A balanced serial K-means based clustering protocol for wireless sensor networks

Wireless sensor networks consisting of nodes with limited battery power are deployed to collect useful information from a certain field. How to schedule the energy resource to improve energy dissipation is one of the challenges in implementation of such system. In this paper, we propose a balanced serial K-means based clustering protocol (BSK-means) for clustering the sensor nodes. The protocol based on K-means algorithm minimizes the amount of energy for the non-cluster head nodes to transmit their data to the cluster head, by minimizing the total sum of squared distances between all the non-cluster head nodes and the closest cluster centers. BSK-means balances each cluster to help in balancing the whole system load on each cluster head. Furthermore, the cluster-heads are selected in terms of two factors, the distance and residual energy. We present the algorithm of this new protocol, analyze its performance, and validate the algorithm by simulations. Both theoretical analyses and simulation results demonstrate that BSK-means can achieve better load-balance and prolong the system lifetime for the networks compared with LEACH.