side smart meter, and the historical data and current environmental parameter analysis. Then, the genetic algorithm (GA) is used to dynamically adjust the charging and discharging strategies of each energy storage module. The genetic algorithm optimizes the charging and discharging strategy to achieve the best energy utilization efficiency by simulating natural selection and genetic mechanisms. According to the optimized charging and discharging strategy, a specific charging and discharging plan is generated as a preliminary charging and discharging plan.

[0157] Step 602: using the preliminary charging and discharging plan, combined with the real-time operating status and historical operating data of the energy storage shelter, and using deep learning technology to predict the changing trend of power supply and demand within a preset time range, a preliminary power demand forecast result is obtained;

[0158] In this step, based on the preliminary charging and discharging plan, combined with the real-time operating status of the energy storage cabin (such as battery temperature, state of charge, internal resistance, voltage, current, etc.) and historical operating data, deep learning technology (such as long short-term memory network LSTM) is used to predict the changing trend of power supply and demand within a preset time range. The deep learning model can capture the complex changing trend of power demand, combine the charging and discharging plan, historical data and current environmental parameters, and generate high-precision preliminary power demand forecast results.

[0159] Step 603: optimizing the preliminary charging and discharging plan using the preliminary power demand forecast result to obtain an optimized charging and discharging plan;

[0160] In this step, the preliminary charging and discharging plan is further optimized based on the preliminary power demand forecast results. By introducing a multi-objective optimization method, the power demand forecast, energy storage capacity limit, charging and discharging rate limit, and health status are comprehensively considered to adjust the details of the charging and discharging plan to ensure that the scheduling plan is more reasonable and efficient. After this round of optimization, an optimized charging and discharging plan is generated, which improves the feasibility and adaptability of the plan.

[0161] Step 604: using the optimized charging and discharging plan, again predicting the power supply and demand change trend within a preset time range through deep learning technology to generate a target power demand prediction result;

[0162] In this step, based on the optimized charging and discharging plan, deep learning technology is used again to predict the changing trend of power supply and demand within the preset time range. This prediction not only refers to the latest charging and discharging plan, but also combines more accurate power demand forecast results, further improving the accuracy and reliability of the prediction, and finally generating the target power demand forecast results.

[0163] The embodiments of the present invention improve the operating efficiency, stability and economy of the modular energy storage cabin through the above steps.

[0164] Based on this, the present invention provides a specific embodiment, wherein the step 105 implements the dispatching instructions of the energy storage module, continuously optimizes the decision-making process through online learning, and generates the optimal control instructions using the adaptive control strategy of reinforcement learning, which specifically includes the following steps:

[0165] Step 701: using the scheduling instruction of the energy storage module to start the charging and discharging operation of the energy storage cabin, and at the same time collecting the real-time operation data of the energy storage cabin during the execution of the scheduling instruction to obtain real-time operation feedback data;

[0166] In this step, the charging and discharging operations of the energy storage cabin are started according to the optimized control instructions generated in the previous step. The system will monitor and record various operating parameters of the energy storage cabin during the execution of these scheduling instructions, including battery temperature, state of charge (SOC), internal resistance, voltage, current, etc., as well as external environmental parameters such as temperature and humidity. These data will be integrated into real-time operation feedback data for subsequent evaluation and optimization.

[0167] Step 702: Based on the real-time operation feedback data and the historical operation data of the energy storage cabin, the current decision-making process is evaluated through an online learning algorithm to obtain a decision evaluation result;

[0168] In this step, the online learning algorithm is used to comprehensively evaluate the current decision-making process based on the real-time operation feedback data and the historical operation data of the energy storage cabin. The online learning algorithm can continuously update the model parameters to ensure that the evaluation results reflect the latest operating conditions. The evaluation content includes the execution effect of the dispatch instruction, the response speed of the system, energy consumption, etc., and finally generates the decision evaluation results to provide a basis for the next step of optimization.

[0169] Step 703: using the decision evaluation results, designing a reinforcement learning environment, defining a reward function, and constructing a reinforcement learning model; and training the reinforcement learning model by simulating different charging and discharging strategies and energy storage module scheduling schemes to obtain an enhanced reinforcement learning model;

[0170] In this step, first, based on the decision evaluation results, a reinforcement learning environment suitable for the operating characteristics of the energy storage cabin is designed. Various possible states, actions, and reward functions are defined in this environment, where the reward function is designed to encourage the system to adopt a more efficient and stable charging and discharging strategy. Then, a reinforcement learning model is constructed, such as a deep Q network (DQN) or a policy gradient method. By simulating different charging and discharging strategies and energy storage module scheduling schemes, the model is trained to enable it to make optimal decisions in a complex and changing environment. After sufficient training, an enhanced reinforcement learning model is generated with stronger learning and adaptability.

