Micro-grid energy storage optimization method and system based on big data analysis

Abstract

The invention relates to the technical field of intelligent power grids, in particular to a micro-grid energy storage optimization method and system based on big data analysis, and the method comprises the steps: obtaining the comprehensive prediction power generation through the prediction segmentation time, a wind power generator set and a solar power generator set, and obtaining the analysis power based on the prediction segmentation time and the comprehensive prediction power generation, an energy storage battery parameter set is obtained, if the analysis electric quantity is larger than or equal to a storage electric quantity threshold value, a target storage battery pack is retrieved from the energy storage battery packs through the energy storage battery parameter set, active equalizing charging is conducted on the target storage battery pack, and an updated storage battery pack is obtained; and after it is confirmed that a preset target energy supply battery pack is retrieved in the energy storage battery packs by using the analysis electric quantity and the energy storage battery parameter set, power is supplied by using the target energy supply battery pack, and an updated power supply battery pack is obtained. According to the method, the energy storage of the micro-grid can be accurately and intelligently optimized.

Description

Technical Field

[0001] The present invention relates to the technical field of smart grids, and in particular, to a method and system for optimizing the energy storage of a microgrid based on big data analysis. Background Art

[0002] With the wide application of renewable energy in microgrids, energy storage battery packs play a crucial role in balancing the power of microgrids and improving power quality. On the contrary, how to accurately and intelligently optimize the energy storage of energy storage battery packs is indispensable for the normal, efficient, and safe operation of energy storage battery packs.

[0003] Currently, the optimization of microgrid energy storage is mainly achieved by collecting the output power data of distributed power sources, load data, and the state of charge data of energy storage battery packs to extend the service life of energy storage battery packs in microgrids.

[0004] Although the above method can achieve the optimization of the energy storage of energy storage battery packs, when optimizing the energy storage of energy storage battery packs, the differences between the energy storage batteries in the energy storage battery pack are not considered, and before realizing the optimization of the energy storage battery pack in the microgrid, the combination of the power that the initial microgrid can supply and the power required by the load is not considered. Furthermore, this leads to the problem of frequent charging and discharging of the energy storage battery pack in the microgrid. Therefore, how to accurately and intelligently optimize the energy storage of the microgrid has become an urgent problem to be solved. Summary of the Invention

[0005] The present invention provides a method for optimizing the energy storage of a microgrid based on big data analysis and a computer-readable storage medium, and its main purpose is to accurately and intelligently optimize the energy storage of the microgrid.

[0006] To achieve the above object, a method for optimizing the energy storage of a microgrid based on big data analysis provided by the present invention includes: Receiving an energy storage optimization instruction, and identifying an initial microgrid to be optimized for energy storage based on the energy storage optimization instruction. The initial microgrid includes a wind turbine set, a fuel generator set, a solar generator set, and an energy storage battery pack. The wind turbine set includes multiple wind turbines, the solar generator set includes multiple solar generators, the energy storage battery pack includes multiple energy storage batteries, and the fuel generator set includes multiple types of fuel generators; Obtaining a comprehensive predicted power generation amount by using a pre-identified prediction segmentation time, the wind turbine set, and the solar generator set; Obtaining the predicted power consumption of the initial microgrid based on the prediction segmentation time, calculating the difference between the comprehensive predicted power generation amount and the predicted power consumption, and obtaining an analysis power amount; Obtain a set of energy storage battery parameters for the energy storage battery pack, where the set of energy storage battery parameters includes multiple energy storage battery parameters, and the energy storage battery parameters correspond to the energy storage batteries one by one. The energy storage battery parameters include: battery SOH value, remaining stored power, battery rated power, and battery SOC value; If the analyzed power is greater than or equal to the preset stored power threshold, use the set of energy storage battery parameters to retrieve the target storage battery pack in the energy storage battery pack, and perform active equalization charging on the target storage battery pack to obtain an updated storage battery pack; If the analyzed power is less than the preset supply power threshold, use the analyzed power and the set of energy storage battery parameters to retrieve in the energy storage battery pack. If the preset target power supply battery pack is retrieved in the energy storage battery pack, use the target power supply battery pack for power supply to obtain an updated power supply battery pack; If the target power supply battery pack cannot be retrieved in the energy storage battery pack, use the predicted power consumption and the set of fuel generators to obtain the target fuel power supply, use the target fuel power supply as the analyzed power, return to the step of obtaining the set of energy storage battery parameters of the energy storage battery pack, and realize the energy storage optimization of the initial microgrid based on the updated storage battery pack or the updated power supply battery pack.

[0007] Optionally, the obtaining of the comprehensive predicted power generation amount by using the pre-confirmed predicted segmentation time, the set of wind turbines, and the set of solar generators includes: Perform the following operations on each wind turbine in the set of wind turbines: Obtain the initial influence factor set of the wind turbine, and use the pre-constructed principal component analysis method to confirm the target influence factor set in the initial influence factor set; Obtain the initial historical data set based on the target influence factor set, where the initial historical data set includes multiple initial historical data, and the initial historical data includes reference influence environment data and initial reference wind power; Obtain the predicted influence environment data based on the predicted segmentation time, the wind turbine, and the target influence factor set, and use the predicted influence environment data, the pre-constructed clustering algorithm, and the reference influence environment data corresponding to the initial historical data in the initial historical data set to obtain the target reference wind power set; Obtain the set of power prediction models for predicting the power generation amount, and obtain the reference predicted wind power set based on the set of power prediction models and the wind turbine; Associate the target reference wind power set and the reference predicted wind power set to obtain the wind power generation reference node; Summarize the wind power generation reference nodes to obtain the wind power generation reference node set, where the wind power generation reference node set includes multiple wind power generation reference nodes, and the wind power generation reference nodes correspond to the wind turbines one by one; Obtain the comprehensive predicted power generation using the wind power generation reference node set and the solar generator set.

[0008] Optionally, the obtaining of the comprehensive predicted power generation using the wind power generation reference node set and the solar generator set includes: Perform the following operations on each solar generator in the solar generator set: Obtain the photovoltaic influence factor set of the solar generator, and use the photovoltaic influence factor set to obtain the photovoltaic power generation reference node set, where the photovoltaic power generation reference node set includes a plurality of photovoltaic power generation reference nodes, and the photovoltaic power generation reference node includes a target reference photovoltaic power set and a reference predicted photovoltaic power set; Obtain the reference accuracy nodes of the power prediction models in the power prediction model set to obtain the reference accuracy node set, where the reference accuracy node includes the number of training data and the number of identification data; Calculate the comprehensive predicted power generation based on the wind power generation reference node set, the reference accuracy node set, and the photovoltaic power generation reference node set.

[0009] Optionally, the calculating of the comprehensive predicted power generation based on the wind power generation reference node set, the reference accuracy node set, and the photovoltaic power generation reference node set includes: Cluster the target reference wind power in the wind power generation reference node set to obtain a plurality of clustered wind power sets, count the number of each clustered wind power in the plurality of clustered wind power sets to obtain a plurality of statistical cluster numbers, and use the plurality of statistical cluster numbers to identify the target clustered power set in the plurality of clustered wind power sets, where the target clustered power set is the clustered wind power set corresponding to the largest statistical cluster number among the plurality of statistical cluster numbers; Calculate the mean value of the target clustered power in the target clustered power set to obtain the clustered wind power mean value; Calculate the comprehensive reference wind power according to the clustered wind power mean value and the reference accuracy node set, obtain the comprehensive reference photovoltaic power based on the photovoltaic power generation reference node set, and calculate the sum of the comprehensive reference wind power and the comprehensive reference photovoltaic power to obtain the comprehensive predicted power generation.

[0010] Optionally, the calculating of the comprehensive reference wind power according to the clustered wind power mean value and the reference accuracy node set is shown by the following formula: ; Where represents the comprehensive reference wind power, are all preset coefficients, represents that the number of the clustered wind power sets is pieces, respectively represent the th statistical cluster number and the The number of statistical clusters, indicating the contribution equivalent of the th cluster wind power and electricity concentration, representing the mean of the cluster wind power and electricity, respectively representing the th cluster wind power and electricity concentration of the th cluster wind power and electricity and the th cluster wind power and electricity, representing the total number of cluster wind power and electricity in the th cluster wind power and electricity concentration, representing the number of training data corresponding to the th reference accuracy node in the reference accuracy node set, representing the total number of reference accuracy nodes in the reference accuracy node set, representing the number of recognition data corresponding to the th reference accuracy node in the reference accuracy node set, representing the reference predicted wind power and electricity corresponding to the th electricity prediction model in the electricity prediction model set.

