Intelligent management method and system of micro-grid

Abstract

The application discloses a kind of wisdom management method and system of micro-grid, belong to energy management field, this method includes: based on the current capacity increase data of load, determine the energy parameter to be compensated;According to the output power of monitored real-time energy storage system, real-time distributed power output power, judge the controlled compensation end corresponding to the energy parameter to be compensated, including: step S21: if the energy parameter to be compensated is lower than first energy threshold, then grid is as controlled compensation end and carries out energy compensation;Otherwise, enter step S22, step S22: judge whether the sum of real-time energy storage system output power and the energy parameter to be compensated falls between the upper and lower limit values of distributed power output power, if yes, then distributed power is as controlled compensation end and carries out energy compensation;If not, enter step S23.The application can avoid the attenuation degree superposition under no interference, affect later maintenance;Use demand can be preferably met.

Description

Technical Field

[0001] This invention relates to the field of energy management, specifically to a smart management method and system for microgrids. Background Technology

[0002] In recent years, with the vigorous development of battery materials, photovoltaic power generation technology, and other technologies, energy storage-related technologies and equipment have been used more and more widely. Due to its high energy density, long life and pollution-free properties, lithium batteries have become one of the preferred storage carriers for energy storage, and the scale of lithium battery energy storage is also growing rapidly.

[0003] A microgrid is a distributed generation system consisting of micro-power sources such as wind power systems and photovoltaic power systems, as well as energy storage systems and loads. It is an independent network capable of providing electrical energy. Microgrids can operate in parallel with the public power grid or operate independently; and they can be supplied with electricity through the public power grid.

[0004] The battery packs configured in the energy storage system are charged when weather conditions are suitable, supplying power to the load, and sending excess power to the public grid. At night, the battery packs are used to power the microgrid and provide insufficient power through the public grid.

[0005] Existing microgrid management systems are relatively crude in their management and maintenance of distributed generation systems (i.e., distributed power sources) and energy storage systems. After the relevant power generation or energy storage equipment is put into use, there is a lack of refined cost and efficiency balance management. This can easily lead to the inability to control or improve the energy storage degradation of lithium batteries in distributed power sources and energy storage systems in a timely and effective manner, resulting in difficulty in maintenance or high maintenance costs in the later stages, and failing to meet the usage requirements well. Summary of the Invention

[0006] The purpose of this invention is to provide a smart management method and system for microgrids to solve the problems mentioned in the background art.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] A smart management method for microgrids includes:

[0009] Step S1: Based on the current capacity increase data of the load, determine the energy parameters to be compensated;

[0010] Step S2: Based on the monitored real-time energy storage system output power and real-time distributed power output power, determine the controlled compensation terminal corresponding to the energy parameter to be compensated, including:

[0011] Step S21: If the energy parameter to be compensated is lower than the first energy threshold, then the power grid is used as the controlled compensation end for energy compensation; otherwise, proceed to step S22.

[0012] Step S22: Determine whether the sum of the real-time energy storage system output power and the energy parameter to be compensated falls between the upper and lower limits of the distributed power source's output power. If so, use the distributed power source as the controlled compensation terminal for energy compensation; otherwise, proceed to step S23.

[0013] Step S23: Use distributed power sources and energy storage systems together as controlled compensation terminals for energy compensation;

[0014] Step S3: Generate the current sub-management policy of the controlled compensation end, record the previous sub-management policy of the controlled compensation end, and switch to the previous sub-management policy of the controlled compensation end after the load capacity drops.

[0015] As a further technical solution of the present invention, before step S2, the method further includes:

[0016] Step S14: Based on the microgrid design parameters, set the upper and lower limits of the output power of the distributed power source and the upper and lower limits of the charging and discharging power of the energy storage system, and use them as constraints to perform value assignment and evolution in the preset energy supply and demand spatiotemporal model to obtain the microgrid operation data simulation set.

[0017] Step S15: Determine the cycle operating cost of the microgrid, and calculate the levelized cost of electricity of the microgrid by combining the peak and valley electricity price information of the current cycle of the power grid. Use the levelized cost of electricity of the microgrid as the objective function, and classify the optimal segmented operating data in the simulation set of microgrid operating data.

[0018] Step S16: Based on the optimal segmented operation data, set and store the sub-management strategies corresponding to distributed power sources and energy storage systems in the microgrid management strategy.

