A multi-scenario grid control method and device applicable to modular energy storage systems

Abstract

This invention discloses a multi-scenario network control method and device applicable to modular energy storage systems, belonging to the field of modular energy storage management technology. The method includes the following steps: acquiring test data of various energy storage unit modules and establishing unit models of the energy storage unit modules based on the test data; acquiring operating condition data of the energy storage unit modules and simulating and evaluating each unit model using the operating condition data to determine the target energy storage unit module; identifying energy storage system information and setting a target integrated energy storage module based on the energy storage system information; the target integrated energy storage module is composed of various target energy storage unit modules; performing simulation analysis based on the target integrated energy storage module and setting an energy storage analysis model; establishing a load prediction model and a condition prediction model, and generating a prediction information map based on the load prediction model and the condition prediction model; performing real-time energy storage analysis and adjustment based on the energy storage analysis model and the prediction information map; and switching scenarios when a switching command is received.

Description

Technical Field

[0001] This invention belongs to the field of modular energy storage management technology, specifically a multi-scenario grid control method and device applicable to modular energy storage systems. Background Technology

[0002] With the widespread use of renewable energy sources, such as solar and wind power generation, the stability of the power system faces new challenges. Modular energy storage systems, due to their flexibility and scalability, have become an important means of balancing supply and demand and improving power quality. By integrating multiple independent energy storage units and modular energy storage converters, modular energy storage systems achieve efficient energy storage and flexible dispatch, which is of great significance for improving grid stability and promoting the consumption of renewable energy.

[0003] However, in the actual operation of modular energy storage systems, the performance of the energy storage converter directly affects the overall efficiency and stability of the system. Especially during frequent switching between grid-connected and off-grid modes, the response speed, control accuracy, and system stability of the energy storage converter face severe challenges. Traditional energy storage system control strategies are often based on fixed parameters or empirical values, making it difficult to adapt to complex and changing load demands and grid conditions. This can lead to adverse phenomena such as energy fluctuations and voltage flicker during grid-connected / off-grid switching, affecting the reliability and safety of the system. Therefore, how to effectively control modular energy storage systems to adapt to different grid scenarios, especially the smooth switching between multiple operating modes, has become an urgent problem to be solved.

[0004] Based on this, the present invention provides a multi-scenario grid control method and device applicable to modular energy storage systems. Summary of the Invention

[0005] To address the problems of the above solutions, this invention provides a multi-scenario grid control method and device suitable for modular energy storage systems.

[0006] The objective of this invention can be achieved through the following technical solutions:

[0007] A multi-scenario grid control method applicable to modular energy storage systems includes the following steps:

[0008] Step 1: Obtain test data for various energy storage unit modules, and establish a unit model for each energy storage unit module based on the test data;

[0009] Step 2: Obtain the operating condition data of the energy storage unit module, simulate and evaluate each unit model using the operating condition data, and determine the target energy storage unit module;

[0010] Step 3: Identify the energy storage system information and set up the target integrated energy storage module based on the energy storage system information; the target integrated energy storage module is composed of various target energy storage unit modules;

[0011] Step 4: Perform simulation analysis based on the target integrated energy storage module and set up the energy storage analysis model;

[0012] Step 5: Establish load forecasting model and conditional forecasting model, and generate forecast information map based on the load forecasting model and conditional forecasting model;

[0013] Step 6: Perform real-time energy storage analysis and adjustment based on the energy storage analysis model and prediction information map; when a switching command is received, perform scenario switching.

[0014] Furthermore, the working condition data consists of each working condition and the working condition value corresponding to each working condition; the working condition is the probability of occurrence of the working condition.

[0015] Furthermore, the step of simulating and evaluating each unit model using the operating condition data to determine the target energy storage unit module includes:

[0016] The simulation results for each working condition are obtained by simulating each working condition in the working condition data using a unit model.