[0011] Optionally, retrieving the target storage battery pack in the energy storage battery pack by using the energy storage battery parameter set includes: Obtaining the monitoring node time series of each energy storage battery in the energy storage battery pack, where the monitoring node time series includes multiple monitoring nodes, and the monitoring nodes include monitoring internal resistance and monitoring temperature; Associating the monitoring nodes with the time corresponding to the obtained monitoring nodes to obtain fitting data nodes, summarizing the fitting data nodes to obtain a fitting data node set, mapping the fitting data nodes in the fitting data node set to a pre-constructed reference coordinate system to obtain a mapping coordinate set, using the pre-constructed curve fitting method and the mapping coordinate set to obtain fitting curves, and summarizing the fitting curves to obtain a fitting curve set, where the fitting curve set includes multiple fitting curves, and the fitting curves correspond to the energy storage batteries one by one; Performing the following operations on each fitting curve in the fitting curve set: Identifying the minimum curvature radius in the fitting curve, calculating the product of the minimum curvature radius and a preset ratio coefficient to obtain an identification range radius, and constructing a fitting screening range with the fitting curve as the central axis and the identification range radius as the radius; Counting the number of fitting curves in the fitting curve set within the fitting screening range to obtain a range curve number, summarizing the range curve numbers to obtain a range curve number set; Calculating the reference projection distance of the fitting curve, and the calculation formula is as follows: ; Among them, represents the reference projection distance, represents that there are monitoring nodes in the monitoring node timing, represents the monitoring internal resistance, represents the monitoring temperature; Summarize the reference projection distances to obtain a set of reference projection distances. Sort the reference projection distances in the set of reference projection distances in ascending order of the reference projection distance to obtain a reference projection distance sequence. Use the set of range curve numbers and the reference projection distance sequence to obtain a range curve number sequence. Based on a preset battery screening threshold, confirm the first curve number in the range curve number sequence. Among them, the first curve number is the first range curve number in the range curve number sequence that is greater than or equal to the battery screening threshold; Use the first curve number to extract a set of screened battery parameters from the set of energy storage battery parameters. Among them, the set of screened battery parameters includes multiple screened battery parameters, and the screened battery parameters include the battery SOH value, the remaining stored power, and the battery SOC value; Use a clustering algorithm to cluster the set of screened battery parameters to obtain one or more sets of distance screening parameters. Count the number of distance screening parameters in each set of distance screening parameters in the one or more sets of distance screening parameters to obtain one or more distance screening quantities; If there is a distance screening quantity greater than or equal to the battery screening threshold among the one or more distance screening quantities, randomly extract the same number of energy storage batteries as the battery screening threshold from the multiple energy storage batteries corresponding to the distance screening quantity to obtain a target storage battery group; Otherwise, skip the first curve number in the range curve number sequence, and return to the step of confirming the first curve number in the range curve number sequence based on the preset battery screening threshold until a target storage battery group is obtained.

[0012] Optionally, the retrieving in the energy storage battery group by using the analyzed power and the set of energy storage battery parameters. If a preset target power supply battery group is retrieved in the energy storage battery group, it includes: Use the predicted segmented time to obtain a battery power threshold, and calculate the number of energy storage batteries according to the battery power threshold and the battery rated power; Sort the energy storage batteries in the energy storage battery group in descending order of the remaining stored power to obtain an energy storage battery sequence. Use the number of energy storage batteries to obtain a retrieval sliding window. According to the retrieval sliding window, sequentially extract retrieval stored power groups in the energy storage battery sequence, and perform the following operations on the extracted retrieval stored power groups: Calculate the sum of the retrieved stored power in the retrieved stored power group to obtain the comprehensive detection power, and compare the comprehensive detection power with the analysis power; If the comprehensive detection power is greater than or equal to the analysis power, return to the step of sequentially extracting the retrieved stored power group in the energy storage battery sequence until the comprehensive detection power is less than the analysis power, and obtain multiple target retrieved stored power groups. Among them, the comprehensive detection power corresponding to the target retrieved stored power group is greater than or equal to the analysis power. Perform the following operations on each target retrieved stored power group in the multiple target retrieved stored power groups: Calculate the variance of the retrieved stored power in the target retrieved stored power group to obtain the comprehensive detection variance, summarize the comprehensive detection variance to obtain a comprehensive detection variance set, and use the comprehensive detection variance set to confirm the target power supply battery group, where the target power supply battery group is multiple energy storage batteries corresponding to the smallest comprehensive detection variance in the comprehensive detection variance set; Otherwise, confirm that there is no such target power supply battery group in the energy storage battery group.

[0013] Optionally, the calculation formula for the number of energy storage batteries according to the battery power threshold and the battery rated power is as follows: ; Wherein, represents the number of energy storage batteries, represents the battery power threshold, represents the battery rated power, represents rounding up.

[0014] Optionally, the obtaining of the target fuel power supply amount by using the predicted power consumption and the fuel generator set includes: Obtain the rated power generation power of each fuel generator in the fuel generator set to obtain a rated power generation power set; Construct a generator set screening formula according to the rated power generation power set and the battery power threshold. The generator set screening formula is as follows: ; Wherein, represents the number of the th fuel generator among multiple fuel generators, represents the th rated power generation power in the rated power generation power set, represents a total of types of fuel generators are used; In a combined form, using the generator set screening formula, extract multiple initial fuel generator sets from the centralized fuel generators, obtain the energy consumption corresponding to each initial fuel generator set among the multiple initial fuel generator sets, obtain the initial energy consumption set, and identify the initial fuel generator set corresponding to the minimum initial energy consumption in the initial energy consumption set to obtain the target fuel generator set; Obtain the power generation power of the target fuel generator set to obtain the target power generation power, calculate the product of the target power generation power and the predicted segmented time and subtract the predicted power consumption to obtain the target fuel power supply.

[0015] To achieve the above object, the present invention also provides a microgrid energy storage optimization system based on big data analysis, including: An initial microgrid confirmation module, configured to receive an energy storage optimization instruction and confirm an initial microgrid to be subjected to energy storage optimization based on the energy storage optimization instruction. The initial microgrid includes a wind turbine set, a fuel generator set, a solar generator set, and an energy storage battery pack. The wind turbine set includes multiple wind turbines, the solar generator set includes multiple solar generators, the energy storage battery pack includes multiple energy storage batteries, and the fuel generator set includes multiple types of fuel generators; A microgrid parameter prediction module, configured to obtain a comprehensive predicted power generation amount by using a pre-confirmed predicted segmented time, a wind turbine set, and a solar generator set; Obtain the predicted power consumption of the initial microgrid based on the predicted segmented time, calculate the difference between the comprehensive predicted power generation amount and the predicted power consumption to obtain the analyzed power amount; An energy storage solution construction module, configured to obtain an energy storage battery parameter set of the energy storage battery pack. The energy storage battery parameter set includes multiple energy storage battery parameters, and the energy storage battery parameters correspond to the energy storage batteries one by one. The energy storage battery parameters include: battery SOH value, remaining stored power, battery rated power, and battery SOC value; If the analyzed power amount is greater than or equal to a preset stored power threshold, retrieve a target stored battery group from the energy storage battery pack by using the energy storage battery parameter set, and perform active equalization charging on the target stored battery group to obtain an updated stored battery group; If the analyzed power amount is less than a preset supply power threshold, retrieve using the analyzed power amount and the energy storage battery parameter set in the energy storage battery pack. If a preset target power supply battery group is retrieved in the energy storage battery pack, use the target power supply battery group for power supply to obtain an updated power supply battery group; The energy storage solution optimization module is used to, if the target power supply battery pack cannot be retrieved from the energy storage battery pack, utilize the predicted power consumption and the fuel generator set to obtain the target fuel power supply amount, take the target fuel power supply amount as the analyzed power amount, return the step of obtaining the energy storage battery parameter set of the energy storage battery pack, and optimize the energy storage of the initial microgrid based on updating the storage battery pack or updating the power supply battery pack.

[0016] To solve the above problems, the present invention also provides an electronic device, which includes: A memory that stores at least one instruction; and A processor that executes the instructions stored in the memory to implement the above-mentioned microgrid energy storage optimization method based on big data analysis.

[0017] To solve the above problems, the present invention also provides a computer-readable storage medium, in which at least one instruction is stored, and the at least one instruction is executed by a processor in an electronic device to implement the above-mentioned microgrid energy storage optimization method based on big data analysis.

[0018] To solve the problems described in the background art, the present invention utilizes pre - confirmed predicted segmented time, a set of wind turbines, and a set of solar generators to obtain the comprehensive predicted power generation. It can be seen that the present invention considers the power that can be generated by the set of wind turbines and the set of solar generators in the initial micro - grid before optimizing the energy storage of the initial micro - grid, that is, the comprehensive predicted power generation. When obtaining the comprehensive predicted power generation, it adopts the form of screening historical data and using a prediction model for prediction to calculate the comprehensive reference wind power. When calculating the comprehensive reference wind power, different weight values are also set in combination with different features to improve the accuracy of the calculated comprehensive reference wind power, and further improve the accuracy of optimizing the energy storage of the micro - grid. If the analyzed power is greater than or equal to the preset stored power threshold, the present invention uses the energy storage battery parameter set to retrieve the target storage battery group in the energy storage battery pack, and actively balances the charge of the target storage battery group to obtain an updated storage battery group. If the analyzed power is less than the preset supply power threshold, the analyzed power and the energy storage battery parameter set are used to retrieve in the energy storage battery pack. If the preset target energy - supplying battery group is retrieved in the energy storage battery pack, the target energy - supplying battery group is used for power supply to obtain an updated power - supplying battery group. It can be seen that the present invention also considers whether the analyzed power is greater than the stored power threshold for determining whether to charge the energy storage battery pack and less than the supply power threshold for using the energy storage battery pack for energy supply before charging and discharging the energy storage battery pack. Before charging the energy storage batteries in the energy storage battery pack, the similarity of the energy storage batteries at different time nodes and the number of energy storage batteries required to be charged simultaneously are also considered, thus avoiding the over - charging phenomenon when charging some energy storage batteries in the target energy storage battery group and improving the safety of charging the target energy storage battery group. When obtaining the target energy - supplying battery group for power supply, the power and power required by the initial micro - grid at the predicted segmented time are also considered, and the target energy - supplying battery group with similar parameters is retrieved, thus avoiding the over - discharging phenomenon of some energy storage batteries in the target energy - supplying battery group. If the target energy - supplying battery group cannot be retrieved in the energy storage battery pack, the present invention uses the predicted power consumption and the set of fuel generators to obtain the target fuel power supply. Taking the target fuel power supply as the analyzed power, it returns to the step of obtaining the energy storage battery parameter set of the energy storage battery pack, and realizes the optimization of the energy storage of the initial micro - grid based on the updated storage battery group or the updated power - supplying battery group. It can be seen that when there is no target energy - supplying battery group capable of supplying energy in the energy storage battery pack, the present invention also considers using the set of fuel generators for power supply, and when using the set of fuel generators for power supply, it also considers the possible surplus power of the set of fuel generators. Therefore, taking the target fuel power supply as the analyzed power, it returns to the step of obtaining the energy storage battery parameter set of the energy storage battery pack to realize the optimization of the micro - grid energy storage. Therefore, the present invention can accurately and intelligently optimize the energy storage of the micro - grid. Brief Description of the Drawings

[0019] Figure 1 Flow schematic diagram of a microgrid energy storage optimization method based on big data analysis provided by an embodiment of the present invention; Figure 2 Functional module diagram of a microgrid energy storage optimization system based on big data analysis provided by an embodiment of the present invention; Figure 3 Structural schematic diagram of an electronic device for implementing the microgrid energy storage optimization method based on big data analysis provided by an embodiment of the present invention.

