Main Article Content
Abstract
Electric Vehicles (EV) have limited air pollution and are many environment friendly, and due to their addition to carbon dioxide reduction, EVs are enchancing increasingly popular nowadays. The government also encourage and supporting the procedure of electric vehicles for the social. The electric vehicle - taxis have been discovered into the common transportation systems to increase EV market distribution. Various from regular taxis that can refuel in minutes, EV taxis’ recharging cycles can be as lengthy as one hour. Due to the lengthy cycle, the poor decision on the charging station, i.e., choosing one without hollow charging piles, may lead to a lengthy waiting time of more than an hour in the bad case. Therefore, choosing the right charging station is very necessary to reduce the overall waiting time. Considering that the waiting time can be a non negligible portion to the mistken work hours, the decision will naturally distrub the revenue of individual EV taxis. The current practice of a taxi driver is to choose a station heuristically without a global knowledge. However the heuristically choice can be a wrong one that leads to more waiting time. The proposed system provides a real-time charging station recommendation system for EV taxis via large-scale GPS text mining. By combining each EV taxi’s historical recharging events and real-time GPS trajectories, the data operational state of each taxi is predicted. Based on this data, for an EV taxi requesting a recommendation, recommend a charging station that leads to the minimal total time previous its recharging starts.