Power quality control method and system based on distributed power system

Abstract

The invention discloses an electric energy quality control method and system based on a distributed electric power system, and relates to the technical field of electric energy quality control, and the method comprises the following steps: obtaining an initial micro-grid topological structure and key features of each node, constructing an electric energy quality index model, and judging whether to carry out topological control or not; solving and converting the initial microgrid topological structure into a simplest topological structure based on a Prim algorithm, and recording a residual edge set; sorting the residual edge sets based on a neural network scoring model, and screening the residual edge sets according to system computing power; reconstructing the simplest topological structure based on the screened residual edge set to obtain a to-be-controlled topological structure set; and obtaining an optimal micro-grid topological structure in the topological structure set based on the electric energy quality index model, comparing the optimal micro-grid topological structure with the initial micro-grid topological structure to obtain a control instruction, and realizing efficient topological reconstruction control of the distributed power system micro-grid so as to regulate and control the electric energy quality.

Description

Technical Field

[0001] The present invention relates to the technical field of power quality control, and more particularly to a power quality control method and system based on a distributed power system. Background Art

[0002] With the development of distributed energy systems, microgrids have gradually become a vital component of power systems. However, due to issues such as unstable distributed power output, frequent node failures, and severe load fluctuations, power quality can easily deteriorate. This is especially pronounced when microgrids operate in islanded mode, manifesting as voltage offsets, frequency fluctuations, and harmonic distortion. Most existing control methods for microgrid topologies are relatively rigid. When power quality issues arise, traditional methods can only switch the microgrid topology through preset rules or manual operations. However, these methods are unable to dynamically assess which topology is most beneficial for power quality, and may even result in unnecessary operations or failures during the switching process.

[0003] For example, the invention patent publication number CN108363306A discloses a method for determining parameters of a microgrid distributed controller based on linear quadratic optimization. This method establishes a microgrid small-signal model based on droop control to achieve reactive power sharing and average voltage recovery. The microgrid small-signal model is converted into multiple single-input, single-output sub-models corresponding to each distributed power source. A distributed output feedback controller and a linear quadratic optimization objective function are designed. A stable feedback controller is selected, and the rate of change of the linear quadratic optimization objective function with respect to the feedback controller is calculated. The feedback controller is improved based on the rate of change, so that the quadratic optimization performance of the improved controller is better than that of the controller before the improvement, thereby obtaining a locally optimal distributed controller. This method designs a microgrid distributed controller based on a linear quadratic optimization strategy, achieves reactive power sharing and average voltage recovery in the microgrid, and thus improves the overall power quality of the microgrid.

[0004] For example, the invention patent announcement with the announcement number CN118054427A discloses an operation control method for a unified power quality conditioner. The present invention provides an operation control method for a unified power quality conditioner, and the operation control method includes: establishing an electrical property value vector diagram of a topology system; establishing a multi-objective optimization problem of a topology system based on the electrical property value vector diagram, and converting the multi-objective optimization problem into a comprehensive single-objective optimization problem according to preset constraints; determining several groups of weight combinations, and obtaining a solution to the comprehensive single-objective optimization problem according to the several groups of weight combinations; determining a fitness function, selecting the optimal solution under the comprehensive single-objective optimization problem according to the fitness function, and determining the optimal weight coefficient under the current training condition according to the optimal solution; selecting several training conditions as input and the corresponding optimal weight coefficient as output, repeating the above steps for training, obtaining a target proxy model, and controlling the operation of the topology system in real time through the target proxy model. The operation control method for a unified power quality conditioner provided by the present invention improves the stability and flexibility of system operation.

[0005] The above disclosed technical solutions have at least the following technical problems: When faced with abnormal power quality or local faults, the system topology structure mostly relies on manual judgment or preset rule switching, and lacks a data-driven adaptive optimization mechanism. This has little impact on the power quality of conventional power systems, but the power quality of distributed power systems' microgrid island mode itself fluctuates greatly, which further exacerbates the problem of poor power quality in island mode.

