An intelligent micro-grid multi-source collaborative optimization control method

Abstract

This invention discloses a multi-source collaborative optimization control method for smart microgrids, relating to the field of energy technology. The method includes: connecting to the user side to predict the power supply demand of the target microgrid in a preset time zone; acquiring a hybrid energy supply module containing multiple distributed power sources; collecting historical power supply logs of the distributed power sources and generating relevant time sequences; performing energy curtailment rate analysis based on this to generate indicators and decisions; optimizing energy storage units after determining that the indicators meet the standards; and then performing multi-source collaborative power supply control according to preset demand. This method solves the technical problems of existing new energy power generation uncertainties that are difficult to accurately predict, and unreasonable energy storage module configurations that lead to significant energy losses during power generation, storage, and distribution, resulting in low energy utilization efficiency and unstable power supply quality. By optimizing and integrating new energy power generation, energy storage modules, and energy distribution in the microgrid, it achieves the technical effect of reducing energy losses and ensuring efficient and high-quality power supply to the microgrid.

Description

Technical Field

[0001] This application relates to the field of energy technology, and in particular to a multi-source collaborative optimization control method for smart microgrids. Background Technology

[0002] In microgrid energy management scenarios, the uncertainty of renewable energy generation leads to particularly prominent power supply stability issues, and the energy loss problem caused by unreasonable energy storage module configuration is also more pronounced. Achieving accurate prediction of renewable energy generation and optimized configuration of energy storage modules has become a crucial aspect of ensuring efficient microgrid operation. Traditional microgrid management is often simplistic and localized, relying solely on limited monitoring methods or fixed control strategies. This results in insufficient control over the overall operation of the microgrid, a lack of in-depth analysis and utilization of historical power supply data, and difficulty in comprehensively and accurately assessing the fluctuations in renewable energy generation and energy storage demand. Furthermore, unreasonable energy allocation leads to energy waste during some periods and insufficient power supply during others. The formulation of energy management solutions is also relatively rigid and fixed, failing to adequately address the complex and ever-changing actual operating conditions of microgrids.

[0003] At present, the relevant technologies have technical problems such as the uncertainty of new energy power generation, which is difficult to predict accurately, and the unreasonable configuration of energy storage modules, which leads to significant energy losses in the process of power generation, storage and distribution, low energy utilization efficiency and unstable power supply quality. Summary of the Invention

[0004] This application provides a multi-source collaborative optimization control method for smart microgrids. It employs a user-side approach to predict the power supply demand of the target microgrid within a preset time zone, acquires a hybrid energy supply module containing multiple distributed power sources, collects historical power supply logs from the distributed power sources and generates relevant time sequences, performs energy curtailment rate analysis to generate indicators and decisions, optimizes energy storage units after determining that the indicators meet the standards, and then performs multi-source collaborative power supply control according to preset requirements. This method achieves optimized integration of new energy generation, energy storage modules, and energy distribution within the microgrid, thereby reducing energy losses and ensuring efficient and high-quality power supply to the microgrid.

[0005] This application provides a multi-source collaborative optimization control method for smart microgrids, including:

[0006] Connecting to the user side, the system predicts the preset power demand information of the target microgrid in a preset time zone; it acquires the hybrid power supply module of the target microgrid, wherein the hybrid power supply module includes multiple distributed power sources; it collects historical power supply logs from the multiple distributed power sources to generate historical predicted power generation time series, historical actual power generation time series, historical energy storage time series, and historical main grid auxiliary power supply time series; based on the historical predicted power generation time series, the historical actual power generation time series, the historical energy storage time series, and the historical main grid auxiliary power supply time series, it performs curtailment rate adaptation analysis to generate curtailment adaptation indicators and curtailment balance decisions; it determines whether the curtailment adaptation indicators are greater than or equal to the predetermined curtailment adaptation indicators; if so, it optimizes the energy storage units of the hybrid power supply module using the curtailment balance decisions to generate an optimized hybrid power supply module; and it uses the optimized hybrid power supply module to perform multi-source coordinated power supply control according to the preset power demand information.

[0007] The proposed method for multi-source collaborative optimization control of smart microgrids first connects to the user side to predict the power supply demand of the target microgrid in a preset time zone, obtains a hybrid energy supply module containing multiple distributed power sources, collects historical power supply logs of distributed power sources and generates relevant time series, performs energy curtailment rate analysis to generate indicators and decisions, optimizes energy storage units after determining that the indicators meet the standards, and then performs multi-source collaborative power supply control according to preset requirements. By realizing the optimized integration of new energy power generation, energy storage modules and energy distribution in the microgrid, the method achieves the technical effect of reducing energy loss and ensuring efficient and high-quality power supply of the microgrid. Attached Figure Description

[0008] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings of the embodiments of the present invention will be briefly described below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from these processes.

