Intelligent power grid adaptive protection control system and method

Abstract

The invention discloses a smart power grid adaptive protection control system and method, relates to the technical field of power quality, and ensures the accuracy and consistency of data by monitoring power data of power grid nodes in real time in combination with a data preprocessing technology. The system adopts a droop control strategy to carry out real-time response control, synchronizes the operation state of the distributed power supply, and dynamically adjusts synchronization parameters. The dynamic adjustment control accurately calculates compensation signals and optimizes operation parameters through methods of a proportional integral controller, an active disturbance rejection controller, fuzzy logic control and the like. According to the strategic decision control level, the system establishes a collaborative prediction model based on the real-time state and prediction data, evaluates different operation modes by adopting an intelligent decision algorithm, and intelligently selects a power grid operation mode and an island operation mode. The system has a fault coping strategy, can quickly position a fault source and start an isolation measure, redistributes a load and a standby power supply according to the fault type and severity, and ensures quick recovery and safety of a power grid.

Description

Technical Field

[0001] The present invention relates to the technical field of power quality, and in particular to a smart grid adaptive protection control system and method. Background Art

[0002] With the rapid development of economy and the increasing energy consumption, smart grid has become the focus of global attention as an important direction of power system modernization. Smart grid integrates advanced information and communication technology, automation control technology and power electronics technology to achieve efficient, reliable and safe operation of power system and provide users with more convenient, economical and environmentally friendly power services.

[0003] In the current technological context, smart grids face many challenges, including how to effectively integrate and optimize distributed energy resources, such as solar energy, wind energy and other renewable energy, and how to deal with dynamic changes and uncertainties in the power grid. In addition, the self-healing ability of the power grid, optimizing energy configuration, and improving the automation and information level of the power grid are also key points in the current technological development.

[0004] Existing smart grid technologies have achieved some key advances, such as the development of UHV AC / DC transmission technology, innovations in intelligent transmission and transformation equipment technology, and breakthroughs in the safe and stable control technology of large-scale AC / DC hybrid power grids. However, despite these advances, smart grids still face some limitations in realizing their full potential, in terms of real-time data collection, condition monitoring, anomaly detection, real-time response control, dynamic adjustment control, and strategic decision control.

[0005] In order to overcome these limitations and further improve the performance of the smart grid, the present invention proposes a smart grid adaptive protection control system and method. Summary of the invention

[0006] In view of the above-mentioned shortcomings of the prior art, an object of the present invention is to provide a smart grid adaptive protection control system and method to solve one or more problems in the prior art.

[0007] To achieve the above object, the technical solution of the present invention is as follows:

[0008] A method for adaptive protection control of a smart grid comprises the following steps:

[0009] S1: Data collection: real-time monitoring and collection of power data such as voltage, current, frequency, power, etc. at each node of the power grid, as well as operating status data of distributed power sources, energy storage systems, loads and other equipment.

[0010] In the above technical solution, through real-time data collection, the transparency and real-time nature of the power grid operation status can be ensured, providing accurate data support for subsequent monitoring, analysis and control, thereby improving the response speed and operation efficiency of the power grid.

[0011] S2: Grid status monitoring and anomaly detection: Establish a grid status monitoring model based on the collected data, analyze the collected data, and determine whether there are any abnormal or sudden conditions in the grid.

[0012] In the above technical solution, abnormal conditions in the power grid, such as overload, voltage fluctuation or frequency deviation, can be discovered in time, so that preventive measures or timely intervention can be taken to avoid potential large-scale power outages and ensure the stability and reliability of the power grid.

[0013] S3: Real-time response control, based on the droop control strategy, quickly responds to grid anomalies and adjusts the output of distributed power sources. Synchronizes the operating status of each distributed power source in the grid. Calculates and adjusts synchronization parameters based on the grid structure and operating status.

[0014] In the above technical solution, through real-time response control, the output of distributed power sources can be quickly adjusted to adapt to the immediate needs of the power grid, achieve load balancing and voltage and frequency stability, thereby improving the adaptability and anti-interference ability of the power grid.

[0015] S4: Dynamic adjustment control.

[0016] S4.1 receives the adjustment parameters of the real-time response control and the grid status information, calculates and outputs the compensation signal.

