This paper presents a comprehensive analysis of nature-inspired metaheuristic algorithms for achieving energy efficiency in the Edge-Cloud environment. The study focuses on the Particle Swarm Algorithm (PSO), Ant Colony Optimization (ACO), and Firefly algorithm, evaluating their performance in workload distribution balance, processing speed, and energy consumption. The simulations are conducted using the ReCloud Simulator. The results reveal that the PSO algorithm outperforms the ACO and Firefly algorithms in workload distribution balance. The ACO algorithm excels in exploration, while the Firefly algorithm demonstrates superior processing speed. However, the Firefly algorithm exhibits slight performance variations due to its sensitivity to workload characteristics. Both the Firefly and PSO algorithms show energy efficiency comparable to or slightly lower than the ACO algorithm. These findings contribute to a better understanding of the strengths and weaknesses of each algorithm, offering valuable insights for researchers and practitioners in the field of energy-efficient computation offloading in the Edge-Cloud environment.
Reference:
Afachao, K., Abu-Mahfouz, A.M. & Hancke, G. 2023. Comparative analysis of nature-inspired algorithms for energy efficiency and load-balancing in the edge-cloud environment. http://hdl.handle.net/10204/13533 .
Afachao, K., Abu-Mahfouz, A. M., & Hancke, G. (2023). Comparative analysis of nature-inspired algorithms for energy efficiency and load-balancing in the edge-cloud environment. http://hdl.handle.net/10204/13533
Afachao, K, Adnan MI Abu-Mahfouz, and GP Hancke. "Comparative analysis of nature-inspired algorithms for energy efficiency and load-balancing in the edge-cloud environment." Southern Africa Telecommunication Networks and Applications Conference (SATNAC) 2023, 27 - 29 August 2023 (2023): http://hdl.handle.net/10204/13533
Afachao K, Abu-Mahfouz AM, Hancke G, Comparative analysis of nature-inspired algorithms for energy efficiency and load-balancing in the edge-cloud environment; 2023. http://hdl.handle.net/10204/13533 .