A method for the prediction of future driving conditions and for the energy management optimisation of a Hybrid Electric Vehicle

Vehicular communications are expected to enable the development of Intelligent Cooperative Systems to be exploited for solving crucial problems related to mobility: road safety, traffic management etc. Information and Communication Technologies could also play a very important role in order to optimize the energy management of conventional, hybrid and electrical vehicles and, thus, to reduce their environment impact. In particular, vehicular communications could be used to predict driving conditions with the objective to determinate future load power demand. An adaptative energy management strategy for series hybrid electric vehicles based on genetic algorithm optimized maps and the SUMO (Simulation of Urban Mobility) predictor is presenter here. The control stategy paremeters are optimized over a series of possible mini cycles (duration $60s$) obteined by a K-means clustering algorithm. These references mini cycles are colled centroids. The centroids are abteined with respect at $60s$ time windowed standard driving cycles (UDDS, EUDC, etc) and realistic driving cycles acquired.