Energy storage regulation method and device for multiple energy storage systems, electronic equipment and storage medium

Abstract

This application relates to the field of power system technology and discloses an energy storage control method, device, electronic equipment, and storage medium for a multi-energy storage system. The energy storage control method provided in this application improves the overall energy storage efficiency and collaborative performance of the energy storage system by dynamically monitoring energy storage efficiency, identifying subsystems to be optimized and auxiliary subsystems, and performing simulations based on parameters of efficient subsystems and adjusting parameter settings.

Description

Technical Field

[0001] This application relates to the field of power system technology, specifically to energy storage control methods, devices, electronic equipment, and storage media for multi-energy storage systems. Background Technology

[0002] With the large-scale application of renewable energy sources such as photovoltaic and wind power in the power grid, their inherent intermittency, volatility, and unpredictability pose significant challenges to the stable operation of the power system. The power grid needs flexible resources with rapid response to balance supply and demand fluctuations, and energy storage systems, as core equipment for smoothing out fluctuations in renewable energy output and optimizing load curves, are becoming increasingly important.

[0003] However, due to limitations in physical and chemical properties, single-type energy storage technologies have significant shortcomings in energy density, response speed, cycle life, and cost-effectiveness, making it difficult to independently cope with complex and ever-changing grid operation scenarios. Furthermore, multi-energy storage systems lack a unified and coordinated control mechanism. Summary of the Invention

[0004] This application provides an energy storage regulation method, device, electronic equipment, and storage medium for an energy storage system, which improves the overall energy storage efficiency and synergistic performance of the energy storage system.

[0005] Firstly, this application provides an energy storage regulation method for a multi-energy storage system, applied to a multi-energy storage system management platform. The method includes: monitoring the energy storage efficiency of each energy storage subsystem in the multi-energy storage system, and determining the energy storage subsystem to be optimized and the auxiliary energy storage subsystem based on the energy storage efficiency, wherein the energy storage efficiency of the auxiliary energy storage subsystem is higher than that of the energy storage subsystem to be optimized; performing energy storage efficiency simulation on the energy storage subsystem to be optimized based on the energy storage setting parameter set of the auxiliary energy storage subsystem, and obtaining simulation results; and setting energy storage parameters for the multi-energy storage system based on the simulation results.

[0006] Based on the above technical means, by dynamically monitoring the energy storage efficiency of each energy storage subsystem in a multi-energy storage system, accurately identifying the subsystem to be optimized, and using the parameters of the efficient auxiliary subsystem for simulation optimization, intelligent and dynamic adjustment of the operating parameters of the multi-energy storage system is realized.

[0007] In an optional implementation, before monitoring the energy storage efficiency of each energy storage subsystem in a multi-energy storage system, the method further includes: determining an energy storage setting parameter group based on the usage scenario of the multi-energy storage system, wherein the energy storage setting parameter group includes multiple energy storage setting parameter sets, and the energy storage setting parameter group is stored in an energy storage setting parameter library; selecting an energy storage setting parameter set whose usage frequency meets preset conditions from the energy storage setting parameter group as the target energy storage setting parameter set of the multi-energy storage system; determining the target energy storage parameters in the target energy storage setting parameter set that are associated with energy storage demand, and optimizing the target energy storage parameters to obtain an optimized energy storage setting parameter set; and storing the optimized energy storage setting parameter set in the corresponding energy storage setting parameter group in the energy storage setting parameter library.

[0008] Based on the above technical means, the problem of fixed parameters and lack of dynamic adjustment in traditional multi-energy storage systems has been solved, enabling the system to flexibly adapt and optimize according to complex and ever-changing usage scenarios and energy storage needs. This significantly improves the overall energy storage efficiency and operating performance of multi-energy storage systems and fully leverages the synergistic advantages of multi-energy storage system integration.

[0009] In one optional implementation, target energy storage parameters associated with energy storage demand are determined from the target energy storage setting parameter set, and the target energy storage parameters are optimized to obtain an optimized energy storage setting parameter set. This includes: analyzing the energy storage demand to obtain a quantified energy storage target; and adjusting the target energy storage parameters associated with the quantified energy storage target using a multi-objective optimization algorithm based on the energy storage dynamic model of the energy storage subsystem and the quantified energy storage target to obtain the optimized energy storage setting parameter set.

[0010] Based on the aforementioned technical means, by analyzing energy storage demand into precise quantitative energy storage targets, a clear numerical basis is provided for the optimization process, avoiding biases caused by subjective judgment.

[0011] In one optional implementation, obtaining the energy storage dynamic model of the energy storage subsystem includes: establishing an initial dynamic model of the energy storage devices based on the characteristic evaluation results of each energy storage device in the energy storage subsystem. The characteristic evaluation results include rated power, rated capacity, charge / discharge efficiency, and response time. The initial dynamic model is used to characterize the charge / discharge curves and the relationship between energy conversion efficiency and time of the energy storage devices. The initial dynamic model includes: ,in, Let represent the charging and discharging efficiency of the i-th energy storage device at time t. This indicates the initial charge / discharge efficiency. This represents the decay coefficient of charge / discharge efficiency over time. This represents the natural degradation of the charging and discharging efficiency of the i-th energy storage device due to accumulated operating time. Indicates the power deviation influence coefficient. This represents the actual power of the i-th energy storage device at time t. This represents the rated power of the i-th energy storage device. Indicates the temperature deviation coefficient. This represents the actual temperature of the i-th energy storage device at time t. The standard operating temperature of the i-th energy storage device is represented. The initial dynamic models of each energy storage device in the energy storage subsystem are integrated to obtain the energy storage dynamic model of the energy storage subsystem. The energy storage dynamic model is used to characterize the charging and discharging timing matching rules, power allocation ratio and energy complementarity strategy between the initial dynamic model and the corresponding energy storage devices.

[0012] Based on the above technical means, by constructing an accurate dynamic energy storage model, the problem of low efficiency caused by inaccurate models in the process of optimizing energy storage parameters is effectively solved.

[0013] In one optional implementation, based on the energy storage dynamic model and quantified energy storage target of the energy storage subsystem, a multi-objective optimization algorithm is used to adjust the target energy storage parameters associated with the quantified energy storage target to obtain an optimized energy storage setting parameter set. This includes: acquiring operational data of the energy storage subsystem, wherein the operational data includes external environmental dynamic data of the energy storage subsystem, health status data of the energy storage devices in the energy storage subsystem, and historical energy storage control data of the energy storage subsystem. External environmental dynamic data includes grid load fluctuations, new energy output forecasts, and real-time electricity price signals. Device health status data includes the remaining lifespan, degradation rate, and preset component operating temperatures of the energy storage devices. Historical energy storage control data includes... The system establishes a mapping relationship between energy storage setting parameters and energy storage efficiency under different scenarios, and records anomaly handling. It normalizes external environmental dynamic data, health status data, and historical energy storage regulation data to obtain normalized data. Based on an unsupervised linear dimensionality reduction algorithm, features are extracted from the normalized data to construct a multi-dimensional correlation model. This model characterizes the correlation between the energy storage subsystem and the environmental, health, and efficiency dimensions. Based on the output of the multi-dimensional correlation model and the quantified energy storage target, a neural network model is used to allocate weights to the multi-objective optimization algorithm, resulting in an optimized energy storage setting parameter set. The output includes an energy storage efficiency prediction curve and parameter sensitivity coefficients.

[0014] Based on the aforementioned technical means, by acquiring multi-dimensional operational data such as dynamic data of the external environment of the energy storage subsystem, health status data of the energy storage equipment, and historical energy storage regulation data, this application can comprehensively capture various factors affecting the performance of the energy storage system, providing rich and realistic input for optimization decisions.

[0015] In one optional implementation, based on the energy storage setting parameter set of the auxiliary energy storage subsystem, energy storage efficiency simulation is performed on the energy storage subsystem to be optimized to obtain simulation results. This includes: verifying the compatibility between the energy storage setting parameter set and the energy storage subsystem to be optimized; when the compatibility meets preset compatibility conditions, applying the energy storage setting parameter set of the auxiliary energy storage subsystem to the energy storage subsystem to be optimized, and adjusting the parameters in the energy storage setting parameter set within a preset range to determine the optimal energy storage efficiency of the energy storage subsystem to be optimized; when applying the energy storage setting parameter set corresponding to the optimal energy storage efficiency to multiple energy storage systems, if the energy storage efficiency of the multiple energy storage systems improves, then the energy storage setting parameter set corresponding to the optimal energy storage efficiency is used as the simulation result; if the energy storage efficiency of the multiple energy storage systems does not improve, then the current energy storage setting parameter set is used as the simulation result.

[0016] Based on the above technical means, it is ensured that local optimization can truly contribute to the improvement of the overall energy storage efficiency of the multi-energy storage system, avoiding ineffective or negative adjustments, thereby significantly improving the accuracy and effectiveness of the collaborative optimization of the multi-energy storage system.

[0017] In one optional implementation, the set of energy storage setting parameters corresponding to the optimal energy storage efficiency is stored in the energy storage setting parameter group corresponding to the energy storage setting parameter library.

[0018] Based on the above-mentioned technical means, the overall operating efficiency and intelligence level of the multi-energy storage system management platform have been effectively improved, enabling it to respond to grid demands and system changes more quickly and accurately.

[0019] Secondly, this application provides an energy storage control device for a multi-energy storage system. The device includes: a monitoring module for monitoring the energy storage efficiency of each energy storage subsystem in the multi-energy storage system, and determining the energy storage subsystem to be optimized and the auxiliary energy storage subsystem based on the energy storage efficiency, wherein the energy storage efficiency of the auxiliary energy storage subsystem is higher than that of the energy storage subsystem to be optimized; a simulation module for performing energy storage efficiency simulation on the energy storage subsystem to be optimized based on the energy storage setting parameter set of the auxiliary energy storage subsystem, and obtaining simulation results; and a setting module for setting energy storage parameters for the multi-energy storage system based on the simulation results.

[0020] Thirdly, this application provides an electronic device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the energy storage control method of the multi-energy storage system described in the first aspect or any corresponding embodiment.

[0021] Fourthly, this application provides a computer-readable storage medium storing computer instructions, which are used to cause a computer to execute the energy storage control method of the multi-energy storage system described in the first aspect or any corresponding embodiment.