[0009] Figure 1 A flowchart illustrating a multi-source collaborative optimization control method for a smart microgrid provided in this application embodiment;

[0010] Figure 2 This is a schematic diagram of the power supply control process of a multi-source collaborative optimization control method for smart microgrids provided in an embodiment of this application. Detailed Implementation

[0011] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below.

[0012] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description of this application will be provided in conjunction with the accompanying drawings. The described embodiments should not be considered as limitations on this application. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0013] In the following description, references to "some embodiments" describe a subset of all possible embodiments. However, it is understood that "some embodiments" may be the same or different subsets of all possible embodiments and may be combined with each other without conflict. The terms "first" and "second" are used merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules not explicitly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only.

[0014] This application provides a method for multi-source collaborative optimization control of smart microgrids, such as... Figure 1 As shown, the method includes:

[0015] Step S100: Connect to the user side and predict the preset power demand information of the target microgrid in the preset time zone. Specifically, the system establishes a connection with the user side to obtain relevant data and information, predict the preset power demand information of the target microgrid in the preset time zone, and analyzes various factors. For example, it analyzes the user's past electricity consumption patterns in the preset time zone, including changes in electricity consumption in different seasons and time periods, refers to historical electricity consumption data for the same period, understands the peak and off-peak electricity consumption of users in similar time periods, considers the current actual situation on the user side, such as whether new electrical equipment has been put into use, or whether there is an expansion or contraction of production scale, which may affect electricity consumption. External environmental factors are also taken into consideration, such as the weather conditions in the preset time zone. If it is a hot summer, the electricity demand for air conditioning will increase; if it is a cold winter, the electricity demand for heating equipment will increase. The collected data is preprocessed and cleaned to remove outliers and erroneous data to ensure the accuracy and reliability of the data. Time series analysis algorithms, such as autoregressive moving average models and seasonal autoregressive integrated moving average models, are used to model historical electricity consumption data. The model can capture the trend, seasonality, and periodicity of electricity consumption data. Combined with machine learning algorithms, such as decision trees, random forests, or neural networks, the preprocessed data is used as input to train the model and learn the complex relationship between user electricity consumption behavior and various influencing factors. For example, the decision tree algorithm can be used to classify and predict electricity demand based on different conditions (such as season, weather, production and operation status, etc.). During the model training process, techniques such as cross-validation are used to optimize the model parameters and improve the accuracy of predictions. When new data is input, the trained model will comprehensively consider historical electricity consumption patterns, current actual conditions, and external environmental factors to perform calculations and analyses. For example, by calculating the mean, variance, and other statistical measures of electricity consumption data in different time periods, and combining them with the weights and coefficients learned by the model, preliminary prediction results are obtained. Finally, the preliminary prediction results are corrected and adjusted, and expert experience or other supplementary information is introduced to further improve the accuracy of predictions, thereby obtaining the final preset power supply demand information.

[0016] Step S200: Obtain the hybrid energy supply module of the target microgrid, wherein the hybrid energy supply module includes multiple distributed power sources. Specifically, the system establishes a connection with the target microgrid through relevant communication protocols and interfaces to obtain relevant information on its energy supply. The obtained information is parsed and filtered to identify relevant data of the hybrid energy supply module. After determining the scope of the hybrid energy supply module, the system focuses on the multiple distributed power sources it contains. For distributed power sources, since their types include wind power, hydropower, and other new energy power generation devices, the system will obtain detailed parameters and characteristic information for each type of power generation device. For wind power devices, the obtained data may include the wind turbine model, rated power, blade length, installation location, wind speed monitoring data, etc. Through this information... Understanding the power generation capacity of wind turbines and their impact on power generation due to wind speed is crucial. For hydropower plants, data acquisition may include the scale of the hydropower station, turbine model, head height, and water flow monitoring data. This allows for an understanding of the power generation potential of the hydropower station and the impact of actual water flow conditions on power generation. Furthermore, the system acquires relevant supporting equipment and control parameters for distributed power sources, such as the specifications and operating parameters of transformers, inverters, and controllers. After acquiring all relevant data, the system integrates and categorizes this information to form a comprehensive and detailed database of multiple distributed power sources within the target microgrid's hybrid energy supply module, providing a foundation for subsequent analysis and optimized control.

