Energy-efficient routing based on vehicular consumption predictions of a mesoscopic learning model

This paper proposes an alternative approach for determining the most energy efficient route towards a destination. An innovative mesoscopic vehicular consumption model that is based on machine learning functionality is introduced and its application in a case study involving Fully Electric Vehicles (FEVs) is examined. The integration of this model in a routing engine especially designed for FEVs is also analyzed and a software architecture for implementing the proposed routing methodology is defined. In order to verify the robustness and the energy efficiency of this methodology, a system prototype has been developed and a series of field tests have been performed. The results of these tests are reported and significant conclusions are derived regarding the generated energy efficient routes.