Microgrid storage and load coordinated control system and method based on time constraint

Abstract

The invention provides a time constraint-based micro-grid storage load coordinated control system and method, and relates to the technical field of micro-grids, and the method comprises the steps: carrying out the operation collection of a micro-grid, and obtaining a plurality of operation data sets; constructing a prediction model to perform operation prediction on the micro-grid to obtain an operation prediction result; constructing a time constraint condition based on the multiple pieces of energy storage data and the multiple pieces of power load data, performing load storage operation control constraint on the microgrid, and generating an energy storage control constraint information set and a load control constraint information set; formulating a coordination control scheme according to the operation prediction result in combination with the energy storage and load control constraint information set; executing the coordination control scheme to perform simulation testing and monitoring feedback, and generating a control feedback result; and generating a coordination control optimization scheme according to the control feedback result to perform intelligent coordination control on the microgrid storage load. The technical problems of low coordination control efficiency and resource waste of a traditional storage load coordination control technology are solved, and the operation efficiency and the power supply stability of the micro-grid are improved.

Description

Technical Field

[0001] The present application relates to the field of microgrid technology, and in particular to a microgrid load-storage coordination control system and method based on time constraints. Background Art

[0002] In the context of today's energy structure transformation and smart grid development, microgrid, as a new type of grid that integrates multiple distributed generation and energy storage technologies and can operate independently, has become one of the key technologies for achieving efficient energy utilization and large-scale integration of renewable energy. Microgrid storage-load coordinated control is the key to ensuring efficient and stable operation of microgrids, which involves the charge and discharge management of energy storage units, the optimal distribution of power loads, and the interaction strategy with the main grid.

[0003] At present, the coordinated control technology of energy storage and load in microgrids mainly relies on traditional prediction models and control methods. These methods can achieve the optimal scheduling of energy storage and load to a certain extent, and ensure the reliable operation of microgrids. However, the existing technology still has certain shortcomings when dealing with the complex and changeable environment of microgrids. First, the accuracy of the prediction model is insufficient, and it is difficult to accurately capture the dynamic characteristics of the microgrid, resulting in a deviation between the control strategy and actual demand. Secondly, the existing technology has difficulties in dealing with time constraints, and it is difficult to ensure the stable operation of the microgrid while meeting specific scheduling requirements. Furthermore, the coordinated control of energy storage and load is inefficient, resulting in a waste of resources. Summary of the invention

[0004] The present application provides a microgrid load-storage coordination control system and method based on time constraints, which solves the technical problem that traditional load-storage coordination control technology is difficult to accurately capture the dynamic characteristics of the microgrid, resulting in low coordination control efficiency and waste of resources, and achieves the technical effect of improving the operating efficiency and power supply stability of the microgrid.

[0005] In view of the above problems, on the one hand, the present application provides a microgrid load-storage coordination control system based on time constraints, the system comprising: an operation acquisition module, the operation acquisition module is used to perform operation acquisition on the microgrid to obtain multiple operation data sets, the multiple operation data sets include multiple power generation source data, multiple energy storage data, and multiple power load data; an operation prediction module, the operation prediction module is used to build a prediction model based on the multiple power generation source data, the multiple energy storage data, and the multiple power load data, and perform operation prediction on the microgrid through the prediction model to obtain an operation prediction result; a time constraint construction module, the time constraint construction module is used to build time constraint conditions based on the multiple energy storage data and the multiple power load data; control constraint operation Module, the control constraint operation module is used to execute the time constraint condition to perform storage-load operation control constraints on the microgrid, and generate a storage control constraint information set and a load control constraint information set; a plan formulation module, the plan formulation module is used to formulate a coordinated control plan based on the operation prediction result in combination with the storage control constraint information set and the load control constraint information set; a control feedback module, the control feedback module is used to execute the coordinated control plan for simulation testing, synchronize the test results to the feedback optimization unit for monitoring and feedback, and generate a control feedback result; a plan optimization module, the plan optimization module is used to update and optimize the coordinated control plan according to the control feedback result, and generate a coordinated control optimization plan to perform intelligent coordinated control on the microgrid storage and load.

[0006] On the other hand, the present application also provides a microgrid load-storage coordinated control method based on time constraints, the method comprising: performing operation collection on the microgrid to obtain multiple operation data sets, the multiple operation data sets including multiple power generation source data, multiple energy storage data, and multiple power load data; constructing a prediction model based on the multiple power generation source data, the multiple energy storage data, and the multiple power load data, and performing operation prediction on the microgrid through the prediction model to obtain operation prediction results; constructing time constraints based on the multiple energy storage data and the multiple power load data; executing the time constraints to perform load-storage operation control constraints on the microgrid, and generating an energy storage control constraint information set and a load control constraint information set; formulating a coordinated control plan based on the operation prediction results combined with the energy storage control constraint information set and the load control constraint information set; executing the coordinated control plan to perform simulation testing, synchronizing the test results to the feedback optimization unit for monitoring and feedback, and generating a control feedback result; updating and optimizing the coordinated control plan based on the control feedback result, and generating a coordinated control optimization plan to perform intelligent coordinated control of the microgrid load-storage.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The operation acquisition module acquires multiple operation data sets by operating the microgrid, providing a real-time data basis for subsequent analysis and control, and ensuring the pertinence and accuracy of the control strategy. The operation prediction module constructs a prediction model based on the multiple power generation source data, the multiple energy storage data, and the multiple power load data, predicts the future operation state of the microgrid, obtains the operation prediction results, provides a basis for the control strategy, and improves the prediction accuracy of the dynamic changes of the microgrid. The time constraint construction module constructs time constraints based on the multiple energy storage data and the multiple power load data to ensure that the control strategy meets specific scheduling and time requirements, and enhances the practicality and adaptability of the control strategy. The control constraint operation module executes the time constraints to constrain the storage and load operation of the microgrid, generates an energy storage control constraint information set and a load control constraint information set, guides the operation of energy storage and load, and improves the efficiency of energy storage and load management. The plan formulation module formulates a coordinated control plan based on the operation prediction results combined with the energy storage control constraint information set and the load control constraint information set, and realizes efficient coordination of energy storage and load. The control feedback module executes the coordinated control scheme for simulation testing, synchronizes the test results to the feedback optimization unit for monitoring and feedback, generates control feedback results, verifies the effectiveness of the control scheme before actual application, and evaluates the actual effect of the control scheme, ensuring the operability and safety of the control scheme, and provides optimization direction. The scheme optimization module updates and optimizes the coordinated control scheme according to the control feedback results, generates a coordinated control optimization scheme to perform intelligent coordinated control of the microgrid load storage to adapt to the real-time changes of the microgrid, and improves the dynamic adaptability and optimization level of the control strategy.

