A Multi-Objectif Genetic Algorithm-Based Adaptive Weighted Clustering Protocol in VANET

International audience—Vehicular Ad hoc NETwork (VANET) is the main component that is used recently for the development of Intelligent Transportation Systems (ITSs). VANET has a highly dynamic and portioned network topology due to the constant and rapid movement of vehicles. Recently, the clustering algorithms are widely used as the control schemes to make VANET topology less dynamic for MAC, routing and security protocols. An efficient clustering algorithm must take into consideration all the necessary information related to node mobility. In this paper, we propose an Adaptive Weighted Clustering Protocol (AWCP), specially designed for vehicular networks, which takes the highway ID, direction of vehicles, position, speed and the number of neighbors vehicles into account in order to enhance the network topology stability. However, the multiple control parameters of our AWCP, make parameter tuning a non-trivial problem. In order to optimize AWCP protocol, we define a multi-objective problem whose inputs are the AWCPs parameters and whose objectives are: providing stable cluster structure as possible, maximizing data delivery rate, and reducing the clustering overhead. We then face this multi-objective problem with the the Multi-Objective Genetic Algorithm (MOGA). We evaluate and compare its performance with other multi-objective optimization techniques: Multi-objective Particle Swarm Optimization (MOPSO) and Multi-objective Differential Evolution (MODE). The experiments analysis reveal that NSGA-II improves the results of MOPSO and MODE in terms of the spacing, spread, and ratio of non-dominated solutions and generational distance metrics used for comparison