Most transportation infrastructure planning studies are conducted with only a few alternative networks and land use scenarios. Generally, these studies analyze only a few transportation-related measures of effectiveness, such as vehicle-miles traveled, congestion, and air-quality emissions. When such a small subset of possible alternatives and variables is analyzed, it is probable that optimal alternative designs are not included. Ideally, all combinations of land use, infrastructure, and social variables would be examined; however, even a small city of 200 traffic zones with an average of 10 land uses will have more than 10200 possible zoning alternatives. A more efficient way to examine an extremely large search set of feasible designs is to employ artificial intelligence techniques to quickly narrow the number of alternatives to be considered. The use of a multiobjective genetic algorithm model to optimize land use, infrastructure, social, and fiscal variables is demonstrated. The model considers three primary objective functions: minimizing travel time, minimizing per capita cost (as related to property taxes), and minimizing land use change. A large number of constraints are used. A Pareto fitness function is used to develop a small set of optimal solutions. The model was applied to Provo, Utah, which is a fast-growing community. More than 1.9 million alternative designs were evaluated, and 195 optimal Pareto plans were found. The Pareto set of optimal solutions indicated that solutions clustering higher-density development along existing arterials were most likely to meet the objectives.
[1]
David E. Goldberg,et al.
Genetic Algorithms in Search Optimization and Machine Learning
,
1988
.
[2]
M. Wegener.
Operational Urban Models State of the Art
,
1994
.
[3]
James Reilly,et al.
A simulation model for state growth management planning and evaluation: The New Jersey case
,
1994
.
[4]
C E Wallace,et al.
HYBRID GENETIC ALGORITHM TO OPTIMIZE SIGNAL PHASING AND TIMING
,
1993
.
[5]
Philip O. Carter.
Techniques for Coordinating and Managing Growth
,
1993
.
[6]
Beyond Sprawl : New Patterns of Growth to Fit the New California
,
2022
.
[7]
Chung-Ju Chang,et al.
Design of a fuzzy traffic controller for ATM networks
,
1996,
TNET.
[8]
Chung-Wei Feng,et al.
Using genetic algorithms to solve construction time-cost trade-off problems
,
1997
.
[9]
Nicos Christofides,et al.
Heuristic techniques in tax structuring for multinationals
,
1996,
IEEE/IAFE 1996 Conference on Computational Intelligence for Financial Engineering (CIFEr).
[10]
John H. Holland,et al.
Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence
,
1992
.
[11]
David E. Goldberg,et al.
SIGNAL TIMING DETERMINATION USING GENETIC ALGORITHMS
,
1992
.
[12]
R. Mackett.
LAND USE TRANSPORTATION MODELS FOR POLICY ANALYSIS
,
1994
.