[0017] Establish a result judgment model, evaluate each simulation result through the result judgment model, and obtain the simulation judgment value of each working condition; identify the working condition value corresponding to each working condition in the working condition data;

[0018] According to the formula Calculate the corresponding unit simulation values;

[0019] In the formula: PA is the unit simulation value; τi is the working condition value of the corresponding working condition; PD(si) is the simulation judgment value, i = 1, 2, ..., n, where n is a positive integer;

[0020] Each energy storage unit module whose simulated value is not greater than the threshold X1 is marked as a candidate unit module;

[0021] Each of the candidate unit modules is displayed to the user, who then selects the candidate unit module for their application and marks the selected candidate unit module as the target energy storage unit module.

[0022] Furthermore, the expression for the result judgment model is:

[0023]

[0024] In the formula: si is the input data, which is the simulation result, i = 1, 2, ..., n, where n is a positive integer; the output data is the simulation judgment value PD(si).

[0025] Furthermore, the setting of the energy storage analysis model specifically includes:

[0026] Identify each target energy storage unit module within the target integrated energy storage module, match the corresponding unit model according to each target energy storage unit module, and establish an integrated model corresponding to the target integrated energy storage module based on each unit model;

[0027] Obtain working condition data, simulate and analyze the working condition data through the comprehensive model to obtain energy storage analysis materials, and establish an energy storage analysis model based on the energy storage analysis materials.

[0028] Furthermore, the generation of the forecast information map based on the load forecasting model and the conditional forecasting model includes:

[0029] Identify the current scenario mode, which includes grid-connected mode and off-grid mode, and mark the current scenario mode as the scenario application mode;

[0030] Based on the aforementioned application scenario, real-time analysis is performed using both load forecasting and conditional forecasting models to obtain corresponding load forecasting curves and conditional forecasting data. The horizontal axis of the load forecasting curve represents time, and the vertical axis represents the predicted load. The conditional forecasting data consists of the forecasting conditions corresponding to each time period.

[0031] Identify the time corresponding to each prediction condition in the conditional prediction data, supplement each prediction condition into the load prediction curve according to the corresponding time, and mark the load prediction curve as a prediction information map.

[0032] Furthermore, methods for real-time energy storage analysis and adjustment based on energy storage analysis models and predictive information maps include:

[0033] The energy storage analysis model is used to analyze the prediction conditions and predicted loads at each time point in the prediction information graph to obtain the corresponding impact values.

[0034] Based on the aforementioned impact values, a scenario switching assessment is conducted to identify time periods that do not meet the scenario switching requirements, which are then marked as energy storage adjustment periods. These energy storage adjustment periods are then marked accordingly in the forecast information map.

[0035] Energy storage adjustment simulation is performed, and the prediction information map is updated based on the load prediction model and the condition prediction model after the simulation adjustment to obtain the prediction information map corresponding to each energy storage adjustment mode, which is marked as the prediction simulation information map.

[0036] The energy storage analysis model is used to analyze the prediction conditions and predicted loads at each time point in the prediction simulation information graph to obtain the corresponding impact values; based on each impact value, it is determined whether the energy storage adjustment method is qualified.

[0037] The qualified energy storage adjustment methods are summarized to obtain the energy storage simulation adjustment results;

[0038] Energy storage adjustments are made based on the results of energy storage simulation.

[0039] Furthermore, methods for real-time energy storage analysis and adjustment based on energy storage analysis models and predictive information maps include:

[0040] Real-time acquisition of energy storage targets and real-time energy storage values; determination of energy storage adjustment segments based on real-time energy storage values ​​and energy storage targets;

[0041] Within the energy storage adjustment section, the prediction conditions and predicted loads corresponding to each time in the prediction information map are analyzed by the energy storage analysis model to obtain the influence value curves corresponding to each energy storage adjustment value. The horizontal axis of the influence value curve is time, and the vertical axis is the influence value.

[0042] The impact value curves are sorted according to the priority of each energy storage adjustment value to obtain the first sequence; the impact value curves in the first sequence are sorted and adjusted in turn to determine the target adjustment method, and the energy storage is adjusted according to the target adjustment method.