[0017] In the above technical solution, dynamic adjustment control can further refine and optimize the operating parameters of the power grid, reduce errors in power grid operation through accurate compensation signal output, and improve the operating accuracy and stability of the power grid.

[0018] S4.2 calculates the phase angles of each distributed power source and key node, and outputs a regulation signal.

[0019] In the above technical solution, by calculating and synchronizing the phase angle, the coordinated operation of various distributed power sources and key nodes in the power grid can be ensured, avoiding power loss and equipment damage caused by phase inconsistency.

[0020] S4.3 predicts grid data based on system status data and dynamically adjusts the output power of distributed power sources and energy storage systems.

[0021] In the above technical solution, predicting grid data and dynamically adjusting output power can better balance supply and demand, optimize resource allocation, improve energy utilization efficiency, and reduce operating costs.

[0022] S5: Strategic decision control, based on the real-time status of the power grid and the forecast data of S4.3, a collaborative forecasting model is established, and an intelligent decision-making algorithm is used to evaluate different operating modes and select the power grid operation mode, island operation mode or hybrid mode.

[0023] In the above technical solution, strategic decision control can intelligently select the best operation mode according to the real-time status and forecast data of the power grid, realize efficient operation of the power grid and optimal allocation of resources, and improve the power grid's ability to respond to emergencies.

[0024] In a preferred embodiment of the present invention, S1 also includes step S1.1, data preprocessing, including data cleaning, data compression, and data synchronization.

[0025] In the above technical solution, the data preprocessing step ensures the quality and consistency of the data, reduces the burden of storage and transmission, and improves the efficiency and accuracy of data processing.

[0026] In a preferred embodiment of the present invention, the anomaly detection in S2 is achieved by one or more of statistical methods, machine learning algorithms, and expert systems.

[0027] In the above technical solution, combining multiple anomaly detection methods can improve the accuracy and reliability of detection, enabling the power grid to more effectively identify and respond to various abnormal situations.

[0028] In a preferred embodiment of the present invention, the calculation method adopted in S4.1 is one or more of a proportional-integral controller, an auto-disturbance rejection controller, and a fuzzy logic control.

[0029] In the above technical solution, using multiple control methods can provide more flexibility and adaptability to adapt to different types of power grid environments and control requirements.

[0030] In a preferred embodiment of the present invention, the method used in S4.2 to calculate and synchronize the phase angle is one or more of a phase-locked loop, a synchronous detection algorithm, and a PQ decoupling conversion algorithm.

[0031] In the above technical solution, the application of multiple phase angle calculation methods improves the accuracy and robustness of power grid synchronization and ensures the stable operation of the power grid.

[0032] In a preferred embodiment of the present invention, the method used in S4.3 predicting data is one or more of renewable energy output prediction, load demand prediction, and time series analysis.

[0033] In the above technical solutions, the comprehensive use of multiple prediction methods can improve the accuracy of prediction and provide more reliable data support for the dynamic adjustment and strategic decision-making of the power grid.

[0034] In a preferred embodiment of the present invention, the intelligent decision-making algorithm in S5 is one or more of fuzzy logic control, machine learning algorithm, and genetic algorithm.

[0035] In the above technical solution, the application of intelligent decision-making algorithm improves the intelligence level of power grid operation mode selection and optimizes the operation efficiency and reliability of the power grid.

[0036] In a preferred embodiment of the present invention, S5 further includes S5.1, fault response strategy, locating the fault source using a fault diagnosis algorithm, and initiating fault area isolation measures, and reallocating loads and backup power sources according to the fault type and severity.

[0037] In the above technical solution, the implementation of the fault response strategy can quickly locate and isolate the fault area, reduce the impact of the fault on the power grid, and improve the recovery speed and safety of the power grid.

[0038] In a preferred embodiment of the present invention, S5 also includes S5.2, which optimizes the load scheduling of multiple microgrids by using genetic algorithm and particle swarm optimization based on the collaborative prediction model.

[0039] In the above technical solution, through the application of collaborative prediction models and optimization algorithms, the loads of multiple microgrids can be managed more effectively, and the energy utilization efficiency and the economy of the power grid can be improved.

[0040] To achieve the above-mentioned purpose, the second technical solution adopted by the present invention is a smart grid adaptive protection control system, which is constructed based on a smart grid adaptive protection control method.