[0022] Fifthly, this application provides a computer program product, including computer instructions, which are used to cause a computer to execute the energy storage control method of the multi-energy storage system described in the first aspect or any corresponding embodiment. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0024] Figure 1 This is a schematic flowchart of the first type of energy storage regulation method according to an embodiment of this application; Figure 2 This is a schematic diagram of a second process of the energy storage regulation method according to an embodiment of this application; Figure 3 This is a schematic diagram of the third process of the energy storage regulation method according to the embodiments of this application; Figure 4 This is a schematic diagram of the fourth process of the energy storage regulation method according to the embodiments of this application; Figure 5 This is a structural block diagram of an energy storage and regulation device according to an embodiment of this application; Figure 6 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0025] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0026] It is understood that before using the technical solutions disclosed in the various embodiments of this application, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this application in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0027] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0028] In related technologies, when multiple energy storage systems are integrated, the lack of a unified management architecture and collaborative control mechanism leads to each energy storage subsystem operating independently with fixed operating parameters that fail to dynamically adjust to actual operating conditions. Consequently, under complex and variable energy demand and grid conditions, this significantly limits the overall energy storage efficiency of integrated multiple energy storage systems, preventing the full realization of their synergistic advantages.

[0029] To address this issue, this application proposes an energy storage regulation method for multi-energy storage systems, applied to a multi-energy storage system management platform. The multi-energy storage system management platform refers to a software and hardware system integrating data acquisition, status monitoring, operation control, and optimized scheduling functions, used for unified management and coordinated regulation of various energy storage subsystems within a multi-energy storage system. For example... Figure 1 As shown, the energy storage regulation methods for multi-energy storage systems include: Step S101: Monitor the energy storage efficiency of each energy storage subsystem in the multi-energy storage system, and determine the energy storage subsystem to be optimized and the auxiliary energy storage subsystem based on the energy storage efficiency, wherein the energy storage efficiency of the auxiliary energy storage subsystem is higher than that of the energy storage subsystem to be optimized.

[0030] Among them, multi-energy storage system refers to a system that integrates two or more different types or sizes of energy storage devices, such as battery energy storage, flywheel energy storage, supercapacitor energy storage, etc. The purpose is to comprehensively utilize the advantages of different energy storage technologies to meet complex energy demands.

[0031] An energy storage subsystem refers to an independently operating or independently manageable energy storage unit within a multi-energy storage system. It can be a single energy storage device or a cluster of similar energy storage devices.

[0032] Energy storage efficiency refers to the ratio of output energy to input energy in an energy storage subsystem during a complete charge-discharge cycle. It is used to measure the energy conversion and storage performance of energy storage devices or systems.

[0033] An energy storage subsystem to be optimized refers to an energy storage subsystem in a multi-energy storage system whose energy storage efficiency is lower than that of other subsystems, and which requires parameter adjustment or operation strategy optimization.

[0034] An auxiliary energy storage subsystem refers to an energy storage subsystem in a multi-energy storage system whose energy storage efficiency is higher than that of the energy storage subsystem to be optimized. Its energy storage setting parameter set can be used as a reference or benchmark for simulating and optimizing the energy storage subsystem to be optimized.

[0035] Specifically, the energy storage efficiency of each energy storage subsystem in a multi-energy storage system is monitored. This monitoring process can be achieved in several ways. For example, input and output energy data for each energy storage subsystem can be collected periodically or in real time, and then the current energy storage efficiency can be obtained by calculating the energy ratio. Specifically, energy metering devices, such as smart meters or power sensors, can be deployed along the charging and discharging paths of the energy storage subsystems to continuously record the electricity data during the charging and discharging process, and efficiency calculations can be performed according to a preset time period. Another approach is to analyze the historical operating data of the energy storage subsystems, combined with their design parameters and aging models, to estimate their energy storage efficiency under current operating conditions. After obtaining the energy storage efficiency of each subsystem, these efficiency values ​​are compared to identify subsystems with relatively low energy storage efficiency as those to be optimized, while subsystems with relatively high energy storage efficiency are identified as auxiliary energy storage subsystems. For example, in a multi-energy storage system containing three energy storage subsystems A, B, and C, if the efficiency of subsystem A is monitored to be 85%, the efficiency of subsystem B is 92%, and the efficiency of subsystem C is 88%, then subsystem A is identified as the energy storage subsystem to be optimized, while subsystem B or C, or both, can be identified as auxiliary energy storage subsystems.

[0036] Step S102: Based on the energy storage setting parameter set of the auxiliary energy storage subsystem, perform energy storage efficiency simulation on the energy storage subsystem to be optimized and obtain simulation results.

[0037] Among them, the energy storage setting parameter set refers to a set of parameters used to control the operation of the energy storage subsystem, such as the upper limit of charging and discharging power, charging and discharging cutoff voltage, operating temperature range, and operating mode. These parameters directly affect the performance and efficiency of the energy storage subsystem.

[0038] Energy storage efficiency simulation refers to the process of establishing a mathematical or physical model of an energy storage subsystem and simulating its operating state and efficiency performance under different energy storage parameter sets in a computer environment in order to predict its performance.

[0039] Simulation results refer to the data and analysis reports obtained after the energy storage efficiency simulation process is completed, which show the efficiency performance and operating characteristics of the energy storage subsystem under a specific set of parameters.

[0040] Specifically, based on the energy storage parameter set of the auxiliary energy storage subsystem, the energy storage efficiency of the subsystem to be optimized is simulated, and the simulation results are obtained. This simulation process aims to predict the performance of the subsystem to be optimized after applying the parameter set of the auxiliary energy storage subsystem. Specifically, the energy storage parameter set currently in use or with historically excellent performance of the auxiliary energy storage subsystem, such as its charging and discharging strategy, voltage and current thresholds, and temperature control range, can be input into the simulation model of the subsystem to be optimized. This simulation model can be a mathematical model based on physical principles or a data-driven machine learning model. By running the simulation, the charging and discharging behavior, energy loss, and final energy storage efficiency of the subsystem to be optimized under these parameter sets can be simulated. For example, if the auxiliary energy storage subsystem adopts a specific segmented charging and discharging strategy, this strategy is applied to the simulation model of the subsystem to be optimized, and its efficiency changes under different load conditions are observed. After the simulation, a series of data will be obtained, including but not limited to the predicted energy storage efficiency, the changing trends of key operating parameters, and potential performance bottlenecks; these data constitute the simulation results.

[0041] Step S103: Set the energy storage parameters for the multi-energy storage system based on the simulation results.

[0042] Specifically, based on the simulation results, energy storage parameters are set for the multi-energy storage system. This step aims to apply the optimized parameters verified by simulation to the actual system to improve overall efficiency. Specifically, the set of energy storage parameters that effectively improve the efficiency of the subsystem to be optimized, as shown in the simulation results, can be deployed to the controller of the subsystem to be optimized. For example, if simulation results show that applying a certain charge / discharge power curve of the auxiliary energy storage subsystem to the subsystem to be optimized can improve its efficiency, then this power curve is issued as a new operating parameter to the subsystem to be optimized. Furthermore, the parameters of other related energy storage subsystems in the multi-energy storage system can also be adjusted collaboratively based on the simulation results to ensure coordinated operation of the entire system and maximize overall efficiency. For example, after adjusting the parameters of the subsystem to be optimized, it may be necessary to fine-tune the parameters of the auxiliary energy storage subsystem to adapt to the new system operating state.

[0043] It is understood that this embodiment achieves intelligent and dynamic adjustment of the operating parameters of the multi-energy storage system by dynamically monitoring the energy storage efficiency of each energy storage subsystem in the multi-energy storage system, accurately identifying the subsystem to be optimized, and using the parameters of the efficient auxiliary subsystem for simulation optimization. This solves the problem of low overall energy storage efficiency in traditional multi-energy storage systems caused by independent operation and fixed parameters, and improves the overall collaborative efficiency and adaptability of the multi-energy storage system under complex and variable energy demands and grid conditions.

[0044] In some embodiments described above in this application, the system is optimized by monitoring energy storage efficiency and performing simulations based on auxiliary subsystem parameters. However, during implementation, parameter settings may lack dynamic adjustment and optimization for different usage scenarios, resulting in fixed parameters that cannot adapt to changes in actual operating conditions, thus limiting the improvement of overall energy storage efficiency. To address this, this application further proposes an energy storage control method for multi-energy storage systems, such as... Figure 2 As shown, the method includes: Step S201: Determine the energy storage setting parameter group according to the usage scenario of the multi-energy storage system. The energy storage setting parameter group includes multiple energy storage setting parameter sets and is stored in the energy storage setting parameter library.

[0045] Specifically, usage scenarios refer to the specific operating environment and task requirements of multiple energy storage systems, such as peak-valley arbitrage, frequency regulation, and smoothing of renewable energy grid connection. Energy storage parameter sets are a series of pre-configured or dynamically generated energy storage parameter sets for specific usage scenarios. The energy storage parameter library is a centralized database storing all energy storage parameter sets, facilitating management and rapid retrieval. In practical applications, determining energy storage parameter sets can be achieved in various ways. For example, based on predefined rules and expert experience, the system can identify the current usage scenario (e.g., if grid load forecasts indicate an impending peak load, it identifies it as a "peak-valley arbitrage" scenario) and retrieve the corresponding energy storage parameter sets from the parameter library. Alternatively, it can be based on machine learning models. The system can train a classification or clustering model using historical operating data. This model can automatically identify the current usage scenario based on real-time environmental data, such as grid load, renewable energy output, and market electricity prices, and recommend or determine the most suitable energy storage parameter sets for that scenario.

[0046] Step S202: Select the set of energy storage setting parameters whose usage frequency meets the preset conditions from the energy storage setting parameter group, and use it as the target energy storage setting parameter set for the multi-energy storage system.

[0047] Specifically, this step aims to select a specific parameter set from the parameter group corresponding to the current scenario for subsequent optimization. Meeting the usage frequency preset condition can refer to selecting parameter sets with low usage frequency or those that have not yet been fully explored, thus promoting a comprehensive exploration of the parameter space. For example, the system can maintain a usage counter for each energy storage setting parameter set, prioritizing the parameter set with the lowest usage frequency in the current energy storage setting parameter group. If multiple parameter sets with the lowest usage frequency exist, selection can be based on other secondary conditions, such as creation time or the effect of the last optimization. Alternatively, the system can employ a polling mechanism to sequentially select each parameter set in the energy storage setting parameter group, or specifically mark parameter sets that have never been selected as target energy storage setting parameter sets and prioritize them, ensuring that all potential parameter configurations are explored and evaluated.

[0048] Step S203: Determine the target energy storage parameters associated with energy storage demand in the target energy storage setting parameter set, and optimize the target energy storage parameters to obtain the optimized energy storage setting parameter set; Specifically, this step focuses on fine-tuning the selected target energy storage parameter set to better meet current energy storage needs. Energy storage needs can be quantified into specific performance indicators, such as maximizing charge / discharge efficiency, minimizing operating costs, and extending equipment lifespan. The optimization process aims to adjust parameters directly related to these needs. For example, based on rule engines and heuristic algorithms, the system can pre-set a series of optimization rules. When the energy storage need is "maximizing discharge power," parameters such as the upper limit of charge / discharge power and the cutoff voltage are adjusted. Combined with heuristic algorithms, such as genetic algorithms and particle swarm optimization, an iterative search is performed within the pre-set parameter range to find the optimal parameter combination that meets the energy storage needs. Alternatively, based on model predictive control, the system can establish a dynamic model of the energy storage subsystem and, combined with real-time energy storage needs and predicted future operating conditions, calculate and adjust the target energy storage parameters in each control cycle through model predictive control algorithms to optimize the performance indicators of the energy storage system while meeting constraints.

