Distributed power supply scheduling optimization method and system

Abstract

The invention provides a distributed power supply scheduling optimization method and system, and relates to the technical field of scheduling optimization, and the method comprises the steps: carrying out the variational mode decomposition of wind power generation, photovoltaic power generation and load historical data, and obtaining a stationary subsequence; performing power prediction on the stationary sub-sequence to obtain power generation power and a load demand prediction value; constructing a multi-target optimization scheduling model by using the generated power and the load demand predicted value, and solving an optimization model of the target optimization scheduling model to obtain an optimal solution; obtaining a microgrid scheduling strategy, and determining an output power reference value of the distributed power supply; and adjusting the output power reference value, and implementing micro-grid scheduling. The technical problems of intermittency of renewable energy sources, limitation of a traditional scheduling strategy and insufficient overall response capability of the system in the prior art can be solved, the technical target of improving the stability and the response capability of the power system is achieved, and the technical effect of improving the continuity of power supply and user experience is achieved.

Description

Technical Field

[0001] The present application relates to the technical field of scheduling optimization, and in particular to a distributed power supply scheduling optimization method and system. Background Art

[0002] With the development of technology, distributed power sources and microgrids have gradually become the direction of power system reform, and have attracted widespread attention for their flexibility and efficiency. Distributed power sources are a decentralized way of producing electricity that can effectively reduce transmission losses. Microgrids are small grid systems that combine multiple energy forms and can operate independently of the main grid.

[0003] However, the existing distributed power and microgrid technologies still face many challenges in practical applications. First, the intermittent and uncertain nature of distributed power sources brings difficulties to the dispatch and stable operation of power systems. The power generation of renewable energy sources such as solar and wind power is greatly affected by weather and environment and is difficult to predict. Volatility may lead to unstable power supply, thus affecting power quality and user experience. Secondly, the existing microgrid dispatching strategies usually rely on centralized control, which may not be flexible enough in the face of the diversity and complexity of distributed resources. Centralized control requires a large amount of communication and computing resources. Once there is a problem with the communication network, it may cause dispatch failure and affect the stability of the system. In addition, traditional control strategies are often updated based on fixed time intervals, which may lead to overly frequent control signal adjustments, increasing the system's computing burden and resource consumption. With the increase in the number of distributed power sources, how to efficiently achieve coordinated dispatch of multiple power sources has become a major problem. Existing systems often lack rapid response and adaptive capabilities when dealing with emergencies and failures, which limits the risk resistance of power systems. In response to these problems, existing technologies urgently need to be improved to better meet the requirements of modern power systems for flexibility, reliability and efficiency.

[0004] In summary, there are technical problems in the existing technology due to the intermittent nature of renewable energy, the limitations of traditional scheduling strategies and the insufficient overall response capability of the system, which leads to the decline in the stability and reliability of the power system, further affecting the continuity of power supply and user experience. Summary of the invention

[0005] The purpose of this application is to provide a distributed power supply scheduling optimization method and system to solve the technical problems in the prior art that the stability and reliability of the power system are reduced due to the intermittent nature of renewable energy, the limitations of traditional scheduling strategies and the insufficient overall responsiveness of the system, further affecting the continuity of power supply and user experience.

[0006] In view of the above problems, the present application provides a distributed power supply scheduling optimization method and system.

[0007] In the first aspect, the present application provides a distributed power supply scheduling optimization method, which is implemented through a distributed power supply scheduling optimization system, including: performing variational mode decomposition on wind power generation, photovoltaic power generation and load historical data to obtain a stationary subsequence; performing power prediction on the stationary subsequence, and obtaining the power generation power and load demand prediction values ​​of the distributed power supply through adaptive differential evolution extreme learning; using the power generation power and load demand prediction values ​​to construct a multi-objective optimization scheduling model, and competitively solving the optimization model of the objective optimization scheduling model to obtain an optimal solution; obtaining a microgrid scheduling strategy based on the optimal solution, and determining the output power reference value of the distributed power supply; adjusting the output power reference value through the secondary control layer of the microgrid, and implementing microgrid scheduling through the adjusted output power.

