ENERGY ECONOMY PREDICTION FOR ELECTRIC CITY BUSES USING MACHINE LEARNING: A DATA-DRIVEN METHODOLOGY

Abstract

Electric city buses have several potential applications as one of several evolving forms of electric transportation. Automobile design and fleet management require an in-depth understanding of real transportation data. The effective functioning of alternative powertrains requires a thorough analysis of certain technological challenges. Designers tend to exercise prudence when the energy consumption is ambiguous, resulting in designs that are both expensive and insufficient. Organizations and scholars are incapable of formulating analytical answers to this problem owing to the intricacy and interrelation of the criteria. Optimizing processes and accurately estimating energy use can yield significant cost reductions. The main aim of the study is to provide an in-depth analysis of the energy usage of BEBs. To accomplish this, we utilize new explanatory components and advanced machine learning techniques to develop performance profiles. Five unique programs are developed to ensure their reliability, precision, and functionality in the realm of prediction generation. Our models exhibited outstanding performance due to the careful selection of characteristics, with an average accuracy above 94% in their predictions. The proposed concept might revolutionize transportation and create a basis for sustainable public transit if executed by manufacturers, fleet administrators, and governments.