[0006] In view of the above problems, the present invention proposes a solution. Summary of the Invention

[0007] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a power quality control method and system based on a distributed power system. By constructing a node state vector, a power quality index model and a topology structure optimization control mechanism, dynamic evaluation of microgrid power quality and adaptive topology reconstruction are realized to solve the problem in the prior art of microgrids in island mode that topology switching relies on preset rules or manual judgment, response lags, and optimization effect is poor, making it difficult to ensure stable power quality in island mode.

[0008] To achieve the above object, the present invention provides the following technical solutions: The power quality control method based on a distributed power system includes the following steps: obtaining the key features of the initial microgrid topology and each of its nodes, constructing a power quality index model and determining whether to perform topology control; converting the initial microgrid topology into a simplest topology based on the Prim algorithm and recording the remaining edge sets; sorting the remaining edge sets based on a neural network scoring model and screening the remaining edge sets according to the system computing power; reconstructing the simplest topology based on the screened remaining edge sets to obtain a set of topologies to be controlled; obtaining the optimal microgrid topology in the topology set based on the power quality index model and comparing it with the initial microgrid topology to obtain control instructions.

[0009] In a preferred embodiment, the method of obtaining the key features of the initial microgrid topology and each node thereof, constructing a power quality index model and determining whether to perform topology control specifically comprises: obtaining the key features of each node of the initial microgrid topology; concatenating the key features of each node into a node state vector in the same order, and calculating the key feature deviation between the node state vector and a preset reference index; training the power quality index model based on a convolutional neural network according to the key feature deviation, outputting a power quality deviation value, and determining whether to perform topology control based on the power quality deviation value.

[0010] In a preferred embodiment, the Prim algorithm is used to solve and convert the initial microgrid topology structure into the simplest topology structure, and the remaining edge set is recorded. Specifically, state constraints are established, and nodes corresponding to key feature deviations that do not meet the state constraints are treated as abnormal nodes, and are removed from the initial microgrid topology structure to obtain a first microgrid topology structure, which includes an edge set; the first microgrid topology structure is solved based on the Prim algorithm to obtain a minimum spanning tree as the simplest topology structure; and the portion of the edge set in the edge set in the first microgrid topology structure that does not belong to the simplest topology structure is recorded as the remaining edge set.

[0011] In a preferred embodiment, the remaining edge sets are sorted based on the neural network scoring model, specifically: edge feature vectors are constructed based on the key features of each node and the distances between edges between nodes; an edge weight scoring model is constructed based on the neural network scoring model according to the historical edge feature vectors, the edge scoring value is output, and the remaining edge sets are sorted and updated.

[0012] In a preferred embodiment, the filtering of the remaining edge set according to the system computing power is specifically as follows: obtaining the system computing power status information, constructing a system computing power margin index based on a linear weighted model; obtaining the number of preferred edges according to the system computing power margin index, and constructing the remaining edge set after filtering based on the remaining edges corresponding to the number of preferred edges before filtering.

[0013] In a preferred embodiment, the simplest topological structure is reconstructed based on the remaining edge set after screening to obtain a set of topological structures to be controlled. Specifically, when the system simulates topological reconstruction, an upper limit on the number of remaining edges that can be added at a single time is set as the maximum limit on the number of edges; in each round of topological reconstruction, edges that do not exceed the maximum limit on the number of edges are selected from the remaining edge set after screening, and are combined with the simplest topological structure to generate several topological structures to be controlled, constituting the set of topological structures to be controlled.

[0014] In a preferred embodiment, the method of obtaining the optimal microgrid topology in the topology set based on the power quality index model is specifically as follows: based on the power quality index model, the power quality deviation value of each topology to be controlled in the topology set to be controlled is calculated and sorted to obtain the minimum power quality deviation value; and the topology corresponding to the minimum power quality deviation value is selected as the optimal topology.

[0015] In a preferred embodiment, the control instructions are obtained by comparing the initial microgrid topology with the edge sets of the optimal topology, determining the edge sets to be disconnected and the edge sets to be closed; sorting the disconnection and closing operations based on load importance and edge priority, and generating corresponding disconnection and closing instructions as control instructions.