[0017] Step S300 involves collecting historical power supply logs from the multiple distributed power sources to generate historical predicted power generation timelines, historical actual power generation timelines, historical energy storage timelines, and historical main grid auxiliary power supply timelines. Specifically, the system sets a collection time range to ensure coverage of at least one year from the present. This time span is chosen to fully capture power supply patterns under different seasons, weather conditions, and changes in electricity demand. For each distributed power source, such as wind power or hydropower, the system connects to the monitoring systems and data recording devices of these power generation devices to obtain detailed power supply data. For wind power devices, the collected data includes the predicted power generation of the wind turbine at various time points, the actual power generation, the charging and discharging status of the energy storage device, and the time and power of main grid auxiliary power supply. Similar information is collected for hydropower devices, such as the predicted turbine power generation, the actual generated power, the operation status of the energy storage component, and specific information on main grid intervention. During the collection process, the system verifies the data in real time. The system employs a comprehensive and meticulous data collection and processing process to ensure the accuracy and completeness of the data. Missing or abnormal data is supplemented or corrected using specific algorithms. The collected raw data is organized and categorized chronologically to generate historical predicted power generation time series, historical actual power generation time series, historical energy storage time series, and historical main grid auxiliary power supply time series. When generating the historical predicted power generation time series, the system extracts the predicted power generation value at each time point and arranges them chronologically. The historical actual power generation time series is based on the actual measured power generation data. The historical energy storage time series records the charging and discharging of energy storage devices at different time points. The historical main grid auxiliary power supply time series clarifies when and at what power the main grid provides auxiliary power to the microgrid. This long-term, comprehensive, and detailed data collection and processing process provides rich and reliable basic data support for subsequent analysis and decision-making.

[0018] Step S400: Based on the historical predicted power generation time series, the historical actual power generation time series, the historical energy storage time series, and the historical main grid auxiliary power supply time series, perform curtailment rate adaptation analysis to generate curtailment adaptation indicators and curtailment balance decisions. Specifically, data on historical predicted power generation time series, historical actual power generation time series, historical energy storage time series, and historical main grid auxiliary power supply time series are acquired and analyzed. During the analysis, the instability of distributed energy generation is a key focus. Historical predicted power generation and actual power generation at each time point are compared. If actual power generation is lower than predicted power generation, and the energy storage unit's power is insufficient to fill the gap, then connection to the main grid is necessary. It is observed whether the power generation at the previous time point was excessive. If excessive, it is determined whether the energy storage unit has sufficient capacity to store the excess energy for auxiliary power supply when subsequent power generation is insufficient. If the energy storage capacity is insufficient, some distributed power generation must be abandoned, resulting in energy waste. Based on the above, a curtailment rate adaptation analysis is performed using complex calculation and evaluation methods. This calculates the proportion of energy abandoned due to energy storage capacity limitations or mismatch between power generation and consumption within a certain time period, thereby generating a curtailment adaptation index. This indicator can intuitively reflect the degree of energy waste. By comprehensively analyzing factors such as the generation characteristics of distributed energy sources, the capacity limitations of energy storage units, the auxiliary power supply of the main grid, and the electricity demand patterns of users, a series of strategies and methods are formulated to reduce energy waste and achieve more optimized energy allocation. These strategies and methods together constitute the energy curtailment balance decision, such as adjusting the generation plan of distributed power sources, optimizing the charging and discharging strategies of energy storage units, and rationally arranging the timing of auxiliary power supply from the main grid. Through the analysis and decision-making process, the aim is to minimize energy waste and improve the energy utilization efficiency and operational stability of microgrids.

[0019] In one possible implementation, a curtailment rate adaptation analysis is performed based on the historical predicted power generation time series, the historical actual power generation time series, the historical energy storage time series, and the historical main grid auxiliary power supply time series to generate curtailment adaptation indicators and curtailment balance decisions. Step S400 further includes step S410, comparing the historical predicted power generation time series and the historical actual power generation time series to calculate and obtain the curtailment rate time series. Specifically, the data of the historical predicted power generation time series includes the predicted values ​​of power generation or electricity at various points in the past. The data of the historical actual power generation time series is obtained, i.e., the corresponding actual power generation or electricity. The predicted value and the actual value at each same time point are compared, and the difference between the two is calculated. The difference at each time point is calculated, i.e., the predicted power generation minus the actual power generation, to obtain the electricity difference. The electricity difference is divided by the predicted power generation to obtain the preliminary curtailment rate at that time point. In order to make the calculation results more accurate and representative, some additional processing may be required, such as weighted averaging of the preliminary curtailment rate over a period of time (such as one day, one week, or one month). The weights can be determined based on the importance of time, seasonal factors, or other relevant factors. Alternatively, the influence of outliers can be excluded. If the difference at a certain time point is too large or too small, or if the abnormal data is caused by special circumstances, its weight can be appropriately reduced or it can be directly removed when calculating the average curtailment rate. The difference can be accurately converted into a curtailment rate value with practical significance and reference value. The curtailment rate of each time point can be calculated in chronological order to form a curtailment rate time series.

