Chronological wild geese optimization algorithm for cluster head selection and routing in wireless sensor network

Abstract

SummaryWireless sensor networks (WSNs) consist of numerous sensor nodes with limited battery life, computational power, and network capabilities. These sensors are deployed in specific areas to monitor environmental physical parameters. Once the data are collected, it is processed and transmitted to a base station (BS) via designated routes. The processes of sensing and transmitting consume significant energy, leading to rapid depletion of node batteries and the occurrence of hot spot problems. Consequently, relying on a single route for data transmission can result in network overhead issues. Enhancing the energy efficiency of WSNs is a persistent challenge. To address this, improvements in processes, such as routing and clustering are necessary. Implementing dynamic cluster head (CH) selection is a key approach for optimal path selection and energy conservation. Accordingly, in this work, a novel multiobjective CH selection and routing method for providing energy‐aware data transmission in WSN is presented. Here, CH selection is carried out using the proposed chronological wild geese optimization (CWGO) technique based on multiple constraints, such as delay, intercluster distance, intracluster distance, Link Life Time (LLT), and predicted energy. Further, the nodes' energy is determined by the deep recurrent neural network (DRNN). Then, the ideal path from the node to the BS is identified by the CWGO considering constraints, like predicted energy, delay, distance, and trust. Moreover, the proposed CWGO is examined considering metrics, like energy, trust, distance, and delay and is found to have attained superior values of 0.963 J, 0.700, 19.468 m, and 0.252 s, respectively.