[0049] Step S204: Store the optimized energy storage setting parameter set in the corresponding energy storage setting parameter group in the energy storage setting parameter library.

[0050] Specifically, this step ensures that the optimized parameter set is persistently saved and incorporated into the energy storage setting parameter library for subsequent use and learning. This forms a closed loop of continuous improvement. For example, if the optimized parameter set is highly similar to or significantly outperforms an existing parameter set, the system can directly overwrite the existing parameter set with the optimized one and update its metadata, such as optimization time and optimization effect. Furthermore, the system can add the optimized parameter set as a new entry to the corresponding energy storage setting parameter group and add tags such as "Latest Optimization" or "Specific to Scenario X," while retaining older parameter sets as historical records or alternative solutions for backtracking analysis or reactivation under specific circumstances.

[0051] Step S205: Monitor the energy storage efficiency of each energy storage subsystem in the multi-energy storage system, and determine the energy storage subsystem to be optimized and the auxiliary energy storage subsystem based on the energy storage efficiency. The auxiliary energy storage subsystem has a higher energy storage efficiency than the energy storage subsystem to be optimized. (See details...) Figure 1 Step S101 in the embodiment will not be described again here.

[0052] Step S206: Based on the energy storage setting parameter set of the auxiliary energy storage subsystem, perform energy storage efficiency simulation on the energy storage subsystem to be optimized, and obtain the simulation results. See details... Figure 1 Step S102 in the embodiment will not be described again here.

[0053] Step S207: Set the energy storage parameters for the multi-energy storage system based on the simulation results. See details... Figure 1 Step S103 in the embodiment will not be described again here.

[0054] It is understood that, through the above technical solution, this application introduces a dynamic parameter preparation and optimization mechanism before monitoring the energy storage efficiency of each energy storage subsystem in a multi-energy storage system. First, the energy storage setting parameter set is determined based on the usage scenario of the multi-energy storage system, ensuring that the initial parameter set is highly matched with the current operating environment and avoiding incompatibility issues caused by using general or outdated parameters. Second, by selecting an energy storage setting parameter set whose usage frequency meets preset conditions as the target, the system can proactively explore a wider parameter configuration space, effectively avoiding getting trapped in local optima, thereby discovering better operating strategies. Third, the target energy storage parameters associated with energy storage needs are specifically identified and optimized, making the optimization process more focused and efficient, ensuring that parameter adjustments accurately respond to actual performance targets. Finally, the optimized parameter set is stored in the energy storage setting parameter library, constructing a feedback mechanism for continuous learning and self-improvement, enabling the system to accumulate experience from each optimization and continuously improve its parameter management and control capabilities. Overall, this solution solves the problem of fixed parameters and lack of dynamic adjustment in traditional multi-energy storage systems, enabling the system to flexibly adapt and optimize according to complex and ever-changing usage scenarios and energy storage needs. This significantly improves the overall energy storage efficiency and operating performance of multi-energy storage systems and fully leverages the synergistic advantages of multi-energy storage system integration.

[0055] In some of the solutions mentioned above in this application, the target energy storage parameters are optimized to improve energy storage efficiency. However, in the process of implementation, the optimization may lack precise adjustment based on dynamic models and quantitative targets, resulting in unsatisfactory optimization results.

[0056] In response, this application further proposes an energy storage regulation method for multi-energy storage systems, such as... Figure 3 As shown, the method includes: Step S301: Determine the energy storage setting parameter group based on the usage scenario of the multi-energy storage system. See details... Figure 2 Step S201 in the embodiment will not be repeated here.

[0057] Step S302: Select the set of energy storage setting parameters whose usage frequency meets the preset conditions from the energy storage setting parameter group, and use it as the target energy storage setting parameter set for the multi-energy storage system; see details below. Figure 2Step S202 in the embodiment will not be repeated here; Step S303: Determine the target energy storage parameters associated with energy storage demand within the target energy storage setting parameter set, and optimize these target energy storage parameters to obtain an optimized energy storage setting parameter set. Specifically, this includes: Step S3031: Analyze the energy storage demand to obtain a quantitative energy storage target.

[0058] Specifically, this step aims to transform abstract or qualitative energy storage needs into concrete, measurable numerical targets. For example, when the energy storage demand is "peak shaving and valley filling," it can be resolved by reducing peak load by a certain number of megawatts within a specific time period, or by charging a certain number of megawatt-hours of electricity during off-peak periods. When the demand is "smoothing renewable energy output," it can be resolved by reducing the volatility of renewable energy output to below a certain percentage. This step can be achieved in several ways: One approach is to use a pre-defined rule engine or expert system to map different types of energy storage demands, such as grid frequency regulation, reserve capacity, and renewable energy grid connection smoothing, to a series of quantitative indicators, such as power response speed, energy throughput, and cycle life. Another approach is to use natural language processing technology to perform semantic analysis on the textual energy storage demands input by users, extract key information, and transform it into structured quantitative targets. For example, from "need to extend battery life," the quantitative target could be "limiting the daily charge / discharge depth to within 80%."

[0059] Step S3032: Based on the energy storage dynamic model and quantified energy storage target of the energy storage subsystem, a multi-objective optimization algorithm is used to adjust the target energy storage parameters associated with the quantified energy storage target to obtain the optimized energy storage setting parameter set.

[0060] The energy storage dynamic model of the energy storage subsystem is used to characterize the real-time behavior and performance changes of the energy storage subsystem under different operating conditions, such as charge-discharge curves, energy conversion efficiency, power response characteristics, and internal losses. It reflects the dynamic response of the system under the influence of factors such as time, temperature, and power, providing accurate predictions of system behavior for optimization algorithms. Multi-objective optimization algorithms are used to seek the optimal balance among multiple conflicting quantitative energy storage objectives. For example, while optimizing energy storage efficiency, it may also be necessary to consider the cycle life and operating cost of the energy storage device. Methods for implementing multi-objective optimization algorithms include: one approach is to use a non-dominated sorting genetic algorithm, which generates a set of non-dominated solutions, each representing a trade-off between different objectives, allowing the system to select an appropriate set of optimization parameters based on actual needs. Another approach is to use a weighted sum method, which transforms the multi-objective problem into a single-objective problem by assigning weights to each quantitative energy storage objective, and then uses traditional optimization algorithms such as particle swarm optimization and simulated annealing to solve it. Target energy storage parameters associated with the quantitative energy storage objectives may include upper limits for charge-discharge power, charge-discharge cutoff voltage, operating temperature range, and operating mode. By adjusting these parameters, the operating strategy of the energy storage subsystem can be changed to better meet quantitative energy storage objectives.

[0061] Step S304: Store the optimized energy storage setting parameter set in the corresponding energy storage setting parameter group in the energy storage setting parameter library. See details... Figure 2 Step S204 in the embodiment will not be repeated here.

[0062] Step S305: Monitor the energy storage efficiency of each energy storage subsystem in the multi-energy storage system, and determine the energy storage subsystem to be optimized and the auxiliary energy storage subsystem based on the energy storage efficiency. The auxiliary energy storage subsystem has a higher energy storage efficiency than the energy storage subsystem to be optimized. (See details...) Figure 1 Step S101 in the embodiment will not be described again here.

[0063] Step S306: Based on the energy storage setting parameter set of the auxiliary energy storage subsystem, perform energy storage efficiency simulation on the energy storage subsystem to be optimized and obtain the simulation results. (See details...) Figure 1 Step S102 in the embodiment will not be described again here.

[0064] Step S307: Set the energy storage parameters for the multi-energy storage system based on the simulation results. See details... Figure 1 Step S103 in the embodiment will not be described again here.

[0065] It is understood that, through the above-described technical solution in this embodiment, this application provides a clear numerical basis for the optimization process by resolving energy storage demand into precise quantitative energy storage targets, thus avoiding biases caused by subjective judgment. Simultaneously, by combining the energy storage dynamic model of the energy storage subsystem, it ensures that the optimization process can fully consider the real-time behavioral changes and dynamic characteristics of the system, thereby significantly improving the accuracy and adaptability of the optimization results. The use of a multi-objective optimization algorithm enables the system to find the optimal balance point among multiple interrelated and potentially conflicting objectives such as efficiency, lifetime, and cost, achieving comprehensive optimization. Ultimately, the obtained optimized energy storage setting parameter set can provide dynamic and precise parameter configuration for multi-energy storage systems, thereby effectively improving the overall energy storage efficiency and operational reliability of multi-energy storage systems.

[0066] In some of the above-mentioned solutions in this application, a dynamic energy storage model is proposed to optimize energy storage parameters. However, in its implementation, without an accurate model to characterize the dynamic behavior of energy storage devices, including charge and discharge curves, changes in energy conversion efficiency over time, and the cooperative relationship between devices, the optimization algorithm may not be able to effectively adjust the parameters, thereby failing to improve the overall efficiency of the multi-energy storage system.

[0067] In response, this application further proposes that the acquisition of the energy storage dynamic model of the energy storage subsystem includes: establishing an initial dynamic model of the energy storage device based on the characteristic evaluation results of each energy storage device in the energy storage subsystem, wherein the characteristic evaluation results include rated power, rated capacity, charge and discharge efficiency, and response time, and the initial dynamic model is used to characterize the charge and discharge curves and the relationship between energy conversion efficiency and time of the energy storage device. The initial dynamic model includes:

[0068] in, Let represent the charging and discharging efficiency of the i-th energy storage device at time t. This indicates the initial charge / discharge efficiency. This represents the decay coefficient of charge / discharge efficiency over time. This represents the natural degradation of the charging and discharging efficiency of the i-th energy storage device due to accumulated operating time. Indicates the power deviation influence coefficient. This represents the actual power of the i-th energy storage device at time t. This represents the rated power of the i-th energy storage device. Indicates the temperature deviation coefficient. This represents the actual temperature of the i-th energy storage device at time t. This represents the standard operating temperature of the i-th energy storage device; The initial dynamic models of each energy storage device in the energy storage subsystem are integrated to obtain the energy storage dynamic model of the energy storage subsystem. The energy storage dynamic model is used to characterize the charging and discharging timing matching rules, power allocation ratio and energy complementarity strategy between the initial dynamic model and the corresponding energy storage devices.

[0069] Specifically, acquiring the dynamic model of the energy storage subsystem aims to provide a precise and real-time predictive tool for the behavior of the energy storage subsystem for multi-energy storage system management platforms. Its role is to abstract the complex and variable physical, chemical, and operational characteristics of the energy storage subsystem into a calculable and predictable mathematical model, thus providing a solid foundation for subsequent optimization of energy storage parameters. This acquisition process can be achieved through various methods, including physical modeling, data-driven modeling, or hybrid modeling. For example, it can be achieved by conducting mechanistic analysis of the electrochemical reaction process of the energy storage device to establish physical equations for its voltage, current, capacity, and other parameters; or by collecting a large amount of historical operating data and utilizing machine learning algorithms, such as regression analysis and neural networks, to learn the behavioral patterns of the device.