[0008] In the second aspect, the present application also provides a distributed power supply scheduling optimization system for executing a distributed power supply scheduling optimization method as described in the first aspect, including: a stable subsequence acquisition module, the stable subsequence acquisition module is used to perform variational mode decomposition on wind power generation, photovoltaic power generation and load historical data to obtain a stable subsequence; a power prediction module, the power prediction module is used to perform power prediction on the stable subsequence, and obtain the power generation power and load demand prediction values ​​of the distributed power supply through adaptive differential evolution extreme learning; an optimal solution acquisition module, the optimal solution acquisition module is used to use the power generation power and load demand prediction values ​​to construct a multi-objective optimization scheduling model, and competitively solve the optimization model of the objective optimization scheduling model to obtain the optimal solution; an output power reference value determination module, the output power reference value determination module is used to obtain a microgrid scheduling strategy according to the optimal solution, and determine the output power reference value of the distributed power supply; a microgrid scheduling module, the microgrid scheduling module is used to adjust the output power reference value through the secondary control layer of the microgrid, and implement microgrid scheduling through the adjusted output power.

[0009] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0010] By performing variational mode decomposition on historical data of wind power generation, photovoltaic power generation and load, a stationary subsequence is obtained; power prediction is performed on the stationary subsequence, and the power generation power and load demand prediction values ​​of the distributed power source are obtained through adaptive differential evolution extreme learning; a multi-objective optimization scheduling model is constructed using the power generation power and load demand prediction values, and the optimization model of the objective optimization scheduling model is competitively solved to obtain the optimal solution; a microgrid scheduling strategy is obtained based on the optimal solution, and the output power reference value of the distributed power source is determined; the output power reference value is adjusted through the secondary control layer of the microgrid, and microgrid scheduling is implemented through the adjusted output power, so as to achieve the technical goal of improving the stability and responsiveness of the power system and achieve the technical effect of improving the continuity of power supply and user experience.

[0011] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0013] Figure 1 A flow chart of a distributed power supply scheduling optimization method for this application;

[0014] Figure 2 This is a structural schematic diagram of a distributed power supply scheduling optimization system for this application.

[0015] Description of reference numerals:

[0016] A stationary subsequence obtaining module 11, a power prediction module 12, an optimal solution obtaining module 13, an output power reference value determining module 14, and a microgrid dispatching module 15. DETAILED DESCRIPTION

[0017] This application provides a distributed power dispatch optimization method and system to solve the technical problem in the prior art that the intermittent nature of renewable energy, the limitations of traditional dispatch strategies, and the insufficient overall response capability of the system lead to a decrease in the stability and reliability of the power system, which further affects the continuity of power supply and user experience. The technical goal of improving the stability and response capability of the power system is achieved, and the technical effect of improving the continuity of power supply and user experience is achieved.

[0018] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0019] For example, please refer to the attached Figure 1 The present application provides a distributed power supply scheduling optimization method, which is applied to a distributed power supply scheduling optimization system and specifically includes the following steps:

[0020] Step 1: Perform variational mode decomposition on the historical data of wind power generation, photovoltaic power generation and load to obtain stable subsequences.

[0021] Specifically, when performing variational mode decomposition on historical data of wind power generation, photovoltaic power generation and load, complex time series data are processed to better understand the patterns and trends in the data. Variational mode decomposition is an effective signal processing technology that can decompose complex signals into several physically meaningful sub-signals, namely stationary subsequences. Stationary subsequences are more regular than the original data, reducing noise and randomness, making subsequent analysis more accurate. Through decomposition, complex data can be converted into a more processable form, providing a stable and reliable basis for power forecasting. The process of variational mode decomposition is not only a process of data simplification, but also one of the key steps to improve the prediction ability of the model. Therefore, it plays an important role in analyzing renewable energy data with high uncertainty and volatility.

[0022] Step 2: Perform power prediction on the stationary subsequence, and obtain the power generation power and load demand prediction values ​​of the distributed power source through adaptive differential evolution extreme learning.

[0023] Specifically, the power of the stationary subsequence is predicted, and the power generation and load demand forecast values ​​of the distributed power generation are obtained through the adaptive differential evolution extreme learning algorithm. Adaptive differential evolution extreme learning is a powerful tool that combines evolutionary algorithms with machine learning. It can adaptively adjust parameters to improve the efficiency and accuracy of the learning process. The stationary subsequence is used as input, and after the model is trained, the output is the forecast value of future power generation and load demand. Not only does it take into account the historical trend of the data, but it also integrates the algorithm's ability to handle unknown situations, and can dynamically adjust to cope with actual changes. The resulting forecast value is more accurate and reliable, providing an accurate basis for the dispatch of microgrids and helping to optimize the overall operation strategy.

