Dynamic partition power distribution network dispatching optimization method and system

Abstract

The invention discloses a dynamic partition power distribution network dispatching optimization method and system, and the method comprises the steps: S1, collecting the real-time operation data of a power distribution network, and carrying out the preprocessing; s2, based on the real-time operation data, dynamically dividing and distributing power grid partitions through a clustering algorithm; s3, for each dynamic partition, establishing a multi-objective optimization model for scheduling optimization; and S4, executing the optimization scheduling instruction and monitoring the effect. The method adapts to fluctuation of power distribution network load and renewable energy sources through dynamic partition, and the scheduling efficiency and the system stability are improved. The system comprises a data acquisition module, a dynamic partition module, an optimization scheduling module and an execution monitoring module, and the method is realized. The method solves the defect that static partition scheduling cannot adapt to dynamic changes in the prior art, and has novelty and creativity.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power distribution network dispatching, in particular to a dynamic partitioning power distribution network dispatching optimization method and system. BACKGROUND

[0002] As an important part of the power system, the dispatching optimization of the power distribution network is crucial for improving power supply reliability and reducing operating costs. Existing power distribution network dispatching methods mostly use static partitioning strategies, i.e., dividing regions according to fixed topological structures and conducting independent dispatching. However, with the large-scale integration of distributed energy sources (such as photovoltaic and wind power), the operating state of the power distribution network presents high dynamicity and uncertainty, and the static partitioning method cannot adapt to load fluctuations and changes in renewable energy output, leading to low dispatching efficiency, voltage out-of-limit, increased network loss, and other problems.

[0003] For example, during load peaks or sudden changes in renewable energy output, static partitioning may not be able to adjust the dispatching strategy in a timely manner, causing local overload or voltage instability. In addition, existing optimization methods often optimize globally, with high computational complexity and slow response speed, making it difficult to meet real-time dispatching requirements.

[0004] Therefore, there is an urgent need for a new method that can dynamically partition and optimize dispatching to improve the adaptability and economy of the power distribution network. SUMMARY

[0005] To solve the existing problems, the present application provides a dynamic partitioning power distribution network dispatching optimization method and system, with the following specific solutions:

[0006] A dynamic partitioning power distribution network dispatching optimization method, comprising the following steps:

[0007] S1, collecting real-time operating data of the power distribution network;

[0008] S2, based on the real-time operating data, dynamically dividing the power distribution network partitions through a clustering algorithm;

[0009] S3, for each dynamic partition, establishing a multi-objective optimization model for dispatching optimization;

[0010] S4, executing the optimized dispatching instructions and monitoring the dispatching effect.

[0011] Preferably, step S1 comprises:

[0012] S11, collecting node voltage, line current, load power, and distributed energy output data of the power distribution network;

[0013] S12, preprocessing the collected data, including data cleaning and normalization.

[0014] Preferably, step S2 comprises:

[0015] S21, calculating electrical distances between nodes based on real-time operation data; S22, dynamically dividing power distribution network partitions according to electrical distances using a clustering algorithm.

[0016] Preferably, in step S21, the electrical distance between nodes is calculated by the following formula: ;

[0017]

[0018] Preferably, in step S22, the clustering algorithm is a K-means clustering algorithm, and the number of clusters is adaptively determined according to real-time operation data.

[0019] Preferably, step S3 comprises:

[0020] S31, establishing a multi-objective optimization model with the minimum network loss, the minimum voltage deviation, and the lowest operation cost as targets;

[0021] S32, solving the multi-objective optimization model using a multi-objective optimization algorithm to obtain an optimized dispatching instruction.

[0022] Preferably, in step S31, the objective function of the multi-objective optimization model is: ;

[0023] Preferably, in step S32, the multi-objective optimization algorithm is an NSGA-II algorithm.