[0009] To summarize, this application achieves precise control of power generation, energy storage and load in the microgrid by coordinating the work of various modules and comprehensively considering time factors, prediction results and constraints. It not only improves the stability and reliability of the microgrid, but also improves the system's adaptability and ability to respond to emergencies, and promotes the development of the power grid in a more intelligent and green direction.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A schematic diagram of the structure of a microgrid load-storage coordination control system based on time constraints provided in an embodiment of the present application;

[0012] Figure 2A schematic diagram of a process for constructing time constraint conditions in a microgrid load-storage coordination control system based on time constraints provided in an embodiment of the present application;

[0013] Figure 3 A schematic diagram of a process for intelligent coordinated control in a microgrid load storage coordinated control system based on time constraints provided in an embodiment of the present application;

[0014] Figure 4 A flow chart of a microgrid load-storage coordination control method based on time constraints provided in an embodiment of the present application.

[0015] Explanation of the reference numerals: operation collection module 10 , operation prediction module 20 , time constraint construction module 30 , control constraint operation module 40 , plan formulation module 50 , control feedback module 60 , plan optimization module 70 . DETAILED DESCRIPTION

[0016] The embodiments of the present application provide a microgrid load-storage coordination control system and method based on time constraints, thereby solving the technical problem that traditional load-storage coordination control technology is difficult to accurately capture the dynamic characteristics of the microgrid, resulting in low coordination control efficiency and waste of resources, thereby achieving the technical effect of improving the operating efficiency and power supply stability of the microgrid.

[0017] Embodiment 1, as Figure 1 As shown, the embodiment of the present application provides a microgrid load storage coordination control system based on time constraints, and the system includes:

[0018] The operation collection module 10 is used to collect operation data of the microgrid to obtain multiple operation data sets, and the multiple operation data sets include multiple power generation source data, multiple energy storage data, and multiple power load data.

[0019] Specifically, the operation acquisition module 10 is the primary link in the microgrid load-storage coordination control system. Its main task is to conduct comprehensive data collection on the real-time operation status of the microgrid to obtain the necessary information for subsequent analysis and control. The operation data set refers to a series of data collected from the microgrid, which reflects various aspects of the power grid, including multiple power generation source data, multiple energy storage data, and multiple power load data. Among them, the power generation source data refers to the output of each power generation facility in the microgrid, such as the electricity generated by solar panels, the output power of wind turbines, etc.; the energy storage data refers to the status of the energy storage device, such as the remaining power of the battery pack, the charge and discharge rate, etc.; the power load data refers to the power consumption data of all power-consuming devices or users in the microgrid, such as load size, power consumption time, load changes, etc., covering the power consumption in different time periods.

[0020] The operation acquisition module 10 uses various sensors and monitoring devices to monitor various parameters of the microgrid in real time. For example, power sensors installed on solar panels and wind turbines can measure their output power, while power meters installed on batteries or other energy storage devices can track their charging and discharging status. As for the user's electricity consumption, it can be recorded by smart meters. The data collected by these devices will be summarized and transmitted to the operation acquisition module 10 through the communication network to form multiple operation data sets. The operation acquisition module 10 realizes comprehensive monitoring of the power generation source, energy storage device and power load in the microgrid, providing a data basis for subsequent prediction and control.

[0021] The operation prediction module 20 is used to build a prediction model based on the multiple power generation source data, the multiple energy storage data, and the multiple power load data, and to perform operation prediction on the microgrid through the prediction model to obtain an operation prediction result.

[0022] Specifically, the core function of the operation prediction module 20 is to use existing data to predict the future operation status of the microgrid. The prediction model is a mathematical model that predicts future power supply and demand by analyzing historical and real-time power generation source data, energy storage data, and power load data. The operation prediction module 20 uses statistical analysis software and machine learning platforms, such as time series analysis, regression analysis, or deep learning networks, to analyze multiple power generation source data, energy storage data, and power load data, build a prediction model, and use the model to predict the future operation of the microgrid to obtain the operation prediction results, where the operation prediction results refer to the data output by the prediction model about the future operation status of the microgrid, such as power generation, energy storage status, load demand, etc.

[0023] Furthermore, the prediction module 20 in the embodiment of the present application is also used to perform the following steps:

[0024] Step P21: using the multiple power generation source data as indexes, matching the multiple energy storage data and the multiple power load data, and obtaining the charge and discharge data and power load data of the multiple power generation sources.

[0025] Step P22: Feature extraction is performed based on the data of the multiple power generation sources combined with the charging and discharging data of the multiple power generation sources and the power load data to obtain energy storage characteristics and load characteristics of the multiple power generation sources.

[0026] Step P23: performing normalization processing based on the energy storage characteristics of the multiple power generation sources and the load characteristics, performing integrated learning based on the normalized characteristics, and training and constructing the prediction model.

[0027] Specifically, the index refers to the reference point used to identify and sort data, that is, the time series of power generation source data. Using the power generation source data as a time index, it can be matched with the energy storage data and the power load data to form a complete picture of power flow. That is, the module will find the corresponding energy storage device charging and discharging activities and the user's power consumption data according to the output time point of the power generation source, thereby depicting the inflow and outflow of electricity, and obtaining the charging and discharging data and power load data of multiple power generation sources. Among them, the charging and discharging data is data about the charging and discharging status of the energy storage system, including charging amount, discharging amount, charging and discharging rate, etc. The power load data is data reflecting the power user demand corresponding to the power generation source, such as load size, load change trend, etc. For example, if the power generation of the photovoltaic power generation system is 500kW at a certain point in time, then the corresponding energy storage system charging and discharging data and power load data should also be data at the same time point. In this way, the charging, discharging and load conditions of each power generation source at a specific time point can be obtained.

[0028] Feature extraction refers to extracting meaningful information from raw data, including energy storage characteristics and load characteristics of multiple power generation sources. This information can reflect the relationship and pattern between power generation sources, energy storage and load. Among them, energy storage characteristics refer to the characteristics extracted from energy storage data that can represent the state and behavior of the energy storage system. Load characteristics refer to the characteristics extracted from power load data that can represent the load demand characteristics. The module extracts features based on the matched data. For example, the battery charging state, discharge rate, etc. can be extracted from energy storage data as energy storage characteristics; load peaks, load fluctuations, etc. can be extracted from power load data as load characteristics. These features will be used to describe the operating characteristics of the microgrid.

