Title : ( Application of Artificial Intelligence for Distribution Network Reconfiguration by Using D3QN Algorithm )
Authors: Amirhossein Ghaemipour , Habib Rajabi Mashhadi , Seyed Hossein Mostafavi ,Access to full-text not allowed by authors
Abstract
Considering that the electricity industry is one of the most important industries in the world, it is necessary for electricity operators to seek to create conditions for the best performance in this industry. There are different solutions for this task. Distribution network Reconfiguration (DNR) is one of the most cost-effective methods for electricity companies. Given the advancement of technology and methods in artificial intelligence, we use this structure in this article. Therefore, in this article, we focused on distribution network (DN) reconfiguring using the Dueling Double Deep Q Network (D3QN) algorithm. The suggested method has been experimented with and investigated on an IEEE 33-bus DN with the objective function of minimizing power losses and minimizing the average voltage deviation of the buses.
Keywords
, Smart Distribution Network, Reconfiguration, Reinforcement Learning, Dueling Double Deep Q network (D3QN) Algorithm@inproceedings{paperid:1104025,
author = {Ghaemipour, Amirhossein and Rajabi Mashhadi, Habib and Mostafavi, Seyed Hossein},
title = {Application of Artificial Intelligence for Distribution Network Reconfiguration by Using D3QN Algorithm},
booktitle = {2025 6th International Conference on Optimizing Electrical Energy Consumption (OEEC), 25-26 February, 2025,},
year = {2025},
location = {IRAN},
keywords = {Smart Distribution Network; Reconfiguration;
Reinforcement Learning; Dueling Double Deep Q network
(D3QN) Algorithm},
}
%0 Conference Proceedings
%T Application of Artificial Intelligence for Distribution Network Reconfiguration by Using D3QN Algorithm
%A Ghaemipour, Amirhossein
%A Rajabi Mashhadi, Habib
%A Mostafavi, Seyed Hossein
%J 2025 6th International Conference on Optimizing Electrical Energy Consumption (OEEC), 25-26 February, 2025,
%D 2025