[0171] Step 704: optimizing the control instructions of the energy storage module using the enhanced reinforcement learning model to generate new control instructions to obtain optimized control instructions;

[0172] In this step, the enhanced reinforcement learning model is used to optimize the existing control instructions. The model predicts the effects of different control instructions based on the current real-time operating status and historical data, and selects the optimal control instructions. These optimized control instructions not only take into account the current power demand and health status, but also take into account the long-term operating efficiency and stability, thereby generating more intelligent and efficient control instructions.

[0173] Step 705: using the optimized control instructions, combined with the real-time operating status and environmental parameters of the energy storage cabin, dynamically adjusting the charging and discharging strategy to generate the optimal control instructions;

[0174] In this step, the optimized control instructions are combined with the real-time operating status and environmental parameters of the energy storage cabin for dynamic adjustment. Through this dynamic adjustment mechanism, it is ensured that each charging and discharging operation is optimized, which not only meets the immediate power demand, but also takes into account the long-term system health and economic benefits. The optimal control instructions finally generated will guide the operation of the energy storage cabin in the future, ensuring its efficient and stable operation.

[0175] Through continuous optimization and dynamic adjustment, the energy storage cabin in the embodiments of the present invention can better cope with emergencies and changing needs.

[0176] Figure 2 A schematic diagram of the structure of an operation control system of a modular energy storage cabin is provided for an embodiment of the present application, such as Figure 2 As shown, the system includes:

[0177] The acquisition module 21 is used to collect the operating parameters of each energy storage module in real time to obtain comprehensive operating data, wherein the operating parameters include: battery temperature, state of charge, internal resistance, voltage, current and external environmental parameters;

[0178] A construction module 22 is used to construct a health status assessment model of the energy storage module based on the comprehensive operation data through a machine learning algorithm to obtain a health index, and at the same time obtain real-time power demand data from the grid company API interface, the user-side smart meter, and historical data and current environmental parameter analysis;

[0179] The prediction module 23 is used to dynamically adjust the charging and discharging strategies of each energy storage module based on the health index and real-time power demand data by using a genetic algorithm to obtain a charging and discharging plan, and to use the charging and discharging plan in combination with deep learning technology to predict the power supply and demand change trend within a preset time range to generate a power demand prediction result;

[0180] A confirmation module 24 is used to confirm the optimal energy storage module scheduling scheme based on the power demand forecast result by using a mixed integer linear programming algorithm to obtain a scheduling instruction for the energy storage module;

[0181] The optimization module 25 is used to implement the dispatching instructions of the energy storage module, optimize the decision-making process through online learning, and generate the best control instructions using the adaptive control strategy of reinforcement learning.

[0182] Figure 2 The operation control system of the modular energy storage cabin can execute Figure 1 The implementation principle and technical effect of the operation control method of a modular energy storage cabin described in the embodiment shown will not be repeated. The specific way in which each module and unit performs operations in the operation control system of a modular energy storage cabin in the above embodiment has been described in detail in the embodiment of the method, and will not be elaborated here.

[0183] Figure 2 The operation control system of a modular energy storage cabin of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0184] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0185] The processing component 32 is used to collect the operating parameters of each energy storage module in real time to obtain comprehensive operating data, wherein the operating parameters include: battery temperature, state of charge, internal resistance, voltage, current and external environmental parameters;

[0186] Based on the comprehensive operation data, a health status assessment model for the energy storage module is established through a machine learning algorithm to obtain a health index, and real-time power demand data is obtained from the grid company API interface, user-side smart meters, historical data, and current environmental parameter analysis;

[0187] Based on the health index and the real-time power demand data, a genetic algorithm is used to dynamically adjust the charging and discharging strategies of each energy storage module to obtain a charging and discharging plan. The charging and discharging plan is used in combination with deep learning technology to predict the changing trend of power supply and demand within a preset time range to generate a power demand forecast result;

[0188] Based on the power demand forecast result, a mixed integer linear programming algorithm is used to confirm the optimal energy storage module scheduling scheme to obtain a scheduling instruction for the energy storage module;

[0189] The dispatching instructions of the energy storage module are implemented, the decision-making process is continuously optimized through online learning, and the adaptive control strategy of reinforcement learning is used to generate the optimal control instructions.

[0190] The processing component 32 includes one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be implemented by one or more application-specific integrated circuits (AICs), digital signal processors (DPs), digital signal processing devices (DPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0191] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (RAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0192] Computing devices also include other components, such as input / output interfaces, display components, and communication components.

