Optimization scheduling methods, systems, equipment, and storage media based on microgrids

Abstract

This application provides an optimized scheduling method, system, equipment, and storage medium based on microgrids, belonging to the field of energy dispatching technology. The method includes: calculating power reliability parameters corresponding to distributed power sources, energy storage health parameters corresponding to energy storage devices, and load demand parameters corresponding to loads based on microgrid operation monitoring data; inputting the power reliability parameters, energy storage health parameters, and load demand parameters into a pre-trained decision tree model to obtain the microgrid's operating state; the microgrid includes distributed power sources, energy storage devices, and loads; the microgrid's operating state includes normal operation and abnormal power supply states; determining a target scheduling mode based on the microgrid's operating state; the target scheduling mode includes either a normal mode or an emergency mode; determining scheduling strategy adjustment parameters based on the target scheduling mode; and using the scheduling strategy adjustment parameters for optimized microgrid scheduling. This application can improve the stability and reliability of microgrid operation.

Description

Technical Field

[0001] This application belongs to the field of energy dispatching technology, and more specifically, relates to optimized dispatching methods, systems, equipment, and storage media based on microgrids. Background Technology

[0002] With the transformation of the energy structure and the development of distributed energy technologies, microgrids are of great significance in improving energy utilization efficiency, enhancing power supply reliability, and promoting the consumption of renewable energy. However, the complexity and uncertainty of their operation pose challenges to optimal scheduling.

[0003] Microgrids can consist of distributed power sources, energy storage devices, and loads, and the characteristics of microgrid components are complex. Energy storage devices undergo long-term use, leading to changes in their health parameters; load power demand dynamically varies due to user behavior and time. Traditional scheduling methods, based on simple optimization models, struggle to account for complex grid changes and cannot flexibly adjust based on actual operating conditions in real time, resulting in microgrids failing to achieve efficient and stable operation. Summary of the Invention

[0004] The purpose of this application is to provide an optimized scheduling method, system, equipment, and storage medium based on microgrids to improve the stability and reliability of microgrid operation.

[0005] A first aspect of this application provides an optimized scheduling method based on a microgrid, comprising:

[0006] Based on the operation monitoring data of the microgrid, the power reliability parameters corresponding to the distributed power source, the energy storage health parameters corresponding to the energy storage device, and the load demand parameters corresponding to the load are calculated. The power reliability parameters, the energy storage health parameters, and the load demand parameters are input into a pre-trained decision tree model to obtain the operating status of the microgrid. The microgrid includes the distributed power source, the energy storage device, and the load. The operating status of the microgrid includes normal operation status and power supply abnormality status.

[0007] The target scheduling mode is determined based on the operating status of the microgrid; the target scheduling mode includes either a normal mode or an emergency mode.

[0008] The scheduling strategy adjustment parameters are determined based on the target scheduling mode; the scheduling strategy adjustment parameters are used to optimize the scheduling of the microgrid.

[0009] A second aspect of this application provides an optimized scheduling system based on a microgrid, comprising:

[0010] The microgrid status analysis module is used to calculate the power reliability parameters corresponding to the distributed power source, the energy storage health parameters corresponding to the energy storage device, and the load demand parameters corresponding to the load based on the microgrid's operation monitoring data. The power reliability parameters, the energy storage health parameters, and the load demand parameters are then input into a pre-trained decision tree model to obtain the microgrid's operating status. The microgrid includes the distributed power source, the energy storage device, and the load. The microgrid's operating status includes normal operation and abnormal power supply status.

[0011] The scheduling mode determination module is used to determine the target scheduling mode based on the operating status of the microgrid; the target scheduling mode includes either a normal mode or an emergency mode.

[0012] The optimization scheduling module is used to determine scheduling strategy adjustment parameters based on the target scheduling mode; the scheduling strategy adjustment parameters are used to optimize the scheduling of the microgrid.

[0013] A third aspect of this application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of the above-described optimized scheduling method based on a microgrid.

[0014] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described optimized scheduling method based on a microgrid.

[0015] The beneficial effects of the microgrid-based optimized scheduling method, system, equipment, and storage medium provided in this application are as follows: On the one hand, this application calculates power reliability parameters, energy storage health parameters, and load demand parameters based on operational monitoring data, enabling comprehensive monitoring of the real-time status of each component within the microgrid and providing a data foundation for precise scheduling. On the other hand, this application introduces a pre-trained decision tree model to analyze parameters, which can quickly identify the normal or abnormal operating state of the microgrid and then match the corresponding target scheduling mode. When this application detects a power supply anomaly, it quickly switches to emergency mode and determines the corresponding scheduling strategy adjustment parameters to optimize the scheduling of the microgrid, thereby prioritizing the power supply to critical loads and avoiding large-scale power outages caused by faults. Under normal operating conditions, the corresponding scheduling strategy adjustment parameters are determined to optimize energy allocation using the normal mode, improving power generation efficiency and energy storage lifespan. This dynamic switching mechanism of this application significantly enhances the microgrid's ability to cope with complex operating conditions, ensures power supply continuity and stability, reduces system operating risks, and achieves efficient and reliable operation of the microgrid. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 A flowchart illustrating an optimized scheduling method based on a microgrid, provided in an embodiment of this application;

[0018] Figure 2 A structural block diagram of an optimized scheduling system based on a microgrid provided in an embodiment of this application;

[0019] Figure 3 This is a schematic block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0020] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the following description will be provided in conjunction with the accompanying drawings and specific embodiments.

[0022] Please refer to Figure 1 , Figure 1 This is a flowchart illustrating an optimized scheduling method based on a microgrid, provided in an embodiment of this application. The method can be executed by an electronic device, and specifically, the method may include S101 to S103.

[0023] S101: Based on the operation monitoring data of the microgrid, calculate the power reliability parameters corresponding to the distributed power source, the energy storage health parameters corresponding to the energy storage device, and the load demand parameters corresponding to the load. Input the power reliability parameters, energy storage health parameters, and load demand parameters into the pre-trained decision tree model to obtain the operating status of the microgrid. The microgrid includes distributed power sources, energy storage devices, and loads. The operating status of the microgrid includes normal operation status and power supply abnormality status.