[0070] When acquiring a dynamic model for energy storage, the initial dynamic model of each energy storage device in the energy storage subsystem is first established based on the characteristic evaluation results. This step is fundamental to building an accurate dynamic model for energy storage. The characteristic evaluation results are a quantitative description of the inherent attributes and performance of a single energy storage device, including rated power, rated capacity, charge / discharge efficiency, and response time. These parameters determine the device's basic operating boundaries and efficiency characteristics.

[0071] The purpose of the initial dynamic model is to preliminarily characterize the charge-discharge curves and energy conversion efficiency of a single energy storage device under ideal or standard conditions over time. Establishing an initial dynamic model can be achieved through various methods. For example, it can involve obtaining performance data of the device under different operating conditions through laboratory testing and calibration, followed by curve fitting or parameter identification; or it can involve referring to the technical manuals and performance curves provided by the device manufacturer and combining them with empirical formulas for preliminary modeling. Rated power refers to the maximum power that the energy storage device can continuously output or absorb under normal operating conditions, defining its power throughput capability. For example, it can be determined by conducting full-power charge-discharge tests. Rated capacity refers to the maximum energy that the energy storage device can store in a fully charged state, defining its energy storage capacity. For example, it can be determined by measuring the amount of electricity that can be stored from a full discharge to a full charge through constant current charge-discharge tests. Charge-discharge efficiency refers to the efficiency of energy conversion during the charge-discharge process, usually expressed as the ratio of output energy to input energy. It quantifies energy loss, and can be calculated by measuring the input and output energy under specific charge-discharge cycles. Response time refers to the time required for an energy storage device to actually execute an operation after receiving an instruction. Its function is to measure the dynamic response speed of the device. For example, it can be determined by measuring the time required from the issuance of an instruction to the power reaching the set value through a step response test.

[0072] The initial dynamic model is used to characterize the charge / discharge curves and energy conversion efficiency of energy storage devices over time. Its core function is to capture the dynamic characteristics of a single energy storage device during operation. The charge / discharge curves describe the changes in parameters such as voltage, current, and capacity over time during the charge / discharge process, while the energy conversion efficiency reflects the energy loss of the device under different operating conditions. This characterization can be achieved through mathematical functions, lookup tables, or state-space models. For example, piecewise linear or polynomial functions can be used to fit the charge / discharge curves; or a battery model based on an equivalent circuit model can be established to simulate its voltage response. The initial dynamic model specifically includes the following formulas: This formula provides a specific, quantitative way to describe the charge and discharge efficiency of the i-th energy storage device at time t. .in, This indicates the initial charge / discharge efficiency, which is the baseline efficiency of the device in an ideal or brand-new state. This represents the decay coefficient of charge / discharge efficiency over time. This represents the natural decay of the charging and discharging efficiency of the i-th energy storage device due to accumulated operating time. This term takes into account the impact of device aging on efficiency and reflects the natural decline in the performance of the device during long-term operation. Indicates the power deviation influence coefficient. This represents the actual power of the i-th energy storage device at time t. This represents the rated power of the i-th energy storage device. This term takes into account the impact on efficiency when the actual operating power deviates from the rated power. For example, excessively high or low power output may lead to a decrease in efficiency. Indicates the temperature deviation coefficient. This represents the actual temperature of the i-th energy storage device at time t. This term represents the standard operating temperature of the i-th energy storage device. It considers the impact of actual operating temperature deviating from the standard operating temperature on efficiency. For example, excessively high or low temperatures can affect the electrochemical reaction rate and internal resistance of the battery, thereby changing the efficiency. By introducing key influencing factors such as time, power, and temperature, this formula can more comprehensively and accurately characterize the dynamic efficiency characteristics of energy storage devices, overcoming the limitations of traditional models that only consider static efficiency.

[0073] Based on this, the initial dynamic models of each energy storage device in the energy storage subsystem are integrated to obtain the energy storage dynamic model of the subsystem. This step aims to elevate the dynamic model of individual devices to the subsystem level to reflect the overall behavior of multiple devices working collaboratively. The integration process is not simply about superimposing individual models, but more importantly, considering the interaction and coordination mechanisms between devices. Integration can be achieved using various methods, such as establishing a multi-input multi-output (MIMO) system model to correlate the inputs and outputs of each device; or constructing an agent-based model to simulate the interaction behavior between devices. The integrated energy storage dynamic model is used to characterize the charging and discharging timing matching rules, power allocation ratios, and energy complementarity strategies between the initial dynamic model and the corresponding energy storage devices. Among them, the charging and discharging timing matching rules refer to the sequence and time relationship of the start-up, stop, and switching of different energy storage devices during the charging and discharging process. For example, devices with fast response speeds can be set to prioritize responding to short-term power fluctuations, while devices with large capacity are responsible for long-term energy storage. Power allocation ratio refers to how to rationally distribute power among various energy storage devices in a subsystem while meeting total power demand. For example, the power allocation ratio can be dynamically adjusted based on factors such as the current health status, efficiency curves, and remaining lifespan of the devices to achieve optimal overall efficiency or maximized lifespan. Energy complementarity strategy refers to how energy storage devices of different types or in different states can cooperate to compensate for their individual shortcomings and leverage overall advantages. For example, battery energy storage systems can provide fast response and high energy density, while flywheel energy storage systems can provide ultra-high power density and long cycle life; the two can complement each other to address different grid demands. By characterizing these collaborative strategies, energy storage dynamic models can more accurately predict the performance of the entire energy storage subsystem under complex operating conditions, providing a basis for refined management and optimization.

[0074] It is understood that, through the above-described technical solution in this embodiment, this application effectively solves the problem of low efficiency caused by inaccurate models during energy storage parameter optimization by constructing an accurate dynamic energy storage model. Specifically, firstly, based on the characteristic evaluation results of each energy storage device in the energy storage subsystem, such as rated power, rated capacity, charge / discharge efficiency, and response time, an initial dynamic model is established. This ensures that the model can accurately capture the charge / discharge curves and the relationship between energy conversion efficiency and time of a single energy storage device during operation, avoiding model distortion caused by ignoring key parameters. In particular, by introducing formulas... This application quantifies the impact of time decay, power deviation, and temperature deviation on equipment efficiency, thus providing a comprehensive and accurate efficiency characterization. This allows the model to truly reflect the performance changes of the equipment during dynamic operation, overcoming the shortcomings of traditional models that cannot handle dynamic factors. Based on this, this application further integrates the initial dynamic models of each energy storage device in the energy storage subsystem to form an energy storage dynamic model of the subsystem. This integration process not only considers the performance of individual devices but also characterizes the charging and discharging timing matching rules, power allocation ratios, and energy complementarity strategies between devices. In this way, the model can accurately reflect the overall behavior and interaction of multiple energy storage devices working collaboratively, thereby supporting refined management and optimization at the subsystem level. Therefore, the obtained energy storage dynamic model can provide highly accurate prediction and evaluation capabilities for subsequent energy storage parameter optimization. When using multi-objective optimization algorithms to adjust target energy storage parameters associated with quantified energy storage objectives, this accurate dynamic model ensures that the optimization algorithm makes decisions based on real, dynamic device behavior, effectively avoiding optimization result deviations caused by model inaccuracies. Ultimately, this enables multi-energy storage systems to achieve more efficient energy conversion and more optimized operating strategies, significantly improving the overall energy storage efficiency and response capability of multi-energy storage systems, and fully leveraging the synergistic advantages of multi-energy storage system integration.

[0075] In some of the above-mentioned solutions in this application, a multi-objective optimization algorithm is proposed to adjust the target energy storage parameters in order to optimize the energy storage setting parameter set. However, in the process of its implementation, due to the lack of full consideration of multi-dimensional operating data such as dynamic changes in the external environment, fluctuations in equipment health status and historical control experience, the optimization process lacks adaptability to actual complex working conditions, which may result in inaccurate parameter adjustment or failure to effectively cope with dynamic energy demand.

[0076] In response, this application further proposes, based on the energy storage dynamic model and quantified energy storage objectives of the energy storage subsystem, to adjust the target energy storage parameters associated with the quantified energy storage objectives using a multi-objective optimization algorithm, thereby obtaining an optimized energy storage setting parameter set, including: Step a1: Obtain the operating data of the energy storage subsystem. The operating data includes the external environment dynamic data of the energy storage subsystem, the health status data of the energy storage devices in the energy storage subsystem, and the historical energy storage control data of the energy storage subsystem. The external environment dynamic data includes grid load fluctuations, new energy output forecasts, and real-time electricity price signals. The device health status data includes the remaining lifespan, decay rate, and preset component operating temperature of the energy storage devices. The historical energy storage control data includes the mapping relationship between energy storage setting parameters and energy storage efficiency under different scenarios, and anomaly handling records.

[0077] Step a2 involves normalizing the external environment dynamic data, health status data, and historical energy storage regulation data to obtain normalized data.

[0078] Step a3: Based on the unsupervised linear dimensionality reduction algorithm, feature extraction is performed on the normalized data to construct a multidimensional correlation model. The multidimensional correlation model is used to characterize the correlation between the energy storage subsystem in the environmental, health and efficiency dimensions.

[0079] Step a4: Based on the output of the multidimensional correlation model and the quantified energy storage target, a neural network model is used to allocate the weights of the multi-objective optimization algorithm to obtain the optimized energy storage setting parameter set. The output results include the energy storage efficiency prediction curve and the parameter sensitivity coefficient.

[0080] Specifically, acquiring operational data from energy storage subsystems aims to provide comprehensive and accurate input for subsequent optimization decisions. Operational data covers multiple key dimensions affecting the performance of energy storage systems. For example, dynamic external environmental data, such as grid load fluctuations, renewable energy output forecasts, and real-time electricity price signals, reflects the external operating environment and market demand of the energy storage system; health status data of energy storage devices, such as the remaining lifespan, degradation rate, and preset component operating temperatures, reveals the physical condition and performance degradation trends of the energy storage devices; historical energy storage control data, such as the mapping relationship between energy storage setting parameters and energy storage efficiency under different scenarios, and anomaly handling records, provides valuable experience and system behavior patterns. This data can be acquired in various ways, such as by using sensors deployed in the energy storage system, such as voltage / current sensors and temperature sensors, to collect equipment operating parameters in real time; by interfacing with grid dispatching systems or meteorological forecasting services to obtain external environmental data; and by querying historical databases or log systems to obtain historical control records. Another approach is to utilize an Internet of Things (IoT) platform to integrate various data sources, achieving unified data collection, transmission, and preliminary processing to ensure data real-time performance and accuracy.