[0024] Step three: construct a multi-objective optimization scheduling model using the power generation and load demand forecast values, and competitively solve the optimization model of the objective optimization scheduling model to obtain the optimal solution.

[0025] Specifically, a multi-objective optimization scheduling model is constructed using the predicted values ​​of power generation and load demand, and the predicted power and load demand are integrated as the input parameters of the model to facilitate more in-depth analysis and decision-making, understand the trade-offs between different objectives, such as operating costs, pollutant emissions, and system stability, and reflect the interaction between objectives through the model. The construction of a multi-objective optimization scheduling model aims to seek the optimal state of the overall performance of the system under different objectives. At this time, through competitive solving, that is, through the algorithm to explore in the possible solution space, one or more non-inferior solutions, that is, Pareto optimal solutions, can be found, which can provide the best operation strategy for the microgrid.

[0026] Step 4: Obtain a microgrid dispatching strategy based on the optimal solution and determine an output power reference value of the distributed power source.

[0027] Specifically, obtaining a microgrid dispatch strategy based on the optimal solution means starting from the results of theoretical optimization and converting the best strategy obtained in the model into specific dispatch instructions. The results in the theoretical model are combined with the operating conditions of the actual system to ensure feasibility at the practical level. By determining the output power reference value of the distributed power source, the microgrid dispatch strategy clarifies the working status of each distributed power source to meet the overall needs of the microgrid. The microgrid dispatch strategy can effectively cope with volatility and uncertainty and provide the optimal solution for system operation. The microgrid dispatch strategy not only considers the current system status, but also needs to make adaptive adjustments to future changes, so as to minimize operating costs and environmental impacts while ensuring stable energy supply.

[0028] Step 5: The output power reference value is adjusted through the secondary control layer of the microgrid, and the microgrid scheduling is implemented through the adjusted output power.

[0029] Specifically, the output power reference value is adjusted through the secondary control layer of the microgrid. In this process, the task of the secondary control layer is to dynamically adjust the output power reference value based on real-time feedback and changes in external conditions. The adjustment needs to be based on the monitoring and analysis of real-time data so that the microgrid can maintain stable operation under changing conditions. Implementing microgrid scheduling through the adjusted output power can ensure that the actual output power and the reference value are consistent, thereby achieving the optimization goal set by the model. The secondary control layer ensures that the operation of the microgrid is always in the best state through real-time response and adaptive adjustment, and can quickly respond to any possible abnormalities. Dynamic adjustment improves the reliability and flexibility of the system.

[0030] The distributed power dispatching optimization method is applied to a distributed power dispatching optimization system, which can achieve the technical goal of improving the stability and responsiveness of the power system and achieve the technical effect of improving the continuity of power supply and user experience.

[0031] Furthermore, the present application also includes:

[0032] Collect travel chain data and functional area attribute data of user resources to obtain departure time, travel time, stay time, mileage, geographic location and charging facility distribution information; establish a travel chain model based on the departure time, travel time, stay time, mileage, geographic location and charging facility distribution information; use the Monte Carlo simulation method combined with the machine learning algorithm to construct an electricity load prediction model, predict the electricity load demand of user resources at different times and locations based on the travel chain model, and add it to the load demand prediction value.

[0033] Specifically, collecting user resource travel chain data and functional area attribute data is the basis for electricity load forecasting. Obtaining information such as the user's departure time, travel time, stay time, mileage, and the geographical location and charging facility distribution of the user's area can help understand the user's activity patterns at different times and locations and identify their potential demand for charging facilities. Data collection usually requires combining multiple sources, such as traffic flow monitoring, user location data, and charging pile distribution statistics, to ensure the multidimensionality and comprehensiveness of the information.

[0034] A travel chain model is established based on the collected departure time, travel time, stay time, mileage, geographic location and charging facility distribution information. The travel chain model is a systematic representation of user travel behavior, which is used to simulate the typical movement path and charging needs of users over a period of time. Through the travel chain model, the location and time where users may stay in a specific period of time, as well as the peak period and frequency of charging behavior, can be identified, providing a visual and structured method for analyzing users' charging needs. The travel chain model not only provides a basis for prediction, but also helps identify key influencing factors, providing strong support for subsequent optimization and strategy formulation.

[0035] Next, we use the Monte Carlo simulation method combined with the machine learning algorithm to build a power load forecasting model. Monte Carlo simulation estimates the probability distribution of charging demand through random sampling, while the machine learning algorithm is responsible for learning patterns and relationships from the data. Combining the two, we can build a power load forecasting model that can simulate the charging needs of users in different scenarios. Using the established travel chain model, we predict the power load demand of user resources at different times and locations, and add the power load demand to the load demand forecast value. This makes the forecast results more accurate and can effectively deal with the uncertainty and randomness in the data.

