Energy Efficiency Analysis in IoT-Driven Computational Intelligence System using Meta-heuristic Optimization Algorithms

The rapid expansion of IoT devices across various domains has introduced significant energy consumption challenges, requiring innovative approaches for enhancing energy efficiency. This paper explores five well-known meta-heuristic optimization algorithms for improving energy efficiency in IoT-driven computational intelligence systems. These five key algorithms are: Gray Wolf Optimizer (GWO), Ant Colony Optimization (ACO), Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Artificial Bee Colony (ABC). We have evaluated these algorithms for their ability to minimize energy consumption while maintaining optimal system performance. By analyzing various energy-efficient strategies, the paper addresses critical issues such as dynamic workload management, resource constraints, and communication overhead that are vital in IoT ecosystems characterized by limited energy resources. The experimental results show that the GWO and PSO algorithms outperformed others in terms of energy savings and convergence speed, demonstrating significant potential for enhancing the sustainability of IoT networks. The paper also discusses the implications of these findings for extending the lifespan of IoT devices and minimizing environmental impact, making meta-heuristic algorithms a promising solution for IoT energy management.