[0081] After acquiring multi-dimensional operational data, it is necessary to normalize the external environment dynamic data, health status data, and historical energy storage regulation data to obtain normalized data. The purpose of this step is to eliminate the influence of differences in units, scales, or numerical ranges between different data sources, ensuring the comparability of all data in subsequent analyses and preventing certain features with large numerical ranges from dominating the optimization process. Common normalization methods include Min-Max standardization, which linearly scales the data to a fixed interval. This effectively eliminates heterogeneity between data, laying the foundation for subsequent feature extraction and model building.

[0082] Subsequently, feature extraction is performed on the normalized data using an unsupervised linear dimensionality reduction algorithm to construct a multidimensional correlation model. This step aims to identify and extract the most representative and informative features from high-dimensional normalized data while reducing data redundancy, thereby constructing a multidimensional correlation model that can characterize the correlation between the energy storage subsystem in environmental, health, and efficiency dimensions. The advantage of unsupervised linear dimensionality reduction algorithms lies in their ability to discover the inherent structure of data without requiring pre-labeled data. For example, Principal Component Analysis (PCA) is a commonly used linear dimensionality reduction technique that projects the original data into a new coordinate system through orthogonal transformation, arranging the projected data in the direction of maximum variance, thus extracting the principal components. Another method is Independent Component Analysis (ICA), which aims to separate multivariate signals into statistically independent non-Gaussian components, which is very effective in revealing hidden independent driving factors in the data. Through these algorithms, the complex interaction patterns between environmental changes, equipment health status, and energy storage efficiency can be effectively captured.

[0083] Finally, based on the output of the multidimensional correlation model and the quantified energy storage objectives, a neural network model is used to allocate weights to the multi-objective optimization algorithm, resulting in an optimized energy storage parameter set. The output of the multidimensional correlation model, such as the energy storage efficiency prediction curve and parameter sensitivity coefficients, provides in-depth insights into the future behavior of the system and the impact of parameters. The energy storage efficiency prediction curve can predict the efficiency performance of the energy storage system under different operating conditions, while the parameter sensitivity coefficients reveal the degree of influence of each energy storage parameter on the overall efficiency. The neural network model, such as a feedforward neural network, can receive these outputs and the quantified energy storage objectives as input. Through its internal nonlinear mapping capabilities, it learns and outputs the optimal weight allocation scheme for the current operating conditions and optimization objectives. These weights will be used to adjust the relative importance of various objective functions in the multi-objective optimization algorithm, such as maximizing efficiency, extending lifetime, and minimizing cost, thereby enabling the optimization algorithm to dynamically and adaptively generate the optimal energy storage parameter set that best meets current needs. For example, when grid load fluctuates drastically, the neural network may allocate higher weights to response speed and power output stability; while when equipment health is poor, it may focus more on extending lifetime and reducing degradation rate.

[0084] In one example, the modeling process of a multi-objective optimization algorithm is as follows: I. Definition of Decision Variables: The core of the algorithm is to find an optimal set of decision variables; let the set of decision variables be denoted as . It includes: : No. An energy storage device at any time The planned charge / discharge power (unit: kW); this is the most crucial continuously controlled variable. Indicates charging. Indicates discharge; : Total time required to complete this energy storage mission (unit: hours); Under the goal of "fastest energy storage", It is itself a variable to be optimized; other discrete or continuous parameters strongly correlated with the quantitative energy storage target, such as charge / discharge cutoff voltage. System-level power allocation weights wait.

[0085] II. Constraint Modeling: The constraints ensure the safety and feasibility of the optimization solution, as follows: Equipment physical constraints are derived from differences in equipment characteristics: Power upper and lower limit constraints: ; : No. The maximum allowable charging power for each device is generally a positive value. : No. The maximum allowable discharge power of a device is generally a negative value, and its absolute value is the upper limit of the discharge power. Energy / capacity constraints: ; : No. The device is The state of charge at time t is determined by Calculated; where Rated capacity (kWh) As the efficiency function, it can be derived from the following The calculation formula is obtained; : No. The upper and lower limits of security for each device's SOC; Power change rate constraint: ; : No. The maximum power ramp rate (kW / min) of a device characterizes the limit of its power response speed; The system energy balance constraint is obtained based on the quantified energy storage target: ; The quantitative energy storage target value (kWh) for this task, i.e., the total energy to be stored; this equation constraint ensures that the optimization result must complete the task. Operational safety constraints: Equipment temperature Current They must meet the absolute safety limits defined in their "Equipment Basic Information".

[0086] III. Multi-objective function modeling: The algorithm simultaneously optimizes the following three objectives to find the Pareto optimal solution set: Fastest energy storage: Minimize the total task time; the objective function is... ,Right now ; Minimize energy loss: Minimize the conversion loss throughout the entire process; the objective function is:

[0087] : No. The device is The efficiency at any given time is calculated by the energy storage dynamic model; this function directly embeds the energy conversion efficiency into the objective function; the optimization objective is... ; Maximize equipment lifespan protection: Minimize the estimated equipment lifespan degradation caused by the task; the objective function can be expressed as:

[0088] These are current stress, temperature stress, and SOC stress functions, respectively, used to quantify the damage rate of instantaneous operating conditions to equipment lifespan; : Corresponding to the The life stress weighting coefficient for each piece of equipment can be adjusted according to the equipment type and health status; the optimization objective is... .

[0089] IV. Solution: The input consists of an initial efficient parameter set that has passed adaptability verification, an energy storage dynamic model of the system to be optimized, and an analytically obtained quantitative energy storage target Etarget. Based on this, a complete multi-objective optimization problem is constructed using the aforementioned modeling method; and a multi-objective evolutionary algorithm (such as NSGA-II) is used to solve the problem. Under the condition of satisfying all constraints, the algorithm generates a set of Pareto optimal solutions through iterative search. Each solution represents a set of feasible decision variable values. and in the target space The middle forms a balancing frontier.

[0090] In one example, the construction and output of the association model include: A shallow neural network, either a multilayer perceptron (MLP) with one hidden layer or a support vector regression (SVR) model, is used as the association model. ; Input: Core feature matrix At a specific moment vector and the basic parameter set for the current operation of energy storage systems. Current average power and SOC; Output: Predicted energy storage efficiency for a short future time period, such as the next 15 minutes. ; Training: Utilizing massive amounts of "parameter-efficiency" records from "historical energy storage regulation data" as training samples. Using mean squared error (MSE) as the loss function for the model Conduct supervised training; Model output: Energy storage efficiency prediction curve: the current moment's... And future environmental prediction data are input into the trained model It can predict efficiency sequences over a future period of time (e.g., the next hour, with a step size of 5 minutes). This forms the prediction curve; Parameter sensitivity coefficient: Calculation method: Local gradient method is used; in the model At the input point (current state), calculate the model output (prediction efficiency) against the input features. and key operating parameters The partial derivatives; Specific formula: For parameters Its sensitivity coefficient The calculation is as follows: Current status

[0091] Physical meaning: The absolute value of the parameter indicates the magnitude of the parameter. The degree to which a small change affects efficiency; the sign indicates the direction of the effect, i.e., positive or negative correlation; for example, the effect on charging current. sensitivity If the value is negative and large in absolute terms, it indicates that slightly reducing the charging current may significantly improve efficiency. The efficiency prediction curve is directly used as one of the input sequences of the LSTM network, providing information for predicting future system performance.

[0092] The parameter sensitivity coefficients are encoded and incorporated into the state space of DQN, enabling the agent to know which parameters have the highest marginal benefit to efficiency in the current state, thereby making more accurate weight allocation decisions.

[0093] It is understood that by acquiring multi-dimensional operational data such as dynamic external environmental data, health status data of energy storage devices, and historical energy storage regulation data of the energy storage subsystem, this application can comprehensively capture various factors affecting the performance of the energy storage system, providing rich and realistic input for optimization decisions. Normalizing these heterogeneous data eliminates dimensional differences and numerical inconsistencies between different data sources, ensuring the comparability and effectiveness of the data in subsequent processing. Furthermore, based on an unsupervised linear dimensionality reduction algorithm, feature extraction is performed on the normalized data to construct a multi-dimensional correlation model. This efficiently identifies and extracts key information from the data, revealing deep correlations between environmental, health, and efficiency dimensions, thereby effectively reducing data redundancy and improving the model's ability to understand complex system behavior. On this basis, a neural network model intelligently allocates the weights of the multi-objective optimization algorithm based on the output results of the multi-dimensional correlation model, such as the energy storage efficiency prediction curve, parameter sensitivity coefficient, and quantified energy storage targets. This allows the optimization process to dynamically adapt to current operating conditions and specific optimization objectives. This enables the optimization algorithm to more accurately balance different optimization objectives, thereby obtaining an optimized energy storage parameter set that better matches actual operating conditions. Overall, this application improves the accuracy, robustness, and adaptability to dynamic environments of energy storage parameter optimization by comprehensively utilizing multi-dimensional data, data processing, and intelligent optimization technologies. It solves the problems of inaccurate parameter adjustment and inability to effectively cope with dynamic energy demand under complex and variable operating conditions by traditional optimization methods, thereby giving full play to the synergistic advantages of multiple energy storage systems and improving overall energy storage efficiency and operational reliability.

[0094] In some of the embodiments described above in this application, simulation based on the energy storage setting parameter set of the auxiliary energy storage subsystem is proposed to optimize the efficiency of multiple energy storage systems. However, in the implementation process, if the compatibility between the parameter set and the energy storage subsystem to be optimized is not verified, the parameter set may not be compatible when applied directly, and the efficiency may not be effectively improved, or even the overall energy storage efficiency may be reduced due to parameter conflicts.

[0095] In response, this application further proposes an energy storage regulation method for multi-energy storage systems, such as... Figure 4 As shown, the method includes: Step S401: Determine the energy storage setting parameter group based on the usage scenario of the multi-energy storage system. See details... Figure 2 Step S201 in the embodiment will not be repeated here.

[0096] Step S402: Select the set of energy storage setting parameters whose usage frequency meets the preset conditions from the energy storage setting parameter group, and use it as the target energy storage setting parameter set for the multi-energy storage system; see details below. Figure 2 Step S202 in the embodiment will not be repeated here; Step S403: Determine the target energy storage parameters associated with energy storage demand within the target energy storage setting parameter set, and optimize these target energy storage parameters to obtain an optimized energy storage setting parameter set. Specifically, this includes: Step S4031 involves analyzing the energy storage demand to obtain quantified energy storage targets. See details in [link / reference]. Figure 3 Step S3031 in the embodiment will not be repeated here; Step S4032: Based on the energy storage dynamic model and quantified energy storage objectives of the energy storage subsystem, a multi-objective optimization algorithm is used to adjust the target energy storage parameters associated with the quantified energy storage objectives, thereby obtaining an optimized energy storage setting parameter set. (See details...) Figure 3 Step S3032 in the embodiment will not be repeated here; Step S404: Store the optimized energy storage setting parameter set in the corresponding energy storage setting parameter group in the energy storage setting parameter library. See details... Figure 2 Step S204 in the embodiment will not be repeated here.