[0024] In this embodiment, operational monitoring data may include parameters such as the output power, voltage / frequency fluctuations, fault frequency, and environmental meteorological data of the distributed power source; the charging / discharging current, rated capacity, charging / discharging duration, remaining capacity, and temperature of the energy storage device; and the real-time power consumption and its time-series characteristics of the load. Power supply reliability parameters can be calculated comprehensively from the output power, voltage / frequency fluctuations, and fault frequency data of the distributed power source, used to assess the power source's ability to provide continuous and stable power. Energy storage health parameters can be calculated comprehensively from the charging / discharging current, rated capacity, remaining capacity, and charging / discharging duration of the energy storage device, reflecting the degree of performance degradation of the energy storage device. Load demand parameters can be calculated from the real-time power consumption and its time-series characteristics, used to reflect the load's power consumption patterns and demand intensity. The decision tree model is a classification model trained based on historical data of the microgrid. It divides nodes by feature parameters and outputs whether the microgrid is currently in a normal or abnormal state.

[0025] This embodiment collects operational monitoring data, calculates parameters for the power supply, energy storage, and load, and inputs these parameters into a pre-trained decision tree model. The decision tree model can make hierarchical judgments based on data characteristics. For example, if both the power supply reliability parameter and the energy storage health parameter are below a threshold, it is determined to be an abnormal power supply state; if all parameters are within the normal range, it is determined to be a normal operating state. This evaluation method, based on multi-dimensional data cross-validation, can more comprehensively and accurately reflect the actual operating status of the microgrid.

[0026] For example, this embodiment can use current and voltage sensors to collect data such as the output power and voltage frequency fluctuations of the distributed power source, and use the obtained data to calculate the power reliability parameters corresponding to the distributed power source; use a power metering module to monitor the charging and discharging current and remaining capacity of the energy storage device, and use the obtained data to calculate the energy storage health parameters corresponding to the energy storage device; use a smart meter to obtain data such as the real-time power demand and power factor of the load, and use the obtained data to calculate the load demand parameters corresponding to the load; and simultaneously access environmental data from a meteorological station to provide a foundation for subsequent steps.

[0027] This embodiment can collect historical operating data, label it as normal or abnormal power supply status, and construct a decision tree model using algorithms such as C4.5 and CART. This embodiment can adjust model parameters through cross-validation, optimize the node partitioning rules of the decision tree model, and improve the classification accuracy of the decision tree model for microgrid operating status.

[0028] This embodiment can input the real-time calculated power supply, energy storage, and load parameters into the trained decision tree model, and after the feature nodes make judgments, quickly output the current operating status of the microgrid, providing a basis for subsequent scheduling mode selection.

[0029] S102: Determine the target scheduling mode based on the microgrid's operating status; the target scheduling mode includes either the normal mode or the emergency mode.

[0030] In this embodiment, the target scheduling mode is determined based on the operating status of the microgrid, specifically including: if the operating status of the microgrid is normal operation, the target scheduling mode is determined to be normal mode; if the operating status of the microgrid is abnormal power supply, the target scheduling mode is determined to be emergency mode.

[0031] In this embodiment, the microgrid's operating status is divided into normal operation and abnormal power supply status. The former refers to a state where distributed power sources, energy storage devices, and loads are all operating stably; the latter can include conditions such as power failure, insufficient energy storage capacity, and load surges. Normal mode is a microgrid optimization scheduling mode based on economic efficiency, optimizing power generation efficiency and reducing energy storage losses. The relevant parameters for normal mode focus on power generation costs, electricity price signals, and energy storage charging and discharging efficiency. In emergency mode, priority is given to ensuring the microgrid's power supply reliability, allowing for some sacrifice in economic efficiency. The relevant parameters for emergency mode focus on critical load priority, the lower limit of remaining energy storage capacity, and power failure recovery time.

[0032] This embodiment automatically matches the scheduling mode based on the operational status assessment results and preset rules. If the power supply, energy storage, and load parameters are all within the normal thresholds, it is determined to be in normal operation, and the normal mode is activated. If abnormal situations such as power outages or depletion of energy storage capacity occur, it immediately switches to emergency mode to ensure continuous power supply to critical loads. This embodiment balances economic efficiency and reliability requirements, avoiding resource waste or power supply accidents.

[0033] For example, this embodiment can establish a hierarchical threshold system based on the performance parameters of microgrid equipment and historical operating data. Regarding power supply reliability, this embodiment can set a generation volatility threshold and a fault probability threshold; for energy storage health parameters, it can set a lower limit threshold for remaining capacity and a threshold for internal resistance growth; for load demand parameters, it can set a threshold for critical load power failure risk and a power overload threshold, forming a complete status judgment benchmark.

[0034] This embodiment can have built-in mapping logic between operating status and scheduling mode. When the power reliability parameter exceeds the threshold and the energy storage health parameter is lower than the threshold, the emergency mode is automatically triggered; if all parameters are within the normal range, it is determined to be in normal operating status, and the normal mode is activated.

[0035] This embodiment can input the operational status assessment results into the rule engine in real time. The engine quickly judges based on preset rules and automatically switches the target scheduling mode. After the mode switch, this embodiment can immediately adjust the output power of distributed power sources, energy storage charging and discharging strategies, and load distribution schemes to ensure that the microgrid operates efficiently in the corresponding mode.

[0036] For example, the decision tree model learns the characteristic boundaries of normal and abnormal states of a microgrid through historical data. For instance, when the power generation volatility parameter corresponding to the power reliability parameter is greater than 15% and the remaining capacity parameter corresponding to the energy storage health parameter is less than 20%, historical data shows that the system is in an abnormal power supply state. The decision tree model will divide such feature combinations into the same node and output an anomaly judgment.

[0037] In practice, the inputs to the decision tree model are normalized power supply reliability parameters, energy storage health parameters, and load demand parameters. The decision tree model calculates feature importance using the C4.5 algorithm or the Gini index, prioritizing parameters such as the power supply failure probability that most significantly distinguishes the state as the root node, and splitting layer by layer until the leaf node outputs the state category (normal / abnormal).