[0043] Furthermore, the method of sequentially adjusting and evaluating according to the order of the influence value curves in the first sequence includes:

[0044] Identify energy storage adjustment periods based on the impact value curve;

[0045] When there is no energy storage adjustment period, the energy storage adjustment value corresponding to the relevant impact value curve is marked as the target adjustment value, and the target adjustment method is determined based on the target adjustment value;

[0046] When there is an energy storage adjustment period, an energy storage adjustment simulation is performed. After the simulation adjustment, the forecast information map is updated based on the load forecasting model and the condition forecasting model to obtain the forecast information map corresponding to each energy storage adjustment mode, which is marked as the forecast simulation information map. The forecast conditions and forecast loads corresponding to each time in the forecast simulation information map are analyzed by the energy storage analysis model to obtain the corresponding impact values. The qualification of the energy storage adjustment mode is determined based on each impact value. If there is no qualified energy storage adjustment mode, the next impact value curve is evaluated. When there is a qualified energy storage adjustment mode, the target adjustment mode is determined based on the qualified energy storage adjustment mode and the energy storage adjustment value.

[0047] A multi-scenario grid control device suitable for modular energy storage systems includes:

[0048] Memory, used to store computer programs;

[0049] A processor is used to execute the computer program to implement a multi-scenario grid control method applicable to modular energy storage systems as described above.

[0050] Compared with the prior art, the beneficial effects of the present invention are:

[0051] By establishing a mathematical model based on test data from modular energy storage converters and setting impact curves for simulated grid-connected / off-grid switching under different loads, combined with load forecasting technology and adjustment strategies, this approach is an effective way to achieve efficient, stable operation and smooth switching of modular energy storage systems. This method not only improves the system's control accuracy and response speed but also significantly enhances its adaptability and reliability, providing strong support for the large-scale integration of renewable energy and the widespread application of distributed energy systems. Attached Figure Description

[0052] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0053] Figure 1 This is a flowchart illustrating a multi-scenario network control method applicable to modular energy storage systems, as described in an embodiment of the present invention. Detailed Implementation

[0054] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0055] like Figure 1 As shown, a multi-scenario grid control method suitable for modular energy storage systems includes the following steps:

[0056] Step 1: Obtain test data for various energy storage unit modules. Energy storage unit modules are modular energy storage devices within an energy storage system. This data can be targeted test data or historical usage data to understand the operating conditions and impacts of different types of energy storage unit modules under various environments, such as grid environment and natural environment. Based on the test data, establish unit models for each energy storage unit module. Unit simulation is a mathematical model built based on existing technology, capable of simulating the operating conditions and impacts of the corresponding energy storage unit module under different conditions. Alternatively, unit models can be built based on digital twin technology.

[0057] Step 2: Obtain operating condition data for the energy storage unit modules, including grid adjustment data, natural environmental condition data, and other data that affect the operation of the energy storage unit modules, summarized based on historical relevant data; that is, the operating condition data includes various operating conditions that the energy storage unit may encounter and the probability of occurrence of each operating condition, and the probability of occurrence of each operating condition is marked as the operating condition value; simulate and evaluate each unit model using the operating condition data to determine each energy storage unit module that meets the operating requirements, and mark it as a candidate unit module; display each candidate unit module to the user, and let the user select the candidate unit module to apply, and mark the applied candidate unit module as the target energy storage unit module;

[0058] In one embodiment, the method for determining the target energy storage unit module can be: manual evaluation and selection by professionals throughout the process.

[0059] In one embodiment, a method for simulating and evaluating each unit model using operating condition data includes:

[0060] The simulation of various working conditions in the working condition data is performed using a unit model to obtain the working status and impact under these conditions, such as the impact on the power grid and its own working effect. These results are then integrated and labeled as simulation results. Standard results are set according to relevant regulations, standards, and requirements; that is, simulation results that are not lower than the standard results are considered to meet the working requirements under these conditions. A result judgment model is established based on the standard results, primarily using data identification and judgment technology, to compare the simulation results with the standard results and determine whether the simulation results meet the standard results. The expression for the result judgment model is: In the formula: si is the input data, which is the simulation result, i = 1, 2, ..., n, where n is a positive integer; the output data is the simulation judgment value PD(si);

[0061] The simulation results are evaluated using a result judgment model to obtain the simulation judgment value corresponding to each working condition.

