Particle Swarm Optimization-Based Data Aggregation in Wireless Sensor Network

Abstract

Wireless sensor networks have battery-operated sensor nodes, which need to be conserved to have prolonged network lifetime. The amount of power consumed for routing sensed data from the sensor node to the sink node is large. Thus, in order to optimize the energy usage in sensor network efficient data aggregation techniques are needed. Particle swarm optimization (PSO) is a speculative and evolutionary computing technique based on swarm intelligence for solving optimization problems in sensor network such as nodes deployment, node scheduling, data clustering, and aggregation. The paper proposes a PSO-based sensor network aggregation protocol (PSO-SNAP) with K-means to provide initial centroid. The PSO has been used to find the optimal aggregated value having minimum quantization error. The output of the K-means algorithm is used as an initial centroid in PSO. Apart from K-means, K-medoid and simple average has also been used to provide initial seed to the PSO algorithm and results of all three approaches are compared.