[0038] For example, when the real-time collected power generation volatility is 20% (exceeding the preset threshold of 15%), the decision tree model continues to judge along the branch where the power generation volatility is greater than 15%. If it also detects that the remaining energy storage capacity is 15% (less than the preset threshold of 20%), it triggers an abnormal power supply status output, driving the system to switch to emergency mode. If all other parameters are normal, it is determined to be in normal operation and maintains normal mode. This process uses a tree-like hierarchical judgment to achieve cross-validation of multi-dimensional parameters, avoiding misjudgment based on a single indicator.

[0039] S103: Determine the scheduling strategy adjustment parameters based on the target scheduling mode; the scheduling strategy adjustment parameters are used to optimize the scheduling of the microgrid.

[0040] In this embodiment, the scheduling strategy adjustment parameters include core indicators used to guide energy allocation and equipment control within the microgrid. For example, these may include the upper / lower limit of the power generation of distributed power sources, the charging and discharging power threshold of energy storage devices, the priority weight of loads, load power, and the start / stop status of each power source and energy storage device.

[0041] This embodiment can generate adaptive scheduling strategies and adjust parameters based on the characteristics of the target scheduling mode through preset functions or algorithms. In normal mode, with economic efficiency as the goal, the power generation capacity and energy storage charging and discharging plan are adjusted in conjunction with real-time electricity prices and generation costs. In emergency mode, priority is given to ensuring power supply to critical loads, and parameters are adjusted to ensure power supply reliability by limiting power consumption of non-critical loads and maximizing energy storage discharge. This embodiment can realize differentiated and precise scheduling of microgrids under different operating conditions, balancing economic and safety requirements.

[0042] For example, this embodiment can establish parameter mapping rule tables for normal mode and emergency mode respectively. For instance, in normal mode, the power generation cost weighting coefficient is set to 0.6, and the real-time electricity price fluctuation threshold is ±10%; in emergency mode, the priority of critical load protection is set to 100%, and the upper limit of energy storage discharge depth is relaxed to 90%.

[0043] This embodiment can construct a multi-objective function encompassing economy, reliability, and equipment lifespan, and use a genetic algorithm or particle swarm optimization algorithm to solve for the optimal parameter combination, satisfying constraints such as power balance and equipment capacity. This embodiment can also adjust power supply, energy storage charging / discharging rate, and load power in real time through a distributed control system. Furthermore, this embodiment requires the design of a transition phase parameter buffer mechanism; for example, during the transition from emergency to normal operation, a 15-minute linear regression threshold for energy storage discharge power is set to avoid frequent equipment start-ups and shutdowns. This embodiment also needs to establish safety boundaries for key parameters to ensure system stability during mode switching.

[0044] As can be seen from the above, on the one hand, this embodiment provides a multi-dimensional data fusion and accurate evaluation mechanism. This embodiment collects power supply, energy storage and load parameters in real time, and cross-validates the operating status by combining decision tree model to avoid misjudgment by a single indicator. For example, by monitoring the power generation volatility and energy storage health status at the same time, potential power supply risks can be identified in advance and the probability of failure can be reduced.

[0045] On the other hand, this embodiment provides a dual-mode dynamic scheduling strategy. This embodiment can automatically switch between normal and emergency modes according to the system status. In normal mode, the power generation cost and energy storage life are optimized first, while in emergency mode, the power supply to critical loads is guaranteed. This achieves a dynamic balance between economy and reliability, and reduces resource waste and power supply accidents.

[0046] On the other hand, this embodiment provides parameter adaptive adjustment technology. This embodiment is based on the target mode to customize the scheduling strategy. It solves the optimal parameters through multi-objective functions and intelligent algorithms. Combined with safety boundaries and buffer mechanisms, it ensures that energy allocation is accurately adapted to the operating conditions. For example, it can smoothly transition from emergency to normal operation, avoid equipment shock, and ultimately improve the operating efficiency and robustness of the microgrid in all scenarios.

[0047] In one embodiment of this application, the operation monitoring data of the microgrid includes operation monitoring data corresponding to distributed power sources, energy storage devices, and loads respectively; the operation monitoring data corresponding to distributed power sources includes: power generation and fault frequency; the operation monitoring data corresponding to energy storage devices includes: rated capacity, remaining power, charging and discharging time, and charging and discharging efficiency; the operation monitoring data corresponding to loads includes: real-time power consumption and time-series characteristics of power demand.

[0048] Among them, the calculation of power reliability parameters for distributed power sources, energy storage health parameters for energy storage devices, and load demand parameters for loads based on microgrid operation monitoring data includes:

[0049] Calculate power supply reliability parameters based on power generation and fault frequency;

[0050] Calculate energy storage health parameters based on rated capacity, remaining power, charging and discharging time, and charging and discharging efficiency;

[0051] Load demand parameters are calculated based on real-time power consumption and the time-series characteristics of power demand.

[0052] In this embodiment, power generation reflects the actual power supply capacity; fault frequency reflects power supply stability; rated capacity refers to the maximum storage capacity of the energy storage device; remaining power reflects the currently available energy storage; charging and discharging time and efficiency reflect the working intensity and performance loss of the energy storage device; real-time power consumption reflects the immediate demand of the load; and the timing characteristics of power demand are used to predict future power consumption trends.

[0053] This embodiment can collect real-time operational data from various components of the microgrid and use statistical analysis and algorithm models to calculate corresponding parameters. For example, it can assess power supply reliability using the degree of power generation fluctuation and fault frequency; predict lifespan loss based on the charging and discharging time and efficiency of energy storage devices; and predict load demand based on historical electricity consumption data and time-series characteristics. These parameters provide quantitative basis for subsequent microgrid operational status assessment, scheduling mode selection, and strategy optimization, enabling refined management and efficient scheduling of the microgrid.

[0054] For example, this embodiment can use a sliding window algorithm to calculate the power generation fluctuation rate, and combine fault frequency data with reliability algorithms such as Markov models to evaluate power supply reliability; based on the cumulative charging and discharging amount and efficiency decay curve of energy storage equipment, the energy storage health status can be calculated by combining the ampere-hour integration method and equivalent circuit model; and time series analysis algorithms can be used to model the real-time power of the load and historical data to predict the peak, valley and changing trends of electricity demand.

