Node clustering and data aggregation in wireless sensor network using sailfish optimization

Wireless sensor networks (WSN) are an assortment of sensor nodes that are used in multiple fields. Wireless sensor networks, often known as WSNs, have garnered much interest recently owing to their limitless potential. Because the WSN field is barely ten years old and WSN has typical characteristics and constraints, there are many problems associated with WSN that need to be studied, analyzed, and solved as well as many challenges that need to be met for its widespread use and easy acceptance by users. These problems and challenges can be attributed to WSNs having typical characteristics and constraints. The growth of WSN technology is limited by lifetime issues. A major portion of power is wasted by forwarding redundant data from the sensor nodes (SN) to the base station (BS). So, a specific and accurate data aggregation technique is needed for successful WSN use. In this work, two major contributions are proposed. Initially, Sail Fish Optimization (SFO) based on cluster head selection algorithm was introduced for clustering. Then, an improved SVM classification algorithm was proposed for data aggregation. The hyperparameters of SVM are adjusted by using Sailfish Optimization. Sailfish Optimization is one of the many nature-inspired optimization techniques. It is based on the hunting nature of sailfish in oceans. In comparison to existing algorithms, the proposed algorithm’s performance is measured in terms of delay, energy, packet delivery ratio, and data classification accuracy compared to other algorithms. The proposed work achieves the overhead with minimal value of 5.56% compared to existing methods. © 2023, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.