Swarm Intelligence-Based Clustering and Routing Using AISFOA-NGWO for WSN

In recent years, energy conservation is an ambitious challenge, because IoT connects a limited number of resource devices. Clustering plays vital role to provide efficient energy saving mechanisms in WSN. Major issues in existing clustering algorithms are short network lifetime, unbalanced loads among sensor nodes in the network, and high end-to-end delays. This paper introduces an integration of novel artificial intelligence-based sailfish optimization algorithm (AISFOA) with Novel GrayWolf Optimization (NGWO) technique. Initially, cluster is formed using AISFOAapproach. Meanwhile, cluster head is elected after network deployment, and it can be changed dynamically based on network lifetime. Second, distance between sensor nodes is estimated by Euclidean distance to avoid data redundancy. Next, a NGWO algorithm is used to select a minimal path for routing. This research work incorporates merits of both clustering and routing techniques that lead to high energy ratio and prolonged network lifespan. Simulation is performed by using anNS2 simulator. The efficiency of the proposed SOA is analyzed with IABCOCT, EPSOCT, and HCCHE. Computer simulation outcome displays that the planned SOA enhances the energy efficiency and network lifetime, and also, it deduces node-to sink delay.