[0016] The system of the power quality control method based on the distributed power system includes: a state perception module, which obtains the key features of the initial microgrid topology and its nodes, constructs a power quality index model and determines whether to perform topology control; a simplest topology generation module, which converts the initial microgrid topology into the simplest topology based on the Prim algorithm and records the remaining edge sets; an edge scoring and screening module, which sorts the remaining edge sets based on the neural network scoring model and screens the remaining edge sets according to the system computing power; a topology construction module, which reconstructs the simplest topology based on the screened remaining edge sets to obtain a set of topology structures to be controlled; and an optimal decision control module, which obtains the optimal microgrid topology in the topology set based on the power quality index model and compares it with the initial microgrid topology to obtain control instructions.

[0017] The technical effects and advantages of the power quality control method based on distributed power system of the present invention are as follows: 1. By constructing a power quality index model and combining it with the simplest topology structure extraction and dynamic edge set update mechanism, the present invention realizes real-time perception and analysis of key characteristics of microgrids, thereby improving the accuracy of power quality anomaly identification and the scientific nature of topology optimization control decision-making.

[0018] 2. The present invention introduces the joint control of neural network scoring and system computing power margin to dynamically generate and screen the optimal edge set, ensuring that the topology structure reconstruction not only has the benefit of improving power quality, but also meets the computing power feasibility and system stability requirements, thereby realizing an efficient and robust topology control strategy. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 The figure is a flow chart of the power quality control method based on a distributed power system according to the present invention.

[0020] Figure 2 It is a structural diagram of the power quality control system based on the distributed power system of the present invention.

[0021] Figure 3 This is a time period curve diagram of the total deviation value of power quality based on the distributed power system of the present invention. DETAILED DESCRIPTION

[0022] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0023] Example 1, Figure 1 The present invention provides a power quality control method based on a distributed power system, comprising the following steps: S1, obtain the initial microgrid topology and key features of each node, build a power quality index model and determine whether to perform topology control; The acquisition of the initial microgrid topology and key features of each node, the construction of a power quality index model and the determination of whether to perform topology control are specifically as follows: Obtain key features of each node in the initial microgrid topology; The key features of each node are spliced into a node state vector in the same order, and the key feature deviation is calculated by comparing the node state vector with the preset reference index; According to the key feature deviation, a power quality index model is trained based on a convolutional neural network, and a power quality deviation value is output. Based on the power quality deviation value, it is determined whether topology control should be performed.

[0024] It should be noted that the key features include real-time voltage value, real-time frequency value and real-time harmonic distortion rate; It should be noted that the node state vector is represented as follows:

[0025] Where, is the node state vector corresponding to node i, is the voltage value of node i, is the frequency value of node i, is the harmonic distortion rate of node i.

[0026] It should be noted that the preset reference indicators include a reference voltage of 220V, a reference frequency of 60Hz and a reference harmonic distortion rate of 3%; It should be noted that the key characteristic deviations include voltage deviation, frequency deviation and harmonic distortion rate deviation of each node; It should be noted that in the above steps, the following is an overview of the calculation: The specific calculation formula of the power quality index model is:

[0027] Where, is the power quality deviation value, is the number of nodes in the microgrid, is the voltage value of node i, is the reference voltage, is the frequency value of node i, is the reference frequency, is the harmonic distortion rate of node i, is the reference harmonic distortion rate, is the absolute voltage deviation, is the absolute frequency deviation, is the harmonic distortion rate deviation, is the voltage deviation, is the frequency deviation, is the weight of the voltage deviation, is the weight of the frequency deviation, is the weight of the harmonic distortion rate deviation.

[0028] It should be noted that 、 and All are set according to the priority and sensitivity of the system to meet , which is usually chosen empirically and optimized through simulation and historical data; It should be noted that the determination of whether to perform topology control based on the power quality deviation value is specifically as follows: When the power quality deviation value is greater than the preset power quality deviation threshold, it is determined to switch the topology structure; otherwise, the initial microgrid topology structure remains unchanged and the process ends.