[0020] Explanation of reference numerals: 1. Electronic device; 10. Processor; 11. Memory; 12. Bus.

[0021] The realization, functional characteristics, and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. Specific embodiments

[0022] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0023] An embodiment of the present application provides a microgrid energy storage optimization method based on big data analysis. The execution subject of the microgrid energy storage optimization method based on big data analysis includes, but is not limited to, at least one of electronic devices such as a server, a terminal, etc. that can be configured to execute the method provided by the embodiment of the present application. In other words, the microgrid energy storage optimization method based on big data analysis can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes, but is not limited to: a single server, a server cluster, a cloud server, or a cloud server cluster, etc.

[0024] Refer to Figure 1 As shown, it is a flow schematic diagram of a microgrid energy storage optimization method based on big data analysis provided by an embodiment of the present invention. In this embodiment, the microgrid energy storage optimization method based on big data analysis includes: S1. Receive an energy storage optimization instruction, and confirm an initial microgrid to be optimized for energy storage based on the energy storage optimization instruction. Among them, the initial microgrid includes a wind turbine set, a fuel generator set, a solar generator set, and an energy storage battery pack. Among them, the wind turbine set includes multiple wind turbines, the solar generator set includes multiple solar generators, the energy storage battery pack includes multiple energy storage batteries, and the fuel generator set includes multiple types of fuel generators.

[0025] It should be explained that the energy storage optimization instruction is an instruction used to optimize the energy storage of the microgrid. The initial microgrid refers to the microgrid to be optimized for energy storage, and the initial microgrid includes a wind turbine set, a fuel generator set, a solar generator set, and an energy storage battery pack. Among them, the wind turbine set includes multiple wind turbines, the solar generator set includes multiple solar generators, the energy storage battery pack includes multiple energy storage batteries, and the fuel generator set includes multiple types of fuel generators. Among them, a wind turbine refers to a wind power device that converts wind energy into electrical energy, a solar generator refers to a device that converts solar energy into electrical energy, an energy storage battery refers to a battery used to store and release electrical energy in the initial microgrid. Here, the energy storage battery is a device for storing electrical energy in the initial microgrid. A fuel generator refers to a device that generates electricity by relying on the combustion of diesel or gasoline to produce power. The difference between the fuel generator and the wind turbine and the solar generator is that the fuel generator has a stable power and can respond in a timely manner to facilitate the power supply to the microgrid.

[0026] It can be understood that the power generation power of the wind turbine and the solar generator is easily affected by environmental factors, resulting in the problem of unstable power generation power of the wind turbine and the solar generator. In order to maintain the normal operation of the load in the microgrid or store the excess electricity generated by the wind turbine and the solar generator, to maintain the stability of the load in the microgrid and avoid waste of the generated electrical energy, it is necessary to frequently charge and discharge the energy storage battery pack used for energy storage. Furthermore, this leads to a shortened lifespan of the energy storage battery pack, a decrease in the ability to store electrical energy, or a large potential safety hazard in the energy storage battery pack. Therefore, the main purpose of the embodiments of the present invention is to improve the intelligence and accuracy of microgrid energy storage optimization, and further extend the lifespan of the energy storage battery.

[0027] S2. Obtain the comprehensive predicted power generation amount by using the pre-confirmed prediction segmentation time, the wind turbine set, and the solar generator set.

[0028] It should be explained that the obtaining of the comprehensive predicted power generation amount by using the pre-confirmed prediction segmentation time, the wind turbine set, and the solar generator set includes: Perform the following operations on each wind turbine in the wind turbine set: Obtain the initial influence factor set of the wind turbine, and use the pre-constructed principal component analysis method to confirm the target influence factor set in the initial influence factor set; Obtain the initial historical data set based on the target influence factor set. Among them, the initial historical data set includes multiple initial historical data, and the initial historical data includes reference influence environment data and initial reference wind power. Obtain predicted environmental impact data based on the predicted segmented time, wind turbines, and the set of target impact factors. Use the predicted environmental impact data, the pre-constructed clustering algorithm, and the reference environmental impact data corresponding to the initial historical data in the initial historical dataset to obtain the target reference wind power set; Obtain a set of power prediction models for predicting power generation. Based on the set of power prediction models and the wind turbines, obtain a reference predicted wind power set; Associate the target reference wind power set and the reference predicted wind power set to obtain wind power generation reference nodes; Summarize the wind power generation reference nodes to obtain a wind power generation reference node set, where the wind power generation reference node set includes multiple wind power generation reference nodes, and the wind power generation reference nodes correspond one-to-one with the wind turbines; Use the wind power generation reference node set and the set of solar generators to obtain the comprehensive predicted power generation.

[0029] It can be understood that the initial impact factors refer to the factors that may affect the power generation efficiency of wind turbines. For example, wind speed, the location of the wind turbine, air density, temperature, etc. The target impact factors refer to the factors that have a greater impact on the power generation efficiency of wind turbines. The technique of using the principal component analysis method to identify the set of target impact factors in the set of initial impact factors is a prior art and will not be elaborated here.

[0030] It should be understood that the set of target impact factors corresponding to the initial historical dataset is the same as the set of target impact factors corresponding to the wind turbines. For example: if the set of target impact factors of a wind turbine includes temperature, air density, and humidity, then the set of target impact factors corresponding to the initial historical data also includes temperature, air density, and humidity. Generally, before obtaining the initial historical dataset, multiple wind turbines with known power generation can be evaluated to obtain the set of target impact factors for each wind turbine. Then, through the set of target impact factors of the wind turbine to be predicted, the initial historical dataset can be extracted from multiple wind turbines with known sets of target impact factors.

[0031] It should be explained that the predicted segmented time refers to the segmented time to be predicted after dividing the preset time. Optionally, the preset time is 24h corresponding to the next day. After dividing the time of one day into 3 segments, the next time period corresponding to the current time is taken as the predicted segmented time. For example, after dividing the time of one day into 3 segments, the three time periods obtained are 0:00 to 8:00, 8:00 to 16:00, and 16:00 to 24:00. If the current time is in the time period of 0:00 to 8:00, then the predicted segmented time is 8:00 to 16:00.

[0032] It should be understood that the predicted impact environmental data refers to the values of the target impact factors corresponding to the target impact factor set at the location of the wind turbine during the predicted segmented time. For example, the predicted segmented time is 15:00 - 17:00, and the target impact factor set corresponding to this wind turbine includes: temperature and humidity. Then the predicted impact environmental data includes: the temperature is 28 degrees Celsius and the humidity is 40%. Here, the predicted impact environmental data indicates that the temperature at the location of this wind turbine from 15:00 to 17:00 is 28 degrees Celsius and the humidity is 40%. Here, the predicted impact environmental data can be obtained in the form of taking an average. For example, the predicted temperature at 15:00 is 29 degrees Celsius, the predicted temperature at 16:00 is 28 degrees Celsius, and the predicted temperature at 17:00 is 27 degrees Celsius. Then the temperature in the predicted impact environmental data is 28 degrees Celsius. The initial reference wind power is the power that the wind turbine can generate under the reference environmental impact data.

[0033] It should be understood that the acquisition method of the reference impact environmental data is the same as that of the predicted impact environmental data, and the time period corresponding to the reference impact environmental data is the same as the time period corresponding to the predicted segmented time. For example, the predicted segmented time is 15:00 - 17:00. Then, the reference impact environmental data and the initial reference wind power at 15:00 - 17:00 are taken from the known operation data of the wind turbine as the initial historical data.

[0034] It should be explained that the target reference wind power set is obtained by using the predicted impact environmental data, the pre - constructed clustering algorithm, and the reference impact environmental data corresponding to the initial historical data in the initial historical data set, including: using the clustering algorithm to cluster the predicted impact environmental data and the reference impact environmental data corresponding to the initial historical data in the initial historical data set to obtain multiple clustered data sets, retrieving the reference impact environmental data including the predicted impact environmental data from the multiple clustered data sets, and extracting the initial reference wind power corresponding to the reference impact environmental data from the reference impact environmental data to obtain the target reference wind power set. Optionally, the k - means clustering algorithm is used as the clustering algorithm. The same effect can be achieved by using other technologies, which will not be elaborated here.

[0035] It should be understood that the power prediction model refers to a model that can predict the generated power. For example, a trained neural network model is used as the power prediction model, and the same effect can be achieved by using other technologies, which will not be elaborated here. The reference predicted wind power refers to the power that can be generated by a wind turbine predicted by using a current prediction model in combination with the characteristics of the wind turbine and the predicted environmental data. Associating the target reference wind power set and the reference predicted wind power set to obtain a wind power generation reference node means using the target reference wind power set and the reference predicted wind power set corresponding to the wind turbine as the basis for evaluating the power that the wind turbine can generate during the predicted segmentation time, and summarizing the target reference wind power set and the reference predicted wind power set to obtain a wind power generation reference node. For example, if the target reference wind power set includes 11 kWh, 13 kWh, and 12 kWh, and the reference predicted wind power set includes 8 kWh and 6 kWh, then associating the target reference wind power set and the reference predicted wind power set will obtain a wind power generation reference node including 11 kWh, 13 kWh, 12 kWh, 8 kWh, and 6 kWh.

