Abstract

Metro trains have non-linear load characteristics, which means that the power sent to them gets distorted. Problems are caused by changes in power, swells, harmonics, and other disturbances. In this research, an artificial intelligence-driven control method was used on a unified power quality conditioner (UPQC) to help reduce power quality problems and improve power quality. Three advanced control methods are built and compared using MATLAB Simulink. Some of these methods are the ANN Controller, the NARMA-L2 Controller, and the PI Controller, improved using the Adaptive Lizard Algorithm. The controls' usefulness is judged by how well they lower the total harmonic distortion (THD) in the source current. The results show that all three AI-based controls work much better than the system that was not paid for. The ANN Controller works the best, followed by the NARMA-L2 Controller, and the PI Controller improved with the Adaptive Lizard Algorithm. These AI-driven control methods can enhance power quality and ensure that metro rail systems run smoothly and efficiently, as shown by how well they work. Modern transportation networks need more advanced ways to handle power quality, and this research helps make those solutions come together.

Details

Title
AI based UPQC control technique for power quality optimization of railway transportation systems
Author
Nishad, D. K. 1 ; Tiwari, A. N. 1 ; Khalid, Saifullah 2 ; Gupta, Sandeep 3 ; Shukla, Anand 4 

 Madan Mohan Malaviya University of Technology, Department of Electrical Engineering, Gorakhpur, India (GRID:grid.449043.e) (ISNI:0000 0004 1771 8190) 
 Airport Authority of India, New Delhi, India (GRID:grid.449043.e) 
 Graphic Era (Deemed to Be University), Electrical Engineering, Dehradun, India (GRID:grid.448909.8) (ISNI:0000 0004 1771 8078) 
 Wollega University, Nekemte, Ethiopia (GRID:grid.449817.7) (ISNI:0000 0004 0439 6014) 
Pages
17935
Publication year
2024
Publication date
2024
Publisher
Nature Publishing Group
e-ISSN
20452322
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
3087466021
Copyright
© The Author(s) 2024. This work is published under http://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.