[0062] According to the formula Calculate the corresponding unit simulation values;

[0063] In the formula: PA is the unit simulation value; τi is the working condition value of the corresponding working condition; PD(si) is the simulation judgment value, i = 1, 2, ..., n, where n is a positive integer;

[0064] Set a threshold X1, such as 0, according to the user's requirements for the energy storage unit module; mark each energy storage unit module whose simulated value is not greater than the threshold X1 as a candidate unit module.

[0065] Step 3: Integrate and mark the target energy storage unit modules used in the energy storage system or the target energy storage unit modules that are subsequently expanded into a target integrated energy storage module, that is, dynamically update the target integrated energy storage module according to the energy storage system information.

[0066] Step 4: Conduct simulation analysis based on the target integrated energy storage module, and set up an energy storage analysis model. This model analyzes the impact of scenario mode switching of the target integrated energy storage module under different loads under current operating conditions. Scenario modes include grid-connected mode and off-grid mode (islanding mode). Subsequent scenario switching refers to switching from grid-connected mode to off-grid mode or vice versa. For ease of analysis and intuitive observation, the switching impact is generally quantified, expressed as an impact value. The greater the adverse impact, the larger its impact value. This can be done using existing numerical conversion methods. For example, determine the various switching impacts that the target integrated energy storage module may have based on the simulation results. The impact data is sorted in descending or ascending order, with the first and last data points set as endpoints of the impact value range, such as 0 or 100. Subsequently, impact values ​​are set for different impacts based on their differences, and then matched during analysis. For example, the impact value is primarily used for subsequent scene mode switching impact assessment. If the user's requirements for the impact of scene mode switching remain unchanged over a long period, it can be represented by 1 or 0; 1 indicates meeting the switching impact requirements, and 0 indicates otherwise. This primarily ensures that scene switching meets the user-defined requirements for smooth scene switching. However, if more frequent standard changes are required, setting the impact value from 0 to 100 is more convenient, and the preset value can be adjusted later.

[0067] The methods for setting up energy storage analysis models include:

[0068] Identify the unit models corresponding to the target energy storage units within the target integrated energy storage module. Based on the unit models of each target energy storage unit, establish a comprehensive model for the target integrated energy storage module. This comprehensive model simulates the operating conditions of the target integrated energy storage module under different operating conditions, acquires operating condition data, and simulates the operating condition data using the comprehensive model to obtain the impact of the target integrated energy storage module under various operating conditions and loads. The impact is then converted into impact values. This data is integrated into energy storage analysis material, and an energy storage analysis model is established based on this material. Alternatively, the energy storage analysis model can be established using existing matching techniques, followed by matching based on the energy storage analysis material; or it can be established using neural networks such as DNN networks, with a training set set based on the energy storage analysis material for training.

[0069] Step 5: Establish a load forecasting model and a condition forecasting model. The load forecasting model is used to forecast the energy storage load, that is, to forecast the load of the current energy storage system and predict the load situation after a period of time. Specifically, it is to establish a load forecasting model using existing load forecasting technologies. The condition forecasting model is used to predict the subsequent operating conditions, based on existing grid forecasting, environmental forecasting and other technologies.

[0070] Identify the current scene pattern and mark it as the scene application pattern;

[0071] In scenario application mode, load forecasting is performed in real time through load forecasting model to obtain load forecasting curve, with time on the horizontal axis and forecasted load on the vertical axis; condition forecasting is performed in real time through condition forecasting model to obtain condition forecasting data, which is then added to the load forecasting curve according to the corresponding time, and the current load forecasting curve is marked as a forecasting information map.

[0072] Step 6: Perform real-time energy storage analysis and adjustment based on the energy storage analysis model and prediction information map; when a switching command is received, perform scenario switching.

[0073] In one embodiment, a method for real-time energy storage analysis and adjustment based on an energy storage analysis model and a prediction information map includes:

[0074] The prediction conditions and predicted loads at each time point in the prediction information map are analyzed using an energy storage analysis model to obtain the corresponding impact values.

[0075] Based on the impact value, scenario switching is assessed, and time periods that do not meet the scenario switching requirements are marked as energy storage adjustment periods. For impact values ​​of 1 or 0, a direct judgment can be made. For impact values ​​between 0 and 100, a judgment is made based on the corresponding preset value. If the value is greater than the preset value, the scenario switching requirements are not met. The energy storage adjustment periods are marked accordingly in the forecast information map.