[0041] In the above technical scheme, this technical scheme builds a comprehensive smart grid adaptive protection control system by comprehensively applying technologies such as real-time data acquisition, status monitoring, real-time response control, dynamic adjustment control and strategic decision control, which significantly improves the stability, reliability and economy of the power grid.

[0042] Compared with the prior art, the beneficial technical effects of the present invention are as follows

[0043] 1. Improve the stability and reliability of the power grid: By integrating real-time data collection, status monitoring, anomaly detection and response control technologies, this solution significantly improves the power grid's recognition and response speed to abnormal situations. By quickly and accurately detecting and locating faults, and adjusting power grid operating parameters in real time, the power grid can quickly resume normal operation, reducing the risk of power outages and power grid collapse.

[0044] (II) Optimizing the operation efficiency and economy of the power grid: Through the synergy of dynamic adjustment control and strategic decision-making control, this solution realizes the refined management of power grid operation. The system can intelligently adjust the output of distributed power sources and energy storage systems based on real-time data and forecast information, and optimize the allocation and utilization of power resources. This not only improves energy utilization efficiency and reduces energy waste, but also helps to reduce operating costs and improve the economy of the power grid.

[0045] (III) Enhance the adaptability and integration capability of the power grid to renewable energy: There is a high proportion of renewable energy facilities in distributed power sources, such as wind power and solar power. This solution improves the adaptability of the power grid to fluctuations in renewable energy through prediction models and intelligent decision-making algorithms. The system can predict the output changes of distributed energy such as wind power and solar power, and adjust the power grid operation strategy accordingly to ensure that the power grid can efficiently integrate and utilize these clean energy. It not only helps promote the green transformation of the energy structure, but also helps achieve sustainable development goals. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a schematic flow chart of the steps of a method for adaptive protection control of a smart grid according to the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present invention more clear, the following is a further detailed description of a smart grid adaptive protection control system and method proposed by the present invention in combination with the accompanying drawings and embodiments. It should be noted that the structure, proportion, size, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the limiting conditions for the implementation of the present invention, so they have no technical substantive significance. Any modification of the structure, change in the proportional relationship or adjustment of the size should still fall within the scope of the technical content disclosed by the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0048] The method for adaptive protection control of a smart grid described in the present invention comprises the following steps:

[0049] S1: Data collection: real-time monitoring and collection of power data such as voltage, current, frequency, power, etc. at each node of the power grid, as well as operating status data of distributed power sources, energy storage systems, loads and other equipment.

[0050] In the above technical solution, through real-time data collection, the transparency and real-time nature of the power grid operation status can be ensured, providing accurate data support for subsequent monitoring, analysis and control, thereby improving the response speed and operation efficiency of the power grid.

[0051] S1.1, data preprocessing, including data cleaning, data compression, and data synchronization.

[0052] In the above technical solution, the data preprocessing step ensures the quality and consistency of the data, reduces the burden of storage and transmission, and improves the efficiency and accuracy of data processing.

[0053] S2: Grid status monitoring and anomaly detection: Establish a grid status monitoring model based on the collected data, analyze the collected data, and determine whether there are any abnormal or sudden conditions in the grid.

[0054] Anomaly detection in S2 is achieved through one or more of statistical methods, machine learning algorithms, and expert systems.

[0055] Statistical methods are based on mathematical principles and identify anomalies by building a probability distribution model of data. This method is simple, intuitive, easy to understand and implement, and has high processing efficiency for large data sets. However, statistical methods usually assume that the data follows a known distribution, such as a normal distribution, which is not always true in practical applications. In addition, statistical methods may have difficulty capturing complex patterns and nonlinear relationships in the data.

[0056] Machine learning algorithms can learn from historical data and build models to automatically identify abnormal patterns. These algorithms are suitable for processing nonlinear data and complex data sets. Machine learning algorithms usually have high flexibility and accuracy. Machine learning algorithms require a large amount of labeled data for training, and the data possessed by smart grids can meet this requirement.

[0057] Expert systems simulate the decision-making process of human experts and use knowledge bases and inference rules to make intelligent decisions. However, the knowledge acquisition and knowledge representation of expert systems are difficult and require in-depth participation of domain experts. In summary, the method for monitoring anomalies is preferably based on machine learning algorithms and supplemented by statistical methods.

