Discovering Regions Where Users Drive Inefficiently on Regular Journeys

In this paper, we propose a mechanism to optimize fuel consumption on regular routes. The idea is to find out in which areas a driver usually realizes inefficient actions from the point of view of energy consumption. The aim is to alert the user in advance in order to adjust the vehicle speed or change gear, avoiding inefficient driving. Unlike other proposals, this solution does not require the driver to change the route in order to save fuel. To detect inefficient areas, the system uses vehicle telemetry: acceleration, deceleration, engine speed, engine load, and vehicle speed. A fuzzy logic system determines whether the driver drove efficiently or not in a region. Then, when the driver drives in the same route, the system predicts if the driver will return to a similar inefficient driving pattern in the nearby region. If the probability is high, the system warns the user. Therefore, the driver can take the appropriate action. The results show that the system reduces the fuel consumption by 7.33% on average and even, in certain cases, the fuel saving is more than 10%.