A bi-objective model for wireless sensor deployment considering coverage and tracking applications
Résumé
In recent years, wireless sensor networks (WSNs) have become very attractive for surveillance applications and particularly for target tracking. When a target has to be located by a WSN, accuracy is an important constraint. Most of the studies made in the WSNs problems deal with either coverage or tracking focus objectives. In this paper, we study a bi-objective sensor placement problem taking into account both coverage and accuracy. The objectives are the minimisation of the number of deployed sensors and the minimisation of the imprecision, under the coverage constraints. The non sorting genetic algorithm (NSGA-II) and multi objective evolutionary algorithm based on decomposition (MOEA/D) have been implemented to solve the problem. The performances of these algorithms are checked with integer programming results for small size instances, and they are compared on large size instances by multi-objective metrics. Results have shown that both implemented algorithms provide optimal solutions for almost small size instances. NSGA-II results are better than MOEA/D on the small size instance set, while MOEA/D outperforms NSGA-II on the large size instance set.