[0024] The application also discloses a power distribution network dispatching optimization system for implementing any of the above methods, comprising:

[0025] a data acquisition module configured to acquire real-time operation data of the power distribution network;

[0026] a dynamic partitioning module configured to dynamically divide power distribution network partitions based on real-time operation data through a clustering algorithm;

[0027] an optimized dispatching module configured to, for each dynamic partition, establish a multi-objective optimization model for dispatching optimization;

[0028] an execution monitoring module configured to execute the optimized dispatching instruction and monitor the dispatching effect.

[0029] Preferably, the data acquisition module comprises a sensor network and a communication unit for real-time data transmission; the dynamic partition module comprises a computing unit for executing a clustering algorithm; the optimization scheduling module comprises an optimization solver for solving a multi-objective optimization model; and the execution monitoring module comprises a control unit and a feedback unit for adjusting scheduling instructions.

[0030] The present application has the advantages of:

[0031] The present application improves the flexibility and accuracy of scheduling by adapting to the changes in the operation state of the power distribution network through dynamic partitioning; the present application balances economy and safety by considering network loss, voltage deviation, and operating cost comprehensively using a multi-objective optimization model; and the present application enhances the self-adaptive ability and robustness of the system through real-time monitoring and feedback. Compared with the prior art, the present application reduces the computational complexity and improves the scheduling response speed. BRIEF DESCRIPTION OF DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings described below are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0033] Figure 1 The present application is a method flowchart. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the following will combine the drawings in the embodiments of the present application to clearly and completely explain the technical solutions in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0035] As Figure 1 A dynamic partitioning power distribution network scheduling optimization method, characterized in that it comprises the following steps:

[0036] S1, collecting real-time operation data of the power distribution network.

[0037] Specifically, it comprises:

[0038] S11, collecting node voltage, line current, load power and distributed energy output data of the power distribution network;

[0039] S12, preprocessing the collected data, including data cleaning and normalization.

[0040] S2, dynamically divide the power distribution network partition based on the real-time operation data through a clustering algorithm.

[0041] Specifically, it comprises:

[0042] S21, calculate the electrical distance between nodes based on real-time operation data; the electrical distance between nodes is calculated by the following formula:

[0043] ;

[0044] The "electrical distance" is a quantitative indicator for measuring the strength of electrical influence between any two nodes, and is an input feature for the clustering analysis (such as K-means algorithm) of the dynamic partition module. The algorithm will automatically classify nodes with small electrical distance as a class and form a "dynamic partition" according to the electrical distance between all nodes.

[0045] S22, dynamically divide the power distribution network partition according to the electrical distance using a clustering algorithm. The clustering algorithm is a K-means clustering algorithm, and the number of clusters is adaptively determined according to real-time operation data.

[0046] S3, for each dynamic partition, establish a multi-objective optimization model for scheduling optimization;

[0047] Specifically, it comprises:

[0048] S31, establish a multi-objective optimization model with the minimum network loss, the minimum voltage deviation and the lowest operation cost as the target;

[0049] The objective function of the multi-objective optimization model is:

[0050] ;

[0051] S32, use a multi-objective optimization algorithm to solve the multi-objective optimization model to obtain the optimal scheduling instruction.

[0052] The multi-objective optimization algorithm is NSGA-II algorithm. Using NSGA-II algorithm to solve the model, the Pareto optimal solution set is obtained, and the final scheduling scheme is selected according to the decision rule.

[0053] S4, executing the optimized scheduling instruction and monitoring the scheduling effect. The scheduling instruction is executed by the control system, such as adjusting the transformer tap, capacitor bank switching, load switching, etc. At the same time, the system operation state is monitored, and if a deviation is found, the dynamic partitioning and optimization process is retriggered.

[0054] The application further discloses a power distribution network scheduling optimization system for implementing any of the above methods.

[0055] A data acquisition module is configured to acquire real-time operation data of the power distribution network.

[0056] A dynamic partitioning module is configured to dynamically partition the power distribution network based on the real-time operation data by using a clustering algorithm.