[0193] The input / output interface provides an interface between the processing component and the peripheral interface module, and the above-mentioned peripheral interface module can be an output device or an input device.

[0194] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0195] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0196] The embodiment of the present invention further provides a computer storage medium storing a computer program, which can achieve the above-mentioned Figure 1 An operation control method and system of a modular energy storage cabin in the illustrated embodiment.

[0197] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0198] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0199] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution 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 ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0200] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for controlling the operation of a modular energy storage shelter, characterized in that: include: Collect the operating parameters of each energy storage module in real time to obtain comprehensive operating data, wherein the operating parameters include: battery temperature, state of charge, internal resistance, voltage, current and external environmental parameters; Based on the comprehensive operation data, a health status assessment model for the energy storage module is established through a machine learning algorithm to obtain a health index, and real-time power demand data is obtained from the grid company API interface, user-side smart meters, historical data, and current environmental parameter analysis; Based on the health index and the real-time power demand data, a genetic algorithm is used to dynamically adjust the charging and discharging strategies of each energy storage module to obtain a charging and discharging plan. The charging and discharging plan is used in combination with deep learning technology to predict the changing trend of power supply and demand within a preset time range to generate a power demand forecast result; Based on the power demand forecast result, a mixed integer linear programming algorithm is used to confirm the optimal energy storage module scheduling scheme to obtain a scheduling instruction for the energy storage module; The dispatching instructions of the energy storage module are implemented, the decision-making process is continuously optimized through online learning, and the adaptive control strategy of reinforcement learning is used to generate the optimal control instructions.

2. The method according to claim 1, characterized in that Based on the power demand forecast result, a mixed integer linear programming algorithm is used to confirm the optimal energy storage module scheduling scheme, and a scheduling instruction of the energy storage module is obtained, including: Using the power demand forecast results, combined with the current health status of the energy storage cabin, energy storage capacity, and charge and discharge rate limits, a multi-objective optimization model is constructed; Using the multi-objective optimization model, a variety of preset target scenarios are generated through Monte Carlo simulation to obtain scheduling plan risk assessment results under various scenarios; Based on the risk assessment results of the scheduling scheme, a mixed integer linear programming algorithm is used to solve the multi-objective optimization model to generate an initial energy storage module scheduling scheme; The initial energy storage module scheduling scheme is used to conduct a comprehensive evaluation through the analytic hierarchy process to determine the optimal energy storage module scheduling scheme.

3. The method according to claim 2, characterized in that Based on the risk assessment results of the scheduling scheme, a mixed integer linear programming algorithm is used to solve the multi-objective optimization model to generate an initial energy storage module scheduling scheme, including: Based on the risk assessment results of the scheduling scheme, the physical constraints and operation rules of the energy storage cabin are integrated to obtain a multi-objective optimization model under constraints; By using the multi-objective optimization model and introducing a time window rolling optimization mechanism, the scheduling plan is optimized and calculated in stages to obtain a staged scheduling plan; According to the phased scheduling plan, a mixed integer linear programming algorithm is used to combine the historical operation data and real-time operation status of the energy storage cabin to perform multi-objective optimization and generate a preliminary energy storage module scheduling plan; Based on comprehensive operating data, a health status assessment model for energy storage modules is established through machine learning algorithms to obtain health status assessment results; Using the preliminary energy storage module scheduling plan in combination with the health status assessment result, the preliminary energy storage module scheduling plan is revised to obtain a revised energy storage module scheduling plan; The revised energy storage module scheduling plan is used to verify the scheduling plan through simulation technology, adjust infeasible scheduling instructions, and generate an initial energy storage module scheduling plan.

4. The method according to claim 3, characterized in that By using the multi-objective optimization model and introducing a time window rolling optimization mechanism, the scheduling scheme is optimized and calculated in stages to obtain a staged scheduling scheme, including: Using the multi-objective optimization model, combined with the real-time operating status of the energy storage cabin and the power demand forecast results within a preset time, a series of time windows are defined to obtain a time window sequence; Using the time window sequence, the scheduling plan within each time window is locally optimized according to the current health status of the energy storage cabin, energy storage capacity, charge and discharge rate limit and external environmental parameters to obtain the local optimal scheduling plan for each time window.

