Neural Network Based Decision Support System for Forecasting the Power Needs of Electric Vehicle

Abstract

Global energy trends are undergoing significant changes, and the future of transportation will promote sustainable development by managing energy production and consumption while reducing vehicle emissions. Electric Vehicles (EVs) have the potential to reshape energy consumption patterns by mitigating environmental risks. In the upcoming years, Artificial Intelligence (AI)-based systems will be pivotal in the comprehensive energy management of EVs. Advanced EV technology and intelligent components will drive innovation in automotive power train design. However, several challenges like regional government support, user acceptance, vehicle range, battery technology, and charging infrastructure hinder widespread EV adoption. Therefore, understanding current conditions and emerging trends is crucial to expand EV penetration. This study explores existing charging technologies and standardization efforts to enhance EV adaptability, along with AI applications in advancing EV intelligence. Range and battery level estimation are critical for the safe and efficient operation of electric vehicles (EVs). This work proposes a Neural Network (NN)-based approach for battery level estimation in EVs. The findings indicate that the suggested neural network-based method can attain greater accuracy and quicker convergence compared to current techniques. This can lead to more efficient electric vehicle operation and enhanced battery lifespan.