[0029] Normalization is to allow different types of data to be compared and analyzed under the same standard, eliminate the impact of dimensions, and make model training more accurate. Ensemble learning is a machine learning method that combines the predictions of multiple models to improve the overall prediction accuracy. The module normalizes the extracted features and converts all data into the same numerical range so that the model can be more easily processed. Finally, an ensemble learning method, such as a random forest or gradient boosting machine or a neural network, is used to train the prediction model so that it learns to predict future electricity supply and demand. For example, using the random forest algorithm, the module can combine multiple decision trees to predict the power generation, energy storage status, and load demand of the microgrid over a period of time in the future.

[0030] Through the above steps, the operation prediction module 20 can build an accurate and reliable prediction model to provide support for the optimized scheduling and stable operation of the microgrid.

[0031] The time constraint building module 30 is used to build time constraint conditions based on the multiple energy storage data and the multiple power load data.

[0032] Specifically, time constraints refer to restrictions or requirements that must be met within a specific time frame. These conditions usually include the charging and discharging time of the energy storage system, the time window for reducing or increasing the power load, etc. They define how the microgrid should operate at different time points to meet the requirements of power supply, demand and safety. The module first analyzes the energy storage data and power load data, and sets thresholds and rule engines based on the analysis results to define time constraints and determine the operating restrictions of the power grid at a specific time point. For example, if it is predicted that the power demand is high during a certain period of time, the system may set rules to ensure that the energy storage equipment is fully charged before then. If a power generation facility needs maintenance, the system will set rules to reduce reliance on the facility during this period. The time constraint construction module 30 ensures that the microgrid can make appropriate adjustments according to changes in time and optimize the use and distribution of electricity.

[0033] Further, such as Figure 2 As shown, the time constraint construction module 30 in the embodiment of the present application is also used to perform the following steps:

[0034] Step P31: Analyze the charge and discharge characteristics based on the multiple energy storage data to obtain energy storage analysis results.

[0035] Step P32: Analyze load change characteristics based on the multiple power load data to obtain load forecast trends.

[0036] Step P33: Determine the power dispatch demand information according to the load forecast trend and the energy storage analysis result.

[0037] Step P34: Calculate the charging and discharging efficiency, and define the energy storage charging and discharging time window in combination with the power dispatch demand information.

[0038] Step P35: Retrieve multiple operation cycles of the microgrid and determine the load fluctuation threshold in combination with the power dispatch demand information, and define the load demand interval value according to the load fluctuation threshold.

[0039] Step P36: Construct the time constraint condition of the microgrid according to the charging and discharging time window and the load demand interval value.

[0040] Specifically, the charge and discharge characteristics refer to the charge and discharge behaviors of energy storage devices in different time periods, which can reflect the supply and demand balance of the power grid. The energy storage analysis results are the conclusions or data drawn through analysis on the charge and discharge characteristics of the energy storage system. The module uses data analysis and mining tools, such as association rule analysis, the pandas library in Python, etc., to process and analyze energy storage data. The average charge and discharge amount of energy storage devices in different time periods, as well as the charge and discharge frequency, are calculated to identify the best charge and discharge characteristics and obtain energy storage analysis results. For example, use time series analysis to identify patterns, such as in which time period the energy storage device is most frequently used, or the behavior of the energy storage device when specific events such as weather changes occur.

[0041] Load change characteristics are trends extracted from power load data, indicating changes in power demand over time. Load forecast trends are predictions of future power load change trends. The module uses time series analysis tools, such as ARIMA models or seasonal decomposition time series analysis, to analyze power load data, such as household and commercial power consumption patterns, predict power load change trends, and obtain load forecast trends.

[0042] Power dispatch demand information is based on load forecast trends and energy storage analysis results, and is the demand and restriction information that guides power dispatch operations. It determines the power distribution needs of the power grid in different time periods. The module combines energy storage analysis results and load forecast trends to determine power dispatch demand information using decision support systems. These systems can help assess how much backup power the grid needs and when it needs it under different forecast scenarios. For example, if the forecast shows that tomorrow's demand will be higher than average, the system may recommend filling up the energy storage equipment in advance.

[0043] The charge and discharge efficiency refers to the energy conversion efficiency of the energy storage device during the charging and discharging process, which directly affects the energy management and cost-effectiveness of the power grid. By calculating this efficiency, the optimal charge and discharge time can be determined to maximize energy utilization. The charge and discharge time window refers to the specific time range in which the power grid can be charged and discharged, which is usually set according to the expected changes in electricity demand and supply. The module records the charge and discharge speed and energy loss under different temperatures and loads, and uses optimization algorithms such as linear programming to calculate the charge and discharge efficiency of the energy storage system, and combines the power dispatch demand information to determine the optimal charge and discharge time window. For example, if the charge and discharge efficiency is highest in the middle of the night, but the electricity demand is lowest, we may choose to charge and discharge during this time period.

[0044] The operating cycle is the time it takes for the power grid to complete a complete cycle, such as 24 hours a day. The load fluctuation threshold is the acceptable range of changes in power demand, which helps define the service level that the power grid must maintain. The load demand interval value is the expected range of load over a certain period of time. The module extracts historical data from the power grid's log system, and then uses historical data and statistical tools, such as variance analysis, to determine the threshold of load fluctuations and define the load demand interval value in combination with power dispatch demand information. For example, if historical data shows that the load has rarely exceeded a certain value in the past few months, we can use it as an upper limit to define the load demand interval value.

[0045] Finally, the module uses optimization algorithms, such as genetic algorithms or particle swarm optimization, to build time constraints. These algorithms can help find the optimal solution to meet the power dispatch requirements while taking into account the charging and discharging time and load demand interval values.

[0046] Through the above steps, the time constraint construction module 30 can ensure that the microgrid operates according to the established constraint conditions at a specific time point or time period, thereby improving the operating efficiency and reliability of the microgrid.

[0047] The control constraint operation module 40 is used to execute the time constraint condition to perform storage-load operation control constraints on the microgrid, and generate an energy storage control constraint information set and a load control constraint information set.