5. The method according to claim 3, characterized in that: According to the phased scheduling plan, a mixed integer linear programming algorithm is used to combine the historical operation data and real-time operation status of the energy storage cabin to perform multi-objective optimization and generate a preliminary energy storage module scheduling plan, including: Utilizing the phased scheduling scheme, combined with the historical operation data and real-time operation status of the energy storage cabin, the operation characteristics of the energy storage cabin are analyzed to obtain the operation characteristics analysis results; Using the operation characteristic analysis results, a customized design of the objective function of the mixed integer linear programming algorithm is performed to obtain a customized multi-objective optimization model; Using the customized multi-objective optimization model, combined with the time window in the phased scheduling plan, multi-objective optimization is solved to generate preliminary multi-objective optimization results; Using the preliminary multi-objective optimization results and combining them with the health status assessment results of the energy storage cabin, the optimization results are refined to obtain a refined multi-objective optimization result; Based on the refined multi-objective optimization results, a plurality of preliminary scheduling schemes are comprehensively evaluated by using a hierarchical analysis method to obtain a preliminary scheduling scheme after evaluation; The evaluated preliminary scheduling plan is used in combination with the real-time operation data of the energy storage cabin to perform dynamic adjustments and generate a preliminary energy storage module scheduling plan.

6. The method according to claim 1, characterized in that Based on the health index and the real-time power demand data, a genetic algorithm is used to dynamically adjust the charging and discharging strategies of each energy storage module to obtain a charging and discharging plan. The charging and discharging plan is used in combination with deep learning technology to predict the power supply and demand change trend within a preset time range to generate a power demand forecast result, including: Using the health index and the real-time power demand data, dynamically adjusting the charging and discharging strategies of each energy storage module through a genetic algorithm to obtain a preliminary charging and discharging plan; Using the preliminary charging and discharging plan, combined with the real-time operating status and historical operating data of the energy storage shelter, the power supply and demand change trend within a preset time range is predicted through deep learning technology to obtain preliminary power demand forecast results; Utilizing the preliminary power demand forecast result, optimizing the preliminary charging and discharging plan to obtain an optimized charging and discharging plan; Utilizing the optimized charging and discharging plan, the changing trend of electricity supply and demand within a preset time range is predicted again through deep learning technology to generate a target electricity demand forecast result.

7. The method according to claim 1, characterized in that Implement the dispatching instructions of the energy storage module, continuously optimize the decision-making process through online learning, and use the adaptive control strategy of reinforcement learning to generate the best control instructions, including: Using the dispatching instruction of the energy storage module to start the charging and discharging operation of the energy storage cabin, and at the same time collecting the real-time operation data of the energy storage cabin during the execution of the dispatching instruction to obtain real-time operation feedback data; Based on the real-time operation feedback data and the historical operation data of the energy storage cabin, the current decision-making process is evaluated through an online learning algorithm to obtain a decision evaluation result; Using the decision evaluation results, a reinforcement learning environment is designed, a reward function is defined, and a reinforcement learning model is constructed. Meanwhile, the reinforcement learning model is trained by simulating different charging and discharging strategies and energy storage module scheduling schemes to obtain an enhanced reinforcement learning model. The enhanced reinforcement learning model is used to optimize the control instructions of the energy storage module, generate new control instructions, and obtain optimized control instructions; By utilizing the optimized control instructions and combining the real-time operating status and environmental parameters of the energy storage cabin, the charging and discharging strategy is dynamically adjusted to generate the optimal control instructions.

8. An operation control system of a modular energy storage cabin, characterized in that: include: The acquisition module is used to collect the operating parameters of each energy storage module in real time to obtain comprehensive operating data, wherein the operating parameters include: battery temperature, state of charge, internal resistance, voltage, current and external environmental parameters; A construction module is used to build a health status assessment model for energy storage modules based on comprehensive operation data through machine learning algorithms to obtain a health index. At the same time, it obtains real-time power demand data from the grid company API interface, user-side smart meters, historical data, and current environmental parameter analysis; A prediction module is used to dynamically adjust the charging and discharging strategies of each energy storage module based on the health index and real-time power demand data by using a genetic algorithm to obtain a charging and discharging plan. The charging and discharging plan is used in combination with deep learning technology to predict the changing trend of power supply and demand within a preset time range to generate a power demand prediction result; A confirmation module, used to confirm the optimal energy storage module scheduling scheme based on the power demand forecast result by using a mixed integer linear programming algorithm to obtain a scheduling instruction for the energy storage module; The optimization module is used to implement the dispatching instructions of the energy storage module, optimize the decision-making process through online learning, and generate the best control instructions using the adaptive control strategy of reinforcement learning.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement an operation control method of a modular energy storage cabin as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, an operation control method of a modular energy storage cabin as described in any one of claims 1 to 7 is implemented.

Images