Swarm intelligence for traffic light scheduling: Application to real urban areas

Abstract

Congestion, pollution, security, parking, noise, and many other problems derived from vehicular traffic are present every day in most cities around the world. The growing number of traffic lights that control the vehicular flow requires a complex scheduling, and hence, automatic systems are indispensable nowadays for optimally tackling this task. In this work, we propose a Swarm Intelligence approach to find successful cycle programs of traffic lights. Using a microscopic traffic simulator, the solutions obtained by our algorithm are evaluated in the context of two large and heterogeneous metropolitan areas located in the cities of Má laga and Sevilla (in Spain). In comparison with cycle programs predefined by experts (close to real ones), our proposal obtains significant profits in terms of two main indicators: the number of vehicles that reach their destinations on time and the global trip time.

Enhancing the urban road traffic with Swarm Intelligence: A case study of Córdoba city downtown

“…In this sense, the use of intelligent methods, and in concrete the use of metaheuristic algorithms [1], [2], have demonstrated their usefulness to the scheduling of traffic lights [5], [13], [11], [14]. However, the use of such an intelligent systems in the literature has been restricted to optimize academic instances, or they are specifically adapted to limited areas in urban scenarios with a few cars and traffic lights.…”

A Multi-Intersection Model and Signal Timing Plan Algorithm for Urban Traffic Signal Control

“…We compare the proposed algorithm with three other state-of-the-art algorithms mentioned in Section 1, including SIA-PSO (Swarm Intelligent Approach-Particle Swarm Optimization) (García-Nieto et al 2012), SOCA (Self-Organizing Control Approach) (Wei et al 2005) and GA+CC (Genetic Algorithm and Cluster Computing) (Sanchez-Medina et al 2010). To be continued These three algorithms mentioned above are the most representative ones of the swarm intelligent approach, reinforced learning and CA approach and the hybrid approach described in Section 1.…”

“…After establishing the model of multi-intersections, the proposed MISTPA can decrease vehicle delay time at each intersection. Had a very simple structure, its neural performance is susceptible to the traffic volumes, so that they had to relearn an effective control approach Decision support systems Almejalli et al 2007 Effectively select the proper strategy, difficult to obtain and maintain historical data and expert knowledge Evolutionary computation and swarm algorithm De Oliveira, Bazzan 2006;García-Nieto et al 2012;Montana, Czerwinski 1996;Sanchez-Medina et al 2010 Requires a great deal of computing resources (a number of simulations). The cost of simulations is high.…”

Intelligent Traffic Light Management using Multi-Behavioral Agents

“…They conclude that to solve this type of problems it is useful to use evolution strategies. In [5] authors show the use of an iterative optimization algorithm (specifically a Particle Swarm Optimization (PSO) algorithm) to find successful cycle programs of traffic lights. They validate their proposal using the SUMO microscopic traffic simulator, obtaining an improvement in terms of total trip times and number of vehicles that arrive at their destination in a predefined simulation time.…”