Predictive Analysis of Battery Usage and Energy Consumption in Electric Buses Using Machine Learning

Abstract: A machine learning-based framework for forecasting the energy efficiency of electric city buses is presented in this study. It is designed to maximize operational efficiency in public transportation networks. The foundation of this system is a specially created dataset that mimics actual operational situations. It includes variables like Passenger count, temperature, HVAC load, auxiliary load, and elevation change. Before the dataset is used to train multiple regression models, it is preprocessed and standardized. The Random Forest Regressor was chosen as the final model because of its strong performance in maximizing the R2 score and minimizing the Root Mean Squared Error (RMSE). Stakeholders can use the model's energy economy prediction in kilometers per kilowatt-hour (km/kWh) to inform their cost management, energy allocation, and route design decisions. Real-time predictions based on user input are made possible by the integration of the trained model into an intuitive Flask web application. The practicality of machine learning in assisting intelligent, energy-conscious electric bus fleet operations is demonstrated by this end-to-end implementation. Keywords: Electric City Buses, Energy Economy Prediction, Machine Learning, Random Forest Regressor, Flask Web Application, km/kWh, Regression Model