[0097] Step S405 involves monitoring the energy storage efficiency of each energy storage subsystem in the multi-energy storage system, and determining the energy storage subsystem to be optimized and the auxiliary energy storage subsystem based on the energy storage efficiency. The auxiliary energy storage subsystem has a higher energy storage efficiency than the energy storage subsystem to be optimized. Specifically, this includes: Step S4051: Verify the compatibility between the energy storage setting parameter set and the energy storage subsystem to be optimized.

[0098] In this context, adaptability refers to the degree of compatibility between a set of energy storage parameters and a specific energy storage subsystem in terms of technical characteristics, operating conditions, and performance requirements. One implementation method is through a pre-defined rule engine. This engine incorporates the operating boundary conditions for various energy storage devices, such as maximum charge / discharge power, voltage range, and temperature limits, as well as specific values ​​from the parameter set. The system compares each parameter in the parameter set with the corresponding boundary conditions of the energy storage devices within the subsystem to be optimized. If all parameters are within acceptable ranges, adaptability is considered satisfied. Another implementation method is through model-based predictive analysis. Using a simplified simulation model of the subsystem to be optimized, the proposed set of energy storage parameters is input, and its performance under typical operating conditions is quickly simulated. If the simulation results show no abnormal operation, no sharp performance degradation, or no exceeding of safety thresholds, adaptability is considered satisfied.

[0099] Step S4052: When the adaptability meets the preset adaptability conditions, the energy storage setting parameter set of the auxiliary energy storage subsystem is applied to the energy storage subsystem to be optimized, and the parameters in the energy storage setting parameter set are adjusted within a preset range to determine the optimal energy storage efficiency of the energy storage subsystem to be optimized.

[0100] The adjustment of the preset range refers to making small, constrained changes to one or more parameter values ​​in the parameter set, based on the confirmed compatibility between the parameter set and the energy storage subsystem to be optimized, in order to explore and find the parameter combination that achieves the highest energy storage efficiency under the subsystem. One implementation method is to use a local search algorithm, such as hill climbing or grid search. A small adjustment range is set around each parameter in the parameter set, and then different parameter combinations within these ranges are systematically tried. Energy storage efficiency simulations are performed for each attempt, and the parameter combination with the highest efficiency is recorded. Another implementation method is to use a surrogate model-based optimization approach. First, a small number of parameter combinations and their corresponding simulation efficiency data are collected within the preset range, and a surrogate model is trained to approximate the relationship between energy storage efficiency and parameters. Then, the surrogate model is used to quickly predict the efficiency of a large number of parameter combinations, and optimization algorithms, such as genetic algorithms and particle swarm optimization, are combined to find the optimal parameters on the surrogate model. Finally, the optimal parameters are verified through accurate simulations.

[0101] Step S4053: When applying the energy storage setting parameter set corresponding to the optimal energy storage efficiency to a multi-energy storage system, if the energy storage efficiency of the multi-energy storage system is improved, then the energy storage setting parameter set corresponding to the optimal energy storage efficiency is used as the simulation result.

[0102] Step S4054: If the energy storage efficiency of the multi-energy storage system does not improve, then the current energy storage setting parameter set is used as the simulation result.

[0103] Specifically, the simulation results here refer to the energy storage parameter set that, after system-level verification, can actually improve the overall energy storage efficiency of a multi-energy storage system. One approach is to judge through comparative simulation. The energy storage subsystem to be optimized, using the energy storage parameter set corresponding to the optimal energy storage efficiency, is simulated together with other energy storage subsystems in the multi-energy storage system to calculate the total energy storage efficiency of the multi-energy storage system. Then, this efficiency is compared with the total energy storage efficiency of the multi-energy storage system when using the current energy storage parameter set. If the former is higher than the latter, the energy storage parameter set corresponding to the optimal energy storage efficiency is adopted. Another approach is to judge through preset performance index evaluation. In addition to simple energy storage efficiency, other key performance indicators of the multi-energy storage system, such as response speed, lifetime loss, and economic benefits, can also be considered. If, after applying the energy storage parameter set corresponding to the optimal energy storage efficiency, the comprehensive performance indicators of the multi-energy storage system show a significant improvement compared to the current setting, then this is taken as the simulation result.

[0104] Step S406: Based on the energy storage setting parameter set of the auxiliary energy storage subsystem, perform energy storage efficiency simulation on the energy storage subsystem to be optimized and obtain the simulation results. (See details...) Figure 1 Step S102 in the embodiment will not be described again here.

[0105] Step S407: Set the energy storage parameters for the multi-energy storage system based on the simulation results. See details... Figure 1 Step S103 in the embodiment will not be described again here.

[0106] It is understood that, through the above-described technical solution in this embodiment, when simulating the energy storage efficiency of the energy storage subsystem to be optimized based on the energy storage setting parameter set of the auxiliary energy storage subsystem, this application first introduces an adaptability verification mechanism. This effectively avoids the problem of simulation result distortion or efficiency reduction in actual application caused by parameter incompatibility, ensuring the reliability and safety of the simulation process. Based on this, by finely adjusting the parameter set within a preset range, the optimal operating point of the energy storage subsystem to be optimized under this parameter set can be explored and locked, achieving more precise local optimization. Finally, by applying the optimized parameter set to multiple energy storage systems and conducting an overall efficiency evaluation, it is ensured that local optimization can truly contribute to the improvement of the overall energy storage efficiency of the multiple energy storage systems, avoiding ineffective or negatively impactful adjustments, thereby significantly improving the accuracy and effectiveness of collaborative optimization of multiple energy storage systems.

[0107] In some of the embodiments described above in this application, a method for obtaining the energy storage setting parameter set corresponding to the optimal energy storage efficiency based on simulation is proposed. However, in this process, the parameter set is not stored, which makes it impossible to accumulate optimization experience, increases the burden of repeated optimization, and reduces the overall efficiency of the multi-energy storage system.

[0108] In this regard, the present application further proposes a method that includes: storing the set of energy storage setting parameters corresponding to the optimal energy storage efficiency in the energy storage setting parameter group corresponding to the energy storage setting parameter library.

[0109] Specifically, the optimal energy storage efficiency corresponding to the energy storage setting parameter set refers to a set of operating parameters that enable the energy storage subsystem to achieve its optimal energy storage efficiency, determined by adjusting parameters and verifying the overall efficiency improvement of multiple energy storage systems after energy storage efficiency simulation of the subsystem to be optimized. These parameters may include, but are not limited to, upper limits of charging and discharging power, charging and discharging cutoff voltage, operating temperature range, and operating mode. Specifically, the parameter set can be represented in a structured data format, for example, as a data record containing multiple parameter fields and their corresponding values; or, the parameter set can be encapsulated as a configurable software module or configuration file, which pre-sets all optimized and verified energy storage operation commands.

[0110] It is understood that the technical solution described in this embodiment stores the optimal energy storage setting parameter set that has been verified through simulation and can improve the efficiency of multiple energy storage systems, thus solving the problem of optimization results not being saved. This storage mechanism enables the system to accumulate valuable optimization experience, forming a reusable parameter knowledge base. When encountering similar energy storage control scenarios or energy storage subsystems to be optimized, the system can first query this energy storage setting parameter base, quickly retrieve and apply the existing optimized parameter set, thereby significantly reducing the workload of repeatedly performing complex simulations and parameter adjustments. This not only avoids unnecessary consumption of computing resources and shortens the deployment time of control strategies, but also effectively improves the overall operating efficiency and intelligence level of the multi-energy storage system management platform by continuously accumulating and reusing optimization results, enabling it to respond to grid demands and system changes more quickly and accurately.

[0111] In some of the solutions mentioned above in this application, a verification of adaptability is proposed to ensure that the parameter set of the auxiliary energy storage subsystem is suitable for the energy storage subsystem to be optimized. However, in this process, there is a lack of specific judgment mechanism to detect whether the parameter set exceeds the physical or operational limits of the energy storage devices in the energy storage subsystem to be optimized, which may lead to equipment overload, performance degradation or system failure, thereby affecting the overall efficiency and safety of the multi-energy storage system.

[0112] In response, this application further proposes to verify the compatibility between the energy storage setting parameter set and the energy storage subsystem to be optimized, including: determining whether the energy storage setting parameter set in the auxiliary energy storage subsystem exceeds the parameter range of the energy storage device in the energy storage subsystem to be optimized, wherein the energy storage setting parameter set includes the upper limit of charging and discharging power, charging and discharging cutoff voltage, operating temperature range, and operating mode.

[0113] Specifically, this judgment aims to ensure that the energy storage setting parameter set provided by the auxiliary energy storage subsystem, when applied to the energy storage subsystem to be optimized, does not cause the energy storage devices in the subsystem to exceed their physical or operational limits for safe, stable, or optimal operation. This is a crucial step in ensuring device lifespan, system safety, and performance. For example, detailed specifications of each energy storage device in the subsystem to be optimized, such as maximum charge / discharge current, maximum / minimum operating voltage, and allowable temperature range, can be pre-stored in a database and compared one by one with the energy storage setting parameter set of the auxiliary energy storage subsystem. If any parameter exceeds the preset range, it is determined to be incompatible. Alternatively, a digital twin model of the energy storage device can be established to simulate the impact of the auxiliary energy storage subsystem's energy storage setting parameter set on the device's operation in a simulation environment, and the simulation results can be monitored in real time to ensure that the device's various operating indicators remain within safe thresholds.

[0114] The upper limit of charging and discharging power, charging and discharging cutoff voltage, operating temperature range, and operating mode included in the energy storage setting parameter set are the most critical control parameters in the operation of the energy storage system, directly affecting the performance, lifespan, and safety of the equipment. Performing an adaptability assessment on these parameters allows for a comprehensive evaluation of the compatibility between the parameter set and the equipment.

[0115] The upper limit of charge and discharge power refers to the maximum power that the energy storage device can withstand during charging and discharging. The system can compare the upper limit of charge and discharge power recommended by the auxiliary energy storage subsystem with the rated power, instantaneous overload capacity, etc. of each energy storage device in the energy storage subsystem to be optimized. Alternatively, the current health status of the energy storage subsystem to be optimized, such as the battery internal resistance and capacity degradation, can be considered to dynamically assess its impact on the actual usable power limit.

[0116] The charge / discharge cutoff voltage refers to the highest and lowest voltage that an energy storage device is allowed to reach during charging and discharging. The system can compare the charge / discharge cutoff voltage recommended by the auxiliary energy storage subsystem with the safe voltage range set by the battery management system (BMS) of the energy storage device in the subsystem to be optimized. Simultaneously, the allowable range of its charge / discharge cutoff voltage can be dynamically adjusted based on the chemical characteristics and cycle life requirements of the energy storage device.