[0048] Specifically, the energy storage control constraint information set includes the operation instructions that the energy storage system should perform under the time constraint, such as the charge and discharge amount, the charge and discharge rate, etc. The load control constraint information set includes the operation instructions that the load should perform under the time constraint, such as the load reduction amount, the load increase amount, etc. The control constraint operation module 40 first analyzes the time constraint conditions and determines the operation instructions of the energy storage and the load. For example, if the time constraint condition requires that the energy storage system must maintain sufficient power supply between 7 pm and 9 pm, then the energy storage control constraint information set will include this requirement. At the same time, if the load forecast trend shows that the load will increase during this time period, the load control constraint information set will include instructions for load reduction or increase. The module uses a pre-control algorithm, such as optimal control theory or predictive control, to generate the control constraint information set of energy storage and load. For example, optimal control theory can be used to determine the optimal charge and discharge strategy of the energy storage system under the time constraint conditions, and predictive control can be used to predict and adjust the load demand. The module can also use a real-time monitoring system, such as a SCADA system, to monitor the operating status of the energy storage and load in real time, and make real-time adjustments according to the control constraint information set. For example, if the actual charge and discharge rate of the energy storage system does not match the instructions in the control constraint information set, the module will adjust the charge and discharge operations of the energy storage system through the SCADA system to ensure that the time constraints are met.

[0049] Through the above steps, the control constraint operation module 40 can ensure that the microgrid operates according to the established constraint conditions at a specific time point or time period, thereby improving the operation efficiency and reliability of the microgrid.

[0050] A plan formulation module 50 is used to formulate a coordinated control plan according to the operation prediction result combined with the energy storage control constraint information set and the load control constraint information set.

[0051] Specifically, the coordinated control scheme refers to the optimal control strategy developed based on the prediction results and control constraint information to guide the operation of the microgrid.

[0052] The plan formulation module 50 first analyzes the operation prediction results to understand the operating status of the microgrid in the future. For example, the prediction model may predict that the power generation of the microgrid will be lower than the load demand between 2 pm and 4 pm. Next, the plan formulation module 50 analyzes the energy storage control constraint information set and the load control constraint information set to determine the operating instructions of the energy storage system and the load under the time constraint. For example, the energy storage control constraint information set may include that between 2 pm and 4 pm, the energy storage system needs to discharge to make up for the lack of power generation. At the same time, the load control constraint information set may include that during this time period, non-essential loads need to be reduced to reduce the total load. Combining this information, the plan formulation module 50 uses an optimization algorithm, such as mixed integer linear programming or a heuristic algorithm, to formulate a coordinated control plan. For example, the optimization algorithm may recommend that the energy storage system discharge at a rate of 200kW between 2 pm and 4 pm, while reducing non-essential loads by 200kW.

[0053] Through the above process, the plan formulation module 50 ensures that the microgrid can maintain stable operation under various conditions while maximizing energy utilization efficiency.

[0054] The control feedback module 60 is used to execute the coordinated control scheme to perform simulation testing, synchronize the test results to the feedback optimization unit for monitoring and feedback, and generate control feedback results.

[0055] Specifically, the control feedback module 60 simulates and tests the coordinated control scheme and sends the test results to the feedback optimization unit for monitoring and further analysis. This process is to evaluate the effectiveness of the coordinated control scheme, ensure that the actual effect of the coordinated control scheme is consistent with expectations, and continuously optimize the control strategy through simulation testing and feedback optimization units to improve the operating efficiency and stability of the microgrid.

[0056] The control feedback module 60 first executes the coordinated control scheme, and then uses simulation software such as PSCAD, MATLAB / Simulink, etc. to simulate the operation of the microgrid when executing the coordinated control scheme. After the test is completed, the control feedback module 60 will synchronize the results to the feedback optimization unit, which is a module that receives the test results and analyzes them to optimize the coordinated control scheme. The feedback optimization unit uses data analysis tools, such as data mining or machine learning algorithms, to evaluate the test results to see whether the coordinated control scheme has achieved the expected results. Based on the analysis results, the feedback optimization unit generates control feedback results to provide direction for the optimization of the coordinated control scheme. Among them, the control feedback results refer to the optimization direction and adjustment suggestions of the control strategy obtained after the simulation test and the feedback optimization unit analysis. Finally, the control feedback module 60 feeds back the control feedback results to the scheme optimization module 70 to update and optimize the coordinated control scheme.

[0057] Furthermore, the control feedback module 60 of the embodiment of the present application is also used to perform the following steps:

[0058] Step P61: retrieve the historical operation power generation data record log and the historical operation load data record log, combine them with the energy storage device to determine multiple simulation test scenarios, and build a simulation test platform.

[0059] Step P62: Synchronize the coordinated control scheme to the simulation test platform, traverse the multiple simulation test scenarios to perform simulation tests, and generate multiple control effects.

[0060] Step P63: Analyze the multiple control effects to perform a balance evaluation on the coordinated control scheme and generate a control balance coefficient.

[0061] Step P64: Correlate and match the control balancing coefficient with the coordinated control scheme, and determine the charging and discharging index, load response index, and grid stability index of the energy storage device according to the matching result.

[0062] Step P65: Add the charging and discharging index of the energy storage device, the load response index, and the grid stability index to the test results.

[0063] Specifically, the historical operation power generation data record log records the data of the microgrid's past power generation. The historical operation load data record log records the data of the microgrid's past load changes. The simulation test scenario refers to the possible scenarios of the simulated microgrid under different operating conditions. The module first calls the historical operation power generation data record log and the load data record log, collects past power generation and load data, and combines the current energy storage device status to determine multiple simulation test scenarios, such as different weather conditions, load change patterns, etc. These scenarios will be used to build a simulation test platform, using professional simulation software to create a variety of possible situations for testing.

[0064] Next, the module synchronizes the coordinated control scheme to the simulation test platform and performs simulation tests in multiple simulation test scenarios to observe its effect. For example, under different weather conditions, the module tests the impact of the coordinated control scheme on the operation of the microgrid. The control effect in the simulation test is analyzed, and data analysis and machine learning tools such as cluster analysis or regression analysis are used to evaluate the effect of the coordinated control scheme in different scenarios. In this way, the module calculates a control balance coefficient, which is an indicator for evaluating the effect of the coordinated control scheme in different scenarios, reflecting the balance and adaptability of the scheme under different conditions.

[0065] The module associates the control balance coefficient with the coordinated control scheme, and uses optimization algorithms such as genetic algorithms, particle swarm optimization, and multi-objective optimization to find the best match, that is, to find a set of charge and discharge indicators and load response indicators to maximize the control balance coefficient, while ensuring that the grid stability indicator is also optimal, thereby determining the charge and discharge indicators, load response indicators, and grid stability indicators of the energy storage device. Among them, the charge and discharge indicators refer to indicators that reflect the charge and discharge performance of the energy storage device. The load response indicator refers to an indicator that reflects the response of the load system to the coordinated control scheme. The grid stability indicator refers to an indicator that reflects the stability of the grid under the coordinated control scheme. Finally, these indicators are integrated into the test results for subsequent analysis and decision-making. These indicators provide a quantitative evaluation of the actual application effect of the scheme, which is used to guide the optimization of the coordinated control scheme.

