Back to results list
Please use this identifier to cite or link to this item:
|Title:||Adaptive traffic light control in wireless sensor network-based Intelligent Transportation System||Authors:||Zhou, Binbin||Keywords:||Hong Kong Polytechnic University -- Dissertations
Intelligent transportation systems
Wireless sensor networks
Traffic signs and signals -- Control systems.
|Issue Date:||2011||Publisher:||The Hong Kong Polytechnic University||Abstract:||Intelligent Transportation System (ITS) refers to a system that integrates advanced communications, computing and electronics technologies into transportation infrastructure and vehicles, to improve safety and efficiency and to reduce traveling time and fuel consumption. The conventional surveillance methods used in ITS to detect real-time traffic data, e.g. video image processing and inductive loops detection, have several shortcomings, such as limited coverage and high costs of implementation and maintenance. Wireless sensor networks (WSNs) offer the potential of providng real-time traffic data without these drawbacks. Hence, in the past decade, WSNs have been applied to ITS to improve the performance of ITS. Controlling traffic lights plays a key role in ITS. An optimal traffic light control approach can increase traffic throughput and reduce waiting time. In this thesis, we investigate how to design methods and algorithms for adaptive traffic light control in a WSN-based ITS. We review the related work on collecting real-time traffic data and on controlling traffic lights, including fixed-time control, actuated control, and adaptive control. We propose models and schemes for adaptive traffic light control for both isolated intersections and multiple intersections. The proposed approaches take advantage of real-time traffic information collected by WSNs to achieve high system throughput, low waiting time and few stops for the vehicles. First, we describe an adaptive traffic light control scheme proposed for an isolated intersection. This scheme can adjust both the sequence and length of traffic lights in accordance with real-time traffic loads. It takes into consideration a number of factors such as traffic volume, waiting time, vehicle density, and others, to determine the sequence and the optimal length of green lights. Simulation results demonstrate that our approach results in much higher throughput and lower average waiting time as compared with the optimal fixed-time control approach and an actuated control approach. We then propose an adaptive traffic light control scheme for multiple intersections. In this case, we need to also consider controlling the traffic lights for multiple adjacent intersections in a distributed way. Our proposed scheme can collect real-time traffic data, and adjust both the sequences and lengths of the green lights of intersections cooperatively. Real-time traffic data, e.g. traffic volumes, waiting time, number of stops, vehicle densities, are taken into account to determine the sequence of green lights in each intersection. The optimal lengths of the green lights can be calculated based on the information about local traffic volumes and the remaining green light durations of neighboring intersections. Simulation results likewise show that our scheme produces much higher throughput, lower average waiting time and fewer average stops, compared with the optimal fixed-time control approach, an actuated control approach, and an adaptive control approach. We have implemented the proposed schemes on our testbed for Intelligent Services with Wireless Sensor Networks, iSensNet to evaluate and demonstrate the performance. Our experimental results show that our approaches can deal with different traffic conditions in an effective manner.||Description:||xvi, 134 p. : ill. ; 31 cm.
PolyU Library Call No.: [THS] LG51 .H577M COMP 2011 ZhouB
|URI:||http://hdl.handle.net/10397/4307||Rights:||All rights reserved.|
|Appears in Collections:||Thesis|
Show full item record
Files in This Item:
|b24415662_link.htm||For PolyU Users||162 B||HTML||View/Open|
|b24415662_ir.pdf||For All Users (Non-printable)||7.26 MB||Adobe PDF||View/Open|
Citations as of Oct 15, 2018
Citations as of Oct 15, 2018
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.