Deep Learning for Power Electronics: Enhancing Efficiency Through Neural Networks

EasyChair Preprint 12277

Abstract

Deep Learning (DL) has emerged as a transformative technology in various fields, and its application in power electronics has shown promising results in enhancing efficiency. This paper explores the integration of neural networks into power electronic systems to optimize performance and reduce energy losses. Traditional control methods in power electronics often face challenges in handling complex and nonlinear systems. Neural networks offer a data-driven approach, allowing for improved adaptability and efficiency in dynamic operating conditions. The paper discusses the implementation of DL techniques, such as artificial neural networks (ANNs) and deep neural networks (DNNs), in the design and control of power converters, inverters, and other power electronic devices. Through extensive simulations and experimental validations, the study demonstrates the potential of DL in accurately predicting and controlling system parameters, leading to increased energy efficiency and reduced losses.

Keyphrases: Inverters, Power Electronics, control systems, deep learning, efficiency optimization, energy loss reduction, neural networks, nonlinear systems, power converters

@booklet{EasyChair:12277,
  author    = {Rohit Sharma},
  title     = {Deep Learning for Power Electronics: Enhancing Efficiency Through Neural Networks},
  howpublished = {EasyChair Preprint 12277},
  year      = {EasyChair, 2024}}