[0058] In the above technical solution, abnormal conditions in the power grid, such as overload, voltage fluctuation or frequency deviation, can be discovered in time, so that preventive measures or timely intervention can be taken to avoid potential large-scale power outages and ensure the stability and reliability of the power grid. Combining multiple anomaly detection methods can improve the accuracy and reliability of detection, enabling the power grid to more effectively identify and respond to various abnormal conditions.

[0059] S3: Real-time response control, based on the droop control strategy, quickly responds to grid anomalies and adjusts the output of distributed power sources. Synchronizes the operating status of each distributed power source in the grid. Calculates and adjusts synchronization parameters based on the grid structure and operating status.

[0060] The droop control strategy simulates the droop characteristics of synchronous generators to achieve automatic output adjustment of distributed power sources in response to grid load changes, thereby maintaining the voltage and frequency stability of the grid. When the grid load increases, the droop control reduces the output voltage of the distributed power sources to attract more current to meet the increased load demand, and vice versa. This strategy improves the self-regulation ability and anti-interference of the grid.

[0061] In the above technical solution, through real-time response control, the output of distributed power sources can be quickly adjusted to adapt to the immediate needs of the power grid, achieve load balancing and voltage and frequency stability, thereby improving the adaptability and anti-interference ability of the power grid.

[0062] S4: Dynamic adjustment control.

[0063] S4.1 receives the adjustment parameters of the real-time response control and the grid status information, calculates and outputs the compensation signal, wherein the calculation method adopted is one or more of the proportional integral controller, the anti-disturbance controller, and the fuzzy logic control.

[0064] Among them, the proportional-integral controller has a simple structure and is easy to implement and adjust. Through proportional and integral action, it can quickly respond to system deviations, reduce steady-state errors, and improve system stability and accuracy. The proportional-integral controller is insensitive to parameter changes and is suitable for a variety of control systems. However, the proportional-integral controller may be difficult to achieve the ideal control effect when facing complex systems, especially when the system has large time-varying or nonlinear characteristics.

[0065] The ADRC estimates and compensates for the disturbance of the system through the extended state observer, thereby improving the robustness of the system. The ADRC does not rely on the precise mathematical model of the controlled object, is suitable for handling uncertainties and external disturbances, and is suitable for complex and changing power grid environments.

[0066] Fuzzy logic control can handle imprecise and uncertain information, providing flexibility and adaptability. It simulates the human decision-making process, is easy to understand and implement, and is suitable for complex systems that are difficult to describe with traditional mathematical models. However, the accuracy and dynamic response of fuzzy controllers are not as good as model-based control strategies.

[0067] In summary, the calculation method is preferably an active disturbance rejection controller.

[0068] In the above technical solution, dynamic adjustment control can further refine and optimize the operating parameters of the power grid, reduce errors in power grid operation through accurate compensation signal output, and improve the operating accuracy and stability of the power grid.

[0069] S4.2 calculates the phase angles of each distributed power source and key node, and outputs a regulation signal.

[0070] In the above technical solution, the phase angle in three-phase alternating current is an important parameter that describes the relative position of the alternating current waveform in the power system. It is the phase difference of the voltage or current waveform. The difference in phase angle is one of the key factors for the stable operation of the power system.

[0071] By calculating and synchronizing the phase angle, the coordinated operation of each distributed power source and key nodes in the power grid can be ensured to avoid power loss and equipment damage caused by phase inconsistency. The method used to calculate and synchronize the phase angle is one or more of a phase-locked loop, a synchronous detection algorithm, and a PQ decoupling conversion algorithm.

[0072] The phase-locked loop is an electronic circuit used to synchronize signals and can accurately track the phase changes of the power grid. It has fast dynamic response and good anti-interference performance, and can ensure the synchronous operation of distributed power sources and the main power grid.

[0073] The synchronization detection algorithm extracts key information from the signal and corrects errors and noise, thereby achieving efficient transmission and interpretation of data and ensuring timing synchronization in data transmission.

[0074] The PQ decoupling conversion method is a method that controls active and reactive power separately, which can improve the stability and efficiency of the power system. It effectively controls the frequency and voltage by controlling active power and reactive power, reduces the complexity of the system, and improves the reliability of the system. Its implementation requires accurate digital modeling of the power system, which can be achieved using the grid status monitoring model established in S2.

