Regresar

Evolutionary design optimisation of traffic signals applied to quito city

Abstract:

This chapter applies evolutionary computation and machine learning methods to study the transportation system of Quito from a design optimisation perspective. It focuses on the optimisation of a large number of traffic lights deployed on a wide area of the city and studies their impact on travel time, emissions, and fuel consumption. An evolutionary algorithm (EA) with specialised mutation operators is proposed to search effectively in large decision spaces, evolving small populations for a short number of generations. The chapter develops an EA to search effectively in large decision spaces under a small budget of iterations (generations), performing a reliable short-term evolution to find high-quality solutions. The EA searches optimal settings for the traffic lights. MATSim simulates traffic lights microscopically using fixed-time controls. The output collected from that iteration of the simulator is used to calculate travel time and passed back to the optimiser as the fitness of the solution.