Study of correlation among several traffic parameters using evolutionary algorithms: traffic flow, greenhouse emissions and network occupancy

Abstract

During the last two years we have been working on the optimisation of traffic lights cycles. We designed an evolutionary, distributed architecture to do this. This architecture includes a Genetic Algorithm for the optimisation. So far we have performed a single criterion optimisation – the total volume of vehicles that left the network once the simulation finishes. Our aim is to extend our architecture towards a multicriteria optimisation. We are considering Network Occupancy and Greenhouse Emissions as suitable candidates for our purpose. Throughout this work we will share a statistical based study about the two new criteria that will help us to decide whether to include them or not in the fitness function of our system. To do so we have used data from two real world traffic networks.