Evolutionary Computation Applied to Urban Traffic Optimization

Abstract

At the present time, many sings seem to indicate that we live a global energy and environmental crisis. The scientific community argues that the global warming process is, at least in some degree, a consequence of modern societies unsustainable development. A key area in that situation is the citizens mobility. World economies seem to require fast and efficient transportation infrastructures for a significant fraction of the population. The non-stopping overload process that traffic networks are suffering calls for new solutions. In the vast majority of cases it is not viable to extend that infrastructures due to costs, lack of available space, and environmental impacts. Thus, traffic departments all around the world are very interested in optimizing the existing infrastructures to obtain the very best service they can provide. In the last decade many initiatives have been developed to give the traffic network new management facilities for its better exploitation. They are grouped in the so called Intelligent Transportation Systems. Examples of these approaches are the Advanced Traveler Information Systems (ATIS) and Advanced Traffic Management Systems (ATMS). Most of them provide drivers or traffic engineers the current traffic real/simulated situation or traffic forecasts. They may even suggest actions to improve the traffic flow. To do so, researchers have done a lot of work improving traffic simulations, specially through the development of accurate microscopic simulators. In the last decades the application of that family of simulators was restricted to small test cases due to its high computing requirements. Currently, the availability of cheap faster computers has changed this situation. Some famous microsimulators are MITSIM(Yang, Q., 1997), INTEGRATION (Rakha, H., et al., 1998), AIMSUN2 (Barcelo, J., et al., 1996), TRANSIMS (Nagel, K. & Barrett, C., 1997), etc. They will be briefly explained in the following section. Although traffic research is mainly targeted at obtaining accurate simulations there are few groups focused at the optimization or improvement of traffic in an automatic manner — not dependent on traffic engineers experience and “art”. O pe n A cc es s D at ab as e w w w .ite ch on lin e. co m

Original document

The different versions of the original document can be found in:

• http://www.intechopen.com/articles/show/title/evolutionary_computation_applied_to_urban_traffic_optimization

• https://www.intechopen.com/citation-pdf-url/5247 under the license cc-by-nc-sa

• http://cdn.intechopen.com/pdfs-wm/5247.pdf,

https://cdn.intechweb.org/pdfs/5247.pdf,

https://www.intechopen.com/books/advances_in_evolutionary_algorithms/evolutionary_computation_applied_to_urban_traffic_optimization,

https://academic.microsoft.com/#/detail/2136037179

• https://www.intechopen.com/download/pdf/5247,

http://dx.doi.org/10.5772/6119