[0029] It should be noted that the power quality deviation value is the output result of the power quality index model and is used to evaluate the quality of node power. The smaller the power quality deviation value, the better the power quality; the larger the power quality deviation value, the worse the power quality. It should be noted that the specific steps for obtaining the preset power quality deviation threshold are: Based on experience, the maximum allowable voltage deviation is set to 7% (0.07), the maximum allowable frequency deviation is set to 0.2Hz, and the maximum allowable harmonic distortion (THD) deviation is set to 5% (0.05); The preset power quality deviation threshold is:

[0030] Where, To preset the power quality deviation threshold, is the weight of the voltage deviation, is the weight of the frequency deviation, is the weight of harmonic distortion rate deviation; It should be noted that for the same node, the preset power quality deviation threshold Power quality deviation value The weight of the voltage deviation, the weight of the frequency deviation, and the weight of the harmonic distortion rate deviation used are consistent.

[0031] S2, based on Prim’s algorithm, solves and transforms the initial microgrid topology into the simplest topology and records the remaining edge set; The Prim algorithm is used to solve the problem of converting the initial microgrid topology into the simplest topology and record the remaining edge sets, specifically: Establishing state constraints, treating nodes corresponding to key feature deviations that do not satisfy the state constraints as abnormal nodes, and removing them from the initial microgrid topology to obtain a first microgrid topology, wherein the first microgrid topology includes an edge set; The first microgrid topology is solved based on Prim's algorithm, and the minimum spanning tree is obtained as the simplest topology; The portion of the edge set in the first microgrid topology structure that does not belong to the simplest topology structure is recorded as a remaining edge set.

[0032] It should be noted that the state constraints are:

[0033] Where, is the voltage deviation, is the frequency deviation, is the voltage value of node i, is the reference voltage, is the frequency value of node i, is the reference frequency, The voltage tolerance is set based on experience. , The frequency tolerance is set based on experience. , is the harmonic distortion rate deviation of node i, is the maximum value of harmonic distortion rate deviation, which is set to 5% based on experience; It should be noted that the minimum spanning tree is used as the simplest topology structure to ensure the basic power supply connectivity of the microgrid; S3, sorts the remaining edge sets based on the neural network scoring model and filters the remaining edge sets based on the system computing power; The remaining edge sets are sorted based on the neural network scoring model, specifically: Construct edge feature vectors based on the key features of each node and the distances between each edge of the nodes; According to the historical edge feature vectors, an edge weight scoring model is constructed based on the neural network scoring model, the edge score value is output, and the remaining edge set is sorted and updated.

[0034] It should be noted that the specific steps for constructing the edge feature vector are: Calculate the voltage difference between each node as the corresponding edge voltage value; Calculate the frequency value difference between each node as the corresponding edge frequency value; Calculate the voltage total harmonic distortion rate difference between each node as the corresponding side voltage total harmonic distortion rate; The edge voltage value, edge frequency value, edge voltage total harmonic distortion rate and the distance between each edge of the nodes are arranged in order to obtain the edge eigenvector.

[0035] It should be noted that in the above steps, the following is an overview of the calculation: The specific formula for the edge voltage value is:

[0036] The specific formula for the edge frequency value is:

[0037] The specific formula for the total harmonic distortion rate of the side voltage is:

[0038] The edge eigenvector is specifically expressed as:

[0039] The edge weight scoring model is specifically:

[0040] Where, is the edge voltage between node i and node j, is the voltage value of node i, is the edge frequency value between node i and node j, is the frequency value of node j, is the total harmonic distortion rate of the edge voltage between node i and node j, is the total harmonic distortion rate of the voltage at node i, is the edge eigenvector, is the line distance between node i and node j, is the edge score value, Scoring models for neural networks.

[0041] It should be noted that is the edge score value, which is the result output by the edge weight scoring model. ,The higher the edge score value indicates that the edge is more suitable for ,topology reconstruction; Furthermore, sorting the remaining edge sets based on the neural network scoring model and filtering the remaining edge sets based on the system computing power has the following advantages: Achieve coordinated control of power quality optimization and system computing power utilization: The neural network scoring model is trained based on edge feature vectors, which can effectively identify edges that have a positive impact on power quality and prioritize their retention; the system computing power margin indicator dynamically limits the number of edges based on the current computing power status, ensuring that the optimization control process runs efficiently within the system's processing range, achieving dual guarantees of performance and efficiency.