[0055] The power reliability parameters, energy storage health parameters, and load demand parameters calculated in this embodiment provide data support for subsequent microgrid operation status assessment, scheduling mode selection, and optimized scheduling strategies, realizing fully automated processing from data acquisition to parameter output.

[0056] This embodiment deeply perceives the status of microgrid equipment through multi-dimensional data collection and precise parameter calculation, identifies risks in advance, and extends energy storage life. This embodiment can accurately predict load demand and reduce electricity costs. The automated processing of this embodiment can shorten the calculation cycle, ensure the rapid response of the microgrid, achieve safe, economical and efficient operation, and significantly improve management efficiency and system reliability.

[0057] In one embodiment of this application, determining scheduling policy adjustment parameters based on a target scheduling mode includes:

[0058] Determine target coefficient constraints based on the target scheduling pattern;

[0059] The scenario adaptation factor is determined based on power reliability parameters, energy storage health parameters, and load demand parameters; the scenario adaptation factor is a comprehensive quantitative indicator of the characteristics of the current operating scenario of the microgrid.

[0060] The target weight coefficient matrix is ​​determined based on the scenario adaptation factor and target coefficient constraints. The target weight coefficient matrix includes the weight coefficients corresponding to the power generation efficiency index, power supply reliability index, and energy storage life loss index. The power generation efficiency index refers to the power generation capacity and efficiency index of distributed power sources in the microgrid. The power supply reliability index refers to the ability of the microgrid to stably supply power to the load. The energy storage life loss index refers to the performance degradation and life consumption index of energy storage equipment due to physical and chemical changes during the charge and discharge cycle.

[0061] Using power generation efficiency, power supply reliability, and energy storage life loss as scheduling optimization objectives, a multi-objective scheduling optimization function is constructed using the objective weight coefficient matrix.

[0062] The scheduling strategy adjustment parameters are determined based on the multi-objective scheduling optimization function.

[0063] In this embodiment, the target coefficient constraint is a hard parameter boundary set for different scheduling modes, such as the power supply reliability weight not less than 70% in emergency mode, and the upper limit of the energy storage life loss weight is 20% in normal mode, to ensure that the scheduling strategy meets the core objectives of the mode.

[0064] The scenario adaptation factor refers to the quantitative expectation of the current operating scenario on the scheduling objectives, obtained by comprehensively considering parameters such as power supply reliability, energy storage health, and load demand. For example, it may increase the weight of power supply reliability during high-load periods. The target weight coefficient matrix may include the weights of power generation efficiency, power supply reliability, and energy storage lifespan loss indicators. In this embodiment, the target weight coefficient matrix can be dynamically adjusted through scenario adaptation factors and target coefficient constraints. The multi-objective scheduling optimization function refers to a mathematical model constructed with the three major indicators as objectives and combined with weight coefficients. Solving this function determines the adjustment parameters of scheduling strategies such as power generation capacity and energy storage charging and discharging strategies.

[0065] This embodiment first determines the basic constraint framework based on the target scheduling mode, then quantifies the current operating condition requirements through scenario adaptation factors, and combines the two to generate a target weight coefficient matrix. This target weight coefficient matrix serves as the core parameter of the multi-objective scheduling optimization function. By solving the multi-objective scheduling optimization function, the optimal scheduling strategy is obtained, achieving a dynamic balance between the economy, reliability, and equipment lifespan of the microgrid under different scenarios.

[0066] For example, in normal mode, the target coefficient constraint is set as follows: power generation efficiency weight not less than 40%, and energy storage lifespan loss weight not exceeding 30%; in emergency mode, the target coefficient constraint is set as follows: power supply reliability weight not less than 70%. The power supply reliability parameters, energy storage health parameters, and load demand parameters are normalized and then weighted and summed to obtain the scenario adaptation factor, quantifying the scenario characteristics. For example, the formula Q = 0.4 × power supply reliability + 0.3 × energy storage health + 0.3 × load importance, where Q is the scenario adaptation factor.

[0067] This embodiment combines scenario adaptation factors with target coefficient constraints to dynamically adjust the weighting coefficients of power generation efficiency, power supply reliability, and energy storage lifespan loss. For example, when the scenario adaptation factor indicates an increase in load demand, within the emergency mode constraint range, the weighting of power supply reliability is increased to 80%.

[0068] This embodiment can construct a multi-objective scheduling optimization function using a weighted coefficient matrix, with the objectives of power generation efficiency, power supply reliability, and energy storage lifespan loss as the goals. The function is solved using a particle swarm optimization algorithm or a genetic algorithm to obtain scheduling strategy adjustment parameters such as distributed power generation capacity, energy storage charging and discharging strategies, and load allocation schemes.

[0069] This embodiment can input the optimized parameters into the microgrid control system for scheduling and monitor the operating data in real time. If the actual effect deviates from the target by more than a threshold, the scenario adaptation factor is recalculated, the weight coefficients are corrected, and the scheduling strategy is iteratively optimized.

[0070] In this embodiment, determining the target coefficient constraint based on the target scheduling mode specifically includes: if the target scheduling mode is the normal mode, then determining the target coefficient constraint as the first coefficient constraint; the first coefficient constraint includes the weight coefficient of the power generation efficiency index in the target weight coefficient matrix being greater than or equal to a first threshold.

[0071] If the target scheduling mode is emergency mode, then the target coefficient constraint is determined to be the second coefficient constraint; the second coefficient constraint includes the weight coefficient of the power supply reliability index in the target weight coefficient matrix being greater than or equal to the second threshold.

[0072] The second threshold is greater than the first threshold.

[0073] In this embodiment, the scenario adaptation factor is determined based on power reliability parameters, energy storage health parameters, and load demand parameters, specifically including: obtaining a reference scenario adaptation factor;

[0074] Based on the reference scenario adaptation factor, power reliability parameters, energy storage health parameters and load demand parameters, the scenario adaptation factor is determined through the first formula.

[0075] The first formula is:

[0076]

[0077] in, As a scene adaptation factor, As a reference scenario adaptation factor, For power supply reliability parameters, For energy storage health parameters, These are the load requirement parameters.