[0066] Through the above steps, the control feedback module 60 can ensure that the coordinated control scheme achieves the expected effect under various possible environments, and improve the operating efficiency and reliability of the microgrid through continuous optimization.

[0067] The scheme optimization module 70 is used to update and optimize the coordinated control scheme according to the control feedback result, and generate a coordinated control optimization scheme to perform intelligent coordinated control on the microgrid load storage.

[0068] Specifically, the scheme optimization module 70 continuously improves the coordinated control scheme according to the control feedback result to improve the operation efficiency and reliability of the microgrid. The coordinated control optimization scheme is a coordinated control scheme updated and optimized according to the control feedback result.

[0069] The scheme optimization module 70 first receives the control feedback results, which include the performance of the coordinated control scheme in different scenarios and optimization suggestions. Then, the scheme optimization module 70 analyzes these feedback results, identifies the problems and potential improvements of the existing scheme, and then proposes an updated control strategy, namely the coordinated control optimization scheme, which includes the updated and optimized control strategy. Finally, the microgrid storage load is intelligently coordinated and controlled according to the coordinated control optimization scheme. The scheme optimization module 70 ensures that the microgrid can adapt to different operating conditions and always maintain high efficiency and stability.

[0070] Furthermore, the solution optimization module 70 of the embodiment of the present application is also used to perform the following steps:

[0071] Step P71: Based on the charging and discharging index of the energy storage device, the load response index, and the grid stability index, the coordinated control scheme is traversed to match adjustable parameters to determine multiple optimized control variables.

[0072] Step P72: Introduce a fitness function, perform fitness analysis on the multiple optimization control variables in turn, obtain multiple optimization control fitnesses, and randomly extract a first optimization control fitness and a second optimization control fitness. There is a corresponding relationship between the first optimization control fitness and the first optimization control variable, and between the second optimization control fitness and the second optimization control variable.

[0073] Step P73: Determine whether the first optimization control fitness is greater than or equal to the second optimization control fitness. If so, add the first optimization control variable corresponding to the first optimization control fitness to the candidate data group. If so, add the second optimization control variable corresponding to the second optimization control fitness to the candidate data group.

[0074] Step P74: Determine whether the multiple optimized control variables meet the taboo table update cycle.

[0075] Step P75: When the multiple optimized control variables satisfy the taboo table update cycle, the first optimized control fitness or the second optimized control fitness is input into the taboo table for updating; when the taboo table update times satisfy the preset update times, the coordinated control optimization scheme is output.

[0076] Preferably, step P72 of the embodiment of the present application further includes:

[0077] Step P72-1: According to the multiple optimized control variables, obtain the optimized trigger frequency characteristics and the optimized trigger time characteristics.

[0078] Step P72-2: Based on the load storage impact factor, weights are assigned to the optimized trigger frequency characteristics and the optimized trigger time characteristics to obtain a first weight and a second weight, wherein the first weight corresponds to the optimized trigger frequency characteristics, and the second weight corresponds to the optimized trigger time characteristics.

[0079] Step P72-3: Based on the first weight and the optimization trigger frequency characteristic, and the second weight and the optimization trigger time characteristic, the fitness function is introduced for calculation to obtain the multiple optimization control fitness.

[0080] Specifically, the optimized control variables refer to the parameters that can be adjusted in the coordinated control scheme, such as the charging and discharging rate of the energy storage system, the load response strategy, etc. The module traverses all the adjustable parameters in the coordinated control scheme based on the charging and discharging indicators of the energy storage equipment, the load response indicators, and the grid stability indicators, that is, according to the charging and discharging capacity of the energy storage system, the response characteristics of the load, and the stability requirements of the grid, a series of possible optimization variables are determined. These variables are factors that can be adjusted in the coordinated control scheme, such as the charging and discharging strategy of the energy storage equipment, the load distribution ratio, and the generator output adjustment.

[0081] Analyze the frequency and time efficiency of each optimized control variable in actual application, and obtain the corresponding optimized trigger frequency characteristics and optimized trigger time characteristics. The optimized trigger frequency characteristics refer to the frequency of the variable being triggered or applied, while the optimized trigger time characteristics refer to the ability of the variable to take effect within a specific time. The storage-load influence factor refers to various factors that affect the operation of energy storage and load, such as grid stability, load demand pattern, capacity of the energy storage system, etc. Based on the storage-load influence factor, the optimized trigger frequency characteristics and the optimized trigger time characteristics are weighted. The weight corresponding to the optimized trigger frequency characteristics is the first weight, and the weight corresponding to the optimized trigger time is the second weight. These weights reflect the importance of different characteristics in the overall optimization goal. Apply these weights to the fitness function to comprehensively evaluate the effect of each optimized control variable, and ensure that the fitness score of each variable can accurately reflect its contribution to the performance of the microgrid through weighted average or other statistical methods.

[0082] The fitness function is used to evaluate the quality of the optimized control variables, usually based on a certain objective function, such as minimizing system cost or maximizing system efficiency. The optimized control fitness is calculated according to the fitness function, which is a numerical value reflecting the quality of the optimized control variables. The fitness function is introduced, and the fitness analysis of the multiple optimized control variables is performed in turn. Each optimized control variable corresponds to an optimized control fitness, and finally multiple optimized control fitnesses are obtained. Two optimized control fitnesses are randomly extracted from the multiple optimized control fitnesses as the first optimized control fitness and the second optimized control fitness, wherein the first optimized control fitness corresponds to the first optimized control variable, and the second optimized control fitness corresponds to the second optimized control variable.

[0083] Compare the optimization control fitness and select the best control variable. If the first variable has a higher fitness score, select it; otherwise select the second variable. Collectively include: judging whether the first optimization control fitness is greater than or equal to the second optimization control fitness, if greater than or equal to, adding the first optimization control variable corresponding to the first optimization control fitness to the candidate data set, if less than, adding the second optimization control variable corresponding to the second optimization control fitness to the candidate data set. The candidate data set is a set of optimization control variables that have been preliminarily screened.