[0057] An optimized scheduling module is configured to establish a multi-objective optimization model for scheduling optimization for each dynamic partition.

[0058] An execution monitoring module is configured to execute the optimized scheduling instruction and monitor the scheduling effect.

[0059] The data acquisition module comprises a sensor network and a communication unit, and is configured to transmit data in real time; the dynamic partitioning module comprises a calculation unit, and is configured to execute the clustering algorithm; the optimized scheduling module comprises an optimization solver, and is configured to solve the multi-objective optimization model; and the execution monitoring module comprises a control unit and a feedback unit, and is configured to adjust the scheduling instruction.

[0060] The application dynamically partitions to adapt to the change of the operation state of the power distribution network, improves the flexibility and accuracy of scheduling, adopts the multi-objective optimization model, comprehensively considers the network loss, voltage deviation and operation cost, balances the economy and safety, and through real-time monitoring and feedback, enhances the self-adaptive ability and robustness of the system.

[0061] Those of skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or combinations of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. Skilled artisans can implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

[0062] The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other variations without departing from the spirit or scope of the disclosure. Thus, the disclosure is not intended to be limited to the examples described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0063] Although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art will understand that modifications can be made to the foregoing embodiments, or other technical features can be substituted therefor, without departing from the spirit and scope of the technical solutions described in the foregoing embodiments.

Claims

1. A dynamic partitioning method for optimizing distribution network scheduling, characterized in that, Includes the following steps: S1. Collect real-time operating data of the power distribution network and perform preprocessing; S2. Based on the preprocessed real-time operating data, the power grid is dynamically divided into zones using a clustering algorithm; S3. For each dynamic partition, establish a multi-objective optimization model to optimize scheduling; S4. Execute the optimized scheduling instructions and monitor the scheduling effect.

2. The method according to claim 1, characterized in that, Step S1 includes: S11. Collect data on node voltage, line current, load power, and distributed energy output of the distribution network; S12. Preprocess the collected data, including data cleaning and normalization.

3. The method according to claim 1, characterized in that, Step S2 includes: S21. Calculate the electrical distance between nodes based on real-time operational data; S22. Use clustering algorithms to dynamically divide and allocate power grid zones based on electrical distance.

4. The method according to claim 3, characterized in that, In step S21, the electrical distance between nodes is calculated using the following formula: ; 5. The method according to claim 3, characterized in that, In step S22, the clustering algorithm is the K-means clustering algorithm, and the number of clusters is adaptively determined based on real-time running data.

6. The method according to claim 1, characterized in that, Step S3 includes: S31. Establish a multi-objective optimization model with the objectives of minimizing network loss, minimizing voltage deviation, and minimizing operating cost; S32. Solve the multi-objective optimization model using a multi-objective optimization algorithm to obtain the optimized scheduling instructions.

7. The method according to claim 6, characterized in that, In step S31, the multi-target optimization 8. The method according to claim 6, characterized in that, In step S32, the multi-objective optimization algorithm is the NSGA-II algorithm.

9. A dynamic partitioning distribution network dispatch optimization system, characterized in that, To implement the method of any one of claims 1-8, comprising: The data acquisition module is used to collect real-time operating data of the power distribution network; The dynamic partitioning module is used to dynamically allocate power grid partitions based on real-time operating data and through clustering algorithms. The optimization scheduling module is used to build a multi-objective optimization model for each dynamic partition to optimize scheduling. The execution monitoring module is used to execute optimized scheduling instructions and monitor the scheduling effect.

10. The system according to claim 9, characterized in that, The data acquisition module includes a sensor network and a communication unit for real-time data transmission; the dynamic partitioning module includes a computing unit for executing clustering algorithms; the optimization scheduling module includes an optimization solver for solving multi-objective optimization models; and the execution monitoring module includes a control unit and a feedback unit for adjusting scheduling instructions.

Images