[0078] In this embodiment, both the second threshold and the first threshold are preset values. In normal mode, this embodiment uses a first coefficient constraint to ensure that the power generation efficiency weight is not lower than the threshold, avoiding a surge in economic costs due to excessive pursuit of reliability or energy storage protection. For example, when energy storage is in good health, charging during low-price periods is still prioritized to reduce costs. In emergency mode, this embodiment uses a second coefficient constraint to increase the power supply reliability weight, ensuring power supply to critical loads even if power generation efficiency or energy storage lifespan targets are compromised.

[0079] In the first formula, the numerator quantifies the combined degree of anomaly of the power supply, energy storage, and load by taking the square root of the sum of squares; the greater the anomaly, the larger the scenario adaptation factor. The denominator is a reference value used for normalization, ensuring the scenario adaptation factor fluctuates around a baseline value. When a parameter deviates from the normal range, the scenario adaptation factor changes accordingly. If the change in the scenario adaptation factor reaches a trigger condition, the weights can be adjusted to respond to anomalies. For example, when the probability of power failure increases, the scenario adaptation factor increases. This embodiment can appropriately increase the reliability weight within the constraints of normal mode to prevent power supply risks in advance.

[0080] In this embodiment, the target coefficient constraint is used to determine the lower limit of the weight coefficients corresponding to the core target parameters, and the scenario adaptation factor fine-tunes the weight coefficient allocation within the constraint range. For example, if the energy storage health status score is low in emergency mode, the energy storage life loss weight can be reduced based on the reliability weight lower limit to allow deeper discharge to ensure power supply, but it must be controlled within the equipment safety boundary.

[0081] For example, in this embodiment, two types of coefficient constraints can be predefined according to the microgrid operating mode:

[0082] Normal mode: Set the first threshold for the weight of power generation efficiency indicators, such as 40%, to ensure the basic priority of economic objectives.

[0083] Emergency mode: Set a second threshold for the power supply reliability index weight, such as 70%, and this threshold is higher than the threshold of normal mode.

[0084] This embodiment first initializes the reference scenario adaptation factor representing the ideal working condition. Specifically, it can be set based on the statistical values ​​of the stable range of each parameter in the historical operating data, such as taking the typical value in the normal mode.

[0085] In this embodiment, the actual values ​​of power reliability parameters, energy storage health parameters, and load demand parameters are compared with reference values. The scenario adaptation factor is calculated using the first formula, which reflects the adjustment requirements of the current operating conditions for the scheduling strategy. The greater the parameter fluctuation, the higher the value of the scenario adaptation factor.

[0086] Within the framework of target coefficient constraints, this embodiment fine-tunes the weights of each target according to preset rules based on the calculation results of the scenario adaptation factor. The adjusted weight coefficients are then input into a multi-objective optimization scheduling function to generate specific scheduling parameters, such as power output and energy storage charging / discharging power, which are then executed through a distributed control system.

[0087] This embodiment ensures the priority of core objectives through target coefficient constraints and dynamically fine-tunes weights by combining scenario adaptation factors to achieve multi-objective collaborative optimization. It reduces costs in normal mode, ensures stable power supply to critical loads in emergency mode, extends energy storage life, and significantly improves the microgrid's dynamic balance between economy, reliability, and equipment protection, as well as its adaptability to complex operating conditions.

[0088] In one embodiment of this application, determining scheduling strategy adjustment parameters based on a multi-objective scheduling optimization function includes:

[0089] Taking the power generation of distributed power sources, the charging and discharging power of energy storage devices, and the load power of each load as scheduling objects, and the maximization of the multi-objective scheduling optimization function as the objective, the genetic algorithm is used to optimize the power generation of distributed power sources, the charging and discharging power of energy storage devices, and the load power of each load to obtain the target power generation of distributed power sources, the target charging and discharging power of energy storage devices, and the target load power of each load.

[0090] The target power generation, target charging and discharging power, and target load power are used as parameters for scheduling strategy adjustment.

[0091] In this embodiment, the multi-objective scheduling optimization function is:

[0092]

[0093] in, Optimize the score to achieve the goal. , and These are the weighting coefficients. The normalized power generation efficiency index This is the normalized power supply reliability index. This is the normalized energy storage life loss index.

[0094] In this embodiment, the scheduling object refers to the directly controllable physical quantity in the microgrid, used to execute optimization strategies. Distributed power generation refers to the active power output of photovoltaic, wind power, and other equipment, limited by environmental factors such as sunlight and wind speed. Energy storage charging and discharging power refers to the charging or discharging rate of battery packs, constrained by remaining capacity, maximum charging and discharging current, etc. Load power refers to the active power demand of various types of loads, divided into critical loads and non-critical loads, which can be adjusted through demand response. The genetic algorithm is a heuristic optimization algorithm that simulates the biological evolution process, iteratively searching for the optimal solution through operations such as selection, crossover, and mutation.

[0095] For example, in normal mode, a microgrid has sufficient solar power during the day, and the load is mainly composed of non-critical equipment. At this time, the dispatching objective focuses on power generation efficiency and energy storage protection. Assume the parameter values ​​are:

[0096] Power generation efficiency index: When the actual power generation of photovoltaic power reaches 85% of the rated power, the corresponding index value is high-efficiency power generation, which is normalized to 0.85, with a full value of 1.

[0097] Power supply reliability indicators: All loads are powered normally, critical loads have a 100% power supply rate, non-critical loads have a 95% power supply rate, and the overall value is 0.98.

[0098] Energy storage life loss index: When the energy storage device is in the charging state, the depth of charge and discharge is controlled at 20%, which is the low loss range, and the value is 0.2. The lower the value, the less loss.

[0099] Weighting coefficients: In normal mode, the weighting is set as follows: power generation efficiency 60%, power supply reliability 30%, and energy storage loss 10%.

[0100] Then, substitute the values ​​of the above parameters into the multi-objective scheduling optimization function to calculate the total score.

