Enhancing Electric Bus Operations Through Predictive Machine Learning Models

Abstract

Electric city buses are emerging as a sustainable alternative to traditional fossil-fuel-based transportation. However, accurately predicting their energy consumption remains a key challenge due to varying factors like traffic, weather, and route conditions. This project proposes a machine learning-based framework to forecast energy usage in electric buses by analyzing real-world data such as speed, passenger load, elevation, and environmental conditions. Algorithms including Random Forest, Support Vector Regression, and Artificial Neural Networks are used to capture complex patterns. The results help optimize charging schedules, reduce energy costs, and extend battery life. This study aims to support intelligent transportation systems by enabling data-driven decision-making, ultimately contributing to more efficient, reliable, and eco-friendly urban mobility.