Optimal Cycle Program of Traffic Lights with Particle Swarm Optimization

JOSÉ MANUEL GARCÍA NIETO; ANA CAROLINA OLIVERA; ENRIQUE ALBA

IEEE TRANSACTIONS ON EVOLUTIONARY COMPUTATION

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

Lugar: New York; Año: 2013 vol. 17 p. 823 - 839

1089-778X

Optimal scheduling of traffic lights, and in particular optimal light cycle programs, is a crucial task in actual cities with potential benefits in terms of energy consumption, traffic flow management, pedestrian safety, and environmental issues. Nevertheless, very few works in the current literature tackle this problem by means of automatic intelligent systems, and, when done, they are focused to limited areas with elementary traffic light schedules. In this work, we propose an optimization approach in which a Particle Swarm Optimizer (PSO) can find successful cycle programs of traffic lights. The solutions obtained are simulated with SUMO, a well-known microscopic traffic simulator. In this study, we have tested two large and heterogeneous metropolitan areas with hundreds of traffic lights located in the cities of Bahía Blanca in Argentina (American style), and Málaga in Spain (European style). Our algorithm is shown to obtain profitable cycle programs of traffic lights for both kinds of cities. In comparison with predefined by experts cycle programs (close to real ones), our PSO achieved quantitative improvements for the two main objectives: the number of vehicles that reach their destinations and the global trip time.