An improved genetic algorithm for wireless sensor networks localization

Abstract

Genetic algorithm in the wireless sensor networks localization has a problem that positioning errors of some nodes are larger, in this paper we propose an improved algorithm based on genetic algorithm with filter replenishment strategy(FRGA), we improve the regional constraint of the initial population of genetic algorithm, and introduce the filter and replenishment strategy, from the perspective of population differences in performance, we delete the poor individual to maintain population overall performance, and solve the problem that localization accuracy of some nodes is poor which caused by the premature convergence. Experiments show that the localization accuracy of the improved algorithm is better than the GA, and the improved algorithm has faster convergence speed, and suitable for large-scale wireless sensor networks.