[0019] This invention provides a smart management system for microgrids, the system comprising:

[0020] The compensation increment determination module is used to determine the energy parameters to be compensated based on the current capacity increase data of the load.

[0021] The controlled end judgment module is used to determine the controlled compensation end corresponding to the energy parameter to be compensated based on the monitored real-time energy storage system output power and real-time distributed power output power.

[0022] The distributed management submodule is used to generate the current sub-management policy of the controlled compensation end, record the previous sub-management policy of the controlled compensation end, and switch to the previous sub-management policy of the controlled compensation end after the load capacity decreases.

[0023] As a further technical solution of the present invention, the system also includes:

[0024] The data simulation module is used to set the upper and lower limits of the output power of the distributed power source and the upper and lower limits of the charging and discharging power of the energy storage system according to the design parameters of the microgrid, and use them as constraints to perform value assignment and evolution in the preset energy supply and demand spatiotemporal model to obtain the microgrid operation data simulation set.

[0025] The sub-strategy partitioning module is used to determine the cycle operation cost of the microgrid and calculate the levelized cost of electricity of the microgrid by combining the peak and valley electricity price information of the current cycle of the power grid. The levelized cost of electricity of the microgrid is used as the objective function to classify the optimal segmented operation data in the simulation set of microgrid operation data.

[0026] The sub-strategy management module is used to set and store the sub-management strategies corresponding to distributed power sources and energy storage systems in the microgrid management strategy based on the optimal segmented operation data.

[0027] Compared with the prior art, the beneficial effects of the present invention are:

[0028] This invention, building upon conventional monitoring of distributed power sources, energy storage systems, and power grids, further refines the incremental (and even decremental) calculations and analyses of load capacity changes. It can generate and control refined energy replenishment strategies for distributed power sources, energy storage systems, or the power grid within a microgrid based on load capacity variations. During strategy generation, it determines the controlled compensation endpoint corresponding to the energy parameter to be compensated based on the monitored real-time output power of the energy storage system and the real-time output power of the distributed power source. This prioritizes equipment with lower maintenance costs for replenishment, avoiding abnormal equipment degradation due to increased replenishment frequency, thus preventing the degradation of distributed power sources and energy storage systems from exceeding the equipment's expected performance (while allowing for normal degradation), or preventing the cumulative degradation under undisturbed conditions that could affect later maintenance. This approach effectively meets user needs. Attached Figure Description

[0029] Figure 1 A flowchart illustrating a smart management method for a microgrid provided by the present invention;

[0030] Figure 2 This is a flowchart illustrating the specific process of determining the controlled compensation end in this invention.

[0031] Figure 3 This is a flowchart illustrating the specific process for determining the energy parameters to be compensated in this invention.

[0032] Figure 4 This is a flowchart illustrating the preprocessing of the acquired relevant information in this invention.

[0033] Figure 5 This is a flowchart illustrating the specific process of preprocessing the acquired relevant information in this invention.

[0034] Figure 6 A flowchart illustrating another intelligent management method for microgrids provided by the present invention;

[0035] Figure 7 A flowchart illustrating another intelligent management method for microgrids provided by the present invention;

[0036] Figure 8 This is a flowchart illustrating the construction of a spatiotemporal model of energy demand according to the present invention.

[0037] Figure 9 This is the first sub-flowchart of a smart management method for a microgrid according to the present invention;

[0038] Figure 10 This is the second sub-flowchart of a smart management method for a microgrid according to the present invention;

[0039] Figure 11 This is a structural block diagram of a smart management system for a microgrid according to the present invention;

[0040] Figure 12 This is a structural block diagram of another intelligent management system for a microgrid according to the present invention;

[0041] Figure 13 This is a structural block diagram of another intelligent management system for microgrids according to the present invention. Detailed Implementation

[0042] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 skilled in the art without creative effort are within the scope of protection of the present invention.

[0043] Please see Figures 1-2 In one embodiment of the present invention, a smart management method for a microgrid is provided, wherein the microgrid generally includes distributed power sources, energy storage systems, and loads, and the distributed power sources include photovoltaic power generation equipment, wind power generation equipment, gas turbine power generation equipment, etc., the energy storage systems include hydrogen storage power generation equipment and lithium battery systems, etc., and other auxiliary equipment, such as cables, voltage transformers, converters, etc.; the method includes:

[0044] Step S1: Based on the current capacity increase data of the load, determine the energy parameters to be compensated;

[0045] Generally, a distributed power source can be configured with one or more power sources. Sometimes, photovoltaic power generation equipment, wind power generation equipment, gas turbine power generation equipment, etc., do not coexist. In this embodiment, the distributed power source may include one of photovoltaic power generation equipment and wind power generation equipment. The energy storage system uses batteries, specifically lithium batteries for energy storage.

