Swarm based Computational Intelligence Techniques for Performance Optimization in Wireless Sensor and Actuator Networks

WSANs are networks that are made of several distinct nodes that collectively understand the environment, subsequently change the state of the atmosphere, and select an appropriate action to perform after substituting on it. As a natural progression of Wireless Sensor Networks (WSNs), WSANs present many of the same research difficulties as well as many new ones. These difficulties come from dealing with incomplete and complex optimization problems, ambiguous data, or processing and gathering data from different areas. Computational intelligence (CI) is a general term that refers to a group of naturally occurring and language-inspired methods that offer powerful answers to real-world problems. As a result, various investigators have moved to CI in their hopes of discovering results for several WSAN-related problems. The present paper examines the application of numerous CI approaches to the WSAN field and review the swarm-based CI techniques for performance optimization of WSANs. After reviewing and classifying previous works, Particle Swarm Optimization (PSO) to maximize energy efficiency, load balancing, and fault tolerance in Wireless Sensor and Actuator Networks (WSANs) is implemented. A comparison of PSO, GA, and ACO in WSAN optimization problems shows that PSO consistently outperforms GA and ACO across all examined measures.