[0084] The taboo table is a mechanism for recording and avoiding the reuse of certain control variables to prevent falling into a local optimal solution. The taboo table update cycle refers to the period in which the taboo table needs to update the control variables. The preset number of updates is a value set in advance. When the taboo table is updated the preset number of times, the update stops and the final coordinated control optimization plan is output. Determine whether multiple optimized control variables meet the taboo table update cycle. If so, the module inputs the first optimized control fitness or the second optimized control fitness into the taboo table for update. Once the predetermined number of updates is reached, the final coordinated control optimization plan will be output to ensure continuous optimization of the plan.

[0085] Through the above steps, the scheme optimization module 70 can ensure that the coordinated control scheme gradually approaches the optimal solution during the iterative optimization process, and avoid falling into the local optimal solution through the taboo table mechanism. Finally, the output coordinated control optimization scheme will guide the microgrid load storage to perform intelligent coordinated control.

[0086] Further, such as Figure 3 As shown, the scheme optimization module 70 of the embodiment of the present application is also used to perform the following steps:

[0087] Step P76: traverse the microgrid to determine multiple data scheduling objects, wherein the multiple data scheduling objects include power supply data, grid data, charge data, and energy storage data.

[0088] Step P77: Perform multi-dimensional control division based on the coordinated control optimization scheme to obtain multiple time scales.

[0089] Step P78: Construct a multi-time scale model based on the multiple time scales.

[0090] Step P79: Synchronize the power supply data, the grid data, the charge data, and the energy storage data to the multi-time scale model to obtain a coordinated control plan of multiple time scales.

[0091] Step P710: Perform intelligent coordinated control on the microgrid load storage according to the coordinated control plan at the multiple time scales.

[0092] Specifically, data scheduling objects refer to key data sources in the microgrid, such as power data, grid data, charge data, energy storage data, etc. First, the module collects key data from the microgrid, that is, determines multiple data scheduling objects, including the energy generation of the power source, the real-time status of the grid, the load demand, and the power status of the energy storage system.

[0093] Next, these data are classified according to the coordinated control optimization scheme, and divided into multiple time scales according to different time requirements, that is, multi-dimensional control division is performed to obtain multiple time scales, so as to better manage the real-time operation of the microgrid. Multi-dimensional control division refers to dividing the coordinated control optimization scheme according to different dimensions or time scales. Multiple time scales refer to the division results of the coordinated control optimization scheme in different time dimensions. Including day-ahead scheduling, intraday rolling scheduling, real-time scheduling, etc. Among them, day-ahead scheduling has a longer time scale, usually 24 hours or longer, which is used to formulate preliminary scheduling plans; intraday rolling scheduling has a shorter time scale, such as 15 minutes to 1 hour, which is used to roll the day-ahead scheduling plan according to real-time conditions; real-time scheduling has the shortest time scale, such as a few minutes or seconds, which is used to quickly respond to system changes and ensure stable system operation.

[0094] Then a multi-time scale model is established. A multi-time scale model refers to a model that reflects the operation of the coordinated control optimization scheme at different time scales. The model can operate at different time scales, consider data and control strategies in different time ranges, and process data and control strategies in different time periods. For example, the short-term time scale may be at the minute or hour level, the medium-term time scale may be at the day or week level, and the long-term time scale may be at the month or year level.

[0095] The collected power supply, grid, load and energy storage data are integrated into this model to obtain coordinated control plans at multiple time scales. Time scale coordinated control plans refer to coordinated control strategies for different time scales generated on the multi-time scale model. These plans cover operations at different time scales, such as short-term load matching, medium-term energy storage and release, and long-term resource planning.

[0096] Ultimately, based on these plans, the microgrid will execute control strategies at different time scales to achieve intelligent coordination of energy storage and loads, ensuring efficient use of energy and stability of the grid.

[0097] In summary, the microgrid load-storage coordination control system based on time constraints provided by the embodiments of the present application has the following technical effects:

[0098] The operation acquisition module 10 acquires multiple operation data sets by operating the microgrid, providing a real-time data basis for subsequent analysis and control, and ensuring the pertinence and accuracy of the control strategy. The operation prediction module 20 constructs a prediction model based on the multiple power generation source data, the multiple energy storage data, and the multiple power load data, predicts the future operation state of the microgrid, obtains the operation prediction results, provides a basis for the control strategy, and improves the prediction accuracy of the dynamic changes of the microgrid. The time constraint construction module 30 constructs time constraints based on the multiple energy storage data and the multiple power load data to ensure that the control strategy meets specific scheduling and time requirements, and enhances the practicality and adaptability of the control strategy. The control constraint operation module 40 executes the time constraint to perform storage and load operation control constraints on the microgrid, generates energy storage control constraint information sets and load control constraint information sets, guides the operation of energy storage and load, and improves the efficiency of energy storage and load management. The plan formulation module 50 formulates a coordinated control plan based on the operation prediction results combined with the energy storage control constraint information set and the load control constraint information set, and realizes efficient coordination of energy storage and load. The control feedback module 60 executes the coordinated control scheme for simulation testing, synchronizes the test results to the feedback optimization unit for monitoring and feedback, generates control feedback results, verifies the effectiveness of the control scheme before actual application, and evaluates the actual effect of the control scheme, ensuring the operability and safety of the control scheme, and provides optimization direction. The scheme optimization module 70 updates and optimizes the coordinated control scheme according to the control feedback results, generates a coordinated control optimization scheme to intelligently coordinate the microgrid load storage to adapt to the real-time changes of the microgrid, and improves the dynamic adaptability and optimization level of the control strategy.

[0099] Overall, the embodiments of the present application achieve precise control of power generation, energy storage and load in the microgrid by coordinating the work of various modules and comprehensively considering time factors, prediction results and constraints. This not only improves the stability and reliability of the microgrid, but also improves the system's adaptability and ability to respond to emergencies, and promotes the development of the power grid in a more intelligent and green direction.

[0100] Embodiment 2, as Figure 4 As shown, an embodiment of the present application provides a microgrid load-storage coordination control method based on time constraints, the method comprising:

[0101] The operation of the microgrid is collected to obtain a plurality of operation data sets, wherein the plurality of operation data sets include a plurality of power generation source data, a plurality of energy storage data, and a plurality of power load data.

[0102] A prediction model is constructed based on the multiple power generation source data, the multiple energy storage data, and the multiple power load data, and an operation prediction of the microgrid is performed through the prediction model to obtain an operation prediction result.

[0103] A time constraint condition is constructed based on the multiple energy storage data and the multiple power load data.