[0046] In distributed power systems, the operating power of each device is controlled by its own configured control system. For example, existing wind power generation equipment has control systems with maximum power point tracking (MPPT), wind speed estimation, load control, and voltage control. Relevant to this step is the fact that wind power control involves load forecasting. When the wind turbine is running at an appropriate speed (not exceeding the rated speed), if the load changes, whether the speed needs to be increased requires calculation of operating costs, considering the wind turbine's lifespan and equipment maintenance costs. Load forecasting is based on wind speed information, time, power growth, and other factors to predict the future wind power output of the wind power generation equipment, matching the load changes of the microgrid and achieving flexible scheduling and management. The control of photovoltaic (PV) power generation equipment is basically the same as that of wind power generation equipment, including maximum power point tracking, voltage control, current control, grid connection control, and feedback mechanisms. The impact of cleaning and maintenance of PV modules on power generation also needs to be considered.

[0047] In energy storage systems, the control systems mainly include demand control and grid-connected operation control; and it is necessary to conduct in-depth analysis of lithium battery capacity decay and continuous stable operation (temperature control), etc.

[0048] Therefore, the current capacity increase data of the load can be determined based on the current, voltage and power information obtained from the control systems of wind power generation equipment, photovoltaic power generation equipment, and energy storage systems.

[0049] In one example of an embodiment, such as Figure 3 As shown, step S1 specifically includes:

[0050] Step S11: Obtain real-time current information, real-time voltage information, and real-time power information of the microgrid's power source during energy conversion.

[0051] Step S12: Determine the current capacity increase data of the load based on the real-time current information, real-time voltage information, and real-time power information;

[0052] Step S13: Calculate the energy parameters to be compensated based on the determined current capacity increase data of the load;

[0053] The power sources of a microgrid include distributed power sources and energy storage systems for discharging.

[0054] In one example, such as Figure 4 As shown, after acquiring real-time current information, real-time voltage information, and real-time power information, some processing can be performed on the acquired data to avoid some duplicate data, invalid data, and improve the processing efficiency of audio information. That is, step S24: preprocess the acquired real-time current information, real-time voltage information, and real-time power information.

[0055] like Figure 5 As shown, step S24 specifically includes:

[0056] Step S241: Filter duplicate and invalid data in the real-time parameters of distributed power sources and energy storage systems;

[0057] Step S242: Mining real-time characteristic parameters of distributed power sources and energy storage systems;

[0058] Step S243: Normalize the real-time characteristic parameters of distributed power sources and energy storage systems.

[0059] Furthermore, such as Figure 10 As shown, in one example, step S243 includes:

[0060] Step S2431: Extract the real-time parameters one by one, and compare the extracted real-time parameters with the real-time feature parameters to analyze the correlation between the extracted real-time parameters and the real-time feature parameters.

[0061] Step S2432: When the real-time parameters extracted one by one are associated with the real-time feature parameters, the real-time parameters extracted one by one are saved.

[0062] Step S2433: When the real-time parameters extracted one by one are not associated with the real-time feature parameters, the real-time parameters extracted one by one are deleted.

[0063] Step S2434: Determine the valid real-time feature parameters by processing invalid values ​​of the real-time parameters;

[0064] To obtain valid real-time feature parameters, extract individual data from each valid real-time feature parameter, and index the other valid real-time parameters besides the individual data. Check the matching degree between the other valid real-time parameters and the individual data, and then filter out duplicate data contained in the valid real-time parameters.

[0065] The correlation analysis between real-time parameters and real-time feature parameters can be achieved using existing deep learning models. This analysis is an existing technology and will not be described in detail here.

[0066] The method in the above embodiments further includes:

[0067] Step S2: Based on the monitored real-time energy storage system output power and real-time distributed power output power, determine the controlled compensation terminal corresponding to the energy parameter to be compensated, including:

[0068] Step S21: If the energy parameter to be compensated is lower than the first energy threshold, then the power grid is used as the controlled compensation end for energy compensation; otherwise, proceed to step S22.