[0036] Further, obtaining the comprehensive predicted power generation by using the wind power generation reference node set and the solar generator set includes: Performing the following operations on each solar generator in the solar generator set: Obtaining the photovoltaic influence factor set of the solar generator, and using the photovoltaic influence factor set to obtain a photovoltaic power generation reference node set, where the photovoltaic power generation reference node set includes multiple photovoltaic power generation reference nodes, and the photovoltaic power generation reference node includes a target reference photovoltaic power set and a reference predicted photovoltaic power set; Obtaining the reference accuracy nodes of the power prediction models in the power prediction model set to obtain a reference accuracy node set, where the reference accuracy node includes the number of training data and the number of recognition data; Calculating the comprehensive predicted power generation based on the wind power generation reference node set, the reference accuracy node set, and the photovoltaic power generation reference node set.

[0037] It should be explained that the photovoltaic influence factor refers to a factor that affects the power generation efficiency of a solar generator. For example, light intensity and temperature. The acquisition method of the photovoltaic influence factor set is the same as that of the target influence factor set, which will not be elaborated here. The acquisition method of the photovoltaic power generation reference node set is the same as that of the wind power generation reference node set, which will not be elaborated here.

[0038] It is understandable that before using the power consumption prediction model, the power consumption prediction model will be tested, that is, the data predicted by the power consumption prediction model will be compared with the known data. When there is no significant difference between the predicted data and the known data, it is determined that the power consumption prediction model can make correct predictions; otherwise, it is determined that the power consumption prediction model makes incorrect predictions. The number of training data refers to the number of data used to test the power consumption prediction model, and the number of recognized data refers to the number of data that the power consumption test model can correctly recognize. For example, if 10 data are used to test the power consumption prediction model and the power consumption prediction model can correctly predict 9 data, then the number of training data is 10 and the number of recognized data is 9. The acquisition method of the reference predicted photovoltaic power set is the same as that of the reference predicted wind power set, which will not be elaborated here. The reference predicted photovoltaic power refers to the power that the solar power generation unit can generate within the predicted time segment. The acquisition method of the target reference photovoltaic power set is the same as that of the target reference wind power set, and the target reference photovoltaic power refers to the power that the solar power generation unit can generate in the historical data.

[0039] Further, calculating the comprehensive predicted power generation based on the wind power generation reference node set, the reference accuracy node set, and the photovoltaic power generation reference node set includes: Cluster the target reference wind power in the wind power generation reference node set to obtain multiple clustered wind power sets, count the number of each clustered wind power in the multiple clustered wind power sets to obtain multiple statistical cluster numbers, and use the multiple statistical cluster numbers to identify the target clustered power set in the multiple clustered wind power sets, where the target clustered power set is the clustered wind power set corresponding to the largest statistical cluster number among the multiple statistical cluster numbers; Calculate the mean value of the target clustered power in the target clustered power set to obtain the mean value of the clustered wind power; Calculate the comprehensive reference wind power based on the mean value of the clustered wind power and the reference accuracy node set, obtain the comprehensive reference photovoltaic power based on the photovoltaic power generation reference node set, and calculate the sum of the comprehensive reference wind power and the comprehensive reference photovoltaic power to obtain the comprehensive predicted power generation.

[0040] It should be noted that clustering the target reference wind power in the wind power generation reference node set to obtain multiple clustered wind power sets means using a clustering algorithm to cluster the target reference wind power in the wind power generation reference node set to obtain multiple sets of different target reference wind power. For example, after clustering 100 target reference wind powers using the k-means clustering algorithm, the 100 target reference wind powers can be clustered into 5 clusters. Among them, each cluster includes multiple target reference wind powers, and the multiple target reference wind powers included in each cluster constitute a clustered wind power set. The method for obtaining the comprehensive reference photovoltaic power is the same as that for obtaining the comprehensive reference wind power, which will not be elaborated here.

[0041] Furthermore, calculating the comprehensive reference wind power according to the clustered wind power mean value and the reference accuracy node set is calculated as follows: ; Wherein, represents the comprehensive reference wind power, are all preset coefficients, represents that the number of clustered wind power sets is pieces, respectively represent the th statistical clustering quantity and the th statistical clustering quantity among multiple statistical clustering quantities, represents the contribution equivalent of the th clustered wind power set among multiple clustered wind power sets, represents the clustered wind power mean value, respectively represent the th and th clustered wind powers in the th clustered wind power set, represents that there are th clustered wind powers in the th clustered wind power set, represents the number of training data corresponding to the th reference accuracy node in the reference accuracy node set, represents that there are reference accuracy nodes in the reference accuracy node set, represents the number of recognition data corresponding to the th reference accuracy node in the reference accuracy node set, represents the reference predicted wind power corresponding to the th power prediction model in the power prediction model set.

[0042] It is understandable that the target clustered power set can represent the set of power that a wind turbine can generate under the target influencing factor set in most cases. Therefore, when calculating the comprehensive reference wind power, using the mean value of the clustered wind power and the statistical clustered quantity as weights, it is set that the smaller the absolute difference between the clustered wind power and the mean value of the clustered wind power, the greater the weight corresponding to the clustered wind power, and when the statistical clustered quantity is larger, the greater the weight corresponding to the clustered wind power set, so as to improve the accuracy of the obtained comprehensive reference wind power.

[0043] S3. Obtain the predicted power consumption of the initial microgrid based on the predicted segmented time, calculate the difference between the comprehensive predicted power generation and the predicted power consumption to obtain the analyzed power.

[0044] It should be explained that the predicted power consumption refers to the power required by the initial microgrid predicted within the predicted segmented time. Optionally, a pre-trained neural network model is used to predict the power required by the initial microgrid to obtain the predicted power consumption. The same effect can be achieved by using other technologies, which will not be elaborated here.

[0045] S4. Obtain the energy storage battery parameter set of the energy storage battery pack. Among them, the energy storage battery parameter set includes multiple energy storage battery parameters, and the energy storage battery parameters correspond to the energy storage batteries one by one. The energy storage battery parameters include: battery SOH value, remaining stored power, battery rated power, and battery SOC value.

[0046] It should be explained that the battery SOH value is an index to measure the battery performance relative to its brand-new state, usually expressed in percentage, which reflects the overall health of the battery and is an existing technology. The battery SOC value represents the ratio of the remaining power of the battery to its rated capacity, usually expressed in percentage. The battery rated power here is the rated output power of the battery, and the remaining stored power refers to the available power stored in the current energy storage battery. Optionally, the energy storage battery parameters can be obtained through the BMS system. The same effect can be achieved by using other technologies, which will not be elaborated here.

[0047] S5. If the analyzed power is greater than or equal to the preset stored power threshold, use the energy storage battery parameter set to retrieve the target storage battery pack in the energy storage battery pack, and perform active equalization charging on the target storage battery pack to obtain the updated storage battery pack.

[0048] Furthermore, the step of using the energy storage battery parameter set to retrieve the target storage battery pack in the energy storage battery pack includes: Obtain the monitoring node time series of each energy storage battery in the energy storage battery pack. Among them, the monitoring node time series includes multiple monitoring nodes, and the monitoring nodes include monitoring internal resistance and monitoring temperature; Associate the monitoring nodes and obtain the corresponding time of the monitoring nodes to obtain the fitting data nodes. Aggregate the fitting data nodes to obtain a set of fitting data nodes. Map the fitting data nodes in the set of fitting data nodes to a pre-constructed reference coordinate system to obtain a set of mapped coordinates. Use the pre-constructed curve fitting method and the set of mapped coordinates to obtain the fitting curves. Aggregate the fitting curves to obtain a set of fitting curves, where the set of fitting curves includes multiple fitting curves, and the fitting curves correspond to the energy storage batteries one by one; Perform the following operations on each fitting curve in the set of fitting curves: Identify the minimum radius of curvature in the fitting curve, calculate the product of the minimum radius of curvature and a preset ratio coefficient to obtain the identified range radius, and construct a fitting screening range with the fitting curve as the central axis and the identified range radius as the radius; Count the number of fitting curves in the set of fitting curves within the fitting screening range to obtain the range curve quantity, and aggregate the range curve quantities to obtain a set of range curve quantities; Calculate the reference projection distance of the fitting curve. The calculation formula is as follows: ; where, represents the reference projection distance, represents that there are monitoring nodes in the monitoring node time series, represents the monitored internal resistance, represents the monitored temperature; Aggregate the reference projection distances to obtain a set of reference projection distances. Sort the reference projection distances in the set of reference projection distances in ascending order of the reference projection distance to obtain a reference projection distance sequence. Use the set of range curve quantities and the reference projection distance sequence to obtain a range curve quantity sequence. Based on a preset battery screening threshold, confirm the first curve quantity in the range curve quantity sequence, where the first curve quantity is the first range curve quantity in the range curve quantity sequence that is greater than or equal to the screening battery threshold; Extract a set of screened battery parameters from the energy storage battery parameter set using the first curve quantity. The set of screened battery parameters includes multiple screened battery parameters, and the screened battery parameters include the battery SOH value, the remaining stored power, and the battery SOC value; Cluster the set of screened battery parameters using a clustering algorithm to obtain one or more sets of distance screening parameters, and count the number of distance screening parameters in each set of distance screening parameters in the one or more sets of distance screening parameters to obtain one or more distance screening quantities; If there is a distance screening quantity greater than or equal to the screening battery threshold among one or more distance screening quantities, randomly extract the same number of energy storage batteries as the screening battery threshold from the multiple energy storage batteries corresponding to the distance screening quantity to obtain a target storage battery group; Otherwise, skip the first curve quantity in the range curve quantity sequence, and return to the step of confirming the first curve quantity in the range curve quantity sequence based on the preset screening battery threshold until a target storage battery group is obtained.