[0036] By providing detailed load forecast data for microgrid dispatch, it helps optimize the layout and usage strategy of charging infrastructure, ultimately improving the system's operating efficiency and user experience.

[0037] Furthermore, the present application also includes:

[0038] Collect microgrid operation data and pollutant emission data to determine influencing factors; construct a multi-objective optimization scheduling model based on the influencing factors, solve the multi-objective optimization scheduling model, and obtain the optimal solution.

[0039] Specifically, collecting microgrid operation data and pollutant emission data is the first step in optimizing microgrid scheduling. Microgrid operation data includes power generation, load demand, power output, energy storage level, etc., while pollutant emission data involves greenhouse gas emissions and other pollution sources. By collecting data, key factors affecting the operating efficiency and environmental performance of microgrids can be identified, such as the proportion of renewable energy, load volatility, equipment efficiency, and emission standards. Influencing factors not only determine the economic benefits of microgrids, but also affect their environmental impact. Therefore, accurate data collection and analysis are crucial for subsequent modeling and optimization.

[0040] According to the collected influencing factors, a multi-objective optimization scheduling model based on the influencing factors is constructed. The core of the multi-objective optimization scheduling model is to balance the economy and environmental protection of the microgrid. By setting multiple optimization goals, such as minimum operating cost, minimum pollutant emissions, maximum renewable energy utilization, etc., scientific guidance of the microgrid scheduling strategy is achieved. When constructing the model, it is necessary to comprehensively consider the interaction between various influencing factors to ensure that the model can truly reflect the actual operating status of the microgrid. The multi-objective optimization scheduling model can help decision makers find the optimal solution in a complex multi-objective environment.

[0041] After constructing the multi-objective optimization scheduling model, the multi-objective optimization scheduling model is solved to obtain the optimal solution. Use optimization algorithms such as linear programming, genetic algorithms, or imperialist competition algorithms to explore possible solution spaces and find the optimal scheduling solution. The optimal solution provides the best balance between the economy and environmental protection of the microgrid, guiding the actual operation and scheduling. By solving the model, the most effective resource allocation and operation strategy can be identified, thereby minimizing costs and environmental impacts while ensuring stable system operation. This solution process is a key step in realizing intelligent management of microgrids.

[0042] By identifying influencing factors, building a multi-objective optimization scheduling model, and then using the optimization algorithm to solve and obtain the optimal solution, it not only helps the microgrid achieve a win-win situation in economic and environmental benefits, but also improves its operating efficiency and reliability, providing technical support for the intelligent development of modern power grids.

[0043] Furthermore, the present application also includes:

[0044] The output power reference value is transmitted to the secondary control layer to determine whether the output power reference value of the distributed power source complies with the optimized operation strategy of the microgrid; if it does not comply with the optimized operation strategy of the microgrid, the microgrid scheduling strategy is adjusted; if it complies with the optimized operation strategy of the microgrid, the output power reference value is adjusted.

[0045] Specifically, passing the output power reference value to the secondary control layer is a key step in microgrid scheduling. The secondary control layer is used to monitor and adjust the distributed power sources in the microgrid in real time to ensure that the output power is consistent with the optimized operation strategy. By passing the output power reference value, the secondary control layer can obtain real-time data about the current state of the system and determine whether the output of the distributed power source meets the predetermined optimization strategy. Allow the system to maintain efficient operation under unstable and fluctuating conditions and provide data support for subsequent adjustments. Ensure the accuracy and timeliness of the reference value transmission so that the secondary control layer can respond quickly and make adjustments.

[0046] On the basis of transmission and monitoring, if the output power reference value of the distributed power generation does not meet the optimized operation strategy of the microgrid, the microgrid dispatching strategy needs to be adjusted in time. This may involve reallocating the power generation load, optimizing resource allocation, or changing the dispatching plan to ensure that the system returns to the optimized state. Through real-time adjustment, the microgrid can dynamically respond to external changes and maintain efficient and stable operation. Adjustment can ensure that the system can still achieve the expected performance goals under various uncertain conditions. At the same time, the reasons that may lead to non-compliance with the optimization strategy are analyzed to optimize the future prediction and dispatching process.