[0069] The first energy threshold is a constant value that can be set as needed. When the energy parameter to be compensated does not exceed 5% of the load value, it can be considered that whether or not energy is added will not significantly affect the operation of the microgrid. Therefore, the first energy threshold can be set to 5% of the load value. In other scenarios, it can also be set to a smaller value.

[0070] Step S22: Determine whether the sum of the real-time energy storage system output power and the energy parameter to be compensated falls between the upper and lower limits of the distributed power source's output power. If so, use the distributed power source as the controlled compensation terminal for energy compensation; otherwise, proceed to step S23.

[0071] Step S23: Use distributed power sources and energy storage systems together as controlled compensation terminals for energy compensation;

[0072] Among them, the total difference in load corresponds to the controlled compensation end;

[0073] In other cases, when the output power of distributed power sources and energy storage systems is at its optimal level, not using grid-supplemented energy can achieve better new energy consumption, increase the revenue of microgrids, and reduce costs. Only when grid connection is required to make up for the difference that occurs when the output power of distributed power sources and energy storage systems is at its optimal level should grid connection be considered.

[0074] After being connected to the power grid, it may generate positive or negative revenue, depending on whether there is surplus power transmitted to the grid; if it is necessary to supplement the power through the grid, the timing of the supplementation also affects the revenue: for example, the electricity price in a certain region;

[0075] Peak hours are 10:00-12:00 and 14:00-19:00, with an electricity price of 1.0377 yuan.

[0076] The off-peak hours are from 00:00 to 8:00, and the electricity price is 0.2320 yuan.

[0077] The normal operating hours are 8:00-10:00, 12:00-14:00, and 19:00-24:00, with an electricity price of 0.6104 yuan.

[0078] Step S3: Generate the current sub-management policy of the controlled compensation end, record the previous sub-management policy of the controlled compensation end, and switch to the previous sub-management policy of the controlled compensation end after the load capacity drops.

[0079] Specifically, for microgrids, intelligent management strategies for controller operation are pre-set, such as: collecting environmental parameters, operating parameters, and load change parameters of the microgrid; establishing a simulation model of the microgrid in HOMER software, and setting the same parameters, constraints, and objective function for the model; and outputting intelligent management strategies by analyzing the operation of the microgrid in HOMER software.

[0080] In one example, minimizing the levelized cost of electricity (LCOE) was chosen as a constraint in the simulation model to more clearly demonstrate the correlation between the lifecycle costs of each system in the microgrid and power generation, specifically the net present value of lifecycle costs divided by the present value of power generation over the system's lifecycle. During the optimization process, LCOE was used to rank all scenarios with different configurations and find the scenario with the minimum LCOE.

[0081]

[0082] Among them, C COE C ANN,TOT C OM These represent the average levelized cost of electricity (LCOE), total annual cost, and operating cost of the microgrid, respectively. ANN,TOT R represents annual energy consumption. DIS Where is the discount rate, V is the residual value of the fixed asset, and T is the present value. DE Total asset depreciation for all systems.

[0083] In one embodiment, such as Figure 6 As shown, before step S2, the method further includes:

[0084] Step S14: Based on the microgrid design parameters, set the upper and lower limits of the output power of the distributed power source and the upper and lower limits of the charging and discharging power of the energy storage system, and use them as constraints to perform value assignment and evolution in the preset energy supply and demand spatiotemporal model to obtain the microgrid operation data simulation set.

[0085] The design parameters of a microgrid mainly include the load, which can be determined by estimation; and the equipment parameters of the distributed power source, such as output power (rated output power, maximum output power, etc.), charging power and discharging power of the energy storage system, input voltage, output voltage, output current and input current, etc.

[0086] When a distributed power source includes multiple power generation devices, the lower limit of the distributed power source's output power is the lower power value of the multiple power generation devices, and the upper limit of the distributed power source's output power is the sum of the power values ​​of the multiple power generation devices.

[0087] The upper and lower limits of the charging power of an energy storage system generally do not affect load compensation, but the upper and lower limits of the discharging power of an energy storage system do affect load compensation and need to be set.