[0104] The time constraint condition is executed to perform storage-load operation control constraints on the microgrid, and a storage control constraint information set and a load control constraint information set are generated.

[0105] A coordinated control plan is formulated according to the operation prediction result in combination with the energy storage control constraint information set and the load control constraint information set.

[0106] The coordinated control scheme is executed to perform simulation testing, and the test results are synchronized to the feedback optimization unit for monitoring feedback to generate control feedback results.

[0107] The coordinated control scheme is updated and optimized according to the control feedback result, and a coordinated control optimization scheme is generated to perform intelligent coordinated control on the microgrid load storage.

[0108] Further, in the embodiment of the present application, a prediction model is constructed based on the multiple power generation source data, the multiple energy storage data, and the multiple power load data, and the method includes:

[0109] The multiple power generation source data are used as indexes to match the multiple energy storage data and the multiple power load data to obtain the charging and discharging data and the power load data of the multiple power generation sources; feature extraction is performed based on the multiple power generation source data in combination with the charging and discharging data and the power load data to obtain the energy storage characteristics and load characteristics of the multiple power generation sources; normalization is performed based on the energy storage characteristics and the load characteristics of the multiple power generation sources, integrated learning is performed based on the normalized characteristics, and the prediction model is trained and constructed.

[0110] Furthermore, in the embodiment of the present application, a time constraint condition is constructed based on the multiple energy storage data and the multiple power load data, and the method includes:

[0111] Based on the multiple energy storage data, the charging and discharging characteristics are analyzed to obtain energy storage analysis results; based on the multiple power load data, the load change characteristics are analyzed to obtain a load forecast trend; according to the load forecast trend and the energy storage analysis results, the power dispatch demand information is determined; the charging and discharging efficiency is calculated, and the energy storage charging and discharging time window is defined in combination with the power dispatch demand information; multiple operation cycles of the microgrid are retrieved and combined with the power dispatch demand information to determine the load fluctuation threshold, and the load demand interval value is defined according to the load fluctuation threshold; according to the charging and discharging time window and the load demand interval value, the time constraint condition of the microgrid is constructed.

[0112] Furthermore, in the embodiment of the present application, the coordinated control scheme is executed to perform simulation testing, and the method includes:

[0113] Retrieve historical power generation data record logs and historical load data record logs and determine multiple simulation test scenarios in combination with energy storage devices to build a simulation test platform; synchronize the coordinated control scheme to the simulation test platform, traverse the multiple simulation test scenarios to perform simulation tests, and generate multiple control effects; analyze the multiple control effects to perform a balance evaluation on the coordinated control scheme and generate a control balance coefficient; associate and match the control balance coefficient with the coordinated control scheme, and determine the charge and discharge index, load response index, and grid stability index of the energy storage device based on the matching results; add the charge and discharge index, load response index, and grid stability index of the energy storage device to the test results.

[0114] Furthermore, in the embodiment of the present application, the coordinated control scheme is updated and optimized according to the control feedback result, and the method includes:

[0115] Based on the charging and discharging index of the energy storage device, the load response index, and the grid stability index, the coordinated control scheme is traversed to match the adjustable parameters and determine multiple optimized control variables; a fitness function is introduced to perform fitness analysis on the multiple optimized control variables in turn to obtain multiple optimized control fitnesses, and a first optimized control fitness and a second optimized control fitness are randomly extracted, and there is a corresponding relationship between the first optimized control fitness and the first optimized control variable, and between the second optimized control fitness and the second optimized control variable; it is determined whether the first optimized control fitness is greater than or equal to the second optimized control fitness, if it is greater than or equal to, the first optimized control variable corresponding to the first optimized control fitness is added to the candidate data group, if it is less than, the second optimized control variable corresponding to the second optimized control fitness is added to the candidate data group; it is determined whether the multiple optimized control variables meet the taboo table update cycle; when the multiple optimized control variables meet the taboo table update cycle, the first optimized control fitness or the second optimized control fitness is input into the taboo table for updating, and when the number of taboo table updates meets the preset number of updates, the coordinated control optimization scheme is output.

[0116] Preferably, in the embodiment of the present application, a fitness function is introduced, and fitness analysis is performed on the multiple optimization control variables in sequence to obtain multiple optimization control fitnesses. The method includes:

[0117] According to the multiple optimized control variables, the optimized trigger frequency characteristics and the optimized trigger time characteristics are obtained; based on the load-storage influence factor, the optimized trigger frequency characteristics and the optimized trigger time characteristics are weighted to obtain a first weight and a second weight, and there is a corresponding relationship between the first weight and the optimized trigger frequency characteristics, and between the second weight and the optimized trigger time characteristics; based on the first weight and the optimized trigger frequency characteristics, and the second weight and the optimized trigger time characteristics, the fitness function is introduced for calculation to obtain the multiple optimized control fitnesses.

[0118] Furthermore, in the embodiment of the present application, a coordinated control optimization scheme is generated to perform intelligent coordinated control on the microgrid storage load, and the method includes:

[0119] Traversing the microgrid to determine multiple data scheduling objects, the multiple data scheduling objects include power supply data, power grid data, charge data, and energy storage data; performing multi-dimensional control division based on the coordinated control optimization scheme to obtain multiple time scales; constructing a multi-time scale model according to the multiple time scales; synchronizing the power supply data, the power grid data, the charge data, and the energy storage data to the multi-time scale model to obtain a coordinated control plan of multiple time scales; and performing intelligent coordinated control of the microgrid load storage according to the coordinated control plan of the multiple time scales.

[0120] Through the above detailed description of the microgrid load-storage coordination control system based on time constraints in this specification, those skilled in the art can clearly understand the microgrid load-storage coordination control method based on time constraints in this embodiment. For the method disclosed in Example 2, since it corresponds to the system disclosed in Example 1 and has corresponding execution steps and beneficial effects, the relevant parts can be referred to the description of the method part.

