Combined Osprey-Chimp Optimization for Cluster Based Routing in Wireless Sensor Networks: Improved DeepMaxout for Node Energy Prediction

Abstract

The significant advances in Wireless Sensor Networks (WSNs) facilitate many latest applications, such as intelligent battlefield, home automation, traffic control, and more. WSNs comprise small autonomously organized sensor nodes that are powered by batteries. The processes of collecting information and data storage, processing, and transmission deplete the energy of these small devices. Energy efficiency is still a major issue to address in WSN routing. Clustering is the best method that has been developed to reduce node energy consumption. However, current clustering methods are unable to effectively distribute the energy requirements of the nodes without considering energy characteristics, number of nodes, and flexibility. This study proposed a new cluster-based routing model for WSNs and emphasized the need for an improved clustering process with new optimization techniques. In particular, the improved DeepMaxout model was adopted to predict the energy of the nodes. Cluster Head (CH) selection is performed considering the nodes' energy as a prime factor. After choosing the CH, the CIOO algorithm incorporates new link quality and trust evaluations while determining the routing process. Finally, a comparison of energy utilization factors was performed between the suggested and traditional approaches.