[0088] Step S15: Determine the cycle operating cost of the microgrid, and calculate the levelized cost of electricity of the microgrid by combining the peak and valley electricity price information of the current cycle of the power grid. Use the levelized cost of electricity of the microgrid as the objective function, and classify the optimal segmented operating data in the simulation set of microgrid operating data.

[0089] Step S16: Based on the optimal segmented operation data, set and store the sub-management strategies corresponding to distributed power sources and energy storage systems in the microgrid management strategy.

[0090] In one example, such as Figure 7 As shown, the method further includes: Step S4: When the real-time capacity of the load decreases, if the current time is in the first time interval, the power grid replenishment is reduced accordingly until the energy dispatched to the power grid is zero; if the current time is in the second time interval, the power storage system replenishment is reduced accordingly and the power grid replenishment is maintained until the energy dispatched to the power grid is zero.

[0091] The first time interval is the non-power supply peak and trough period; the second time interval is the power supply trough period.

[0092] In this example, there may be a third time interval, namely the peak power supply period. At this time, the energy dispatched to the grid by the microgrid is zero. When the load of the microgrid increases, the power supply is guaranteed by increasing the output power of distributed power sources and energy storage systems.

[0093] In one example, such as Figure 8 As shown, in step S14, a spatiotemporal model of energy supply and demand is first established, specifically including:

[0094] Step S141: Obtain historical power generation data of distributed power sources, historical charging and discharging data of energy storage systems, and historical power consumption data of loads;

[0095] Step S142: Based on the obtained historical power generation data, historical charge and discharge data, and historical power consumption data, analyze and determine the correlation between distributed power sources, energy storage systems, and loads;

[0096] The relationships between distributed power sources, energy storage systems, and loads can be determined manually or by classifying them using existing knowledge graphs. The inputs to the knowledge graphs are historical power generation data, historical charging and discharging data, and historical power consumption data, which will not be detailed here.

[0097] Step S143: Based on the determined correlation, construct a spatiotemporal model of energy demand.

[0098] In one example, such as Figure 9 As shown, in step S23, the energy replenishment ratio of the distributed power source and energy storage system is preset and stored in the management database; wherein the setting of the energy replenishment ratio includes:

[0099] Step S231: Determine the distributed power generation operation model and the energy storage system operation model based on the microgrid design parameters;

[0100] Step S232: Input the energy parameters to be compensated into the distributed power source operation model and output the cost data and operation and maintenance data of the distributed power source; input the energy storage system operation model and output the cost data and operation and maintenance data of the energy storage system.

[0101] Step S233: Based on the energy parameters to be compensated, compare the cost data and operation and maintenance data of the distributed power source with the cost data and operation and maintenance data of the energy storage system to determine the energy compensation ratio of the distributed power source and the energy storage system.

[0102] In another embodiment, such as Figure 11 As shown, a smart management system for a microgrid includes:

[0103] The compensation increment determination module 100 is used to determine the energy parameters to be compensated based on the current capacity increase data of the load.

[0104] The controlled end judgment module 200 is used to determine the controlled compensation end corresponding to the energy parameter to be compensated based on the monitored real-time energy storage system output power and real-time distributed power output power.

[0105] The distributed management submodule 300 is used to generate the current sub-management policy of the controlled compensation end, record the previous sub-management policy of the controlled compensation end, and switch to the previous sub-management policy of the controlled compensation end after the load capacity decreases.

[0106] In one example of an embodiment, such as Figure 12 As shown, the system also includes:

[0107] The data simulation module 400 is used to set the upper and lower limits of the output power of the distributed power source and the upper and lower limits of the charging and discharging power of the energy storage system according to the design parameters of the microgrid, and use them as constraints to perform value assignment and evolution in the preset energy supply and demand spatiotemporal model to obtain the microgrid operation data simulation set.

[0108] The sub-strategy partitioning module 500 is used to determine the cycle operation cost of the microgrid and calculate the levelized cost of electricity of the microgrid by combining the peak and valley electricity price information of the current cycle of the power grid. The levelized cost of electricity of the microgrid is used as the objective function to classify the optimal segmented operation data in the simulation set of microgrid operation data.

[0109] The sub-strategy management module 600 is used to set and store the sub-management strategies corresponding to distributed power sources and energy storage systems in the microgrid management strategy based on the optimal segmented operation data.

