A Hybrid Approach for State-of-Charge Forecasting in Battery-Powered Electric Vehicles

International audience Nowadays, electric vehicles (EV) are increasingly penetrating thetransportation roads in most countries worldwide. Many efforts areoriented toward the deployment of the EVs infrastructures,including those dedicated to intelligent transportation andelectro-mobility as well. For instance, many Moroccan organizationsare collaborating to deploy charging stations in mostly allMoroccan cities. Furthermore, in Morocco, EVs are tax-free, andtheir users can charge for free their vehicles in any station.However, customers are still worried by the driving range of EVs.For instance, a new driving style is needed to increase the drivingrange of their EV, which is not easy in most cases. Therefore, theneed for a companion system that helps in adopting a suitabledriving style arise. The driving range depends mainly on thebattery’s capacity. Hence, knowing in advance the battery’sstate-of-charge (SoC) could help in computing the remaining drivingrange. In this paper, a battery SoC forecasting method isintroduced and tested in a real case scenario on Rabat-Salé-Kénitraurban roads using a Twizy EV. Results show that this method is ableto forecast the SoC up to 180 s ahead with minimal errors and lowcomputational overhead, making it more suitable for deployment inin-vehicle embedded systems.