Cellular Network Based Real-Time Road Traffic State Estimation Framework for Urban Road Networks
No Thumbnail Available
Date
2017-01-04
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Addis Ababa University
Abstract
With the rapid increase of urban development and the surge in vehicle ownership, urban road
transport problems like traffic accident and congestion caused huge waste of time, property
damage and environmental pollution in recent years. To address these problems, use of
Information Communication Technology–based transport systems that can support maximum
utilization of the existing road transport infrastructure has been proposed by different
researchers. Road monitoring systems are one of these solutions which support road users to
make informed decisions. However, the current road traffic monitoring systems use road side
infrastructures for road traffic data collection and these technologies lack accurate and up-to-date
traffic data covering the whole road network. By comparison, cellular networks are already
widely deployed and can provide large road network coverage. Besides, 3G and 4G cellular
networks provide mobile phone positioning facility with better performance accuracy and this
opportunity can help to obtain accurate traffic flow information in cost effective manner on the
entire road networks. Mobile positioning technologies which aim to collect road traffic data in
cellular networks can be either Handset-based or Network-based. Each of these technologies
differ in their positioning accuracy as well as area coverage. But, there is no single cellular
network positioning technology that can support wide area coverage with high accuracy
simultaneously. To improve positioning accuracy, coverage and communication latency of
iv
positioning technologies, combination (hybrid) of Handset-based and Network-based positioning
techniques has been proposed. The objective of this research is, therefore, to develop a real-time
road traffic estimation framework, which utilizes a hybrid cellular network positioning
technology as a source of road traffic data.
To achieve this objective, the study uses a design science research approach. Detail literature
review on past and current research studies was conducted to identify the need for better road
traffic flow estimation accuracy together with improved performance of the procedures. With the
help of systematic literature review better understanding on road traffic flow estimation
procedures and tools was identified.
The results of literature review on the different positioning principles and state estimation
models formed a base to design a hybrid mobile phone positioning and tracking algorithm and
real-time road traffic state estimation framework. An experimental research method is employed
in evaluating the accuracy of the proposed hybridized positioning technology and validating the
performance of road traffic state estimation framework. To evaluate the operational effectiveness
of the framework sample road networks of Addis Ababa city are used. Data is gathered based on
simulation experiment and also from field test conducted using J2ME location API (JSR-179)
software installed on A-GPS enabled mobile phone moving in all journey of a moving vehicle.
The evaluation of the framework using both simulation data and real-world data indicated that
the developed estimation model could help to generate reliable traffic state information on urban
roads.
To validate the research process and evaluate practical utility of the research result, a theoretical
literature support and expert survey were employed respectively. Accordingly, both the process
and result are found to be valid, reliable and practical.
Description
Keywords
Cellular Network, Positioning Technology, Framework, Artificial Neural Network, State Estimation