[0047] If the output power reference value of the distributed generation meets the optimized operation strategy of the microgrid, the output power reference value is slightly adjusted to refine the control process and further improve the system efficiency and power quality. Even if the reference value meets the strategy requirements, through slight adjustments, the system can achieve a better performance level, such as reducing energy consumption, reducing fluctuations or improving response speed. Adjustments are based on real-time data feedback and environmental changes to ensure that the microgrid is further optimized on the basis of meeting the strategy requirements. Adjusting the strategy not only helps to achieve the optimal allocation of resources, but also improves the overall responsiveness and operating efficiency of the system.

[0048] By comparing the predetermined strategy with real-time data, it is decided whether to adjust the microgrid dispatch strategy or output power. This reflects the intelligence and dynamic adjustment capabilities of the microgrid system, ensuring that the system can achieve efficient and optimized resource utilization in a complex operating environment.

[0049] Furthermore, the present application also includes:

[0050] In view of the adjustment of the voltage and frequency of the output power reference value, a finite-time consistency control strategy of the event trigger mechanism is designed; event trigger conditions are set in the event trigger mechanism, the status information of the distributed power source is monitored through the event trigger conditions, and event-driven control signal updates are implemented; the update signal is used to reduce the number of control task executions, obtain the recovery speed and control accuracy of the microgrid voltage and frequency, and obtain the adjusted output power.

[0051] Specifically, a finite-time consistency control strategy with an event-triggered mechanism is designed for the adjustment of the voltage and frequency of the output power reference value in order to improve the response speed and stability of the microgrid. Traditional control methods usually rely on fixed time intervals to update control signals, but this approach may lead to unnecessary calculations and waste of resources. In the finite-time consistency control strategy, the event-triggered mechanism allows the system to update the signal only when significant changes are detected, thereby optimizing the use of system resources. Not only can it respond quickly to changes, but it can also restore the voltage and frequency to the expected values ​​within a limited time, maintaining the efficient operation of the system. Through the control strategy, the microgrid can better adapt to changes in a dynamic environment and achieve more stable power output.

[0052] Set event trigger conditions for the event trigger mechanism to ensure real-time monitoring and timely response to the system status. Event trigger conditions are an important basis for determining when to update control signals in the system, and are set based on voltage and frequency deviations or the status information of distributed power sources. When the conditions are met, the system immediately triggers the event and updates the control signal, so that the system remains efficient and stable in actual operation. Microgrids can quickly respond to environmental changes or load fluctuations, adjust the operating status in a timely manner, and avoid unnecessary resource consumption and system fluctuations. Setting appropriate trigger conditions is crucial to ensure efficient operation and response speed of the system.

[0053] By applying the update signal, the number of executions of the control task can be reduced, thereby improving the voltage and frequency recovery speed and control accuracy of the microgrid. Traditional control methods may update signals frequently, which not only increases the computational burden of the system, but also may cause lags in the control signal. Under the event-driven mechanism, signal updates are only performed when needed, which significantly reduces the frequency of control tasks while ensuring the system's ability to quickly recover to a stable state. The efficient control method not only improves the operating efficiency of the microgrid, but also reduces the system's energy consumption and resource waste, ensuring accurate adjustment of the output power. The updated output power reference value can better match the system requirements and achieve the optimal operating state of the microgrid.

[0054] The control strategy can not only quickly restore the voltage and frequency, but also ensure the stability and reliability of the system under different environmental conditions.

[0055] Furthermore, the present application also includes:

[0056] When the microgrid is in island mode, the isolated microgrid is obtained, and coordinated control of distributed power sources is performed based on the designed distributed finite-time secondary control protocol; for the abnormal communication network interruption in the isolated microgrid, a prediction and compensation algorithm of the abnormal communication network interruption is extracted according to the coordinated control; the response scheduling strategy of the distributed power source when the communication network is abnormally interrupted is determined by using the prediction and compensation algorithm, and the adjusted output power is obtained through the response scheduling strategy.

[0057] Specifically, when the microgrid is in island mode, it is crucial to obtain the status information of the isolated microgrid, because the microgrid operates independently of the main grid and must maintain its own power balance. The coordinated control of distributed power sources is performed based on the distributed finite-time quadratic control protocol obtained by design, aiming to ensure that the various distributed power sources in the isolated microgrid can work together to maintain the stability and reliability of the system. The finite-time control protocol means that the system can achieve the control target within a preset time, which is critical for coping with rapid changes and uncertainties in island mode. Through this distributed control, the system can operate efficiently with limited resources while ensuring the stability of voltage and frequency.

