Home // VEHICULAR 2012, The First International Conference on Advances in Vehicular Systems, Technologies and Applications // View article

Intelligent Traffic Control Based on Multi-armed Bandit and Wireless Scheduling Techniques

Authors:
Chanwoo Park
Jungwoo Lee

Keywords: ITS; Vehicular Network; IEEE 802.11 DCF/PCF; MAB.

Abstract:
Intelligent Transportation System (ITS) researches, including vehicular communications, have been making great advancements to improve road safety and traffic flow efficiency. In this paper, we propose two new traffic control systems. In the first method, we assume a system with fully autonomous cars and infrastructure to avoid collision completely. Vehicles communicate with the access point in both random access mode and polling mode, and the movement of the automobiles will be coordinated by the infrastructure using IEEE 802.11 DCF/PCF mechanisms. In the second method, there is a given set of lanes with unknown reward statistics and we consider the lanes as a multi-armed bandit. We use multi-armed bandit algorithm to choose the best lane to drive in and to maximize the total expected reward while minimizing the regret. Traffic congestion is very difficult to predict and deal with because it is a function of many unknown factors such as number of cars, weather, road constructions, and accidents. The proposed algorithms are designed for urban road networks to ease the congestion, and make it more predictable at the same time. We find that the first algorithm makes the traffic system able to balance efficiency and fairness and the second algorithm helps vehicles choose the best lane with minimizied regret.

Pages: 23 to 27

Copyright: Copyright (c) IARIA, 2012

Publication date: June 24, 2012

Published in: conference

ISSN: 2327-2058

ISBN: 978-1-61208-241-7

Location: Venice, Italy

Dates: from June 24, 2012 to June 29, 2012