[0076] Energy storage adjustment simulation involves simulating the energy storage system's adjustments, such as increasing energy storage, adjusting charging and discharging rates, and inverter output power. This determines whether the system can promptly meet standards and achieve a smooth transition between scenarios when a mode switching command is received. For example, switching from grid-connected to off-grid mode requires rapid adjustment of the energy storage system's charging and discharging rates and the inverter's output power; switching from off-grid to grid-connected mode requires a pre-synchronization control strategy to quickly synchronize the inverter's output voltage amplitude and phase with the mains grid. Therefore, energy storage adjustments can be pre-simulated and analyzed to determine which conditions allow for a smooth transition when a scenario switching command is received, and these results are integrated into the energy storage simulation.

[0077] For example, an energy storage adjustment simulation is performed, and the prediction information map is updated based on the load prediction model and the condition prediction model. The energy storage adjustment will lead to load changes. The specific energy storage adjustment can be carried out by adjusting one adjustable parameter at a time, or a corresponding simulation adjustment strategy can be preset, and the simulation adjustment is carried out according to the simulation adjustment strategy. The prediction information map corresponding to each energy storage adjustment method is obtained and marked as the prediction simulation information map.

[0078] The prediction conditions and predicted loads at each time point in the prediction simulation information graph are analyzed using an energy storage analysis model to obtain the corresponding impact values; the suitability of the energy storage adjustment method is then determined based on these impact values.

[0079] The qualified energy storage adjustment methods are summarized to obtain the energy storage simulation adjustment results.

[0080] Energy storage adjustments are made based on the results of energy storage simulations; specifically, adjustments can be made randomly or by using other selection criteria and priority evaluation methods to select the appropriate energy storage adjustment method for the application.

[0081] In one embodiment, the energy storage system manages energy storage according to actual conditions during application. Therefore, there is an energy storage target during the management process, namely the expected energy storage target to be achieved at each time. As conditions change, the energy storage target is in a state of flux. In order to ensure the operation of the energy storage system, corresponding adjustments can be made based on the energy storage target. Another method for real-time energy storage analysis and adjustment based on energy storage analysis models and predictive information maps is as follows:

[0082] The system acquires the energy storage target and the current energy storage value in real time, and marks the current energy storage value as the real-time energy storage value. Based on the real-time energy storage value and the energy storage target, the system determines the energy storage adjustment segment, which is the distance from the real-time energy storage value to the energy storage target, including the corresponding endpoints.

[0083] Within the energy storage adjustment section, the prediction conditions and predicted loads corresponding to each time in the prediction information map are analyzed by the energy storage analysis model to obtain the influence value curves corresponding to each energy storage adjustment value. The horizontal axis represents time and the vertical axis represents influence value.

[0084] The curves of each influence value are sorted in descending order of energy storage adjustment value, with the larger the energy storage adjustment value, the closer it is to the energy storage target; thus, the first sequence is obtained. Specifically, the energy storage adjustment values ​​are sorted according to their priority order, generally with higher priority for values ​​closer to the energy storage target. If the priority is not determined according to this principle, the order of the energy storage adjustment values ​​is determined according to the analysis method of the energy storage target. Since the existing technology evaluates each energy storage value when determining the energy storage target, the priority of each energy storage adjustment value can be determined based on its determination method.

[0085] The energy storage system is adjusted and evaluated sequentially according to the order of the impact value curves in the first sequence, the target adjustment method is determined, and the energy storage system is adjusted according to the target adjustment method.

[0086] The method of sequentially adjusting and evaluating based on the order of the influence value curves in the first sequence includes:

[0087] Identify energy storage adjustment periods based on the impact value curve;

[0088] When there is no energy storage adjustment period, the energy storage adjustment value corresponding to the impact value curve is marked as the target adjustment value, and the target adjustment method is determined based on the target adjustment value.