[0117] The operating temperature range refers to the range of ambient temperatures that the energy storage device can withstand during normal operation. The system can compare the recommended operating temperature range of the auxiliary energy storage subsystem with the optimal / safe temperature range determined by the manufacturer's specifications or actual operating experience of the energy storage devices in the subsystem to be optimized. Furthermore, the system can also assess whether the subsystem to be optimized can operate stably within the recommended operating temperature range by considering its heat dissipation capacity and predicted ambient temperature.

[0118] Operating modes refer to the control strategies and behavioral patterns adopted by energy storage devices in different application scenarios, such as peak shaving, frequency regulation, and backup power. The system can match the operating modes suggested by the auxiliary energy storage subsystem with the list of operating modes supported by the energy storage devices in the subsystem to be optimized, and assess whether the devices can meet performance requirements under that mode. Alternatively, it can analyze the impact of operating modes on device lifespan, efficiency, etc., to assess whether it meets the long-term operational goals of the subsystem to be optimized.

[0119] It is understood that, through the above technical solution in this embodiment, this application effectively solves the parameter compatibility problem by clearly determining whether the energy storage setting parameter set in the auxiliary energy storage subsystem exceeds the parameter range of the energy storage device in the energy storage subsystem to be optimized, specifically covering key dimensions such as the upper limit of charging and discharging power, charging and discharging cutoff voltage, operating temperature range, and operating mode. This ensures that any parameter set obtained from the auxiliary energy storage subsystem is physically compatible and operationally safe when applied to the energy storage subsystem to be optimized, thereby avoiding the risks of equipment overload, performance degradation, or system failure.

[0120] In some optional embodiments, this application proposes a multi-energy storage system management platform, which includes a data interaction unit, a simulation testing unit, a control execution unit, a status monitoring unit, and a three-dimensional data fusion unit. The data interaction unit is used for real-time data transmission across energy storage systems; the simulation testing unit is used for efficiency simulation and adaptability verification of a single energy storage system under different parameter combinations; the control execution unit is used for real-time issuance of parameter control commands for a single energy storage system; the status monitoring unit is used to collect operating data of each independent energy storage system through voltage / current sensors, temperature sensors, and SOC detectors; and the three-dimensional data fusion unit is used for preprocessing, feature extraction, and correlation modeling of multi-dimensional data.

[0121] Specifically, the data interaction unit is responsible for data exchange within the multi-energy storage system management platform and with external systems. Its core function is to ensure real-time, accurate, and reliable data transmission between different energy storage subsystems, between energy storage subsystems and the management platform, and between the management platform and the power grid or other external systems. This unit can be implemented using a publish / subscribe model based on message queue telemetry transport protocols or advanced message queue protocols, ensuring efficient data distribution and low-latency transmission. Through clearly defined interface specifications, it achieves data interoperability between heterogeneous systems.

[0122] The simulation test unit aims to simulate the behavior and efficiency of a single energy storage system under different combinations of operating parameters, and to verify the suitability of these parameter combinations for the energy storage system. This helps to evaluate and optimize the operating strategy of the energy storage system before actual deployment, reducing trial-and-error costs. This unit can be used to establish a mathematical model of the energy storage system, such as based on an equivalent circuit model or electrochemical model, and perform offline simulation using numerical simulation software; alternatively, it can employ digital twin technology to construct a virtual model of the energy storage system, driving the virtual model's operation with real-time data for online or semi-online simulation testing.

[0123] The control and execution unit is responsible for distributing the optimized control commands generated by the multi-energy storage system management platform to each energy storage subsystem in real time, and ensuring the accurate execution of these commands. Its function is to achieve precise control and dynamic adjustment of the energy storage system's operating status. This unit can communicate with the local controller of the energy storage subsystem via industrial Ethernet or fieldbus protocols, issuing commands such as charging and discharging power, voltage thresholds, and operating modes; alternatively, it can send commands to edge computing devices or energy storage subsystem controllers via a secure encrypted channel through a cloud-based remote control interface, achieving remote and centralized control.

[0124] The status monitoring unit is used to collect real-time operating data from each independent energy storage system, including key parameters such as voltage, current, temperature, and state of charge (SOC). Its purpose is to comprehensively understand the real-time operating status of the energy storage system, providing a data foundation for subsequent analysis, decision-making, and control. This unit can convert the collected analog signals into digital signals by deploying high-precision voltage sensors, current sensors, temperature sensors, and SOC detectors based on coulomb counters or open-circuit voltage methods, and then upload them to the management platform via a data acquisition module. Alternatively, it can utilize the communication interfaces built into smart meters and battery management systems (BMS), such as RS485 or CAN bus, to directly acquire the operating data of the energy storage devices, and then perform protocol conversion and data aggregation through a gateway device.

[0125] The 3D data fusion unit is responsible for preprocessing, feature extraction, and correlation modeling of data from different dimensions, such as external environment, equipment health, and historical operating efficiency. Its purpose is to integrate heterogeneous, multi-source data to reveal the deep operational patterns and interrelationships of energy storage systems under complex conditions, providing support for intelligent decision-making. This unit can employ preprocessing techniques such as data cleaning, missing value imputation, and outlier detection, and use linear dimensionality reduction algorithms such as Principal Component Analysis (PCA) and Independent Component Analysis (ICA) for feature extraction, constructing correlation models based on multiple regression or Support Vector Machines (SVMs). Alternatively, it can utilize deep learning techniques for feature learning and combine graph neural networks or recurrent neural networks to construct multidimensional correlation models capable of capturing temporal sequences and interrelationships.

[0126] It is understood that, through the above technical solutions in this embodiment, the multi-energy storage system management platform proposed in this application effectively solves the coordination problems existing in traditional platforms in terms of data interaction, simulation testing, control execution and status monitoring through its integrated unit architecture.

[0127] In one example, a specific case will be used to illustrate the above technical solution in more detail: Within an industrial park, a multi-energy storage system was deployed, comprising two different types of energy storage subsystems: a lithium-ion battery energy storage subsystem, such as energy storage subsystem A, and a flow battery energy storage subsystem, such as energy storage subsystem B. Energy storage subsystem A has high power density and fast response capability, but its cycle life is relatively short and it is more sensitive to operating temperature; energy storage subsystem B has high energy density and long cycle life, but its response speed is relatively slow.

[0128] In traditional operation, energy storage subsystems A and B operate independently, with their operating parameters such as maximum charging / discharging power, charging / discharging cutoff voltage, and operating temperature range mostly set at the factory or fixed after initial commissioning. This results in low overall energy storage efficiency for the multi-system approach under complex conditions such as large fluctuations in the park's grid load and unstable renewable energy output, failing to fully leverage the synergistic and complementary advantages of the two energy storage technologies. For example, energy storage subsystem A may experience accelerated degradation due to frequent high-power charging and discharging, while the potential of energy storage subsystem B remains untapped.

[0129] To address these issues, the industrial park introduced a multi-energy storage system management platform. This platform integrates a data interaction unit, a simulation testing unit, a control execution unit, a status monitoring unit, and a 3D data fusion unit.

[0130] First, before monitoring the energy storage efficiency of each energy storage subsystem in the multi-energy storage system, the platform performs a series of preparatory tasks. The status monitoring unit collects real-time operating data of energy storage subsystems A and B using voltage / current sensors, temperature sensors, and SOC detectors. The 3D data fusion unit determines a series of energy storage setting parameter sets based on the specific usage scenario of the industrial park, such as smoothing photovoltaic power generation fluctuations and peak shaving / valley filling, and stores these parameter sets in the energy storage setting parameter library. Next, the platform selects a set of energy storage setting parameters from the set whose usage frequency meets preset conditions as the target energy storage setting parameter set for the current multi-energy storage system.

[0131] Subsequently, the platform analyzes the energy storage demand to obtain quantified energy storage targets, such as reducing the peak grid load by 5MW within the next two hours while controlling the average operating temperature of energy storage subsystem A below 30℃. The 3D data fusion unit establishes an initial dynamic model for each energy storage device based on the characteristic evaluation results of each energy storage device in energy storage subsystems A and B, including rated power, rated capacity, charge / discharge efficiency, and response time. For example, for the lithium-ion battery in energy storage subsystem A, its initial dynamic model of charge / discharge efficiency considers the initial charge / discharge efficiency, the decay coefficient of charge / discharge efficiency over time, the power deviation influence coefficient, and the temperature deviation coefficient. These initial dynamic models are integrated to obtain the energy storage dynamic model of the energy storage subsystem, which characterizes the charge / discharge timing matching rules, power allocation ratios, and energy complementarity strategies among different energy storage devices.

[0132] After acquiring the energy storage dynamic model and quantified energy storage targets of the energy storage subsystem, the platform employs a multi-objective optimization algorithm to adjust the target energy storage parameters associated with the quantified energy storage targets. Specifically, the platform acquires operational data of the energy storage subsystem, including dynamic data of the external environment, such as grid load fluctuations, new energy output predictions, real-time electricity price signals, and health status data of energy storage devices, such as the remaining lifespan and decay rate of energy storage subsystem A; the preset component operating temperatures and historical energy storage control data of energy storage subsystem B. The three-dimensional data fusion unit normalizes this data and extracts features based on an unsupervised linear dimensionality reduction algorithm to construct a multi-dimensional correlation model. This model characterizes the correlation between the energy storage subsystem and the energy storage subsystem in the environmental, health, and efficiency dimensions. Finally, based on the output of the multi-dimensional correlation model, including the energy storage efficiency prediction curve and parameter sensitivity coefficient, and the quantified energy storage targets, a neural network model is used to allocate the weights of the multi-objective optimization algorithm, thereby obtaining an optimized energy storage setting parameter set. This optimized energy storage setting parameter set is then stored in the corresponding energy storage setting parameter group in the energy storage setting parameter library.

[0133] After completing the above preparations, the platform enters the core control phase. The status monitoring unit continuously monitors the energy storage efficiency of each energy storage subsystem in the multi-energy storage system. Suppose that at a certain moment, the platform monitors that the energy storage efficiency of energy storage subsystem A is 85%, while the energy storage efficiency of energy storage subsystem B is 90%. At this point, the platform determines that energy storage subsystem A is the energy storage subsystem to be optimized, and energy storage subsystem B is the auxiliary energy storage subsystem, because the energy storage efficiency of auxiliary energy storage subsystem B is higher than that of energy storage subsystem A.

