Perceptron-based AOW Clustering Algorithms

摘要

Clustering Algorithms has been widely used in Ad hoc network with its ability to construct network quickly, conveniently and flexibly and without the need of default network infrastructure. In this paper, Firstly, some shortcomings of the typical algorithm AOW (adaptive on-demand weighted algorithm) are introduced and analyzed. Then, we discusses the calculating method of nodes weights with perceptron algorithm and the cluster heads selecting process with modified algorithms based on original AOW to meet system requirements. So, a adaptive on-demand weighted algorithm based perceptron (PerAOW) is proposed to select cluster heads in Ad hoc network. Compared to AOW, simulation results proved that the proposed algorithm are improving network topological structure and giving 5.2% better load balance factor (LBF).