The localization in wireless sensor networks by using secretary bird optimization algorithm

Day after day, wireless sensor networks are attracting the attention of researchers and authors due to the urgent need for their applications in the fields of medicine, science, and engineering. Wireless sensor networks are vital to the Internet of Things. These networks consist of sensors, or nodes, distributed in a targeted area to monitor, track, control, and detect data. There are many challenges facing wireless sensor networks, such as node deployment, energy consumption, data collection, and node localization. This study focuses on localization in WSNs, as collecting data extracted from a given event that occurs at a time in these networks is of great importance. Here comes the role of localization to estimate the physical locations of sensors in the network whose locations are unknown. Furthermore, the potential of using the coordinates of these locations to determine the optimal route in these networks, thereby minimizing energy consumption and prolonging the lifespan of individual nodes, therefore, the localization represents one of the most critical challenges in resource-constrained WSNs. Many researchers consider localization problems as optimization problems to enhance performance and accuracy. The best approach to address the localization problem involves utilizing swarm intelligence algorithms, which have demonstrated greater effectiveness than classical methods. The scientists presented quite significant evidence for metaheuristic algorithms-based swarm intelligence outperforms traditional optimization methods in complex optimization tasks and dynamic multi-modal environments, as they have a remarkable ability to explore the solution area on a large domain, adapt to changing conditions, deal with uncertainty, and have greater flexibility with multi-objective optimization problems, allowing processing without the need for complex modifications. This study aims to predict the location of wireless sensors using the proposed Secretary Bird Optimization algorithm, which simulates the flocking behavior of the Secretary Bird in Africa. A comparison was conducted between the effectiveness of the proposed algorithm and the particle swarm optimization algorithm (PSO); the simulation outcome showed that SBOA is more accurate and has higher performance in node localization than PSO.