[0058] Designing and applying a predictive compensation algorithm for abnormal communication network interruptions in isolated microgrids is the key to maintaining stable system operation. When communication is interrupted, the distributed power sources in the microgrid cannot receive and send control signals in real time, resulting in system imbalance. Therefore, the predictive compensation algorithm for abnormal communication network interruptions extracted based on coordinated control can predict the possible impact of communication interruptions in advance and formulate corresponding compensation measures. By analyzing historical data and current system status, possible abnormal situations are predicted, and system parameters are automatically adjusted when communication is interrupted to ensure the continuity and stability of power supply. The compensation mechanism can effectively reduce the negative impact of communication interruptions on the system and improve the anti-interference ability of the microgrid in island mode.

[0059] Using the prediction compensation algorithm to determine the response scheduling strategy of distributed power sources when the communication network is abnormally interrupted is an important step to ensure the efficient operation of the microgrid in the island mode. Based on the comprehensive analysis of the current state of the system and the predicted anomalies, the optimal output power adjustment plan in the case of communication interruption is formulated. Through the response scheduling strategy, the microgrid can make autonomous adjustments based on local data and prediction results without communication support to maintain stable operation of the system. The adjusted output power ensures power quality and power supply reliability through internal coordination and automatic adjustment, thereby achieving the goal of optimizing the operation of the microgrid in the island mode. It not only enhances the robustness of the system, but also improves the adaptability of the microgrid in various abnormal situations.

[0060] By acquiring the status of isolated microgrids, coordinated control of distributed power sources is achieved based on distributed control protocols and predictive compensation algorithms, effectively responding to abnormal communication network interruptions and ensuring the continuous and stable operation of the system.

[0061] Furthermore, the present application also includes:

[0062] The voltage and frequency consistency of the distributed power source is restored through the response scheduling strategy and added to the adjusted output power.

[0063] Specifically, achieving consistency recovery of voltage and frequency of distributed power sources through response scheduling strategy is a key step in optimizing operation in microgrid island mode. When the microgrid operates in island mode, the voltage and frequency of each distributed power source may be inconsistent due to the lack of regulation of the main grid, which will affect the stability and power quality of the system. The response scheduling strategy analyzes and adjusts the output characteristics of each distributed power source to ensure that each power source can operate consistently without the support of the main grid. Consistency recovery not only helps to improve the overall coordination of the system, but also reduces equipment loss and failure risks caused by voltage and frequency fluctuations.

[0064] After the consistency of voltage and frequency is restored, the adjustment is added to the adjusted output power, and the microgrid can better control its power output and bring it closer to the predetermined optimized state. Specifically, the adjusted output power reflects the dynamic adjustment results of the system in real-time operation, ensuring that a stable and reliable power supply can still be provided in island mode. By incorporating the results of consistency restoration into the adjustment of output power, the operating efficiency and reliability of the microgrid have been significantly improved, which not only improves the power quality, but also maximizes the use of existing distributed resources and achieves the best allocation of resources.

[0065] Through real-time monitoring and dynamic adjustment, the consistency of voltage and frequency is restored, ensuring the stability and efficiency of the microgrid in an isolated environment. By combining the consistency recovery strategy with the adjusted output power, the microgrid can autonomously maintain the balance and stability of the power system without relying on the main grid, providing important technical support for the intelligent and adaptive operation of the microgrid, effectively improving the system's risk resistance and self-healing capabilities, thereby ensuring that the microgrid can continue to provide high-quality power services under various complex operating conditions.

[0066] In summary, the distributed power supply scheduling optimization method provided by this application has the following technical effects:

[0067] By performing variational mode decomposition on historical data of wind power generation, photovoltaic power generation and load, a stationary subsequence is obtained; power prediction is performed on the stationary subsequence, and the power generation power and load demand prediction values ​​of the distributed power source are obtained through adaptive differential evolution extreme learning; a multi-objective optimization scheduling model is constructed using the power generation power and load demand prediction values, and the optimization model of the objective optimization scheduling model is competitively solved to obtain the optimal solution; a microgrid scheduling strategy is obtained based on the optimal solution, and the output power reference value of the distributed power source is determined; the output power reference value is adjusted through the secondary control layer of the microgrid, and microgrid scheduling is implemented through the adjusted output power, so as to achieve the technical goal of improving the stability and responsiveness of the power system and achieve the technical effect of improving the continuity of power supply and user experience.