[0042] Improving the real-time performance and engineering applicability of topology reconstruction strategies: By controlling the size of the combination in the screening stage, the computational complexity of topology reconstruction can be significantly reduced, avoiding the computational delay caused by excessive combinations, and helping to improve the response speed and deployment feasibility of the reconstruction strategy in actual microgrid systems.

[0043] Enhance the system's adaptability and robustness to complex operating scenarios: The joint mechanism can dynamically adjust the edge set screening strategy based on the system's operating status and external disturbances to adapt to typical scenarios such as load fluctuations, changes in power access, or local failures, thereby improving the stability and adaptability of topology optimization under variable operating conditions.

[0044] Suppressing the risk of combinatorial explosion and improving reconstruction decision-making efficiency: In topology optimization, the number of candidate edge combinations grows exponentially. Through the dual mechanisms of scoring and sorting and computing power screening, the solution space is effectively narrowed, ineffective calculations and resource waste are avoided, and the speed and effectiveness of the decision-making process are improved.

[0045] Promote the intelligent and data-driven evolution of microgrid control: The scoring model has learning capabilities and can continuously optimize the edge weight judgment logic as operating data accumulates, providing key support for building an intelligent microgrid control system with self-learning and self-adaptive capabilities.

[0046] The remaining edge sets are screened according to the system computing power, specifically: Obtain system computing power status information and construct system computing power margin indicators based on a linear weighted model; The number of preferred edges is obtained according to the system computing power margin indicator, and the remaining edges corresponding to the number of preferred edges before screening are used to construct the remaining edge set after screening.

[0047] It should be noted that the system computing power status information includes the CPU idle rate, memory remaining rate, and the time consumed by the topology optimization in the previous cycle; It should be noted that the specific steps for obtaining the preferred number of edges are as follows: Set the relationship between the system computing power margin index range and the number of preferred edges; Based on the specific value range of the system computing power margin indicator and the relationship between the system computing power margin indicator range and the number of preferred edges, find the maximum number of preferred edges that the system can process within the range. It should be noted that in the above steps, the following is an overview of the calculation: The specific calculation formula for the system computing power margin index is:

[0048] The relationship between the system computing power margin index range and the number of preferred edges is as follows:

[0049] Where, is the system computing power margin indicator, is the system CPU idle rate, is the remaining rate of system memory, The time taken for the topology optimization system in the previous cycle, is the empirical weight of the CPU idle rate, is the empirical weight of the system memory remaining rate, is the empirical weight of the time consumed by the topology optimization system in the previous cycle, The number of preferred edges that can be added to the current system.

[0050] S4, reconstructing the simplest topological structure based on the remaining edge set after screening to obtain the set of topological structures to be controlled; The simplest topological structure is reconstructed based on the remaining edge set after screening to obtain a set of topological structures to be controlled, specifically: When the system simulates topology reconstruction, set the upper limit of the number of remaining edges that can be added at a time as the maximum limit on the number of edges; During each round of topology reconstruction simulation, edges not exceeding the maximum limit are selected from the remaining edge set after screening, and are combined with the simplest topological structure to generate several topological structures to be controlled, forming a set of topological structures to be controlled.

[0051] It should be noted that the maximum number of edges is determined based on the upper limit of the number of remaining edges that can be added to the system at one time, and the upper limit of the number of remaining edges that can be added at one time is set based on the operational stability requirements during the reconstruction of the microgrid topology structure. It can be set comprehensively based on the system's historical operating data, power quality fluctuation threshold and electrical safety margin factors.

