Markov Decision Processes: Discrete Stochastic Dynamic Programming
Markov Decision Processes: Discrete Stochastic Dynamic Programming
A road timetableTM to aid vehicle routing and scheduling
Computers and Operations Research
Charging scheduling with minimal waiting in a network of electric vehicles and charging stations
VANET '11 Proceedings of the Eighth ACM international workshop on Vehicular inter-networking
Constraint-Based charging scheduler design for electric vehicles
ACIIDS'12 Proceedings of the 4th Asian conference on Intelligent Information and Database Systems - Volume Part III
A model-based online mechanism with pre-commitment and its application to electric vehicle charging
Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems - Volume 2
Joint Proceedings of the Workshop on AI Problems and Approaches for Intelligent Environments and Workshop on Semantic Cities
Hi-index | 0.00 |
En-route charging stations allow electric vehicles to greatly extend their range. However, as a full charge takes a considerable amount of time, there may be significant waiting times at peak hours. To address this problem, we propose a novel navigation system, which communicates its intentions (i.e., routing policies) to other drivers. Using these intentions, our system accurately predicts congestion at charging stations and suggests the most efficient route to its user. We achieve this by extending existing time-dependent stochastic routing algorithms to include the battery's state of charge and charging stations. Furthermore, we describe a novel technique for combining historical information with agent intentions to predict the queues at charging stations. Through simulations we show that our system leads to a significant increase in utility compared to existing approaches that do not explicitly model waiting times or use intentions, in some cases reducing waiting times by over 80% and achieving near-optimal overall journey times.