[0020] Step S420: Combine the curtailment rate time series, the historical energy storage time series, and the historical main grid auxiliary power supply time series to perform energy loss matching analysis under continuous nodes, and generate the curtailment adaptation index and the curtailment balance decision. Specifically, the system acquires pre-calculated time-series data on energy curtailment rates, as well as historical energy storage time-series data (including the charging, discharging, and remaining capacity of energy storage devices at various time points) and historical auxiliary power supply time-series data from the main grid (the power supply and duration of the main grid at different time points). Starting from the first time node, the system analyzes consecutive time nodes sequentially, considering the energy curtailment rate, the status of energy storage devices (charging / discharging status and remaining capacity), and the auxiliary power supply status of the main grid at each time node. It calculates the energy losses caused by factors such as mismatch between power generation and consumption, energy storage capacity limitations, and auxiliary power supply from the main grid at consecutive time nodes. Based on the calculation results of energy losses, combined with preset evaluation standards and targets, an energy curtailment adaptation index is generated. This index measures the efficiency and waste level of the entire system in energy utilization. Based on the analysis of energy losses and the prediction of future energy supply and demand, a series of strategies and decisions are formulated to optimize energy allocation and utilization and reduce energy losses. These strategies and decisions together constitute the energy curtailment balance decision, such as adjusting power generation plans, optimizing the operation strategies of energy storage devices, and rationally arranging the timing of auxiliary power supply from the main grid.

[0021] In one possible implementation, energy loss matching analysis is performed at consecutive nodes by combining the energy curtailment rate time series, the historical energy storage time series, and the historical main grid auxiliary power supply time series to generate the energy curtailment adaptation index and the energy curtailment balance decision. Step S420 further includes step S421, performing balance pairing at consecutive nodes by combining the energy curtailment rate time series and the historical main grid auxiliary power supply time series to generate energy balance results. Specifically, data from the energy curtailment rate time series and the historical main grid auxiliary power supply time series are acquired, and hypothetical analysis is performed, assuming that the previously curtailed energy can be stored and used to replace the electricity replenished by the main grid. Through a series of calculations and simulations, this energy redistribution is carried out at consecutive time nodes to achieve the goal of minimizing energy loss while meeting electricity demand, generating a series of result data.

[0022] Step S422, wherein the energy balance results all include a sequence of continuous energy curtailment recovery characteristic values. Specifically, this includes a sequence of continuous energy curtailment recovery characteristic values, which reflects the characteristic values ​​of the curtailed energy that can be recovered under assumed conditions.

[0023] Step S423: Based on the continuous energy waste recovery characteristic value sequence and the historical energy storage time series, energy storage capacity is fitted to generate a continuous capacity time series. Specifically, the previously generated continuous energy waste recovery characteristic value sequence and historical energy storage time series data are obtained. Using a mathematical model, the required capacity of the energy storage unit is fitted and calculated according to the recovered energy waste characteristic values ​​and historical energy storage conditions. By continuously adjusting and optimizing the calculation parameters, the required energy storage capacity values ​​at different time points are obtained, thereby generating a continuous capacity time series that reflects the energy storage capacity demand that changes over time.

[0024] Step S424: Perform capacity clustering analysis on the continuous capacity time series to generate clustered capacity feature values. Specifically, to obtain continuous capacity time series data, since configuring energy storage units directly according to the maximum demand capacity would lead to high costs and potential capacity waste, it is necessary to perform capacity clustering analysis on the continuous capacity time series. By grouping, clustering, and statistically analyzing the capacity values ​​at different time points, regions with relatively concentrated capacity values ​​are identified. The data in these concentrated regions are further calculated and processed to generate clustered capacity feature values. These feature values ​​can represent a relatively reasonable and economical energy storage capacity level to a certain extent.

[0025] Step S425: Compare the aggregated capacity characteristic value with the original energy storage capacity of the energy storage unit to generate the curtailment adaptation index, and generate the curtailment balance decision based on the aggregated capacity characteristic value. Specifically, the aggregated capacity characteristic value is compared with the original energy storage capacity of the energy storage unit. If the difference is large, it indicates that there is a significant problem with the current energy storage configuration, and the curtailment adaptation index will be large, meaning there is a stronger need for optimization. If the difference is small, it indicates that the current energy storage configuration is relatively reasonable and there is not much need for optimization. Based on the comparison result, the curtailment adaptation index is generated. This index is used to measure the rationality of the energy storage configuration and the degree of optimization required. Based on the aggregated capacity characteristic value and combined with other relevant factors, a curtailment balance decision is generated, including whether it is necessary to adjust the energy storage capacity and optimize the energy storage control strategy, so as to achieve more efficient energy management.

[0026] In one possible implementation, capacity clustering analysis is performed on the continuous capacity time series to generate clustered capacity feature values. Step S424 further includes step S4241, extracting multiple capacity feature values ​​based on the continuous capacity time series. Specifically, continuous capacity time series data is acquired, reflecting the capacity required by energy storage units at different time points. Representative key values ​​are extracted as capacity feature values. Using a quantile method, such as quartiles, the continuous capacity time series data is divided into four equal parts. Values ​​at specific positions (such as the first quartile, the second quartile, and the third quartile) are selected as key values. For continuous capacity time series with significant curve changes, extraction is based on slope changes, and values ​​corresponding to points where the slope changes significantly are selected as key values.