[0101] For example, in emergency mode, if there is a sudden shortage of energy storage capacity and an increase in critical loads at night, the scheduling objective will be to ensure stable power supply. Assume the parameter values ​​are:

[0102] Power generation efficiency index: When photovoltaic power generation stops and the power supply relies on high-cost grid electricity, the power generation efficiency parameter drops to 0.5.

[0103] Power supply reliability index: Critical loads must be 100% guaranteed, and all non-critical loads must be disconnected. The value is 1.0.

[0104] Energy storage life loss index: When the energy storage is discharged to 15% of the remaining capacity, close to the safety lower limit, the loss increases significantly, and the value is taken as 0.8.

[0105] Weighting coefficients: In emergency mode, power supply reliability is set at 70%, power generation efficiency at 20%, and energy storage loss at 10%.

[0106] Substitute the above parameter values ​​into the multi-objective scheduling optimization function to calculate the total score.

[0107] For example, in this embodiment, the scheduling object parameters such as the power generation of the distributed power source, the charging and discharging power of the energy storage device, and the load power of each load can be encoded as chromosomes. The target optimization score calculated by the multi-objective scheduling optimization function is used as the fitness. Through population evolution, the parameter combination that maximizes the target optimization score is found, namely the target power generation, the target charging and discharging power, and the target load power.

[0108] For example, in this embodiment, weighting coefficients can be set according to the scheduling mode. For instance, in normal mode, the power generation efficiency weight is 60%, the power supply reliability weight is 30%, and the energy storage loss weight is 10%, prioritizing the reduction of power generation costs; in emergency mode, the power supply reliability weight is increased to 70%, allowing for the sacrifice of some economic efficiency and energy storage lifespan to ensure power supply.

[0109] In this embodiment, all target parameters are uniformly scaled to the [0,1] interval to ensure that indicators with different dimensions can be directly weighted and summed.

[0110] In this embodiment, continuous parameters such as power generation, charging and discharging power, and load distribution power are discretized into gene fragments with finite values. For example, photovoltaic power is divided into 10 levels (0-100% rated power).

[0111] This embodiment randomly generates multiple feasible scheduling schemes, such as 100 individuals, ensuring that each scheme meets power balance constraints and equipment physical constraints, such as power generation + energy storage discharge = load + energy storage charging + electricity purchase, and upper and lower limits of energy storage capacity, etc.

[0112] This embodiment calculates the multi-objective function value for each set of schemes; a higher value indicates a better scheme. For example, a scheme with high power generation efficiency and low energy storage loss in normal mode will have a higher fitness score. This embodiment sorts by fitness, retaining the top 50% of high-quality individuals and eliminating the bottom 50% of low-quality individuals. This embodiment randomly selects two high-quality individuals and exchanges some genes, such as exchanging energy storage charging power and load allocation strategies, to generate new individuals. This embodiment makes small, random adjustments to some parameters of the new individuals, such as ±5% power generation, to increase population diversity. This embodiment repeats the above steps until the termination condition is met, such as no improvement in fitness for 10 consecutive generations or reaching the 200-generation iteration limit, then outputs the optimal scheme as the scheduling parameter.

[0113] By flexibly adjusting the weighting coefficients, the microgrid in this embodiment can switch scheduling strategies on demand among economy, reliability, and equipment protection to adapt to different operating conditions. The genetic algorithm introduced in this embodiment can avoid getting trapped in local optima through large-scale parallel search, quickly finding a better solution that balances multiple objectives. This embodiment can optimize the scheduling strategy in real time without manual intervention and ensures safe equipment operation through constraints, improving the microgrid's ability to cope with uncertainties. This embodiment is easy to integrate new objectives (such as carbon emission targets) or constraints (such as grid interaction requirements), and can adapt to future microgrid upgrade needs by adjusting the multi-objective function and algorithm parameters.

[0114] Corresponding to the microgrid-based optimized scheduling method in the above embodiments, Figure 2 This is a block diagram illustrating the structure of an optimized scheduling system based on a microgrid, as provided in one embodiment of this application. For ease of explanation, only the parts relevant to the embodiment of this application are shown. References Figure 2 The microgrid-based optimized scheduling system 20 includes: a microgrid status analysis module 21, a scheduling mode determination module 22, and an optimized scheduling module 23.

[0115] Among them, the microgrid status analysis module 21 is used to calculate the power reliability parameters corresponding to the distributed power source, the energy storage health parameters corresponding to the energy storage device, and the load demand parameters corresponding to the load based on the operation monitoring data of the microgrid. The power reliability parameters, energy storage health parameters, and load demand parameters are input into the pre-trained decision tree model to obtain the operating status of the microgrid. The microgrid includes distributed power sources, energy storage devices, and loads. The operating status of the microgrid includes normal operation status and power supply abnormal status.

[0116] The scheduling mode determination module 22 is used to determine the target scheduling mode based on the operating status of the microgrid; the target scheduling mode includes either the normal mode or the emergency mode.

[0117] The optimized scheduling module 23 is used to determine the scheduling strategy adjustment parameters based on the target scheduling mode; the scheduling strategy adjustment parameters are used to optimize the scheduling of the microgrid.

[0118] In one embodiment of this application, the operation monitoring data of the microgrid includes operation monitoring data corresponding to distributed power sources, energy storage devices, and loads respectively; the operation monitoring data corresponding to distributed power sources includes: power generation and fault frequency; the operation monitoring data corresponding to energy storage devices includes: rated capacity, remaining power, charging and discharging time, and charging and discharging efficiency; the operation monitoring data corresponding to loads includes: real-time power consumption and power demand time-series characteristics; the microgrid state analysis module 21 is specifically used to calculate power supply reliability parameters based on power generation and fault frequency;

[0119] Calculate energy storage health parameters based on rated capacity, remaining power, charging and discharging time, and charging and discharging efficiency;

[0120] Load demand parameters are calculated based on real-time power consumption and the time-series characteristics of power demand.

[0121] In one embodiment of this application, the optimization scheduling module 23 is specifically used to determine the target coefficient constraint based on the target scheduling mode;

[0122] The scenario adaptation factor is determined based on power reliability parameters, energy storage health parameters, and load demand parameters; the scenario adaptation factor is a comprehensive quantitative indicator of the characteristics of the current operating scenario of the microgrid.