[0110] In one example of an embodiment, such as Figure 12 As shown, the system also includes:

[0111] The reduction control module 700 is used to reduce the grid's energy supply when the real-time capacity of the load decreases. If the current time is in the first time interval, the grid's energy supply will be reduced accordingly until the energy dispatched to the grid is zero. If the current time is in the second time interval, the energy supply of the energy storage system will be reduced accordingly while the grid's energy supply will be maintained until the grid's energy supply is zero.

[0112] The first time interval is the non-power supply peak and trough period; the second time interval is the power supply trough period.

[0113] The above embodiments provide a smart management method for microgrids, and based on this method, a smart management system for microgrids is also provided. In this method, more refined incremental calculations and analyses of load capacity changes are performed. Based on load capacity changes, refined strategies for replenishing distributed power sources, energy storage systems, or the grid within the microgrid are generated and controlled. During strategy generation, the controlled compensation end corresponding to the energy parameter to be compensated is determined based on the monitored real-time output power of the energy storage system and the real-time output power of the distributed power source. This considers avoiding maintenance costs for important equipment (such as photovoltaic modules and batteries) in the distributed power source and energy storage system, prioritizing the use of equipment with lower maintenance costs for replenishment, thus avoiding abnormal equipment degradation due to an additional increase in replenishment frequency. This prevents the degradation of distributed power sources and energy storage systems from exceeding the equipment's expectations, while allowing for normal equipment degradation; or avoids the superposition of degradation levels under interference-free conditions, which could affect later maintenance. This method can better meet usage requirements.

[0114] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0115] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A smart management method for microgrids, characterized in that, The method includes: Step S1: Based on the current capacity increase data of the load, determine the energy parameters to be compensated; Step S2: Based on the monitored real-time energy storage system output power and real-time distributed power output power, determine the controlled compensation terminal corresponding to the energy parameter to be compensated, including: Step S21: If the energy parameter to be compensated is lower than the first energy threshold, then the power grid is used as the controlled compensation end for energy compensation; otherwise, proceed to step S22. Step S22: Determine whether the sum of the real-time energy storage system output power and the energy parameter to be compensated falls between the upper and lower limits of the distributed power source's output power. If so, use the distributed power source as the controlled compensation terminal for energy compensation; otherwise, proceed to step S23. Step S23: Use distributed power sources and energy storage systems together as controlled compensation terminals for energy compensation; Step S3: Generate the current sub-management policy of the controlled compensation terminal, record the previous sub-management policy of the controlled compensation terminal, and switch to the previous sub-management policy of the controlled compensation terminal after the load capacity drops. Before step S2, the method further includes: Step S4: Based on the microgrid design parameters, set the upper and lower limits of the output power of the distributed power source and the upper and lower limits of the charging and discharging power of the energy storage system, and use them as constraints to perform value assignment and evolution in the preset energy supply and demand spatiotemporal model to obtain the microgrid operation data simulation set. Step S5: Determine the cycle operating cost of the microgrid, and calculate the levelized cost of electricity of the microgrid by combining the peak and valley electricity price information of the current cycle of the power grid. Use the levelized cost of electricity of the microgrid as the objective function, and classify the optimal segmented operating data in the simulation set of microgrid operating data. Step S6: Based on the optimal segmented operation data, set and store the sub-management strategies corresponding to distributed power sources and energy storage systems in the microgrid management strategy.

2. The intelligent management method for a microgrid according to claim 1, characterized in that, In step S4, a spatiotemporal model of energy supply and demand is first established, specifically including: Step S41: Obtain historical power generation data of distributed power sources, historical charging and discharging data of energy storage systems, and historical power consumption data of loads; Step S42: Based on the obtained historical power generation data, historical charge and discharge data, and historical power consumption data, analyze and determine the correlation between distributed power sources, energy storage systems, and loads; Step S43: Based on the determined correlation, construct a spatiotemporal model of energy demand.

3. The intelligent management method for a microgrid according to claim 1, characterized in that, Step S1 specifically includes: Step S11: Obtain real-time current information, real-time voltage information, and real-time power information of the microgrid's power source during energy conversion. Step S12: Determine the current capacity increase data of the load based on the real-time current information, real-time voltage information, and real-time power information; Step S13: Calculate the energy parameters to be compensated based on the determined current capacity increase data of the load; The power sources of a microgrid include distributed power sources and energy storage systems for discharging.