[0068] Embodiment 2: Based on the distributed power dispatch optimization method in the above embodiment, the present application also provides a distributed power dispatch optimization system, please refer to the attached Figure 2 ,include:

[0069] A steady subsequence acquisition module 11, the steady subsequence acquisition module 11 is used to perform variational mode decomposition on wind power generation, photovoltaic power generation and load historical data to obtain a steady subsequence; a power prediction module 12, the power prediction module 12 is used to perform power prediction on the steady subsequence, and obtain the power generation power and load demand prediction values ​​of the distributed power source through adaptive differential evolution extreme learning; an optimal solution acquisition module 13, the optimal solution acquisition module 13 is used to construct a multi-objective optimization scheduling model using the power generation power and load demand prediction values, and to competitively solve the optimization model of the objective optimization scheduling model to obtain the optimal solution; an output power reference value determination module 14, the output power reference value determination module 14 is used to obtain a microgrid scheduling strategy according to the optimal solution, and determine the output power reference value of the distributed power source; a microgrid scheduling module 15, the microgrid scheduling module 15 is used to adjust the output power reference value through the secondary control layer of the microgrid, and implement microgrid scheduling through the adjusted output power.

[0070] Furthermore, the power prediction module 12 in the distributed power supply scheduling optimization system is also used for:

[0071] Collect travel chain data and functional area attribute data of user resources to obtain departure time, travel time, stay time, mileage, geographic location and charging facility distribution information; establish a travel chain model based on the departure time, travel time, stay time, mileage, geographic location and charging facility distribution information; use the Monte Carlo simulation method combined with the machine learning algorithm to construct an electricity load prediction model, predict the electricity load demand of user resources at different times and locations based on the travel chain model, and add it to the load demand prediction value.

[0072] Furthermore, the optimal solution obtaining module 13 in the distributed power supply scheduling optimization system is also used for:

[0073] Collect microgrid operation data and pollutant emission data to determine influencing factors; construct a multi-objective optimization scheduling model based on the influencing factors, solve the multi-objective optimization scheduling model, and obtain the optimal solution.

[0074] Furthermore, the microgrid dispatching module 15 in the distributed power dispatching optimization system is also used for:

[0075] The output power reference value is transmitted to the secondary control layer to determine whether the output power reference value of the distributed power source complies with the optimized operation strategy of the microgrid; if it does not comply with the optimized operation strategy of the microgrid, the microgrid scheduling strategy is adjusted; if it complies with the optimized operation strategy of the microgrid, the output power reference value is adjusted.

[0076] Furthermore, the microgrid dispatching module 15 in the distributed power dispatching optimization system is also used for:

[0077] In view of the adjustment of the voltage and frequency of the output power reference value, a finite-time consistency control strategy of the event trigger mechanism is designed; event trigger conditions are set in the event trigger mechanism, the status information of the distributed power source is monitored through the event trigger conditions, and event-driven control signal updates are implemented; the update signal is used to reduce the number of control task executions, obtain the recovery speed and control accuracy of the microgrid voltage and frequency, and obtain the adjusted output power.

[0078] Furthermore, the microgrid dispatching module 11 in the distributed power dispatching optimization system is also used for:

[0079] When the microgrid is in island mode, the isolated microgrid is obtained, and coordinated control of distributed power sources is performed based on the designed distributed finite-time secondary control protocol; for the abnormal communication network interruption in the isolated microgrid, a prediction and compensation algorithm of the abnormal communication network interruption is extracted according to the coordinated control; the response scheduling strategy of the distributed power source when the communication network is abnormally interrupted is determined by using the prediction and compensation algorithm, and the adjusted output power is obtained through the response scheduling strategy.

[0080] Furthermore, the microgrid dispatching module 15 in the distributed power dispatching optimization system is also used for:

[0081] The voltage and frequency consistency of the distributed power source is restored through the response scheduling strategy and added to the adjusted output power.

[0082] Each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The distributed power scheduling optimization method and specific examples in the aforementioned embodiment 1 are also applicable to a distributed power scheduling optimization system in this embodiment. Through the aforementioned detailed description of a distributed power scheduling optimization method, those skilled in the art can clearly understand a distributed power scheduling optimization system in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0083] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0084] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A distributed power supply scheduling optimization method, characterized in that: include: Perform variational mode decomposition on historical data of wind power generation, photovoltaic power generation and load to obtain stationary subsequences; Performing power prediction on the stationary subsequence, and obtaining the power generation power and load demand prediction value of the distributed power source through adaptive differential evolution extreme learning; A multi-objective optimization scheduling model is constructed using the power generation and load demand forecast values, and an optimization model of the objective optimization scheduling model is competitively solved to obtain an optimal solution; Obtaining a microgrid dispatching strategy according to the optimal solution, and determining an output power reference value of the distributed power source; The output power reference value is adjusted through the secondary control layer of the microgrid, and the microgrid scheduling is implemented through the adjusted output power.