[0123] The target weight coefficient matrix is ​​determined based on the scenario adaptation factor and target coefficient constraints. The target weight coefficient matrix includes the weight coefficients corresponding to the power generation efficiency index, power supply reliability index, and energy storage life loss index. The power generation efficiency index refers to the power generation capacity and efficiency index of distributed power sources in the microgrid. The power supply reliability index refers to the ability of the microgrid to stably supply power to the load. The energy storage life loss index refers to the performance degradation and life consumption index of energy storage equipment due to physical and chemical changes during the charge and discharge cycle.

[0124] Using power generation efficiency, power supply reliability, and energy storage life loss as scheduling optimization objectives, a multi-objective scheduling optimization function is constructed using the objective weight coefficient matrix.

[0125] The scheduling strategy adjustment parameters are determined based on the multi-objective scheduling optimization function.

[0126] In one embodiment of this application, the optimized scheduling module 23 is further configured to determine the target coefficient constraint as a first coefficient constraint if the target scheduling mode is a normal mode; the first coefficient constraint includes the weight coefficient of the power generation efficiency index in the target weight coefficient matrix being greater than or equal to a first threshold.

[0127] If the target scheduling mode is emergency mode, then the target coefficient constraint is determined to be the second coefficient constraint; the second coefficient constraint includes the weight coefficient of the power supply reliability index in the target weight coefficient matrix being greater than or equal to the second threshold.

[0128] The second threshold is greater than the first threshold.

[0129] In one embodiment of this application, the optimized scheduling module 23 is further used to obtain a reference scene adaptation factor;

[0130] Based on the reference scenario adaptation factor, power reliability parameters, energy storage health parameters and load demand parameters, the scenario adaptation factor is determined through the first formula.

[0131] The first formula is:

[0132]

[0133] in, As a scene adaptation factor, As a reference scenario adaptation factor, For power supply reliability parameters, For energy storage health parameters, These are the load requirement parameters.

[0134] In one embodiment of this application, the optimization scheduling module 23 is further used to optimize the power generation of the distributed power source, the charging and discharging power of the energy storage device and the load power of each load using a genetic algorithm, with the goal of maximizing the multi-objective scheduling optimization function, to obtain the target power generation of the distributed power source, the target charging and discharging power of the energy storage device and the target load power of each load.

[0135] The target power generation, target charging and discharging power, and target load power are used as parameters for scheduling strategy adjustment.

[0136] In one embodiment of this application, the multi-objective scheduling optimization function is:

[0137]

[0138] in, Optimize the score to achieve the goal. , and These are the weighting coefficients. The normalized power generation efficiency index This is the normalized power supply reliability index. This is the normalized energy storage life loss index.

[0139] See Figure 3 , Figure 3 This is a schematic block diagram of an electronic device provided according to an embodiment of this application. Figure 3 The electronic device 300 in this embodiment may include one or more processors 301, one or more input devices 302, one or more output devices 303, and one or more memories 304. The processors 301, input devices 302, output devices 303, and memories 304 communicate with each other via a communication bus 305. The memories 304 store computer programs, including program instructions. The processors 301 execute the program instructions stored in the memories 304. Specifically, the processors 301 are configured to invoke the program instructions to perform the functions of the modules in the aforementioned system embodiments, for example... Figure 2The functions of the microgrid status analysis module 21, the scheduling mode determination module 22, and the optimized scheduling module 23 are shown.

[0140] It should be understood that, in the embodiments of this application, the processor 301 may be a central processing unit (CPU), but it may also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0141] Input device 302 may include a touchpad, a fingerprint sensor (for collecting the user's fingerprint information and fingerprint orientation information), a microphone, etc., and output device 303 may include a display (LCD, etc.), a speaker, etc.

[0142] The memory 304 may include read-only memory and random access memory, and provides instructions and data to the processor 301. A portion of the memory 304 may also include non-volatile random access memory. For example, the memory 304 may also store information about the type of energy storage device.

[0143] In specific implementations, the processor 301, input device 302, and output device 303 described in the embodiments of this application can execute the implementation methods described in the embodiments of the optimized scheduling method based on microgrids provided in the embodiments of this application, or they can execute the implementation methods of the electronic device 300 described in the embodiments of this application, which will not be repeated here.

[0144] In another embodiment of this application, a computer-readable storage medium is provided. This computer-readable storage medium stores a computer program, which includes program instructions. When executed by a processor, the program instructions implement all or part of the processes in the methods described above. Alternatively, the computer program can instruct related hardware to complete the process. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include any entity or device capable of carrying computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0145] The computer-readable storage medium can be an internal storage unit of the electronic device in any of the foregoing embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium can also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc., equipped on the electronic device. Furthermore, the computer-readable storage medium can include both internal and external storage units of the electronic device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium can also be used to temporarily store data that has been output or will be output.

[0146] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this application.

[0147] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the electronic devices and units described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0148] In the several embodiments provided in this application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be indirect coupling or communication connection through some interfaces or units, or it may be an electrical, mechanical, or other form of connection.

[0149] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of this application, depending on actual needs.

