Voronoi Neighbor Based Energy Efficient Event Detection in Wireless Sensor Networks

In a wireless sensor network (WSN), a dense deployment results in nodes having overlapping communication and sensing ranges. In such an environment, an event is monitored and reported by multiple nodes, generating high traffic and consuming most of their resources simultaneously. High in-network traffic and redundant readings pauperize the accuracy of the event detection and significantly affect the decision making process. In this work, a novel interpolation technique is proposed to minimize the in-network traffic at the leaf level. Pairwise Markov model along with local inference at every intermediate node, is used to determine the shortest path with minimum energy consumption in a network modelled as a Markov Random Field (MRF). Simulation results prove that the proposed scheme is able to achieve significantly accurate event reporting rate as compared to other existing schemes.