[0027] Step S4242 involves performing pairwise enumeration and deviation calculations on the multiple capacity feature values, clustering capacity feature values ​​with deviations less than a preset deviation to generate multiple concentrated feature sets. Specifically, the extracted capacity feature values ​​are obtained, and each feature value is paired one by one, with the deviation between them calculated. A preset deviation value is set as a judgment criterion. If the deviation between two capacity feature values ​​is less than this preset deviation value, they are grouped into one category. By clustering similar capacity feature values ​​together, multiple concentrated feature sets are formed.

[0028] Step S4243: Calculate the ratio of the data volume in the multiple concentrated feature sets to the total data volume of the multiple capacity feature values. Calculate the mean of the concentrated feature set with the largest ratio to generate the aggregated capacity feature value. Specifically, count the data volume of the capacity feature values ​​in each concentrated feature set, divide the data volume of each concentrated feature set by the total data volume of the multiple capacity feature values ​​to obtain the ratio of the data volume of each concentrated feature set, find the concentrated feature set with the largest ratio, and calculate the mean of all capacity feature values ​​in this concentrated feature set. The final mean result is the aggregated capacity feature value, representing a relatively typical and representative capacity level.

[0029] Step S500: Determine whether the energy curtailment adaptation index is greater than or equal to the predetermined energy curtailment adaptation index. If so, optimize the energy storage unit of the hybrid energy supply module based on the energy curtailment balance decision to generate an optimized hybrid energy supply module. Specifically, obtain the calculated energy curtailment adaptation index, determine the pre-set predetermined energy curtailment adaptation index, and compare the energy curtailment adaptation index with the predetermined energy curtailment adaptation index. If the energy curtailment adaptation index is less than the predetermined energy curtailment adaptation index, it indicates that the current energy utilization is relatively good, and there is no need to optimize the energy storage unit; the system can continue to operate according to the current configuration. If the energy curtailment adaptation index is greater than or equal to the predetermined energy curtailment adaptation index, it means that there is significant room for improvement in the current energy utilization, and optimization is required. Adjust and optimize the energy storage unit in the hybrid energy supply module based on the previously generated energy curtailment balance decision. The optimization operation includes adjusting the capacity of the energy storage unit. For example, the number of energy storage batteries can be increased or decreased to adapt to different energy storage needs. The charging and discharging strategies of energy storage units can be optimized, such as by changing parameters like the starting threshold and speed of charging and discharging, to improve energy storage efficiency and response speed. The collaborative working mode between energy storage units and other distributed power sources and the main grid can be improved to ensure that energy storage units can play a more effective role under different energy supply and demand conditions. Through optimized operation, optimized hybrid energy supply modules can be generated to improve the energy utilization efficiency and stability of the entire microgrid system.

[0030] In one possible implementation, it is determined whether the energy curtailment adaptation index is greater than or equal to a predetermined energy curtailment adaptation index. If so, the energy storage unit of the hybrid energy supply module is optimized based on the energy curtailment balance decision to generate an optimized hybrid energy supply module. Step S500 further includes step S510, obtaining the unit energy storage structure and unit capacity of the energy storage unit. Specifically, the system obtains detailed technical specifications of the energy storage unit through a communication connection with the energy storage unit or by extracting information from a relevant database. This includes understanding the basic composition of the energy storage unit, such as whether it uses a battery pack, supercapacitor, or other types of energy storage devices, and determining the amount of energy that each unit energy storage structure can store, i.e., the unit capacity.

[0031] Step S520: Taking the energy curtailment balance decision as the objective, and based on the unit capacity, the superposition of unit energy storage structures is performed to generate an optimization decision. Specifically, based on the obtained unit energy storage structures and unit capacity, the previously derived energy curtailment balance decision is used as the optimization target direction. The energy curtailment balance decision includes specific requirements or improvement directions for energy storage capacity. Based on the size of the unit capacity, the number of unit energy storage structures that need to be superimposed is calculated to meet the requirements of the energy curtailment balance decision. Through calculation and planning, a specific optimization decision is generated, which clarifies the number and type of unit energy storage structures that need to be added or adjusted.

[0032] Step S530: The optimization decision is sent to the first associated personnel to optimize the configuration of the energy storage unit. Specifically, after generating the optimization decision, the system accurately sends this decision to the first associated personnel through a specific communication channel. The first associated personnel are usually relevant technical or management personnel responsible for the configuration and maintenance of the energy storage unit. After receiving the optimization decision, they perform actual operations and adjustments to the energy storage unit according to the content of the decision, such as installing new energy storage equipment, changing the configuration of existing equipment, or adjusting its operating parameters, to achieve optimized configuration of the energy storage unit, thereby improving the energy management efficiency and stability of the entire microgrid system.