[0134] Next, based on the energy storage setting parameter set of auxiliary energy storage subsystem B, the platform performs energy storage efficiency simulation on energy storage subsystem A. The simulation test unit first verifies the compatibility between the energy storage setting parameter set of energy storage subsystem B and energy storage subsystem A. For example, it determines whether parameters such as the upper limit of charge / discharge power, charge / discharge cutoff voltage, operating temperature range, and operating mode of energy storage subsystem B exceed the parameter range of the energy storage devices in energy storage subsystem A. If a parameter of energy storage subsystem B, such as high discharge power, exceeds the safe range of energy storage subsystem A, the simulation test unit will adjust it to ensure that the parameter is within the acceptable range of energy storage subsystem A. When the compatibility meets the preset conditions, the simulation test unit applies the adjusted energy storage setting parameter set of auxiliary energy storage subsystem B to energy storage subsystem A and adjusts the parameters within the preset range to determine the optimal energy storage efficiency of energy storage subsystem A.

[0135] After the simulation is completed, the platform evaluates whether the overall energy storage efficiency of the multi-energy storage system is improved when the energy storage parameter set corresponding to the optimal energy storage efficiency is applied to the entire multi-energy storage system. If the overall energy storage efficiency is improved, the energy storage parameter set corresponding to the optimal energy storage efficiency is used as the simulation result. If the overall energy storage efficiency is not improved, the current energy storage parameter set is used as the simulation result.

[0136] Finally, based on the simulation results, the control and execution unit sets the energy storage parameters for the multiple energy storage systems. For example, if the simulation results show that adjusting the charging and discharging strategy of energy storage subsystem A to a mode closer to the stable operation of energy storage subsystem B can effectively reduce the temperature stress of energy storage subsystem A and improve its long-term efficiency, the control and execution unit will issue real-time commands to adjust the charging and discharging power limits and temperature control strategies of energy storage subsystem A. Simultaneously, the set of energy storage setting parameters corresponding to this optimal energy storage efficiency will be stored in the corresponding energy storage setting parameter group in the energy storage setting parameter library for subsequent learning and reuse.

[0137] Compared to existing technologies where each energy storage subsystem operates independently with fixed parameters, this solution utilizes a multi-energy storage system management platform to achieve real-time monitoring and dynamic evaluation of the efficiency of each subsystem. When a subsystem is found to be inefficient, it intelligently adopts the operating strategies of more efficient auxiliary energy storage subsystems. Rigorous simulation verification and parameter adaptability assessment ensure the safety and effectiveness of the optimization scheme. This cross-energy storage subsystem collaborative optimization mechanism combines advanced technologies such as dynamic models, multi-objective optimization, and neural networks. This allows multiple energy storage systems to dynamically adjust operating parameters based on real-time operating conditions and energy storage demands, significantly improving overall energy storage efficiency and fully leveraging the synergistic advantages of multi-energy storage system integration, overcoming the efficiency limitations of traditional control modes.

[0138] This embodiment also provides an energy storage control device for a multi-energy storage system. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0139] This embodiment provides an energy storage control device for a multi-energy storage system, such as... Figure 5 As shown, it includes: The monitoring module 501 is used to monitor the energy storage efficiency of each energy storage subsystem in the multi-energy storage system, and to determine the energy storage subsystem to be optimized and the auxiliary energy storage subsystem based on the energy storage efficiency. The energy storage efficiency of the auxiliary energy storage subsystem is higher than that of the energy storage subsystem to be optimized.

[0140] Simulation module 502 performs energy storage efficiency simulation on the energy storage subsystem to be optimized based on the energy storage setting parameter set of the auxiliary energy storage subsystem, and obtains simulation results.

[0141] Module 503 is configured to set energy storage parameters for the multi-energy storage system based on simulation results.

[0142] The energy storage control device for a multi-energy storage system provided in this application can execute the energy storage control method for a multi-energy storage system provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing the method. Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0143] Figure 6 This application provides a schematic diagram of the structure of an electronic device.

[0144] The following is a detailed reference. Figure 6 This diagram illustrates a suitable structural schematic for implementing the electronic device described in the embodiments of this application. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 601, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 602 or a program loaded from memory 608 into random access memory (RAM) 603. The RAM 603 also stores various programs and data required for the operation of the electronic device. The processor 601, ROM 602, and RAM 603 are interconnected via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0145] Typically, the following devices can be connected to I / O interface 605: input devices 606 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 607 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 608 including, for example, magnetic tapes, hard disks, etc.; and communication devices 609. Communication device 609 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 6 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0146] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 609, or installed from a memory 608, or installed from a ROM 602. When the computer program is executed by the processor 601, it performs the functions defined in the energy storage control method for a multi-energy storage system according to embodiments of this application.

[0147] Figure 6 The electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0148] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the energy storage control method of the multi-energy storage system shown in the above embodiments is implemented.

[0149] A portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0150] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method for energy storage regulation of a multi-energy storage system, characterized in that, The method, applied to a multi-energy storage system management platform, includes: Monitor the energy storage efficiency of each energy storage subsystem in a multi-energy storage system, and determine the energy storage subsystem to be optimized and the auxiliary energy storage subsystem based on the energy storage efficiency, wherein the energy storage efficiency of the auxiliary energy storage subsystem is higher than that of the energy storage subsystem to be optimized. Based on the energy storage setting parameter set of the auxiliary energy storage subsystem, the energy storage efficiency of the energy storage subsystem to be optimized is simulated, and the simulation results are obtained. Based on the simulation results, the energy storage parameters of the multi-energy storage system are set.

2. The method of claim 1, wherein, Before monitoring the energy storage efficiency of each energy storage subsystem in the multi-energy storage system, the method further includes: Based on the usage scenario of the multi-energy storage system, an energy storage setting parameter group is determined, wherein the energy storage setting parameter group includes multiple energy storage setting parameter sets, and the energy storage setting parameter group is stored in an energy storage setting parameter library; Select a set of energy storage setting parameters whose usage frequency meets preset conditions from the energy storage setting parameter group, and use it as the target energy storage setting parameter set of the multi-energy storage system. Determine the target energy storage parameters associated with energy storage demand in the target energy storage setting parameter set, and optimize the target energy storage parameters to obtain an optimized energy storage setting parameter set; The optimized energy storage setting parameter set is stored in the energy storage setting parameter group corresponding to the energy storage setting parameter library.

3. The method of claim 2, wherein, The step of determining the target energy storage parameters associated with energy storage demand in the target energy storage setting parameter set, and optimizing the target energy storage parameters to obtain an optimized energy storage setting parameter set, includes: The energy storage demand is analyzed to obtain a quantitative energy storage target; Based on the energy storage dynamic model of the energy storage subsystem and the quantitative energy storage target, a multi-objective optimization algorithm is used to adjust the target energy storage parameters associated with the quantitative energy storage target to obtain an optimized energy storage setting parameter set.

4. The method of claim 3, wherein, The acquisition of the energy storage dynamic model of the energy storage subsystem includes: Based on the characteristic evaluation results of each energy storage device in the energy storage subsystem, an initial dynamic model of the energy storage device is established. The characteristic evaluation results include rated power, rated capacity, charge / discharge efficiency, and response time. The initial dynamic model is used to characterize the charge / discharge curves and energy conversion efficiency of the energy storage device over time. The initial dynamic model includes: wherein, represents the charge-discharge efficiency of the i-th energy storage device at time t, represents the initial charge-discharge efficiency, represents the decay coefficient of the charge-discharge efficiency over time, represents the natural decay amount of the charge-discharge efficiency of the i-th energy storage device due to the cumulative operation time, represents the power deviation influence coefficient, represents the actual power of the i-th energy storage device at time t, represents the rated power of the i-th energy storage device, represents the temperature deviation coefficient, represents the actual temperature of the i-th energy storage device at time t, represents the standard working temperature of the i-th energy storage device; The initial dynamic models of each energy storage device in the energy storage subsystem are integrated to obtain the energy storage dynamic model of the energy storage subsystem. The energy storage dynamic model is used to characterize the charging and discharging timing matching rules, power allocation ratio, and energy complementarity strategy between the initial dynamic model and the corresponding energy storage devices.

5. The method according to claim 3, characterized in that, The step involves adjusting the target energy storage parameters associated with the quantified energy storage target using a multi-objective optimization algorithm based on the energy storage dynamic model of the energy storage subsystem and the quantified energy storage target, to obtain an optimized energy storage setting parameter set, including: The operation data of the energy storage subsystem is obtained, wherein the operation data includes the external environment dynamic data of the energy storage subsystem, the health status data of the energy storage devices in the energy storage subsystem, and the historical energy storage regulation data of the energy storage subsystem; The external environment dynamic data, the health status data, and the historical energy storage regulation data are normalized to obtain normalized data; Feature extraction is performed on the normalized data based on an unsupervised linear dimensionality reduction algorithm to construct a multidimensional correlation model, wherein the multidimensional correlation model is used to characterize the correlation relationship of the energy storage subsystem in the environmental dimension, health dimension and efficiency dimension. Based on the output of the multidimensional correlation model and the quantified energy storage target, a neural network model is used to allocate the weights of the multi-objective optimization algorithm to obtain an optimized energy storage setting parameter set. The output includes an energy storage efficiency prediction curve and a parameter sensitivity coefficient.

6. The method according to claim 1, characterized in that, The energy storage efficiency simulation of the energy storage subsystem to be optimized is performed based on the energy storage setting parameter set of the auxiliary energy storage subsystem, and the simulation results are obtained, including: Verify the compatibility between the energy storage setting parameter set and the energy storage subsystem to be optimized; When the adaptability meets the preset adaptability conditions, the energy storage setting parameter set of the auxiliary energy storage subsystem is applied to the energy storage subsystem to be optimized, and the parameters in the energy storage setting parameter set are adjusted within a preset range to determine the optimal energy storage efficiency of the energy storage subsystem to be optimized. When the set of energy storage settings corresponding to the optimal energy storage efficiency is applied to the multi-energy storage system, if the energy storage efficiency of the multi-energy storage system is improved, then the set of energy storage settings corresponding to the optimal energy storage efficiency is used as the simulation result. If the energy storage efficiency of the multi-energy storage system does not improve, the current energy storage setting parameter set will be used as the simulation result.

7. The method according to claim 6, characterized in that, The method further includes: storing the set of energy storage setting parameters corresponding to the optimal energy storage efficiency in the energy storage setting parameter group corresponding to the energy storage setting parameter library.

8. An energy storage control device for a multi-energy storage system, characterized in that, The device includes: The monitoring module is used to monitor the energy storage efficiency of each energy storage subsystem in the multi-energy storage system, and to determine the energy storage subsystem to be optimized and the auxiliary energy storage subsystem based on the energy storage efficiency, wherein the energy storage efficiency of the auxiliary energy storage subsystem is higher than the energy storage efficiency of the energy storage subsystem to be optimized. The simulation module is used to perform energy storage efficiency simulation on the energy storage subsystem to be optimized based on the energy storage setting parameter set of the auxiliary energy storage subsystem, and obtain simulation results. The setting module is used to set the energy storage parameters of the multi-energy storage system based on the simulation results.

9. An electronic device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the energy storage control method of any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the energy storage control method of the multi-energy storage system according to any one of claims 1 to 7.

Images