Distribution network fault section location method and system based on ielm algorithm

Abstract

The present disclosure provides a distribution network fault section location method and system based on the IELM algorithm, including the following steps: reading the distribution network information, and establishing the first-layer distribution network fault and the second-layer distribution network fault combined with the layered processing idea. Power grid faults; traversing the established first-level distribution network faults, constructing the fitting degree function of the first-level distribution network faults; optimizing and judging the fitting degree function of the constructed first-level distribution network faults, If the optimal solution is reached, then directly output the fault section of the distribution network, otherwise enter the next step: use the global optimization idea to search for suspicious sections of the fitting function of the first-level distribution network faults, and construct suspicious sections The set of suspicious sections constructed is used as the solution space of the second-level distribution network fault, and the IELM algorithm is used to locate the fault section of the distribution network. The disclosure proposes the idea of ​​layered processing and global optimization, which has good accuracy and fault tolerance for distribution networks of different structures and scales, and achieves the purpose of reducing the scale of the solution space.

Description

technical field [0001] The disclosure belongs to the technical field of distribution network fault location, and in particular relates to a distribution network fault section location method and system based on the IELM algorithm. Background technique [0002] The statements in this section merely provide background information related to the present disclosure and do not necessarily constitute prior art. [0003] Quickly and accurately locating the fault section in the distribution network is the premise of isolating the fault area in time and restoring the power supply in the non-fault area, which is of great significance for improving the reliability of the system. In the field of distribution network fault location, scholars at home and abroad have proposed various methods such as fault line selection, fault distance measurement, and fault section location. With the continuous development of distribution network automation and communication technology, feeder monitoring...

AI Technical Summary

Problems solved by technology

However, the matrix algorithm has poor fault tolerance and needs to establish a network description matrix. When the structure of the distribution network is complex and the number of line sections is large, the establishment of the network description matrix requires a lot of human resources.

Although some scholars have proposed some matrix algorithms with a certain degree of fault tolerance, the problem of establishing a network description matrix for the realization of matrix algorithms has not been solved, which makes it difficult for matrix algorithms to be applied to complex distribution networks.

The intelligent optimization algorithm has global convergence in theory, but in practical applications, due to the randomness of the search in the solution space, the intelligent optimization algorithm may have local convergence

And the size of its solution space is proportional to the size of the distribution network, which makes the intelligent optimization algorithm have a fatal flaw of poor accuracy in large-scale distribution network applications

Some experts and scholars have proposed to divide the distribution grid by region, by first locating the fault area and then locating the fault section, to achieve the purpose of reducing the solution space of the intelligent optimization algorithm. This has indeed improved the accuracy of the algorithm to a certain extent, but It still does not meet the requirements of the distribution network for high accuracy of the algorithm

Limited by this, it is always difficult to apply intelligent optimization algorithms to large-scale distribution networks

Images