Multi‐objective cluster head‐based energy aware routing using optimized auto‐metric graph neural network for secured data aggregation in Wireless Sensor Network

Abstract

SummaryThe data are combined and transmitted through wireless sensor network (WSN) in internet of things applications. Multi‐Objective Cluster Head Based Energy Aware Routing using Auto‐Metric Graph Neural Network with Hybrid Balancing Composite Motion and Border Collie Optimization is proposed in this article for secured data aggregation (SDA) in WSN. The proposed method activates routing procedure via cluster head (CH). Hence, data aggregation basis Auto‐Metric Graph Neural Network selects CH depending upon multi‐objective fitness function. This fitness function deems factors, such as energy, delay, throughput, distance amid the nodes, capacity, collision, traffic rate, and cluster density. After CH selection, malicious node is present in the cluster. The optimum path is depending on three parameters: trust, connectivity, and quality of service (QoS). These three parameters have optimized under Hybrid Balancing Composite Motion and Border Collie Optimization method for ideal path selection. The ideal path is employed to transmit the gathered data to base station. The proposed technique is executed in network simulator, and its efficiency is evaluated under performance metrics, like network lifetime, packet delivery ratio, and delay. The proposed technique achieves 19.67%, 22.38%, and 27.45% better network lifetime; 28.92%, 25.83%, and 19.46% better packet delivery ratio; and 12.32%, 34.54%, and 22.33% lower delay while compared to the existing models: Taylor‐spotted hyena optimization for dependable and energy‐efficient CH selection‐based safe data routing and fault tolerance in WSN (T‐SHO‐DAWSN), multi‐objective cluster head utilizing SAPGAN for secured data aggregation (SAPGAN‐DAWSN), and energy efficient data accumulation design for protected routing protocol in WSN (MDAS‐DAWSN) methods, respectively.