Multi-objective Grey Wolf Optimization based self configuring wireless sensor network

Wireless Sensor Networks are essential for monitoring physical objects in smart systems powered by the Internet of Things. It gathers information by detecting the surroundings and transmits it to a central repository. In this study, an unknown domain was explored using multi-objective optimization. This proposed work employs Multi-objective Grey Wolf Optimization to form effective clustering among nodes and also for choosing the cluster head. Based on the multi-objective fitness function, the cluster heads are selected. For every iteration, the cluster heads are changed thereby saving the consumption of energy and also resulting in an increase in network lifespan. The suggested method divides the network into various optimal-sized clusters and chooses the best cluster heads. The performance of the multi-objective exploration is presented. The proposed method`s key contributions are by utilizing MOGWO for efficient clustering and CH selection, ultimately enhancing network performance. It dynamically adjusts CHs, resulting in energy savings and an extended network lifespan. MOGWO takes into account multiple objectives simultaneously. Through network configuration optimization, MOGWO enhances resource utilization, resulting in lower energy consumption, extended network lifetime, and improved overall efficiency.