Smart and Sustainable Scheduling of Charging Events for Electric Buses

Abstract

AbstractThe Irish transportation sector currently accounts for more than 30% of the energy related CO2 emissions of the country. Therefore, in order to reach the sustainable goals, the Irish government is working on multiple incentives to promote Electric Vehicles (EV) and infrastructure to decarbonize the sector, e.g., free domestic charging points, tool reductions, and the implementation of electric Buses (eBuses) in the medium to long term. In particular, eBuses operate with rechargeable batteries with a capacity to store approximately 300 kWh (and up to 600 kWh), equivalent to around 29.9 L of diesel, while reaching approx. 200 km. In order to ensure a proper transition from regular diesel buses to eBuses, charging times must be coordinated to ensure each bus has adequate energy to complete their operational route. In this work, we present a framework for an efficient management of renewable energies to charge a fleet of eBuses without perturbing the quality of service. Our framework starts by building a deep learning model for wind power forecasting to predict clean energy time windows, i.e., periods of time when the production of clean energy exceeds the demand of the country. Then, the optimization phase schedules charging events to reduce the use of non-clean energy to recharge eBuses while passengers are embarking or disembarking. The proposed framework is capable of overcoming the unstable and chaotic nature of wind power generation to operate the fleet without perturbing the quality of service. As expected, the size of the batteries does have a positive impact on the percentage of clean energy required to operate large fleets of eBuses. Methods developed in this paper help to mitigate potentially inaccuracies derived the prediction models. Our extensive empirical validation with real instances from Ireland suggests that our solutions can significantly reduce non-clean energy consumed on large datasets.