4. The intelligent management method for a microgrid according to claim 3, characterized in that, After step S23, the method further includes: Step S24: Preprocess the acquired real-time current information, real-time voltage information, and real-time power information; this preprocessing includes: Step S241: Filter duplicate and invalid data in the real-time parameters of distributed power sources and energy storage systems; Step S242: Mining real-time characteristic parameters of distributed power sources and energy storage systems; Step S243: Normalize the real-time characteristic parameters of distributed power sources and energy storage systems.

5. The intelligent management method for a microgrid according to claim 4, characterized in that, Step S243 includes: Step S2431: Extract the real-time parameters one by one, and compare the extracted real-time parameters with the real-time feature parameters to analyze the correlation between the extracted real-time parameters and the real-time feature parameters. Step S2432: When the real-time parameters extracted one by one are associated with the real-time feature parameters, the real-time parameters extracted one by one are saved. Step S2433: When the real-time parameters extracted one by one are not associated with the real-time feature parameters, the real-time parameters extracted one by one are deleted. Step S2434: Determine the valid real-time feature parameters by processing invalid values ​​of the real-time parameters.

6. The intelligent management method for a microgrid according to claim 1, characterized in that, The method further includes: Step S7: When the real-time capacity of the load decreases, if the current time is in the first time interval, the power grid's energy replenishment is reduced accordingly until the energy dispatched to the power grid is zero; if the current time is in the second time interval, the energy storage system's energy replenishment is reduced accordingly while the power grid's energy replenishment is maintained until the energy dispatched to the power grid is zero. The first time interval is the non-power supply peak and trough period; the second time interval is the power supply trough period.

7. The intelligent management method for a microgrid according to claim 1, characterized in that, In step S23, the energy replenishment ratio of the distributed power source and energy storage system is preset and stored in the management database; wherein the setting of the energy replenishment ratio includes: Step S231: Determine the distributed power generation operation model and the energy storage system operation model based on the microgrid design parameters; Step S232: Input the energy parameters to be compensated into the distributed power source operation model and output the cost data and operation and maintenance data of the distributed power source; input the energy storage system operation model and output the cost data and operation and maintenance data of the energy storage system. Step S233: Based on the energy parameters to be compensated, compare the cost data and operation and maintenance data of the distributed power source with the cost data and operation and maintenance data of the energy storage system to determine the energy compensation ratio of the distributed power source and the energy storage system.

8. A smart management system for a microgrid, characterized in that, The system includes: The compensation increment determination module is used to determine the energy parameters to be compensated based on the current capacity increase data of the load. The controlled end judgment module is used to determine the controlled compensation end corresponding to the energy parameter to be compensated based on the monitored real-time energy storage system output power and real-time distributed power output power. The distributed management submodule is used to generate the current sub-management policy of the controlled compensation end, record the previous sub-management policy of the controlled compensation end, and switch to the previous sub-management policy of the controlled compensation end after the load capacity decreases. Based on the monitored real-time output power of the energy storage system and the real-time output power of the distributed power source, determine the controlled compensation terminal corresponding to the energy parameters to be compensated, including: Step S21: If the energy parameter to be compensated is lower than the first energy threshold, then the power grid is used as the controlled compensation end for energy compensation; otherwise, proceed to step S22. Step S22: Determine whether the sum of the real-time energy storage system output power and the energy parameter to be compensated falls between the upper and lower limits of the distributed power source's output power. If so, use the distributed power source as the controlled compensation terminal for energy compensation; otherwise, proceed to step S23. Step S23: Use distributed power sources and energy storage systems together as controlled compensation terminals for energy compensation; The system also includes: The data simulation module is used to set the upper and lower limits of the output power of the distributed power source and the upper and lower limits of the charging and discharging power of the energy storage system according to the design parameters of the microgrid, and use them as constraints to perform value assignment and evolution in the preset energy supply and demand spatiotemporal model to obtain the microgrid operation data simulation set. The sub-strategy partitioning module is used to determine the cycle operation cost of the microgrid and calculate the levelized cost of electricity of the microgrid by combining the peak and valley electricity price information of the current cycle of the power grid. The levelized cost of electricity of the microgrid is used as the objective function to classify the optimal segmented operation data in the simulation set of microgrid operation data. The sub-strategy management module is used to set and store the sub-management strategies corresponding to distributed power sources and energy storage systems in the microgrid management strategy based on the optimal segmented operation data.

Images