[0121] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A microgrid load-storage coordination control system based on time constraints, characterized in that: The system comprises: An operation acquisition module, wherein the operation acquisition module is used to acquire a plurality of operation data sets from the microgrid operation, wherein the plurality of operation data sets include a plurality of power generation source data, a plurality of energy storage data, and a plurality of power load data; An operation prediction module, the operation prediction module is used to build a prediction model based on the multiple power generation source data, the multiple energy storage data, and the multiple power load data, and perform operation prediction on the microgrid through the prediction model to obtain an operation prediction result; A time constraint building module, the time constraint building module is used to build a time constraint condition based on the multiple energy storage data and the multiple power load data; A control constraint operation module, the control constraint operation module is used to execute the time constraint condition to perform storage-load operation control constraint on the microgrid, and generate an energy storage control constraint information set and a load control constraint information set; A scheme formulation module, the scheme formulation module is used to formulate a coordinated control scheme according to the operation prediction result combined with the energy storage control constraint information set and the load control constraint information set; A control feedback module, which is used to execute the coordinated control scheme to perform simulation testing, synchronize the test results to the feedback optimization unit for monitoring and feedback, and generate control feedback results; A scheme optimization module is used to update and optimize the coordinated control scheme according to the control feedback result, and generate a coordinated control optimization scheme to perform intelligent coordinated control on the microgrid load storage.

2. The microgrid load-storage coordination control system based on time constraints according to claim 1, characterized in that: The operation prediction module is also used to perform the following steps: Using the multiple power generation source data as indexes, matching the multiple energy storage data and the multiple power load data, and obtaining the charge and discharge data and power load data of the multiple power generation sources; Based on the data of the multiple power generation sources combined with the charging and discharging data of the multiple power generation sources and the power load data, feature extraction is performed to obtain energy storage features and load features of the multiple power generation sources; Normalization is performed based on the energy storage characteristics of the multiple power generation sources and the load characteristics, and integrated learning is performed according to the normalized characteristics to train and construct the prediction model.

3. The microgrid load-storage coordination control system based on time constraints according to claim 1, characterized in that: The time constraint building module is also used to perform the following steps: Analyze the charge and discharge characteristics based on the multiple energy storage data to obtain an energy storage analysis result; Analyzing load change characteristics based on the plurality of power load data to obtain a load forecast trend; Determine power dispatch demand information according to the load forecast trend and the energy storage analysis result; Calculate the charging and discharging efficiency, and define the energy storage charging and discharging time window in combination with the power dispatching demand information; Retrieving multiple operation cycles of the microgrid and combining the power dispatch demand information to determine a load fluctuation threshold, and defining a load demand interval value according to the load fluctuation threshold; The time constraint condition of the microgrid is constructed according to the charging and discharging time window in combination with the load demand interval value.

4. The microgrid load-storage coordination control system based on time constraints according to claim 1, characterized in that: The control feedback module is also used to perform the following steps: Retrieve historical power generation data record logs and historical load data record logs and combine them with energy storage equipment to determine multiple simulation test scenarios and build a simulation test platform; Synchronizing the coordinated control scheme to the simulation test platform, traversing the multiple simulation test scenarios to perform simulation tests, and generating multiple control effects; Analyze the multiple control effects to perform a balance evaluation on the coordinated control scheme and generate a control balance coefficient; Associating and matching the control balancing coefficient with the coordinated control scheme, and determining the charging and discharging index, load response index, and grid stability index of the energy storage device according to the matching result; The charging and discharging index of the energy storage device, the load response index, and the grid stability index are added to the test results.

5. The microgrid load storage coordination control system based on time constraints as claimed in claim 4, characterized in that: The solution optimization module is also used to perform the following steps: Based on the charging and discharging index of the energy storage device, the load response index, and the grid stability index, the coordinated control scheme is traversed to match adjustable parameters to determine a plurality of optimized control variables; Introducing a fitness function, performing fitness analysis on the multiple optimization control variables in turn, obtaining multiple optimization control fitnesses, and randomly extracting a first optimization control fitness and a second optimization control fitness, wherein the first optimization control fitness and the first optimization control variable, and the second optimization control fitness and the second optimization control variable have a corresponding relationship; Determine whether the first optimization control fitness is greater than or equal to the second optimization control fitness, if so, add the first optimization control variable corresponding to the first optimization control fitness to the candidate data set, if less than, add the second optimization control variable corresponding to the second optimization control fitness to the candidate data set; Determining whether the plurality of optimized control variables satisfy a taboo table update period; When the multiple optimized control variables satisfy the taboo table update cycle, the first optimized control fitness or the second optimized control fitness is input into the taboo table for updating, and when the taboo table update times satisfies the preset update times, the coordinated control optimization scheme is output.

6. The microgrid load storage coordination control system based on time constraints as claimed in claim 5, characterized in that: The solution optimization module is also used to perform the following steps: According to the plurality of optimized control variables, obtaining optimized trigger frequency characteristics and optimized trigger time characteristics; Based on the load-storage impact factor, weights are assigned to the optimized trigger frequency feature and the optimized trigger timeliness feature to obtain a first weight and a second weight, wherein the first weight corresponds to the optimized trigger frequency feature, and the second weight corresponds to the optimized trigger timeliness feature; The fitness function is introduced to perform calculation based on the first weight and the optimization trigger frequency characteristic, and the second weight and the optimization trigger time characteristic to obtain the multiple optimization control fitnesses.

7. The microgrid load storage coordination control system based on time constraints according to claim 1, characterized in that: The solution optimization module is also used to perform the following steps: Traversing the microgrid to determine a plurality of data scheduling objects, wherein the plurality of data scheduling objects include power supply data, grid data, charge data, and energy storage data; Perform multi-dimensional control division based on the coordinated control optimization scheme to obtain multiple time scales; constructing a multi-timescale model according to the multiple timescales; Synchronizing the power supply data, the grid data, the charge data, and the energy storage data to the multi-time scale model to obtain a coordinated control plan of multiple time scales; Intelligent coordinated control of the microgrid load storage is performed according to the coordinated control plan at the multiple time scales.

8. A time-constrained microgrid load-storage coordination control method, characterized in that: The method comprises: Performing operation collection on the microgrid to obtain a plurality of operation data sets, wherein the plurality of operation data sets include a plurality of power generation source data, a plurality of energy storage data, and a plurality of power load data; Building a prediction model based on the multiple power generation source data, the multiple energy storage data, and the multiple power load data, and performing operation prediction on the microgrid through the prediction model to obtain an operation prediction result; Establishing a time constraint condition based on the plurality of energy storage data and the plurality of power load data; Executing the time constraint condition to perform storage-load operation control constraints on the microgrid, and generating an energy storage control constraint information set and a load control constraint information set; Formulate a coordinated control plan based on the operation prediction result combined with the energy storage control constraint information set and the load control constraint information set; Execute the coordinated control scheme to perform simulation testing, synchronize the test results to the feedback optimization unit for monitoring feedback, and generate control feedback results; The coordinated control scheme is updated and optimized according to the control feedback result, and a coordinated control optimization scheme is generated to perform intelligent coordinated control on the microgrid load storage.

Images