Multi-objective cluster head based energy efficient routing using THDCNN with hybrid capuchin search and woodpecker mating algorithm in WSN

Nowadays, Wireless Sensor Networks (WSN) is becoming essential application domains, particularly in event tracking and monitoring without human intervention. The sensor nodes are classified as having a limited lifespan in WSN because of continuous sensing, consequently, the battery drains quickly. A precise clustering and optimum path selection from sensor nodes to sink becomes significant to preserve energy. This paper proposes a Multi-Objective Based Clustering utilizing Tree Hierarchical Deep Convolutional Neural Network and Hybrid Capuchin search and Woodpecker mating Algorithm guides routing approach for sustaining energy efficiency in WSN (THDCNN-HCWA). By integrating a Tree Hierarchical Deep Convolutional Neural Network (THDCNN) with a Hybrid Capuchin Search and Woodpecker Mating Algorithm (HCWA), the method addresses critical challenges such as high traffic flow and energy depletion near the base station. The THDCNN facilitates intelligent Cluster head selection based on multiple objectives, including delay, distance, energy, cluster density, and traffic rate, ensuring optimal routing paths. The proposed technique is implemented in NS2. This innovative approach significantly enhances packet delivery ratios and overall throughput, thereby extending the operational lifespan of sensor nodes. The proposed THDCNN-HCWA method attains 25.3, 10.76, 45.67, 49.15, 50.12 and 35% higher alive nodes and 22.32, 16.76, 27.67, 11.71, 30.32 and 27.02% higher detection rate when compared with existing methods. This comprehensive strategy not only optimizes energy consumption but also ensures robust data transmission, marking a significant advancement in the field of energy-efficient routing in WSNs.