[0052] Furthermore, when the system simulates topology reconstruction, setting an upper limit on the number of remaining edges that can be added at a time as the maximum limit on the number of edges has the following advantages: Controlling the amplitude of topology adjustments: By limiting the number of newly added edges in each round of topology reconstruction, it is possible to effectively avoid excessive topology changes at one time, thereby reducing the risk of power quality fluctuations caused by structural mutations. Ensure system operation stability: Gradually introducing edge connections helps maintain the stability of key parameters such as voltage, current, and frequency during microgrid operation, preventing abnormal phenomena such as local overload, harmonic accumulation, or islanding effects; Enhanced controllability and observability of the reconfiguration process: Round-by-round, phased topology adjustments facilitate evaluation of power quality trends at each stage, enabling the control system to more accurately intervene in optimized control decisions. Reduce system computational complexity: By limiting the search space for edge combinations, the number of candidate topologies in each round is effectively reduced, improving the system's ability to perform real-time optimization and control decisions under limited computing power; Facilitates coordinated optimization with the power quality assessment model: Introducing only a small amount of structural changes in each round facilitates clearer analysis of the impact of specific edges on power quality indicators, improving the response accuracy and guiding value of the assessment model.

[0053] S5, based on the power quality index model, the optimal microgrid topology in the topology set is obtained and compared with the initial microgrid topology to obtain a control instruction.

[0054] The method of obtaining the optimal microgrid topology in the topology set based on the power quality index model is specifically as follows: Calculate the power quality deviation value of each topology to be controlled in the set of topology structures to be controlled based on the power quality index model and sort them to obtain the minimum power quality deviation value; The topology corresponding to the minimum power quality deviation value is selected as the optimal topology.

[0055] The control instructions are obtained by comparing the initial microgrid topology structure, specifically: By comparing the edge sets of the initial microgrid topology and the optimal topology, the edge sets that need to be disconnected and the edge sets that need to be closed are determined; The opening and closing operations are sorted based on load importance and edge priority, and corresponding opening and closing instructions are generated as control instructions.

[0056] It should be noted that the importance of the loads is divided according to the power supply security requirements of the area in which they are located; areas such as medical institutions and data centers that have extremely high requirements for power supply continuity are set as high-level load areas, and their power supply must be guaranteed first; commercial areas, office areas, etc. are set as medium-level load areas, and their priority is lower than that of high-level loads when power resources are limited; residential lighting, etc. are set as low-level load areas, and a certain degree of power supply interruption or delay can be tolerated in extreme cases; It should be noted that the edge priority is divided according to the functional type of the edge: the backbone edge connecting the high-level load area or important substation node is set as the high priority edge; the edge connecting the ordinary load area is set as the medium priority edge; the backup or redundant edge that is only enabled in the event of a fault, maintenance or emergency is set as the low priority edge; Figure 2 The system of the power quality control method based on the distributed power system of the present invention includes: The state perception module obtains the initial microgrid topology and key features of each node, builds a power quality index model, and determines whether to perform topology control; The simplest topology generation module converts the initial microgrid topology into the simplest topology based on the Prim algorithm and records the remaining edge sets; The edge scoring and screening module sorts the remaining edge sets based on the neural network scoring model and screens the remaining edge sets based on the system computing power; The topology construction module reconstructs the simplest topology structure based on the remaining edge set after screening to obtain the set of topology structures to be controlled; The optimal decision control module obtains the optimal microgrid topology in the topology set based on the power quality index model and compares it with the initial microgrid topology to obtain control instructions.

[0057] Figure 3 The curve change trend of the total power quality deviation value in each time period of the power quality index model of the present invention is given; the power quality index model includes voltage deviation, frequency deviation, THD deviation and total power quality deviation value, reflecting that the change of the total power quality deviation value curve is determined by the combined influence of voltage deviation, frequency deviation and THD deviation; The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0058] The above embodiments may be implemented in whole or in part through software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0059] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0060] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0061] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0062] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A power quality control method based on a distributed power system, characterized in that: The steps include: Obtain the initial microgrid topology and key features of each node, build a power quality index model, and determine whether to perform topology control; Based on Prim's algorithm, the initial microgrid topology is converted into the simplest topology and the remaining edge sets are recorded. Sort the remaining edge sets based on the neural network scoring model and filter the remaining edge sets based on the system computing power; Reconstruct the simplest topological structure based on the remaining edge set after screening to obtain the set of topological structures to be controlled; Based on the power quality index model, the optimal microgrid topology in the topology set is obtained and compared with the initial microgrid topology to obtain the control instructions.

