A framework for BEB energy prediction using low-resolution open-source data-driven model

The accurate calculation of the energy consumption (EC) rates of Battery-Electric Buses (BEBs) might be ambiguous due to uncertainties in amassing real-world operation data such as speed profiles, route topology, passenger loading, and weather conditions. Therefore, attaining an extensive validated EC prediction model is essential to surmount the challenges in collecting real-world data. In this respect, this study develops and assesses an open-source low-resolution data-driven framework to estimate BEB's EC in transit operation, using vehicular, operational, topological, and external parameters. Moreover, a three-step validation process is used to assess the proposed framework's performance. The results show that the prediction model provides a reasonable error margin (20%). The validation analyses show a powerful goodness-of-fit where the prediction model can explain more than 90% of the EC variation. The framework can superbly provide transit planners and agencies with an optimal transit operating profile that reinforces the BEB’s energy savings.