[0033] Step S600: Using the optimized hybrid energy supply module, multi-source coordinated power supply control is performed based on the preset power demand information. Specifically, the system acquires the relevant parameters and configuration information of the optimized hybrid energy supply module. The optimized hybrid energy supply module includes adjusted and improved distributed power sources (such as wind power, hydropower, etc.) and energy storage units. The system acquires the previously predicted preset power demand information, which clarifies the amount of electricity required by the user within a specific time period. The system then begins multi-source coordinated power supply control. During the control process, the system monitors the power generation status and output power of each distributed power source in real time. For example, for wind power, real-time wind speed and turbine operation are monitored to determine its power generation; for hydropower, water flow speed and turbine operation are monitored. Based on the preset power demand information and the actual power generation status of each distributed power source, the system dynamically adjusts the output of each power source. In terms of power, if the power output of a distributed power source is insufficient, the system will increase the output power of other power sources to make up for the shortfall and give full play to the role of energy storage units. When the total power generation of distributed power sources exceeds the preset power supply demand, the excess electrical energy will be stored in the energy storage units. When the total power generation is insufficient, electrical energy will be released from the energy storage units in a timely manner to supplement the power supply. Throughout the power supply process, the system will also continuously adjust and optimize according to the actual situation to ensure that it can always stably and efficiently meet the preset power supply demand and maintain connection with the main grid. In extreme cases (such as when all distributed power sources and energy storage units cannot meet the demand), power support from the main grid will be introduced in a timely manner. Through multi-source coordinated power supply control, the optimized hybrid energy supply module can be effectively utilized to ensure the reliability and stability of power supply.

[0034] In one possible implementation, such as Figure 2As shown, the optimized hybrid power supply module performs multi-source collaborative power supply control based on the preset power supply demand information. Step S600 further includes step S610, which performs power supply prediction for the multiple distributed power sources in the preset time zone and generates multiple distributed power supply prediction values. Specifically, operational data from multiple distributed power sources (such as wind power and hydropower) over a period of time is collected, including historical data on power generation in different seasons, weather conditions, and time points. Using this historical data, a predictive model is constructed. Based on machine learning algorithms, such as neural networks, a multi-layered neural network structure is built. The network is trained by inputting a large amount of historical data, allowing it to learn complex patterns and relationships in the data. For example, by inputting weather conditions, seasonal information, equipment parameters, and corresponding power generation data at different times, the neural network can automatically extract features and establish a non-linear mapping relationship between the predicted output and the input. Before the arrival of the preset time zone, the relevant current parameters (such as current weather conditions, seasonal information, equipment operating status, etc.) are input into the trained predictive model. The model analyzes and calculates the input data to predict the power supply situation of each distributed power source in the preset time zone and generates multiple corresponding distributed power supply prediction values.

[0035] Step S620: Determine whether the sum of the multiple distributed energy supply prediction values ​​is greater than the preset power supply demand information. Specifically, add the generated multiple distributed energy supply prediction values ​​to obtain the total energy supply, obtain the determined preset power supply demand information, and compare the total energy supply with the preset power supply demand information.

[0036] Step S630: If the sum of the power supply predictions of the multiple distributed power supply values ​​is less than or equal to the preset power supply demand information, deviation compensation is performed based on the stored energy of the energy storage unit, and the power supply difference is calculated. Specifically, when it is found that the sum of the power supply predictions of multiple distributed power supply values ​​is less than or equal to the preset power supply demand information, it means that there may be a power shortage. The current stored energy of the energy storage unit is checked, and the power supply difference that needs to be compensated is calculated based on the difference between the preset power supply demand and the sum of the distributed power supply.

[0037] Step S640: Based on the power supply difference, the main grid is introduced to jointly control the power supply with the multiple distributed power sources and the energy storage unit. Specifically, according to the calculated power supply difference, the main grid introduction mechanism is activated. The main grid, multiple distributed power sources, and the energy storage unit work together to provide power to the user. During the joint power supply control process, the output status and power quality of each power source are monitored in real time. The output power ratio of each power source is dynamically adjusted according to actual needs to ensure stable and continuous satisfaction of the user's preset power supply needs, optimize the power supply strategy, and minimize the use of the main grid to reduce costs and improve energy utilization efficiency.

