SWUTC Research Project Description
Title of Project: Ant Colony Optimization Algorithm for Signal Coordination of Oversaturated Traffic Networks
Project Number: 169113
Principal Investigator:
Emily Zechman
(979) 845-2875
P.I. Affiliation: Texas A&M University
ezechman@tamu.edu
Project Monitor:
Billy M. Williams, Ph.D., P.E.
Assistant Professor
Department of Civil, Construction, and Environmental Engineering
Campus Box 7908, Room 418 Mann Hall
North Carolina State University
Raleigh, NC 27695-7908
Phone: 919.515.7813
billy_williams@ncsu.edu
Project Status: Active
Date Started: 9/1/08
Estimation Completion Date: 8/31/09
Estimated Cost - Current Fiscal: $50,000
Estimated Cost - Total Planned: $50,000
Project Summary:
Project Abstract:
Traffic congestion is a daily and growing problem of the modern era in mostly all major cities in the world. The increasing traffic demand puts a lot of strain on the existing transportation system. One of the major problems is the oversaturated network conditions especially at the peak hours. Oversaturation occurs when queues of vehicles fill entire approaching streets and interfere with the performance of adjacent upstream intersections. The general traffic conditions, measured in terms of increasing the overall throughput of vehicles and reducing the total travel time, have been shown to be significantly improved by an effective employment of intelligent transportation system techniques. However, much research has been devoted to the development of signal control algorithms under normal traffic conditions and very few of them explicitly take into account oversaturated conditions. In addition, these existing algorithms are too slow or require very high computational power to be effective in a reasonably short time. The Ant Colony Optimization technique is a probabilistic technique to solve optimization problems. It is relatively novel and has produced excellent results in various other fields of research and applications. Its major quality is the ability to reach good solutions (even if not optimal) in a very short time and this characteristic is essential to solve the complex oversaturated network conditions in real time. A successful adaptation and implementation of this algorithm will identify signal coordination to alleviate stress on traffic networks during peak hours.
Project Objectives:
The overall objective of this study is to investigate the effectiveness of the ACO algorithm in solving the traffic signal control under oversaturated conditions. We will investigate its ability to reach optimality conditions and especially its ability to reach acceptable solutions in a very short time, which would make it a good candidate for a practical use, since most of these problems need to be solved in real time.
Task Descriptions:
Task 1.
Perform a literature review to analyze all the techniques currently used to solve oversaturated networks.
Task 2.
Develop a code of the ACO algorithm suitable to solve the oversaturated traffic control problem.
Task 3.
Develop a simulation model to test the oversaturated conditions of a traffic network using the ACO.
Task 4.
Evaluate the ACO performance and compare the results with other known solution techniques, such as the Genetic Algorithms or others.
Task 5.
Prepare final report.
Index Terms:
Traffic congestion, Traffic signal control systems, Traffic signal timing, Ant colony optimization, Algorithms, Oversaturation (Traffic flow), Research projects