Intelligent traffic management for the Kumasi Metropolis
Loading...
Date
NOVEMBER, 2018
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
The problem of vehicular traffic congestion is universal yet there has not been a long-term
permanent solution to this problem, and it is increasingly worsening by the day all around the
world with severe vehicular traffic taking its toll on all road users. With the upsurge in urban
traffic jams, innovative control strategies are therefore essential to allow efficient flow of
vehicular movement. It is thus not surprising that a myriad of novel control strategies has been
developed over the past years in an attempt to manage the ever-growing urban gridlock. Many
of the currently used traffic control strategies are based on the relatively inefficient fixed-time
traffic systems, like in the case of Ghana, or on a central traffic-responsive control system,
which is challenging to implement and even much more difficult to maintain. As a consequence
of inefficiencies in traffic control, road users are saddled with regular and inconveniently long
waiting times in queues. To mitigate this problem, a distributed artificial intelligence and
multi-agent system is proposed as a viable approach to manage the traffic menace. The
proposed system uses historical data for traffic management and was designed and
implemented using Simulation of Urban Mobility (SUMO) software. Iterative learning control
which is a technique for refining the momentary response performance of a system that
functions repetitively over a fixed period of time is used to tune the phase splits of the traffic
controller to obtain the optimal controller duty cycles with the least delay, resulting in frequent
traffic flows, minimum waiting times and shorter queued vehicles. The result obtained in the
comparison of the current fixed time-controlled system and designed system clearly indicated
that the proposed system outperformed the fixed-time cycle controllers in every key
performance index selected for evaluation.
Description
A thesis submitted to the Department of Electrical and Electronic Engineering, Kwame Nkrumah University of Science and Technology, Kumasi in partial fulfilment of the requirements for the award of the degree of Master of Philosophy in Telecommunication Engineering.
Keywords
Intelligent Traffic Management, Simulation, Artificial Intelligence, Urban Mobility (SUMO) Software, Kumasi Metropolis, Ghana