2. The power quality control method based on a distributed power system according to claim 1, characterized in that: The acquisition of the initial microgrid topology and key features of each node, the construction of a power quality index model and the determination of whether to perform topology control are specifically as follows: Obtain key features of each node in the initial microgrid topology; The key features of each node are spliced into a node state vector in the same order, and the key feature deviation is calculated by comparing the node state vector with the preset reference index; According to the key feature deviation, a power quality index model is trained based on a convolutional neural network, and a power quality deviation value is output. Based on the power quality deviation value, it is determined whether topology control should be performed.

3. The power quality control method based on a distributed power system according to claim 2, characterized in that: The Prim algorithm is used to solve the problem of converting the initial microgrid topology into the simplest topology and record the remaining edge sets, specifically: Establishing state constraints, treating nodes corresponding to key feature deviations that do not satisfy the state constraints as abnormal nodes, and removing them from the initial microgrid topology to obtain a first microgrid topology, wherein the first microgrid topology includes an edge set; The first microgrid topology is solved based on Prim's algorithm, and the minimum spanning tree is obtained as the simplest topology; The portion of the edge set in the first microgrid topology that does not belong to the simplest topology structure is recorded as a remaining edge set.

4. The power quality control method based on a distributed power system according to claim 3, characterized in that: The remaining edge sets are sorted based on the neural network scoring model, specifically: Construct edge feature vectors based on the key features of each node and the distances between each edge of the nodes; According to the historical edge feature vectors, an edge weight scoring model is constructed based on the neural network scoring model, the edge score value is output, and the remaining edge set is sorted and updated.

5. The power quality control method based on a distributed power system according to claim 4, characterized in that: The remaining edge sets are screened according to the system computing power, specifically: Obtain system computing power status information and construct system computing power margin indicators based on a linear weighted model; The number of preferred edges is obtained according to the system computing power margin indicator, and the remaining edges corresponding to the number of preferred edges before screening are used to construct the remaining edge set after screening.

6. The power quality control method based on a distributed power system according to claim 5, characterized in that: The simplest topological structure is reconstructed based on the remaining edge set after screening to obtain a set of topological structures to be controlled, specifically: When the system simulates topology reconstruction, set the upper limit of the number of remaining edges that can be added at a time as the maximum limit on the number of edges; In each round of topology reconstruction, edges not exceeding the maximum limit are selected from the remaining edge set after screening, and are combined with the simplest topological structure to generate several topological structures to be controlled, forming a set of topological structures to be controlled.

7. The power quality control method based on a distributed power system according to claim 6, characterized in that: The method of obtaining the optimal microgrid topology in the topology set based on the power quality index model is specifically as follows: Calculate the power quality deviation value of each topology to be controlled in the set of topology structures to be controlled based on the power quality index model and sort them to obtain the minimum power quality deviation value; The topology corresponding to the minimum power quality deviation value is selected as the optimal topology.

8. The power quality control method based on a distributed power system according to claim 7, characterized in that: The control instructions are obtained by comparing the above with the initial microgrid topology, which are as follows: By comparing the edge sets of the initial microgrid topology and the optimal topology, the edge sets that need to be disconnected and the edge sets that need to be closed are determined; The opening and closing operations are sorted based on load importance and edge priority, and corresponding opening and closing instructions are generated as control instructions.

9. A system using the power quality control method based on a distributed power system according to any one of claims 1 to 8, characterized in that: include: The state perception module obtains the initial microgrid topology and key features of each node, builds a power quality index model, and determines whether to perform topology control; The simplest topology generation module converts the initial microgrid topology into the simplest topology based on the Prim algorithm and records the remaining edge sets; The edge scoring and screening module sorts the remaining edge sets based on the neural network scoring model and screens the remaining edge sets based on the system computing power; The topology construction module reconstructs the simplest topology structure based on the remaining edge set after screening to obtain the set of topology structures to be controlled; The optimal decision control module obtains the optimal microgrid topology in the topology set based on the power quality index model and compares it with the initial microgrid topology to obtain control instructions.

Images