[0049] It should be noted that the stored power threshold is a preset value used to determine whether the analyzed power needs to be stored in the storage battery group. The technology of actively balancing the charge of the target storage battery group is an existing technology and will not be elaborated here. When calculating the reference projection distance, only the data of the monitored internal resistance and the monitored temperature are used for calculation.

[0050] Furthermore, the monitoring node is a node used to characterize the changes in temperature and internal resistance of the energy storage battery over time during operation. Optionally, the monitoring node time series is obtained by the charge and discharge cycle test method, and the same technical effect can be achieved by using other methods, which will not be elaborated here. The monitored internal resistance refers to the internal resistance of the energy storage battery, and the monitored temperature refers to the temperature of the energy storage battery. Generally, the time corresponding to the monitored internal resistance of different monitoring nodes is different, and the time corresponding to the monitored temperature of different monitoring nodes is also different. Optionally, the Cartesian coordinate system is used as the reference coordinate system. Optionally, the polynomial fitting method is used as the curve fitting method. The screening battery parameter set is extracted from the energy storage battery parameter set using the first curve quantity, including: after confirming multiple energy storage batteries in the energy storage battery group according to the first curve quantity, extracting the corresponding screening battery parameters of the multiple energy storage batteries from the energy storage battery parameter set to obtain the screening battery parameter set.

[0051] It should be noted that the fitting curve is a curve used to characterize the changes in the internal resistance and temperature of the battery over time. Optionally, the x-axis in the Cartesian coordinate system is used as time, the y-axis is the monitored internal resistance, and the z-axis is the monitored temperature. The monitoring nodes in the monitoring node time series are mapped to the Cartesian coordinate system, and the monitoring nodes mapped to the Cartesian coordinate system are fitted into a curve using the polynomial fitting method. The minimum curvature radius refers to the smallest curvature radius, and the technology of identifying the minimum curvature radius in the fitting curve is an existing technology and will not be elaborated here. The proportion coefficient is a preset value used to construct the fitting screening range. Optionally, the proportion coefficient is set to 0.8, and the same effect can be achieved by using other technologies, which will not be elaborated here.

[0052] Further, with the fitting curve as the central axis and the recognition range radius as the radius, the constructed fitting and screening range is the pipe range that changes with the fitting curve, and the cross-section of any pipe in the pipe range is a circular cross-section. When there is a fitting curve in the fitting and screening range, it indicates that there is a working condition of the energy storage battery during operation that is the same as the working condition of the energy storage battery corresponding to the fitting curve. Here, the working condition refers to the internal resistance and temperature of the energy storage battery.

[0053] It should be explained that the smaller the reference projection distance, the better the working condition of this type of energy storage battery during operation. Obtaining the range curve quantity sequence using the range curve quantity set and the reference projection distance sequence means: sorting the range curve quantities in the range curve quantity set according to the order of the reference projection distances in the reference projection distance sequence to obtain the range curve quantity sequence. Generally, the working conditions of the energy storage batteries in the same fitting and screening range are similar.

[0054] It can be understood that the screening battery threshold refers to the number of energy storage batteries used for charging simultaneously. Optionally, the screening battery threshold is obtained by manual setting, and the same effect can be achieved using other technologies, which will not be elaborated here. The purpose of setting the screening battery threshold is to prevent overcharging when charging some batteries.

[0055] Further, the method of clustering the screening battery parameter set using the clustering algorithm is the same as the method of obtaining the target reference wind power quantity set using the predicted impact environment data, the pre-constructed clustering algorithm, and the reference impact environment data corresponding to the initial historical data in the initial historical data set, which will not be elaborated here.

[0056] It can be understood that the fitting curves in the same fitting and screening range have the same working condition during operation, but their battery SOH values, remaining stored power, and battery SOC values are not the same. Therefore, in the present invention, the screening battery parameter set is clustered to screen the energy storage batteries in the energy storage battery pack again, so as to screen out the energy storage batteries with similar battery SOH values, remaining stored power, and battery SOC values. Furthermore, it is ensured that all the energy storage batteries in the target storage battery pack have similar battery SOH values, resistance during operation, temperature during operation, remaining stored power, and battery SOC values, so as to improve the lifespan of the energy storage batteries in the target storage battery pack and reduce the danger during the charging of the energy storage batteries. The step of skipping the first curve quantity in the range curve quantity sequence and returning the first curve quantity confirmed in the range curve quantity sequence based on the preset screening battery threshold means skipping the first confirmed first curve quantity in the range curve quantity sequence and sequentially confirming the second first curve quantity, the third first curve quantity, and so on according to the order of the range curve quantity in the range curve quantity sequence until the target storage battery pack is confirmed.

[0057] S6. If the analyzed power is less than the preset supply power threshold, the analyzed power and the energy storage battery parameter set are used to search in the energy storage battery pack. If a preset target energy supply battery pack is retrieved in the energy storage battery pack, the target energy supply battery pack is used to supply power to obtain an updated power supply battery pack.

[0058] Furthermore, the method of searching the energy storage battery pack by analyzing the power and the energy storage battery parameter set, if a preset target energy supply battery pack is found in the energy storage battery pack, includes: The predicted segment time is used to obtain a battery power threshold, and the number of energy storage batteries is calculated according to the battery power threshold and the battery rated power; The energy storage batteries in the energy storage battery group are sorted in descending order of remaining storage power to obtain an energy storage battery sequence. The number of energy storage batteries is used to obtain a search sliding window. According to the search sliding window, search storage power groups are sequentially extracted from the energy storage battery sequence, and the following operations are performed on the extracted search storage power groups: Calculate the sum of the retrieved stored power in the retrieved stored power group to obtain the comprehensive detected power, and compare the comprehensive detected power with the analyzed power; If the comprehensive detected power is greater than or equal to the analyzed power, the process returns to the step of sequentially extracting the search and storage power groups from the energy storage battery sequence until the comprehensive detected power is less than the analyzed power, thereby obtaining multiple target search and storage power groups, wherein the comprehensive detected power corresponding to the target search and storage power groups is greater than or equal to the analyzed power, and the following operation is performed on each of the multiple target search and storage power groups: Calculating the variance of the retrieval storage power in the target retrieval storage power group to obtain a comprehensive detection variance, summarizing the comprehensive detection variance to obtain a comprehensive detection variance set, and using the comprehensive detection variance set to identify the target energy supply battery group, wherein the target energy supply battery group is the multiple energy storage batteries corresponding to the smallest comprehensive detection variance in the comprehensive detection variance set; Otherwise, it is confirmed that the target energy supply battery pack does not exist in the energy storage battery pack.

[0059] It should be noted that when the analyzed power level is less than the supply power threshold, it indicates that the initial microgrid needs to be powered by the energy storage batteries in the energy storage battery pack or by a fuel generator. The battery power threshold refers to the power required by the energy storage battery pack to supply the initial microgrid. Optionally, multiple power values consumed by the initial microgrid are obtained by predicting the segment time, and the maximum value of these multiple power values is used as the battery power threshold.

[0060] It is understandable that the size of the retrieval sliding window is the same as the number of energy storage batteries. For example, if the number of energy storage batteries is 5, a sliding window with a window size of 5 is used as the retrieval sliding window. Generally, when using a sliding window, it is also necessary to set the sliding step of the sliding window. For example, there are 6 remaining stored power levels in the energy storage battery sequence, which are: 9, 8, 6, 4, 3, and 2, and the number of energy storage batteries is 3, then the analyzed power is 15. Using the retrieval sliding window, 4 retrieval stored power groups can be extracted from the energy storage battery sequence, and the 4 retrieval stored power groups are respectively: 9, 8, and 6, 8, 6, and 4, 6, 4, and 3, 4, 3, and 2. After calculating the comprehensive detection power based on the retrieval stored power groups and comparing it with the analyzed power, the third and fourth retrieval stored power groups are eliminated, that is, two target retrieval stored power groups are retained, which are: 9, 8, and 6, 8, 6, and 4.

[0061] Further, the calculation formula for the number of energy storage batteries according to the battery power threshold and the rated power of the battery is as follows: ; Wherein, represents the number of energy storage batteries, represents the battery power threshold, represents the rated power of the battery, represents rounding up.

[0062] S7. If the target power supply battery group cannot be retrieved from the energy storage battery group, the target fuel power supply is obtained by using the predicted power consumption and the fuel generator set. Taking the target fuel power supply as the analyzed power, return to the step of obtaining the energy storage battery parameter set of the energy storage battery group, and realize the energy storage optimization of the initial microgrid based on updating the storage battery group or updating the power supply battery group.

[0063] It should be explained that the method of obtaining the target fuel power supply by using the predicted power consumption and the fuel generator set includes: Obtain the rated power generation of each fuel generator in the fuel generator set to obtain a set of rated power generations; Construct a generator set screening formula according to the set of rated power generations and the battery power threshold. The generator set screening formula is as follows: ; Wherein, represents the number of the th fuel generator among multiple fuel generators, represents the th rated power generation in the set of rated power generations, represents a total of types of fuel generators are used; In a combined manner, using the generator set screening formula, extract multiple initial fuel generator sets from the fuel generators, obtain the energy consumption corresponding to each of the multiple initial fuel generator sets, obtain the initial energy consumption set, identify the initial fuel generator set corresponding to the minimum initial energy consumption in the initial energy consumption set, and obtain the target fuel generator set; Obtain the power generation power of the target fuel generator set to obtain the target power generation power, calculate the product of the target power generation power and the predicted segmented time and subtract the predicted power consumption to obtain the target fuel power supply.