2. A distributed power supply scheduling optimization method as claimed in claim 1, characterized in that: Obtain load demand forecasts, including: Collect the user resources' travel chain data and functional area attribute data to obtain departure time, travel time, stay time, mileage, geographic location and charging facility distribution information; Establishing a travel chain model according to the departure time, travel time, stay time, mileage, geographic location and charging facility distribution information; The Monte Carlo simulation method is combined with a machine learning algorithm to build an electricity load forecasting model. The electricity load demand of user resources at different times and locations is predicted according to the travel chain model and added to the load demand forecast value.

3. A distributed power supply scheduling optimization method as claimed in claim 1, characterized in that: The method of constructing a multi-objective optimization scheduling model by using the power generation and load demand forecast values, and competitively solving the optimization model of the objective optimization scheduling model to obtain the optimal solution includes: Collect microgrid operation data and pollutant emission data to determine influencing factors; A multi-objective optimization scheduling model based on the influencing factors is constructed, and the multi-objective optimization scheduling model is solved to obtain the optimal solution.

4. A distributed power supply scheduling optimization method as claimed in claim 1, characterized in that: The adjusting the output power reference value through the secondary control layer of the microgrid includes: The output power reference value is transmitted to the secondary control layer to determine whether the output power reference value of the distributed power source complies with the optimization operation strategy of the microgrid; If it does not conform to the optimized operation strategy of the microgrid, the microgrid dispatching strategy is adjusted; if it conforms to the optimized operation strategy of the microgrid, the output power reference value is adjusted.

5. A distributed power supply scheduling optimization method as claimed in claim 4, characterized in that: The adjusting the output power reference value through the secondary control layer of the microgrid also includes: Designing a finite time consistency control strategy for an event trigger mechanism for adjusting the voltage and frequency of the output power reference value; Setting an event trigger condition in the event trigger mechanism, monitoring the state information of the distributed power source through the event trigger condition, and implementing event-driven control signal update; The update signal is used to reduce the number of control task executions, obtain the recovery speed and control accuracy of the microgrid voltage and frequency, and obtain the adjusted output power.

6. A distributed power supply scheduling optimization method as claimed in claim 1, characterized in that: The adjusting the output power reference value through the secondary control layer of the microgrid also includes: When the microgrid is in island mode, the isolated microgrid is obtained, and the coordinated control of distributed power sources is performed based on the designed distributed finite-time quadratic control protocol; For the abnormal interruption of the communication network in the isolated microgrid, extracting a prediction and compensation algorithm of the abnormal interruption of the communication network according to the coordinated control; The prediction compensation algorithm is used to determine the response scheduling strategy of the distributed power source when the communication network is abnormally interrupted, and the adjusted output power is obtained through the response scheduling strategy.

7. A distributed power supply scheduling optimization method as claimed in claim 6, characterized in that: The voltage and frequency consistency of the distributed power source is restored through the response scheduling strategy and added to the adjusted output power.

8. A distributed power supply scheduling optimization system, characterized in that: The steps for implementing a distributed power supply scheduling optimization method as described in any one of claims 1 to 7 include: A stationary subsequence acquisition module, wherein the stationary subsequence acquisition module is used to perform variational modal decomposition on wind power generation, photovoltaic power generation and load historical data to obtain a stationary subsequence; A power prediction module, which is used to perform power prediction on the stationary subsequence and obtain the power generation power and load demand prediction value of the distributed power source through adaptive differential evolution extreme learning; An optimal solution obtaining module, wherein the optimal solution obtaining module is used to construct a multi-objective optimization scheduling model using the power generation and load demand forecast values, and to competitively solve the optimization model of the objective optimization scheduling model to obtain an optimal solution; An output power reference value determination module, the output power reference value determination module is used to obtain a microgrid dispatching strategy according to the optimal solution and determine an output power reference value of the distributed power source; A microgrid dispatching module is used to adjust the output power reference value through the secondary control layer of the microgrid, and implement microgrid dispatching through the adjusted output power.

Images