[0075] In summary, the method for calculating and synchronizing the phase angle is to use a phase-locked loop for preliminary synchronization, then perform fine-tuning through a synchronization detection algorithm, and finally use a PQ decoupling conversion algorithm for long-term stability control.

[0076] In the above technical solution, the application of multiple phase angle calculation methods improves the accuracy and robustness of power grid synchronization and ensures the stable operation of the power grid.

[0077] S4.3 Predict the grid data based on the system status data and dynamically adjust the output power of the distributed power source and energy storage system. The prediction data adopts one or more methods of renewable energy output prediction, load demand prediction, and time series analysis.

[0078] Renewable energy output forecasting is used to predict the power generation output of renewable energy sources such as wind and solar, taking into account weather patterns, seasonal changes and historical power generation data, which can improve the grid's ability to adapt to fluctuations in renewable energy.

[0079] Load demand forecasting predicts future electricity demand by analyzing historical electricity consumption data, economic growth trends, seasonal factors and weather changes. This approach helps grid operators prepare in advance to ensure that electricity supply meets demand and avoids under- or oversupply.

[0080] Time series analysis uses historical data points to predict future data trends and is applicable to data sets with obvious time dependencies. It can reveal trends, periodicity, and seasonality in the data, providing a basis for predicting future changes.

[0081] In summary, the method of forecasting data is to use time series analysis for long-term trend forecasting, renewable energy output forecasting for medium-term scheduling, and load demand forecasting for short-term and immediate adjustments.

[0082] In the above technical solutions, the comprehensive use of multiple prediction methods can improve the accuracy of prediction and provide more reliable data support for the dynamic adjustment and strategic decision-making of the power grid. Predicting power grid data and dynamically adjusting output power can better balance the supply and demand relationship, optimize resource allocation, improve energy utilization efficiency, and reduce operating costs.

[0083] S5: Strategic decision control, based on the real-time status of the power grid and the forecast data of S4.3, a collaborative forecasting model is established, and an intelligent decision-making algorithm is used to evaluate different operating modes and select the power grid operation mode, island operation mode or hybrid mode.

[0084] In the grid operation mode, the microgrid is connected to the main grid and can exchange power with each other. The operation of the microgrid is controlled by the frequency and voltage of the main grid, and usually does not require independent stability control equipment;

[0085] The island operation mode refers to the mode in which the microgrid is disconnected from the main grid for some reason and operates independently. At this time, the microgrid must rely on its own control equipment to maintain the stability of voltage and frequency to ensure the power supply of internal loads.

[0086] The intelligent decision-making algorithm in S5 is one or more of fuzzy logic control, machine learning algorithm, and genetic algorithm.

[0087] Fuzzy logic control does not rely on precise mathematical models, can handle uncertainty and ambiguity, has strong adaptability and is easy to implement.

[0088] Machine learning algorithms are able to learn patterns from large amounts of data and are applicable to complex nonlinear systems with high flexibility and accuracy.

[0089] Genetic algorithm is an optimization algorithm suitable for global optimization problems and has good search ability and robustness.

[0090] Genetic algorithms can handle complex optimization problems and find global optimal solutions, which is crucial for load dispatch optimization. At the same time, genetic algorithms can provide powerful search capabilities when looking for the best grid operation mode or island operation mode, ensuring that the grid can operate efficiently and stably under various conditions.

[0091] In summary, the optimal intelligent decision-making algorithm is a genetic algorithm.

[0092] S5.1, Fault response strategy, uses fault diagnosis algorithm to locate the fault source and initiates fault area isolation measures. Reallocate load and backup power according to fault type and severity.

[0093] Fault diagnosis algorithms are technologies used in smart grids to quickly identify and locate grid faults. These algorithms analyze grid operation data and help the system respond promptly when anomalies occur to maintain grid stability and reliability.

[0094] In the above technical solution, the implementation of the fault response strategy can quickly locate and isolate the fault area, reduce the impact of the fault on the power grid, and improve the recovery speed and safety of the power grid.

[0095] S5.2, based on the collaborative prediction model, genetic algorithm and particle swarm optimization are used to optimize the load scheduling of multiple microgrids.

[0096] Genetic algorithms simulate the process of natural selection, have good global search capabilities, and can effectively avoid falling into local optimal solutions. They are suitable for complex optimization problems and do not require gradient information of the problem, so they are suitable for many types of optimization problems.