[0038] In one possible implementation, determining whether the sum of the energy supply predictions from the multiple distributed energy supply values ​​is greater than the preset power demand information, step S620 further includes step S621: if the sum of the energy supply predictions from the multiple distributed energy supply values ​​is greater than the preset power demand information, the deviation is calculated, and energy storage is generated. Specifically, when the sum of the multiple distributed energy supply prediction values ​​exceeds the preset power demand information, the difference between the two is first calculated; this difference is the energy supply deviation. Since the energy supply exceeds the demand, this excess energy will be considered for storage. Therefore, the amount of energy that can be used for storage is calculated based on this deviation, i.e., energy storage is generated.

[0039] Step S622: Determine whether the stored energy is greater than or equal to the real-time remaining capacity of the energy storage unit. If not, based on the stored energy and the preset power supply demand information, perform power supply control and energy storage control on the multiple distributed power sources according to the nearest neighbor mechanism. Specifically, the real-time remaining capacity of the energy storage unit is obtained and compared with the previously calculated energy storage capacity. If the energy storage capacity is less than the real-time remaining capacity, it means that the energy storage unit has enough space to store the excess energy. If the energy storage capacity is greater than or equal to the real-time remaining capacity, it means that the energy storage unit cannot fully accommodate the excess energy. Based on the energy storage capacity and the preset power supply demand information, power supply control and energy storage control are performed on multiple distributed power sources according to the nearest proximity mechanism. The nearest proximity mechanism means that the regulation is carried out in a way that is closest to the actual demand and energy storage capacity. For example, the power generation of some distributed power sources is reduced to reduce the current power generation and make it closer to the preset power supply demand; or the energy storage strategy is adjusted to prioritize the storage of a portion of energy while reasonably controlling the power generation capacity to achieve energy balance and optimized utilization. By achieving effective control of distributed power sources, the stability and efficiency of energy supply are ensured, while maximizing the utilization and storage of excess energy.

[0040] In one possible implementation, it is determined whether the stored energy is greater than or equal to the real-time remaining capacity of the energy storage unit. If not, based on the stored energy and the preset power demand information, power supply control and energy storage control are performed on the multiple distributed power sources according to the nearest neighbor mechanism. Step S622 further includes step S6221: if the stored energy is less than the real-time remaining capacity of the energy storage unit, the necessary curtailment rate is calculated. Specifically, when it is determined that the stored energy is less than the real-time remaining capacity of the energy storage unit, it reflects that even if all the excess stored energy is stored in the energy storage unit, some energy will still not be stored or consumed by the user end. It is necessary to calculate the necessary curtailment rate by comparing the excess energy (stored energy) with the total power generation and obtaining the proportion of energy that must be curtailed, i.e., the necessary curtailment rate, according to a certain calculation formula.

[0041] Step S6222 involves controlling the power generation of the multiple distributed power sources based on the required curtailment rate. Specifically, after obtaining the calculated required curtailment rate, power generation control is performed on the multiple distributed power sources according to this ratio. This involves adjusting the operating parameters of the power sources, such as reducing the wind turbine speed of wind power generation and reducing the water flow of hydropower generation, thereby reducing the power generation capacity of the distributed power sources and decreasing their power output. Through control, the electrical energy generated by the power sources is better matched with the demand of the user end and the storage capacity of the energy storage unit, avoiding excessive energy waste and achieving stable and efficient operation of the microgrid.

[0042] This application embodiment uses a user-side prediction of the power supply demand of the target microgrid in a preset time zone, obtains a hybrid energy supply module containing multiple distributed power sources, collects historical power supply logs of distributed power sources and generates relevant time series, performs energy curtailment rate analysis to generate indicators and decisions, optimizes energy storage units after determining that the indicators meet the standards, and then performs multi-source coordinated power supply control according to preset requirements. By realizing the optimized integration of new energy power generation, energy storage modules and energy distribution in the microgrid, the technical effect of reducing energy loss and ensuring efficient and high-quality power supply of the microgrid is achieved.

[0043] The specific embodiments described above do not constitute a limitation on the scope of protection of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this application should be included within the scope of protection of this application. In some cases, the actions or steps described in this application can be performed in a different order than that shown in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A multi-source collaborative optimization control method for intelligent microgrids, characterized in that, include: Connect to the user side and predict the preset power supply demand information of the target microgrid in the preset time zone; Obtain the hybrid power supply module of the target microgrid, wherein the hybrid power supply module includes multiple distributed power sources; Historical power supply logs are collected from the multiple distributed power sources to generate historical predicted power generation time series, historical actual power generation time series, historical energy storage time series, and historical main grid auxiliary power supply time series. Based on the historical predicted power generation time series, the historical actual power generation time series, the historical energy storage time series, and the historical main grid auxiliary power supply time series, an energy curtailment rate adaptation analysis is performed to generate energy curtailment adaptation indicators and energy curtailment balance decisions. Determine whether the energy curtailment adaptation index is greater than or equal to the predetermined energy curtailment adaptation index. If so, optimize the energy storage unit of the hybrid energy supply module based on the energy curtailment balance decision to generate an optimized hybrid energy supply module. The optimized hybrid power supply module performs multi-source coordinated power supply control based on the preset power supply demand information.