[0064] It should be explained that the rated power generation power refers to the maximum electric power that the fuel generator can continuously and stably output under rated conditions. Obtaining the energy consumption corresponding to each of the multiple initial fuel generator sets means obtaining the energy consumption required by the initial fuel generator in the predicted segmented time by combining the fixed energy consumption of the initial fuel generator in the initial fuel generator set and the unit energy consumption that changes with time, which is a prior art and will not be elaborated here. The target power generation power refers to the sum of the power generation powers corresponding to the target fuel generators in the target fuel generator set. The product of the target power generation power and the predicted segmented time is used to represent the amount of electricity that the target power generation power can generate within the predicted segmented time. Subtracting the predicted power consumption from this amount of electricity means the remaining amount of electricity after supplying the initial microgrid, that is, the target fuel power supply.

[0065] Furthermore, taking the target fuel power as the analyzed power is to determine whether the target fuel power meets the storage condition, that is, whether it is greater than or equal to the storage power threshold, so as to facilitate the storage of the target fuel power. Generally, the initial microgrid usually also includes a temporary power supply unit, such as a supercapacitor. When storing the target fuel power, it is also possible to consider storing the target fuel power in the temporary power supply unit, and the method of storing the target fuel power in the temporary power supply unit is the same as the method of storing the target fuel power in the target storage battery pack, which will not be elaborated here. For example, when the analyzed power is greater than zero and less than the storage power threshold or the analyzed power is less than zero and greater than or equal to the supply power threshold, the temporary power supply unit can be used for power supply or the temporary power supply unit can be used to store the power.

[0066] To solve the problems described in the background art, the present invention utilizes pre - confirmed predicted segmented time, a set of wind turbines, and a set of solar generators to obtain the comprehensive predicted power generation. It can be seen that the present invention considers the power that can be generated by the set of wind turbines and the set of solar generators in the initial micro - grid before realizing the energy storage optimization of the initial micro - grid, that is, the comprehensive predicted power generation. When obtaining the comprehensive predicted power generation, it adopts the form of screening historical data and using a prediction model for prediction to calculate the comprehensive reference wind power. When calculating the comprehensive reference wind power, different weight values are also set in combination with different characteristics to improve the accuracy of the calculated comprehensive reference wind power, and further improve the accuracy of the energy storage optimization of the micro - grid. If the analyzed power is greater than or equal to the preset stored power threshold, the present invention uses the energy storage battery parameter set to retrieve the target storage battery group in the energy storage battery pack, and actively balances the charge of the target storage battery group to obtain an updated storage battery group. If the analyzed power is less than the preset supply power threshold, the analyzed power and the energy storage battery parameter set are used to retrieve in the energy storage battery pack. If the preset target energy - supplying battery group is retrieved in the energy storage battery pack, the target energy - supplying battery group is used for power supply to obtain an updated power - supplying battery group. It can be seen that before charging and discharging the energy storage battery pack, the present invention also considers whether the analyzed power is greater than the stored power threshold for determining whether to charge the energy storage battery pack and less than the supply power threshold for using the energy storage battery pack for energy supply. Before charging the energy storage batteries in the energy storage battery pack, the similarity of the energy storage batteries at different time nodes and the number of energy storage batteries required to be charged simultaneously are also considered. Thus, the phenomenon of over - charging some energy storage batteries in the target energy storage battery group is avoided, and the safety of charging the target energy storage battery group is improved. When obtaining the target energy - supplying battery group for power supply, the power and power required by the initial micro - grid at the predicted segmented time are also considered, and the target energy - supplying battery group with similar parameters is retrieved. Furthermore, the phenomenon of over - discharging some energy storage batteries in the target energy - supplying battery group is avoided. If the target energy - supplying battery group cannot be retrieved in the energy storage battery pack, the present invention uses the predicted power consumption and the set of fuel generators to obtain the target fuel power supply. Taking the target fuel power supply as the analyzed power, it returns to the step of obtaining the energy storage battery parameter set of the energy storage battery pack, and realizes the energy storage optimization of the initial micro - grid based on the updated storage battery group or the updated power - supplying battery group. It can be seen that when there is no target energy - supplying battery group capable of supplying energy in the energy storage battery pack, the present invention also considers using the set of fuel generators for power supply. When using the set of fuel generators for power supply, the possible surplus power of the set of fuel generators is also considered. Therefore, taking the target fuel power supply as the analyzed power, it returns to the step of obtaining the energy storage battery parameter set of the energy storage battery pack to realize the optimization of the micro - grid energy storage. Therefore, the present invention can accurately and intelligently optimize the energy storage of the micro - grid.

[0067] As shown Figure 2 in the figure, it is a functional module diagram of a microgrid energy storage optimization system based on big data analysis provided by an embodiment of the present invention.

[0068] The microgrid energy storage optimization system 100 based on big data analysis according to the present invention can be installed in an electronic device. According to the functions achieved, the microgrid energy storage optimization system 100 based on big data analysis can include an initial microgrid confirmation module 101, a microgrid parameter prediction module 102, an energy storage scheme construction module 103, and an energy storage scheme optimization module 104. The modules described in the present invention can also be referred to as units, which refer to a series of computer program segments that can be executed by a processor of an electronic device and can complete fixed functions, and are stored in the memory of the electronic device.

[0069] The initial microgrid confirmation module 101 is configured to receive an energy storage optimization instruction and confirm an initial microgrid to be optimized for energy storage based on the energy storage optimization instruction. Among them, the initial microgrid includes a wind turbine set, a fuel generator set, a solar generator set, and an energy storage battery pack. Among them, the wind turbine set includes multiple wind turbines, the solar generator set includes multiple solar generators, the energy storage battery pack includes multiple energy storage batteries, and the fuel generator set includes multiple types of fuel generators; The microgrid parameter prediction module 102 is configured to obtain a comprehensive predicted power generation amount by using a pre-confirmed prediction segmentation time, a wind turbine set, and a solar generator set; Based on the prediction segmentation time, obtain the predicted power consumption of the initial microgrid, calculate the difference between the comprehensive predicted power generation amount and the predicted power consumption, and obtain the analyzed power amount; The energy storage scheme construction module 103 is configured to obtain an energy storage battery parameter set of the energy storage battery pack. Among them, the energy storage battery parameter set includes multiple energy storage battery parameters, and the energy storage battery parameters correspond to the energy storage batteries one by one. The energy storage battery parameters include: battery SOH value, remaining stored power, battery rated power, and battery SOC value; If the analyzed power amount is greater than or equal to a preset stored power threshold, use the energy storage battery parameter set to retrieve a target storage battery group in the energy storage battery pack, and perform active equalization charging on the target storage battery group to obtain an updated storage battery group; If the analyzed power amount is less than a preset supply power threshold, use the analyzed power amount and the energy storage battery parameter set to retrieve in the energy storage battery pack. If a preset target power supply battery group is retrieved in the energy storage battery pack, use the target power supply battery group to supply power to obtain an updated power supply battery group; The energy storage solution optimization module 104 is configured to, if a target power supply battery pack cannot be retrieved from the energy storage battery pack, use the predicted power consumption and the fuel generator set to obtain the target fuel power supply, use the target fuel power supply as the analyzed power, and return to the step of obtaining the energy storage battery parameter set of the energy storage battery pack, and optimize the energy storage of the initial microgrid based on updating the storage battery pack or updating the power supply battery pack.

[0070] Specifically, when the modules in the microgrid energy storage optimization system 100 based on big data analysis described in the embodiments of the present invention are used, they adopt the same technical means as those in the Figure 1 microgrid energy storage optimization method based on big data analysis described above, and can produce the same technical effects, which will not be elaborated here.

[0071] As Figure 3 shown, it is a schematic structural diagram of an electronic device for implementing the microgrid energy storage optimization method based on big data analysis provided by an embodiment of the present invention.

[0072] The electronic device 1 may include a processor 10, a memory 11, and a bus 12, and may further include a computer program stored in the memory 11 and executable on the processor 10, such as a microgrid energy storage optimization method program based on big data analysis.

[0073] Among them, the memory 11 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, magnetic disk, optical disk, etc. The memory 11 may be an internal storage unit of the electronic device 1 in some embodiments, such as the mobile hard disk of the electronic device 1. The memory 11 may also be an external storage device of the electronic device 1 in other embodiments, such as a plug-in mobile hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. equipped on the electronic device 1. Further, the memory 11 also includes the internal storage unit of the electronic device 1 and the external storage device. The memory 11 can be used not only to store application software installed on the electronic device 1 and various types of data, such as the code of the microgrid energy storage optimization method program, but also to temporarily store data that has been output or will be output.

[0074] In some embodiments, the processor 10 may be composed of an integrated circuit. For example, it may be composed of a single packaged integrated circuit, or may be composed of multiple packaged integrated circuits with the same or different functions, including a combination of one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control core (Control Unit) of the electronic device, connecting all components of the entire electronic device through various interfaces and circuits, and by running or executing programs or modules stored in the memory 11 (such as the microgrid energy storage optimization method program based on big data analysis, etc.), and calling the data stored in the memory 11, to execute various functions of the electronic device 1 and process data.

[0075] The bus 12 may be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus 12 can be divided into an address bus, a data bus, a control bus, etc. The bus 12 is configured to enable connection communication between the memory 11 and at least one processor 10, etc.

[0076] Figure 3 Only the electronic device with components is shown. Those skilled in the art can understand that, Figure 3 the shown structure does not constitute a limitation on the electronic device 1, and it may include fewer or more components than shown, or combine certain components, or have a different component layout.

[0077] For example, although not shown, the electronic device 1 may further include a power source (such as a battery) for powering each component. Preferably, the power source may be logically connected to the at least one processor 10 through a power management device, so as to implement functions such as charge management, discharge management, and power consumption management through the power management device. The power source may also include any components such as one or more DC or AC power sources, a recharge device, a power failure detection circuit, a power converter or inverter, and a power status indicator. The electronic device 1 may also include various sensors, a Bluetooth module, a Wi-Fi module, etc., which will not be elaborated here.