[0097] The particle swarm optimization algorithm is inspired by the social behavior of bird flocks. It is simple, easy to implement, and performs well in many continuous optimization problems. The particle swarm optimization algorithm can quickly find the approximate optimal solution to the problem through collaboration and information sharing between particles.

[0098] The collaborative forecasting model improves the stability and accuracy of the forecast by integrating the outputs of multiple forecasting models. This approach can reduce the bias and uncertainty that may exist in a single model. When the collaborative forecasting model is combined with genetic algorithms and particle swarm optimization, the search capabilities of these optimization algorithms can be used to select and adjust the weights of multiple forecasting models to achieve the best forecasting effect, thereby providing more accurate data support for load scheduling.

[0099] In the above technical solution, through the application of collaborative prediction models and optimization algorithms, the loads of multiple microgrids can be managed more effectively, and the energy utilization efficiency and the economy of the power grid can be improved.

[0100] In the above technical solutions, the application of intelligent decision-making algorithms improves the intelligence level of grid operation mode selection and optimizes grid operation efficiency and reliability. Strategic decision control can intelligently select the best operation mode based on the real-time status and forecast data of the grid, realize efficient operation of the grid and optimal allocation of resources, and improve the grid's ability to respond to emergencies.

[0101] To achieve the above-mentioned purpose, the second technical solution adopted by the present invention is a smart grid adaptive protection control system, which is constructed based on a smart grid adaptive protection control method.

[0102] Real-time response control, dynamic adjustment control, and strategic decision control respectively respond to requirements of different time scales and complexities.

[0103] Real-time control usually has the fastest response speed. It is based on preset rules and algorithms and makes adjustments directly to the immediate abnormal or unbalanced conditions of the power grid.

[0104] Dynamic adjustment control further refines the grid parameters based on real-time control. It uses more complex anti-disturbance controller algorithms to eliminate frequency and voltage errors that cannot be completely eliminated in real-time control and optimize the overall operation performance of the grid. Dynamic adjustment control considers a relatively long time scale, but still needs to maintain a fast response speed to cope with continuous changes in the grid.

[0105] Strategic decision control is the highest level of control, focusing on long-term grid operation optimization and strategic decision-making. Based on real-time data and forecast information, strategic decision control uses intelligent decision-making algorithms to evaluate the pros and cons of different operation modes and intelligently selects grid mode, island operation mode or hybrid operation mode. The decision-making process at this level of control is more complex, but it is critical to ensure the economy, safety and reliability of the grid.

[0106] In the above technical scheme, this technical scheme builds a comprehensive smart grid adaptive protection control system by comprehensively applying technologies such as real-time data acquisition, status monitoring, real-time response control, dynamic adjustment control and strategic decision control, which significantly improves the stability, reliability and economy of the power grid.

[0107] Example

[0108] The method for adaptive protection control of a smart grid described in the present invention comprises the following steps:

[0109] S1: Data collection: real-time monitoring and collection of power data such as voltage, current, frequency, power, etc. at each node of the power grid, as well as operating status data of distributed power sources, energy storage systems, loads and other equipment.

[0110] S1.1, data preprocessing, including data cleaning, data compression, and data synchronization.

[0111] S2: Grid status monitoring and anomaly detection: Establish a grid status monitoring model based on the collected data, analyze the collected data, and determine whether there are any abnormal or sudden conditions in the grid.

[0112] The method for monitoring anomalies is preferably based on machine learning algorithms and supplemented by statistical methods.

[0113] S3: Real-time response control, based on the droop control strategy, quickly responds to grid anomalies and adjusts the output of distributed power sources. Synchronizes the operating status of each distributed power source in the grid. Calculates and adjusts synchronization parameters based on the grid structure and operating status.

[0114] S4: Dynamic adjustment control.

[0115] S4.1 receives the adjustment parameters of the real-time response control and the grid status information, calculates and outputs the compensation signal, wherein the calculation method adopted is the active disturbance rejection controller.

[0116] S4.2 calculates the phase angles of each distributed power source and key node, and outputs a regulation signal.

[0117] The method for calculating and synchronizing the phase angle is to use a phase-locked loop for preliminary synchronization, then perform fine-tuning through a synchronization detection algorithm, and finally use a PQ decoupling conversion algorithm for long-term stability control.

