Nearby allocation of emergency repair resources for multiple faults in distribution networks based on parallel CNN algorithm

In order to improve the efficiency of emergency repair for multiple faults in distribution networks, a method for allocating emergency repair resources for multiple faults in distribution networks based on parallel convolutional neural network (CNN) algorithm is studied. This method uses a matrix op...

Full description

Saved in:
Bibliographic Details
Published in:AIP advances 2024-08, Vol.14 (8), p.085306-085306-10
Main Authors: Feng, Bo, Zhang, Wei, Huang, Weixiang, Chen, Qianyi, Li, Shan
Format: Article
Language:English
Subjects:
Algorithms
Artificial neural networks
Economic impact
Emergency procedures
Fault detection
Fault location
Fault minimization
Faults
Repair time
Resource allocation
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In order to improve the efficiency of emergency repair for multiple faults in distribution networks, a method for allocating emergency repair resources for multiple faults in distribution networks based on parallel convolutional neural network (CNN) algorithm is studied. This method uses a matrix operation based multiple fault detection method for distribution networks. After determining the location of multiple faults based on the direction of fault power, the principle is to allocate emergency repair resources nearby for multiple faults, with the goal of minimizing economic losses caused by the fault point and minimizing fault repair time. The objective function for allocating emergency repair resources nearby is constructed, and parallel CNN algorithm is used to solve the problem by classification, to find the feasible solution with the minimum mean square error between the objective function and the feasible solution set for nearby allocation of emergency repair resources, and it is used as the optimal solution for nearby allocation of repair resources. The experimental results show that when the proposed method is used to allocate emergency repair resources for multiple faults in the distribution network, the optimal time for setting the repair plan is 0.53 and 0.96 s, respectively, with an average allocation accuracy of 91%. It has been confirmed that this method can achieve the optimal decision of resource allocation plan in a short period of time, improving the efficiency of emergency repair.
ISSN:2158-3226
2158-3226
DOI:10.1063/5.0210959