[0078] Furthermore, the electronic device 1 may further include a network interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device 1 and other electronic devices.

[0079] Optionally, the electronic device 1 may further include a user interface, which may be a display, an input unit (such as a keyboard), and optionally, the user interface may also be a standard wired interface or a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) toucher, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display the information processed in the electronic device 1 and to display a visual user interface.

[0080] The microgrid energy storage optimization method program stored in the memory 11 of the electronic device 1 is a combination of multiple instructions. When running in the processor 10, it can achieve: Receive an energy storage optimization instruction, and confirm an initial microgrid to be optimized for energy storage based on the energy storage optimization instruction. Among them, the initial microgrid includes a wind turbine set, a fuel generator set, a solar generator set, and an energy storage battery pack. Among them, the wind turbine set includes multiple wind turbines, the solar generator set includes multiple solar generators, the energy storage battery pack includes multiple energy storage batteries, and the fuel generator set includes multiple types of fuel generators; Obtain the comprehensive predicted power generation using the pre-confirmed prediction segmentation time, wind turbine set, and solar generator set; Obtain the predicted power consumption of the initial microgrid based on the prediction segmentation time, calculate the difference between the comprehensive predicted power generation and the predicted power consumption, and obtain the analyzed power; Obtain the energy storage battery parameter set of the energy storage battery pack. Among them, the energy storage battery parameter set includes multiple energy storage battery parameters, and the energy storage battery parameters correspond to the energy storage batteries one by one. The energy storage battery parameters include: battery SOH value, remaining stored power, battery rated power, and battery SOC value; If the analyzed power is greater than or equal to the preset stored power threshold, use the energy storage battery parameter set to retrieve the target storage battery pack in the energy storage battery pack, and perform active equalization charging on the target storage battery pack to obtain an updated storage battery pack; If the analyzed power is less than the preset supply power threshold, use the analyzed power and the energy storage battery parameter set to retrieve in the energy storage battery pack. If a preset target power supply battery pack is retrieved in the energy storage battery pack, use the target power supply battery pack to supply power to obtain an updated power supply battery pack; If the target power supply battery pack cannot be retrieved from the energy storage battery pack, the target fuel power supply amount is obtained by using the predicted power consumption and the fuel generator set. Taking the target fuel power supply amount as the analyzed power amount, return to the step of obtaining the energy storage battery parameter set of the energy storage battery pack, and realize the energy storage optimization of the initial microgrid based on updating the storage battery pack or updating the power supply battery pack.

[0081] Specifically, for the specific implementation method of the above instructions by the processor 10, reference can be made to Figures 1 to 3 the description of the relevant steps in the corresponding embodiment, which will not be elaborated here.

[0082] Furthermore, if the modules / units integrated in the electronic device 1 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM, Read-Only Memory).

[0083] The present invention also provides a computer-readable storage medium, and the readable storage medium stores a computer program. When the computer program is executed by the processor of the electronic device, it can realize: Receiving an energy storage optimization instruction, and confirming an initial microgrid to be subjected to energy storage optimization based on the energy storage optimization instruction. The initial microgrid includes a wind turbine set, a fuel generator set, a solar generator set, and an energy storage battery pack. Among them, the wind turbine set includes multiple wind turbines, the solar generator set includes multiple solar generators, the energy storage battery pack includes multiple energy storage batteries, and the fuel generator set includes multiple types of fuel generators; Obtaining the comprehensive predicted power generation amount by using the pre-confirmed predicted segmented time, wind turbine set, and solar generator set; Obtaining the predicted power consumption of the initial microgrid based on the predicted segmented time, calculating the difference between the comprehensive predicted power generation amount and the predicted power consumption, and obtaining the analyzed power amount; Obtaining the energy storage battery parameter set of the energy storage battery pack. Among them, the energy storage battery parameter set includes multiple energy storage battery parameters, and the energy storage battery parameters correspond to the energy storage batteries one by one. The energy storage battery parameters include: battery SOH value, remaining stored power, battery rated power, and battery SOC value; If the analyzed power amount is greater than or equal to the preset stored power threshold, use the energy storage battery parameter set to retrieve the target storage battery pack in the energy storage battery pack, and perform active equalization charging on the target storage battery pack to obtain an updated storage battery pack; If the analyzed power consumption is less than the preset supply power threshold, retrieve in the energy storage battery pack using the analyzed power consumption and the energy storage battery parameter set. If the preset target power supply battery pack is retrieved in the energy storage battery pack, use the target power supply battery pack for power supply to obtain an updated power supply battery pack; If the target power supply battery pack cannot be retrieved in the energy storage battery pack, obtain the target fuel power supply using the predicted power consumption and the fuel generator set. Use the target fuel power supply as the analyzed power consumption, and return to the step of obtaining the energy storage battery parameter set of the energy storage battery pack. Achieve energy storage optimization of the initial microgrid based on the updated storage battery pack or the updated power supply battery pack.

[0084] In several embodiments provided by the present invention, it should be understood that the disclosed devices, systems, and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative, and there may be other division methods in actual implementation.

[0085] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0086] In addition, the functional modules in various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a combination of hardware and software functional modules.

[0087] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A microgrid energy storage optimization method based on big data analysis, characterized in that The method includes: Receiving an energy storage optimization instruction, and based on the energy storage optimization instruction, identifying an initial microgrid to be optimized for energy storage, where the initial microgrid includes a set of wind turbines, a set of fuel generators, a set of solar generators, and an energy storage battery pack. Among them, the set of wind turbines includes multiple wind turbines, the set of solar generators includes multiple solar generators, the energy storage battery pack includes multiple energy storage batteries, and the set of fuel generators includes multiple types of fuel generators; Obtaining a comprehensive predicted power generation amount by using pre-confirmed predicted segmented time, the set of wind turbines, and the set of solar generators; Based on the predicted segmented time, obtaining the predicted power consumption of the initial microgrid, calculating the difference between the comprehensive predicted power generation amount and the predicted power consumption, and obtaining an analyzed power amount; Obtaining a set of energy storage battery parameters of the energy storage battery pack, where the set of energy storage battery parameters includes multiple energy storage battery parameters, and the energy storage battery parameters correspond to the energy storage batteries one by one. The energy storage battery parameters include: battery SOH value, remaining stored power, battery rated power, and battery SOC value; If the analyzed power amount is greater than or equal to a preset stored power threshold, then use the set of energy storage battery parameters to retrieve a target storage battery group in the energy storage battery pack, and perform active equalization charging on the target storage battery group to obtain an updated storage battery group; If the analyzed power amount is less than a preset supply power threshold, then use the analyzed power amount and the set of energy storage battery parameters to retrieve in the energy storage battery pack. If a preset target power supply battery group is retrieved in the energy storage battery pack, then use the target power supply battery group for power supply to obtain an updated power supply battery group; If the target power supply battery group cannot be retrieved in the energy storage battery pack, then obtain a target fuel power supply amount by using the predicted power consumption and the set of fuel generators, use the target fuel power supply amount as the analyzed power amount, return to the step of obtaining the set of energy storage battery parameters of the energy storage battery pack, and realize the energy storage optimization of the initial microgrid based on the updated storage battery group or the updated power supply battery group.

2. The microgrid energy storage optimization method based on big data analysis according to claim 1, wherein, The obtaining of the comprehensive predicted power generation amount by using pre-confirmed predicted segmented time, the set of wind turbines, and the set of solar generators includes: Performing the following operations on each wind turbine in the set of wind turbines: Obtaining an initial set of influence factors of the wind turbine, and using a pre-constructed principal component analysis method to identify a target set of influence factors in the initial set of influence factors; Based on the target set of influence factors, obtaining an initial historical data set, where the initial historical data set includes multiple initial historical data, and the initial historical data includes reference influence environment data and initial reference wind power; Based on the predicted segmented time, the wind turbine, and the target set of influence factors, obtaining predicted influence environment data, and using the predicted influence environment data, a pre-constructed clustering algorithm, and the reference influence environment data corresponding to the initial historical data in the initial historical data set to obtain a target set of reference wind powers; Obtaining a set of power prediction models for predicting power generation amount, and based on the set of power prediction models and the wind turbine, obtaining a set of reference predicted wind powers; Associating the target set of reference wind powers and the set of reference predicted wind powers to obtain a wind power generation reference node; Summarize the above-mentioned wind power reference nodes to obtain a wind power reference node set. Among them, the wind power reference node set includes multiple wind power reference nodes, and the wind power reference nodes correspond to wind turbines one by one; Use the wind power reference node set and the solar generator set to obtain the comprehensive predicted power generation.

3. The microgrid energy storage optimization method based on big data analysis according to claim 2, wherein, The step of using the wind power reference node set and the solar generator set to obtain the comprehensive predicted power generation includes: Perform the following operations on each solar generator in the solar generator set: Obtain the photovoltaic influence factor set of the solar generator, and use the photovoltaic influence factor set to obtain a photovoltaic power generation reference node set. Among them, the photovoltaic power generation reference node set includes multiple photovoltaic power generation reference nodes, and the photovoltaic power generation reference nodes include a target reference photovoltaic power set and a reference predicted photovoltaic power set; Obtain the reference accuracy nodes of the power prediction models in the power prediction model set to obtain a reference accuracy node set. Among them, the reference accuracy nodes include the number of training data and the number of identification data; Calculate the comprehensive predicted power generation based on the wind power reference node set, the reference accuracy node set, and the photovoltaic power generation reference node set.

