Machine Learning Based Resourceful Clustering With Load Optimization for Wireless Sensor Networks

Abstract

The sensors grouped to gather to form the network of their own, in the wireless medium and communicating to the each other over radio, faces issues that leads to failure in continuous communication, causing miss communication as it is powered by batteries with limited energy availability So it becomes essential to device a perfect routing scheme that is energy efficient. Though the clustering approach was found to be highly efficient to manage the transmission from source to the target. The elected head in each cluster has to take the entire load on it as it has to gather all the data and transmit it to the base station. So it was necessary to balance the load in the network formed using the sensor and communicating in wireless medium. The GWO (Grey Wolf Optimization)-PSO (Particle Swarm Optimization) based clustering is followed in the paper to have a perfect clustering with balanced load as well as energy efficient optimization. The method followed in the paper was simulated using the network simulator-Two to identify the performance improvements in the sensor networks communicating in wireless medium.