Xu, Jin
University of Quebec

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Enhancement of the Estimation of Energy Consumption for Electric Vehicles by Using Machine Learning Cabani, Adnane; Zhang, Peiwen; Khemmar, Redouane; Xu, Jin
Bulletin of Electrical Engineering and Informatics List of Accepted Papers (with minor revisions)
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v10i2.2717

Abstract

Three main classes are considered of significant influence factors when predicting theenergy consumption rate of Electric Vehicles (EV): environment, driver behaviour, and vehicle. These classes take into account constant or variable parameters which influ-ences the energy consumption of the EV. In this paper, we develop a new model taking into account the three classes as well as the interaction between them in order to im-prove the quality of EV energy consumption. The model depends on a new approach based on machine learning and especially k-NN algorithm in order to estimate the EVenergy consumption. Following a lazy learning paradigm, this approach allows better estimation performance. The advantage of our proposal, in regards to mathematical approach, is taking into account the real situation of the ecosystem on the basis of historical data. In fact, the behavior of the driver (driving style, heating usage, air con-ditioner usage, battery state, etc.) impacts directly the EV energy consumption. The obtained results show that we can reach up to 96.5% of accuracy about the estimatedof energy-consumption. The proposed method is used in order to find the optimal pathbetween two points (departure-destination) in terms of energy consumption.