4. The microgrid energy storage optimization method based on big data analysis according to claim 3, characterized in that The step of calculating the comprehensive predicted power generation based on the wind power reference node set, the reference accuracy node set, and the photovoltaic power generation reference node set includes: Cluster the target reference wind power in the wind power reference node set to obtain multiple clustered wind power sets, count the number of each clustered wind power in the multiple clustered wind power sets to obtain multiple statistical cluster numbers, and use the multiple statistical cluster numbers to identify the target clustered power set in the multiple clustered wind power sets. Among them, the target clustered power set is the clustered wind power set corresponding to the largest statistical cluster number among the multiple statistical cluster numbers; Calculate the mean value of the target clustered power in the target clustered power set to obtain the mean value of the clustered wind power; Calculate the comprehensive reference wind power according to the mean value of the clustered wind power and the reference accuracy node set, obtain the comprehensive reference photovoltaic power based on the photovoltaic power generation reference node set, and calculate the sum of the comprehensive reference wind power and the comprehensive reference photovoltaic power to obtain the comprehensive predicted power generation.

5. The microgrid energy storage optimization method based on big data analysis according to claim 4, characterized in that The formula for calculating the comprehensive reference wind power according to the mean value of the clustered wind power and the reference accuracy node set is as follows: ； Among them, represents the comprehensive reference wind power and electricity, are all preset coefficients, represents that the number of the clustering wind power and electricity sets is pieces, respectively represent the th statistical clustering quantity and the th statistical clustering quantity among multiple statistical clustering quantities, represents the contribution equivalent of the th clustering wind power and electricity set among multiple clustering wind power and electricity sets, represents the clustering wind power and electricity mean value, respectively represent the th th clustering wind power and electricity and the th clustering wind power and electricity in the th clustering wind power and electricity set, represents that there are clustering wind power and electricity in the th clustering wind power and electricity set, represents the number of training data corresponding to the th reference accuracy node in the reference accuracy node set, represents that there are reference accuracy nodes in the reference accuracy node set, represents the number of recognition data corresponding to the th reference accuracy node in the reference accuracy node set, represents the reference predicted wind power and electricity corresponding to the th electricity prediction model in the electricity prediction model set.

6. The microgrid energy storage optimization method based on big data analysis according to claim 5, characterized in that The step of retrieving the target storage battery pack in the energy storage battery pack using the energy storage battery parameter set includes: Obtain the monitoring node time series of each energy storage battery in the energy storage battery pack. Among them, the monitoring node time series includes multiple monitoring nodes, and the monitoring nodes include monitoring internal resistance and monitoring temperature; Associate the monitoring nodes with the time corresponding to the obtained monitoring nodes to obtain fitting data nodes, summarize the fitting data nodes to obtain a fitting data node set, map the fitting data nodes in the fitting data node set to a pre-constructed reference coordinate system to obtain a mapping coordinate set, use the pre-constructed curve fitting method and the mapping coordinate set to obtain fitting curves, and summarize the fitting curves to obtain a fitting curve set. Among them, the fitting curve set includes multiple fitting curves, and the fitting curves correspond to the energy storage batteries one by one; Perform the following operations on each fitting curve in the fitting curve set: Identify the minimum curvature radius in the fitted curve, calculate the product of the minimum curvature radius and a preset ratio coefficient to obtain the identification range radius, and construct a fitting screening range with the fitted curve as the central axis and the identification range radius as the radius; Count the number of fitted curves in the fitting screening range to obtain the range curve number, and summarize the range curve numbers to obtain a range curve number set; Calculate the reference projection distance of the fitted curve, and the calculation formula is as follows: ； Among them, represents the reference projection distance, represents that there are monitoring nodes in the monitoring node timing, represents the monitoring internal resistance, represents the monitoring temperature; Summarize the reference projection distances to obtain a reference projection distance set, sort the reference projection distances in the reference projection distance set in ascending order of the reference projection distance to obtain a reference projection distance sequence, use the range curve number set and the reference projection distance sequence to obtain a range curve number sequence, and based on a preset screening battery threshold, confirm the first curve number in the range curve number sequence, where the first curve number is the first range curve number in the range curve number sequence that is greater than or equal to the screening battery threshold; Extract a screening battery parameter set from the energy storage battery parameter set using the first curve number, where the screening battery parameter set includes multiple screening battery parameters, and the screening battery parameters include the battery SOH value, the remaining stored power, and the battery SOC value; Use a clustering algorithm to cluster the screening battery parameter set to obtain one or more distance screening parameter sets, and count the number of distance screening parameters in each distance screening parameter set in the one or more distance screening parameter sets to obtain one or more distance screening numbers; If there is a distance screening number greater than or equal to the screening battery threshold in the one or more distance screening numbers, randomly extract the same number of energy storage batteries as the screening battery threshold from the multiple energy storage batteries corresponding to the distance screening number to obtain a target storage battery group; Otherwise, skip the first curve number in the range curve number sequence, and return to the step of confirming the first curve number in the range curve number sequence based on the preset screening battery threshold until a target storage battery group is obtained.

7. The microgrid energy storage optimization method based on big data analysis according to claim 6, characterized in that, The retrieval in the energy storage battery group using the analysis power and the energy storage battery parameter set, if a preset target power supply battery group is retrieved in the energy storage battery group, includes: Use the predicted segmented time to obtain a battery power threshold, and calculate the number of energy storage batteries according to the battery power threshold and the battery rated power; Sort the energy storage batteries in the energy storage battery group in descending order of the remaining stored power to obtain an energy storage battery sequence, use the number of energy storage batteries to obtain a retrieval sliding window, and according to the retrieval sliding window, sequentially extract retrieval stored power groups from the energy storage battery sequence, and perform the following operations on the extracted retrieval stored power groups: Calculate the sum of the retrieval stored power in the retrieval stored power group to obtain a comprehensive detection power, and compare the comprehensive detection power with the analysis power; If the comprehensive detected power is greater than or equal to the analyzed power, return the step of sequentially extracting the retrieved stored power groups in the energy storage battery sequence until the comprehensive detected power is less than the analyzed power, obtaining multiple target retrieved stored power groups, where the comprehensive detected power corresponding to the target retrieved stored power group is greater than or equal to the analyzed power. For each target retrieved stored power group in the multiple target retrieved stored power groups, perform the following operations: Calculate the variance of the retrieved stored power in the target retrieved stored power group to obtain the comprehensive detection variance, summarize the comprehensive detection variances to obtain a comprehensive detection variance set, and use the comprehensive detection variance set to identify the target power supply battery group, where the target power supply battery group is multiple energy storage batteries corresponding to the smallest comprehensive detection variance in the comprehensive detection variance set; Otherwise, confirm that there is no such target power supply battery group in the energy storage battery group.

8. The microgrid energy storage optimization method based on big data analysis according to claim 7, characterized in that, The calculation formula for the number of energy storage batteries according to the battery power threshold and the rated power of the battery is as follows: ； Among them, represents the number of energy storage batteries, represents the battery power threshold, represents the rated power of the battery, represents rounding up.

9. The microgrid energy storage optimization method based on big data analysis according to claim 8, characterized in that, The obtaining of the target fuel power supply using the predicted power consumption and the fuel generator set includes: Obtain the rated power generation of each type of fuel generator in the fuel generator set to obtain a rated power generation set; Construct a generator set screening formula based on the rated power generation set and the battery power threshold. The generator set screening formula is as follows: ； Among them, represents the quantity of the th fuel generator among multiple fuel generators, represents the th rated power generation, represents a total of types of fuel generators are adopted; In a combined form, use the generator set screening formula to extract multiple initial fuel generator sets from the fuel generator set, obtain the energy consumption corresponding to each initial fuel generator set in the multiple initial fuel generator sets to obtain an initial energy consumption set, and identify the initial fuel generator set corresponding to the smallest initial energy consumption in the initial energy consumption set to obtain the target fuel generator set; Obtain the power generation of the target fuel generator set to obtain the target power generation, calculate the product of the target power generation and the predicted segment time and subtract the predicted power consumption to obtain the target fuel power supply.

10. A microgrid energy storage optimization system based on big data analysis, characterized in that, The system includes: An initial microgrid confirmation module for receiving an energy storage optimization instruction and confirming an initial microgrid to be optimized for energy storage based on the energy storage optimization instruction, where the initial microgrid includes a wind generator set, a fuel generator set, a solar generator set, and an energy storage battery group, where the wind generator set includes multiple wind generators, the solar generator set includes multiple solar generators, the energy storage battery group includes multiple energy storage batteries, and the fuel generator set includes multiple types of fuel generators; A microgrid parameter prediction module for obtaining a comprehensive predicted power generation using the pre-confirmed predicted segment time, wind generator set, and solar generator set; Based on the predicted segment time, obtain the predicted power consumption of the initial microgrid, calculate the difference between the comprehensive predicted power generation and the predicted power consumption to obtain the analyzed power; An energy storage solution construction module for obtaining an energy storage battery parameter set of the energy storage battery group, where the energy storage battery parameter set includes multiple energy storage battery parameters, and the energy storage battery parameters correspond to the energy storage batteries one by one. The energy storage battery parameters include: battery SOH value, remaining stored power, battery rated power, and battery SOC value; If the analyzed power is greater than or equal to the preset stored power threshold, retrieve the target storage battery pack from the energy storage battery pack using the energy storage battery parameter set, and perform active equalization charging on the target storage battery pack to obtain an updated storage battery pack; If the analyzed power is less than the preset supply power threshold, retrieve using the analyzed power and the energy storage battery parameter set in the energy storage battery pack. If the preset target power supply battery pack is retrieved in the energy storage battery pack, use the target power supply battery pack for power supply to obtain an updated power supply battery pack; The energy storage scheme optimization module is configured to, if the target power supply battery pack cannot be retrieved in the energy storage battery pack, obtain the target fuel power supply using the predicted power consumption and the fuel generator set, use the target fuel power supply as the analyzed power, return to the step of obtaining the energy storage battery parameter set of the energy storage battery pack, and realize the energy storage optimization of the initial microgrid based on the updated storage battery pack or the updated power supply battery pack.

Images