Performance analysis of iterative linear regression‐based clustering in wireless sensor networks

Abstract

Clustering, an energy efficient approach is preferred in wireless sensor network due to the limited energy consumption of sensor nodes. Clustering saves energy as the communication is restricted to a few nodes, thereby increasing the network lifetime. Recently, an iterative linear regression-based clustering is proposed to improve the cluster quality in a wireless sensor network. The quality of clusters so obtained is evaluated through Matlab using the cluster validity analysis platform. However, the performance of the clusters so obtained using iterative linear regression in terms of energy efficiency is not dealt. Hence, an attempt is made to investigate the performance of the network through real time experiments. The network performances are studied in terms of intra-cluster and inter-cluster energy consumption, first node death, half node death and last node death. To prove the effectiveness of the proposed technique, it is compared with the standard k-means clustering algorithm. The results reveal that the clusters obtained using iterative linear regression is efficient in enhancing the lifetime of the wireless sensor network.