[0118] S4.3 predicts grid data based on system status data and dynamically adjusts the output power of distributed power sources and energy storage systems. The method used for predicting data uses time series analysis for long-term trend prediction, renewable energy output prediction for medium-term scheduling, and load demand prediction for short-term and immediate adjustments.

[0119] S5: Strategic decision control, based on the real-time status of the power grid and the forecast data of S4.3, a collaborative forecasting model is established, and an intelligent decision-making algorithm is used to evaluate different operating modes and select the power grid operation mode, island operation mode or hybrid mode.

[0120] The intelligent decision-making algorithm is genetic algorithm.

[0121] S5.1, Fault response strategy, uses fault diagnosis algorithm to locate the fault source and initiates fault area isolation measures. Reallocate load and backup power according to fault type and severity.

[0122] S5.2, based on the collaborative prediction model, genetic algorithm and particle swarm optimization are used to optimize the load scheduling of multiple microgrids.

[0123] The smart grid adaptive protection control system described in the present invention is constructed based on a smart grid adaptive protection control method.

[0124] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A method for adaptive protection control of a smart grid, characterized in that The following steps are included: S1: Data collection, real-time monitoring and collection of power data such as voltage, current, frequency, power, etc. at each node of the power grid, as well as operating status data of distributed power sources, energy storage systems, loads, etc. S2: Grid status monitoring and anomaly detection: Establish a grid status monitoring model based on the collected data, analyze the collected data, and determine whether there are abnormal or sudden conditions in the grid; S3: Real-time response control, based on the droop control strategy, quickly responds to grid anomalies and adjusts the output of distributed power sources; synchronizes the operating status of each distributed power source in the grid; calculates and adjusts synchronization parameters according to the grid structure and operating status; S4: Dynamic adjustment control, S4.1 receives the adjustment parameters of the real-time response control and the grid status information, calculates and outputs the compensation signal; S4.2 calculates the phase angles of each distributed power source and key node, and outputs a regulation signal; S4.3 predicts grid data based on system status data and dynamically adjusts the output power of distributed power sources and energy storage systems; S5: Strategic decision control, based on the real-time status of the power grid and the forecast data of S4.3, a collaborative forecasting model is established, and an intelligent decision-making algorithm is used to evaluate different operating modes and select the power grid operation mode, island operation mode or hybrid mode.

2. A method for adaptive protection control of a smart grid as claimed in claim 1, characterized in that: S1 also includes step S1.1, data preprocessing, including data cleaning, data compression, and data synchronization.

3. The method for adaptive protection control of a smart grid according to claim 1, characterized in that: Anomaly detection in S2 is achieved through one or more of statistical methods, machine learning algorithms, and expert systems.

4. The method for adaptive protection control of a smart grid according to claim 1, characterized in that: The calculation method used in S4.1 is one or more of a proportional-integral controller, an auto-disturbance rejection controller, and a fuzzy logic control.

5. The method for adaptive protection control of a smart grid according to claim 1, characterized in that: S4.2 The method used to calculate and synchronize the phase angle is one or more of a phase-locked loop, a synchronous detection algorithm, and a PQ decoupling conversion algorithm.

6. The method for adaptive protection control of a smart grid according to claim 1, characterized in that: S4.3 The method used for forecasting data is one or more of renewable energy output forecasting, load demand forecasting, and time series analysis.

7. The method for adaptive protection control of a smart grid according to claim 1, characterized in that: The intelligent decision-making algorithm in S5 is one or more of fuzzy logic control, machine learning algorithm, and genetic algorithm.

8. The method for adaptive protection control of a smart grid according to claim 1, characterized in that: S5 also includes S5.1, fault response strategy, which uses fault diagnosis algorithms to locate the source of the fault and initiate fault area isolation measures; reallocate loads and backup power sources according to the type and severity of the fault.

9. A method for adaptive protection control of a smart grid as claimed in claim 8, characterized in that: S5 also includes S5.2, which uses genetic algorithm and particle swarm optimization to optimize the load scheduling of multiple microgrids based on the collaborative prediction model.

10. A smart grid adaptive protection control system, characterized in that: A method for adaptive protection control of a smart grid comprising the steps of any one of claims 1 to 9.

Images