2. The intelligent microgrid multi-source collaborative optimization control method as described in claim 1, characterized in that, Based on the historical predicted power generation time series, the historical actual power generation time series, the historical energy storage time series, and the historical main grid auxiliary power supply time series, an energy curtailment rate adaptation analysis is performed to generate energy curtailment adaptation indicators and energy curtailment balance decisions, including: By comparing the historical predicted power generation time series with the historical actual power generation time series, the curtailment rate time series is calculated and obtained. By combining the energy curtailment rate time series, the historical energy storage time series, and the historical main grid auxiliary power supply time series, energy loss matching analysis is performed under continuous nodes to generate the energy curtailment adaptation index and the energy curtailment balance decision.

3. The intelligent microgrid multi-source collaborative optimization control method as described in claim 2, characterized in that, By combining the energy curtailment rate time series, the historical energy storage time series, and the historical main grid auxiliary power supply time series, energy loss matching analysis is performed under continuous nodes to generate the energy curtailment adaptation index and the energy curtailment balance decision, including: By combining the energy curtailment rate time series and the historical main grid auxiliary power supply time series, balance pairing is performed under continuous nodes to generate energy balance results; The energy balance results all include a sequence of continuous energy waste recovery characteristic values; Based on the continuous energy waste recovery characteristic value sequence and the historical energy storage time series, the energy storage capacity is fitted to generate a continuous capacity time series. Capacity clustering analysis is performed on the continuous capacity time series to generate clustered capacity feature values; By comparing the aggregated capacity characteristic value with the original energy storage capacity of the energy storage unit, the curtailment adaptation index is generated, and the curtailment balance decision is generated based on the aggregated capacity characteristic value.

4. The intelligent microgrid multi-source collaborative optimization control method as described in claim 3, characterized in that, Capacity clustering analysis is performed on the continuous capacity time series to generate clustered capacity feature values, including: Multiple capacity feature values ​​are extracted based on the continuous capacity time series; The multiple capacity feature values ​​are subjected to pairwise enumeration and deviation calculation. Capacity feature values ​​with deviations less than a preset deviation are clustered to generate multiple concentrated feature sets. Calculate the ratio of the data volume in the multiple clustered feature sets to the total data volume of the multiple capacity feature values, and calculate the mean of the clustered feature set with the largest ratio to generate the clustered capacity feature value.

5. The intelligent microgrid multi-source collaborative optimization control method as described in claim 1, characterized in that, The energy storage unit of the hybrid energy supply module is optimized using the aforementioned energy waste balance decision to generate an optimized hybrid energy supply module, including: Obtain the unit energy storage structure and unit capacity of the energy storage unit; With the aforementioned energy curtailment balance decision as the objective, and based on the unit capacity, the superposition of unit energy storage structures is performed to generate an optimal decision; The optimization decision is sent to the first associated person to optimize the configuration of the energy storage unit.

6. The intelligent microgrid multi-source collaborative optimization control method as described in claim 1, characterized in that, The optimized hybrid power supply module performs multi-source coordinated power supply control based on the preset power demand information, including: In the preset time zone, power supply prediction is performed on the multiple distributed power sources to generate multiple distributed power supply prediction values. Determine whether the sum of the predicted energy supply values ​​from the multiple distributed energy supply systems is greater than the preset power demand information; If the sum of the energy supply predictions of the multiple distributed energy supply is less than or equal to the preset power supply demand information, deviation compensation is performed based on the stored energy of the energy storage unit to calculate the energy supply difference. Based on the aforementioned power supply difference, the main power grid is introduced to jointly control the power supply with the multiple distributed power sources and the energy storage unit.

7. The intelligent microgrid multi-source collaborative optimization control method as described in claim 6, characterized in that, Determining whether the sum of the predicted power supply values ​​of the multiple distributed power supply values ​​is greater than the preset power demand information further includes: If the sum of the energy supply predictions of the multiple distributed energy supply values ​​is greater than the preset power supply demand information, the deviation is calculated and energy storage is generated. Determine whether the stored energy is greater than or equal to the real-time remaining capacity of the energy storage unit. If not, based on the stored energy and the preset power supply demand information, perform power supply control and energy storage control on the multiple distributed power sources according to the nearest neighbor mechanism.

8. The intelligent microgrid multi-source collaborative optimization control method as described in claim 7, characterized in that, Determining whether the stored energy is greater than the real-time remaining capacity of the energy storage unit further includes: If the stored energy is less than the real-time remaining capacity of the energy storage unit, the energy curtailment rate must be calculated. Based on the required curtailment rate, the power generation of the multiple distributed power sources is controlled.

Images