Performance measures of fuzzy C-means algorithm in wireless sensor networks

The major issues that govern performance of wireless sensor networks (WSNs) are efficient uses of limited resources and appropriate routing decisions of network paths under the severely constrained energy scenario. In this work, to address these issues uses of k-means and fuzzy C-means algorithms are investigated for clusters formation and subsequent selection of cluster heads (CHs). For all these newly formed clusters; selection of cluster head is done based on member sensor nodes residual energy status (RES) followed by estimation of Euclidean distances. Depending upon the Euclidean distance measures between the sink node and the estimated energy-centroid (EC) of clusters these clusters are classified into five types. The RES estimation is exercised for all the CHs and sensor nodes (SNs) of the network. Outcomes of simulation results indicate superior performance of fuzzy-c means algorithm compared to k-means algorithm. Further, a case study is presented, wherein the sink is allowed to have some movements in the service area. Here, different quadrant of service area exhibits different pattern of query spatial distribution. The optimal location of sink is sought to support energy efficient operational aspects of the WSNs.