[0150] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0151] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An optimized scheduling method based on microgrids, characterized in that, include: Based on the operation monitoring data of the microgrid, the power reliability parameters corresponding to the distributed power source, the energy storage health parameters corresponding to the energy storage device, and the load demand parameters corresponding to the load are calculated. The power reliability parameters, the energy storage health parameters, and the load demand parameters are input into a pre-trained decision tree model to obtain the operating status of the microgrid. The microgrid includes the distributed power source, the energy storage device, and the load. The operating status of the microgrid includes normal operation status and power supply abnormality status. The target scheduling mode is determined based on the operating status of the microgrid; Determine the target coefficient constraints based on the target scheduling mode; Obtain the reference scene adaptation factor; The scenario adaptation factor is a comprehensive quantitative indicator of the characteristics of the current operating scenario of the microgrid. The scenario adaptation factor is determined based on the reference scenario adaptation factor, the power reliability parameters, the energy storage health parameters, and the load demand parameters, using a first formula. The first formula is: ； in, As a scene adaptation factor, As a reference scenario adaptation factor, For power supply reliability parameters, For energy storage health parameters, For load requirement parameters; The target weight coefficient matrix is ​​determined based on the scenario adaptation factor and the target coefficient constraint. The target weight coefficient matrix includes the weight coefficients corresponding to the power generation efficiency index, the power supply reliability index, and the energy storage life loss index. The power generation efficiency index refers to the power generation capacity and efficiency index of distributed power sources in the microgrid. The power supply reliability index refers to the ability of the microgrid to stably supply power to the load. The energy storage life loss index refers to the performance degradation and life consumption index of energy storage devices due to physicochemical changes during charge and discharge cycles. Using power generation efficiency, power supply reliability, and energy storage life loss as scheduling optimization objectives, a multi-objective scheduling optimization function is constructed using the objective weight coefficient matrix. The scheduling strategy adjustment parameters are determined based on the multi-objective scheduling optimization function; these parameters are used to optimize the scheduling of the microgrid. The determination of the target scheduling mode based on the microgrid's operating status includes: if the microgrid's operating status is normal operation, then the target scheduling mode is determined to be normal mode; if the microgrid's operating status is abnormal power supply, then the target scheduling mode is determined to be emergency mode.

2. The optimized scheduling method based on microgrids as described in claim 1, characterized in that, The operation monitoring data of the microgrid includes the operation monitoring data corresponding to the distributed power source, the energy storage device and the load respectively; The operation monitoring data corresponding to the distributed power source includes: power generation and fault frequency; the operation monitoring data corresponding to the energy storage device includes: rated capacity, remaining power, charging and discharging time and charging and discharging efficiency; the operation monitoring data corresponding to the load includes: real-time power consumption and power demand time-series characteristics. The calculation of power reliability parameters for distributed power sources, energy storage health parameters for energy storage devices, and load demand parameters for loads based on microgrid operation monitoring data includes: The power supply reliability parameters are calculated based on the power generation capacity and the fault frequency. The energy storage health parameters are calculated based on the rated capacity, the remaining power, the charging and discharging duration, and the charging and discharging efficiency. The load demand parameters are calculated based on the real-time power consumption and the time-series characteristics of power demand.

3. The optimized scheduling method based on microgrids as described in claim 1, characterized in that, The determination of target coefficient constraints based on the target scheduling mode includes: If the target scheduling mode is the normal mode, then the target coefficient constraint is determined to be the first coefficient constraint; the first coefficient constraint includes the weight coefficient of the power generation efficiency index in the target weight coefficient matrix being greater than or equal to a first threshold. If the target scheduling mode is an emergency mode, then the target coefficient constraint is determined to be a second coefficient constraint; the second coefficient constraint includes the weight coefficient of the power supply reliability index in the target weight coefficient matrix being greater than or equal to a second threshold. Wherein, the second threshold is greater than the first threshold.

4. The optimized scheduling method based on microgrids as described in claim 1, characterized in that, The step of determining the scheduling strategy adjustment parameters based on the multi-objective scheduling optimization function includes: Taking the power generation of the distributed power source, the charging and discharging power of the energy storage device, and the load power of each load as the scheduling objects, and the maximization of the multi-objective scheduling optimization function as the objective, the genetic algorithm is used to optimize the power generation of the distributed power source, the charging and discharging power of the energy storage device, and the load power of each load to obtain the target power generation of the distributed power source, the target charging and discharging power of the energy storage device, and the target load power of each load. The target power generation, the target charging and discharging power, and the target load power are used as scheduling strategy adjustment parameters.

5. The optimized scheduling method based on microgrids as described in claim 1, characterized in that, The multi-objective scheduling optimization function is: in, Optimize the score to achieve the goal. , and These are the weighting coefficients. The normalized power generation efficiency index This is the normalized power supply reliability index. This is the normalized energy storage life loss index.

6. An optimized scheduling system based on a microgrid, characterized in that, include: The microgrid status analysis module is used to calculate the power reliability parameters corresponding to the distributed power source, the energy storage health parameters corresponding to the energy storage device, and the load demand parameters corresponding to the load based on the microgrid's operation monitoring data. The power reliability parameters, the energy storage health parameters, and the load demand parameters are then input into a pre-trained decision tree model to obtain the microgrid's operating status. The microgrid includes the distributed power source, the energy storage device, and the load. The microgrid's operating status includes normal operation and abnormal power supply status. The scheduling mode determination module is used to determine the target scheduling mode based on the operating status of the microgrid; the target scheduling mode includes either a normal mode or an emergency mode. The scheduling mode determination module is specifically used to determine the target scheduling mode as normal mode if the microgrid is in normal operation mode, and to determine the target scheduling mode as emergency mode if the microgrid is in abnormal power supply mode. The optimization scheduling module is used to determine target coefficient constraints based on the target scheduling mode; Obtain the reference scene adaptation factor; The scenario adaptation factor is a comprehensive quantitative indicator of the characteristics of the current operating scenario of the microgrid. The scenario adaptation factor is determined based on the reference scenario adaptation factor, the power reliability parameters, the energy storage health parameters, and the load demand parameters, using a first formula. The first formula is: ； in, As a scene adaptation factor, As a reference scenario adaptation factor, For power supply reliability parameters, For energy storage health parameters, For load requirement parameters; The target weight coefficient matrix is ​​determined based on the scenario adaptation factor and the target coefficient constraint. The target weight coefficient matrix includes the weight coefficients corresponding to the power generation efficiency index, the power supply reliability index, and the energy storage life loss index. The power generation efficiency index refers to the power generation capacity and efficiency index of distributed power sources in the microgrid. The power supply reliability index refers to the ability of the microgrid to stably supply power to the load. The energy storage life loss index refers to the performance degradation and life consumption index of energy storage devices due to physicochemical changes during charge and discharge cycles. Using power generation efficiency, power supply reliability, and energy storage life loss as scheduling optimization objectives, a multi-objective scheduling optimization function is constructed using the objective weight coefficient matrix. The scheduling strategy adjustment parameters are determined based on the multi-objective scheduling optimization function; the scheduling strategy adjustment parameters are used to optimize the scheduling of the microgrid.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 5.

Images