[0089] When there is an energy storage adjustment period, an energy storage adjustment simulation is performed. After the simulation adjustment, the forecast information map is updated based on the load forecasting model and the condition forecasting model to obtain the forecast information map corresponding to each energy storage adjustment method. This map is marked as the forecast simulation information map, excluding the adjustment of the energy storage value, and the default fixed energy storage adjustment value is used. The forecast conditions and forecast loads corresponding to each time in the forecast simulation information map are analyzed by the energy storage analysis model to obtain the corresponding impact values. The suitability of the energy storage adjustment method is determined based on each impact value. If there is no suitable energy storage adjustment method, the next impact value curve is evaluated. If there is a suitable energy storage adjustment method, the target adjustment method is determined based on the suitable energy storage adjustment method and the energy storage adjustment value.

[0090] A multi-scenario grid control device suitable for modular energy storage systems includes:

[0091] Memory, used to store computer programs;

[0092] The processor is used to execute computer programs to implement the steps of the above embodiment (a multi-scenario grid control method applicable to modular energy storage systems).

[0093] The above formulas are all numerical calculations after removing dimensions. The formulas are obtained by software simulation based on a large amount of data and are closest to the real situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulation based on a large amount of data.

[0094] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0095] The above description is merely a preferred embodiment of the present invention and does not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

[0096] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

[0097] For ease of description, the above apparatus is described in terms of function, with each unit described separately. Of course, in implementing this application, the functions of each unit can be implemented in one or more software and / or hardware components. Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0098] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0099] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 The function specified in one or more boxes.

[0100] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

Claims

1. A multi-scenario network configuration control method suitable for a modular energy storage system, characterized in that, The method comprises the following steps: Step 1: obtaining test data of various energy storage unit modules, and establishing a unit model of the energy storage unit module based on the test data; Step 2: obtaining working condition data of the energy storage unit module, simulating and evaluating each unit model based on the working condition data, and determining a target energy storage unit module; Step 3: identifying energy storage system information, and setting a target comprehensive energy storage module according to the energy storage system information; the target comprehensive energy storage module is composed of each target energy storage unit module; Step 4: simulating and analyzing according to the target comprehensive energy storage module, and setting an energy storage analysis model; Step 5: establishing a load prediction model and a condition prediction model, and generating a prediction information graph based on the load prediction model and the condition prediction model; Step 6: performing real-time energy storage analysis and adjustment based on the energy storage analysis model and the prediction information graph; When a switching instruction is received, scene switching is performed.

2. The multi-scenario network configuration control method for the modular energy storage system according to claim 1, wherein, The working condition data is composed of each working condition and a working condition value corresponding to each working condition; the working condition is the occurrence probability of the working condition.

3. The multi-scenario network configuration control method for the modular energy storage system according to claim 2, wherein, The determination of the target energy storage unit module based on the simulation and evaluation of each unit model based on the working condition data comprises: Simulating each working condition in the working condition data by using the unit model to obtain a simulation result corresponding to each working condition; Establishing a result judgment model, evaluating each simulation result by using the result judgment model to obtain a simulation judgment value of each working condition, and identifying a working condition value corresponding to each working condition in the working condition data; According to the formula the corresponding cell simulation value is calculated; In the formula, PA is a unit simulation value, τi is a working condition value of a corresponding working condition, PD(si) is a simulation judgment value, i=1, 2, …, n, and n is a positive integer; Each energy storage unit module with a unit simulation value not greater than a threshold value X1 is marked as a selected unit module; Each selected unit module is displayed to a user, and the user selects an applied selected unit module, and the selected applied selected unit module is marked as a target energy storage unit module.

4. The multi-scenario network configuration control method for the modular energy storage system according to claim 3, wherein, The expression of the result judgment model is: In the formula, si is input data, the input data is a simulation result, i=1, 2, …, n, n is a positive integer, and output data is a simulation judgment value PD(si).

5. The multi-scenario network configuration control method for modular energy storage system according to claim 1, wherein, The setting of the energy storage analysis model specifically comprises: Identifying each target energy storage unit module in the target comprehensive energy storage module, matching a corresponding unit model according to each target energy storage unit module, and establishing a comprehensive model corresponding to the target comprehensive energy storage module according to each unit model; Obtaining working condition data, simulating and analyzing the working condition data by using the comprehensive model to obtain energy storage analysis materials, and establishing an energy storage analysis model based on the energy storage analysis materials.

6. The multi-scenario network configuration control method for a modular energy storage system according to claim 1, wherein, The generation of the prediction information graph based on the load prediction model and the condition prediction model comprises: Identifying a current scene mode, the scene mode comprising a grid-connected mode and an off-grid mode, and marking the current scene mode as a scene application mode; Real-time analysis is performed on the load prediction model and the conditional prediction model respectively based on the application mode of the scenario, and corresponding load prediction curves and conditional prediction data are obtained; the horizontal axis of the load prediction curve is time, and the vertical axis is predicted load; the conditional prediction data is composed of predicted conditions corresponding to each time; The time corresponding to each predicted condition in the conditional prediction data is identified, each predicted condition is supplemented to the load prediction curve according to the corresponding time, and the load prediction curve is marked as a prediction information graph.

7. The multi-scenario network configuration control method for a modular energy storage system according to claim 1, wherein, The method for real-time energy storage analysis and adjustment based on the energy storage analysis model and the prediction information graph comprises: The predicted conditions and the predicted load corresponding to each time in the prediction information graph are analyzed by the energy storage analysis model, and corresponding influence values are obtained; Scene switching evaluation is performed according to the influence values, time periods that do not meet the scene switching requirements are obtained, and are marked as energy storage adjustment periods; the energy storage adjustment periods are marked in the prediction information graph; Energy storage adjustment simulation is performed, and the prediction information graph is updated based on the load prediction model and the conditional prediction model after the simulation adjustment, and corresponding prediction information graphs under each energy storage adjustment mode are obtained and marked as prediction simulation information graphs; The predicted conditions and the predicted load corresponding to each time in the prediction simulation information graph are analyzed by the energy storage analysis model, and corresponding influence values are obtained; whether the energy storage adjustment mode is qualified is determined according to the influence values; The qualified energy storage adjustment modes are summarized, and an energy storage simulation adjustment result is obtained; Energy storage adjustment is performed according to the energy storage simulation adjustment result.

8. The multi-scenario network configuration control method for a modular energy storage system according to claim 1, wherein, The method for real-time energy storage analysis and adjustment based on the energy storage analysis model and the prediction information graph comprises: Real-time energy storage targets and real-time values are obtained; the energy storage adjustment section is determined according to the real-time values and the targets; The predicted conditions and the predicted load corresponding to each time in the prediction information graph are analyzed by the energy storage analysis model in the energy storage adjustment section, and influence value curves corresponding to each energy storage adjustment value are obtained; the horizontal axis of the influence value curve is time, and the vertical axis is the influence value; The influence value curves are sorted according to the priority of each energy storage adjustment value, and a first sequence is obtained; the target adjustment mode is determined by sequentially adjusting and evaluating according to the sorting of each influence value curve in the first sequence, and the energy storage is adjusted according to the target adjustment mode.

9. The multi-scenario network configuration control method for a modular energy storage system according to claim 8, wherein, The method for sequentially adjusting and evaluating according to the sorting of each influence value curve in the first sequence comprises: Energy storage adjustment period identification is performed according to the influence value curve; When there is no energy storage adjustment period, the energy storage adjustment value corresponding to the corresponding influence value curve is marked as a target adjustment value, and the target adjustment mode is determined according to the target adjustment value; When the energy storage adjustment period is present, energy storage adjustment simulation is performed, and the prediction information graph is updated based on the load prediction model and the condition prediction model after the simulation adjustment, obtaining the corresponding prediction information graph under each energy storage adjustment mode, marked as the prediction simulation information graph; the prediction conditions and the prediction load corresponding to each time in the prediction simulation information graph are analyzed through the energy storage analysis model, obtaining the corresponding influence value; whether the energy storage adjustment mode is qualified is judged according to each influence value; when there is no qualified energy storage adjustment mode, the next influence value curve is evaluated; when there is a qualified energy storage adjustment mode, the target adjustment mode is determined according to the qualified energy storage adjustment mode and the energy storage adjustment value.

10. A multi-scenario network configuration control device suitable for a modular energy storage system, characterized in that, Comprise: a memory for storing a computer program; a processor for executing the computer program to implement a multi-scenario network construction control method for a modular energy storage system according to any one of claims 1 to 9.

Images