Leveraging Swarm Intelligence Algorithms for Load Balancing in Cloud Computing Infrastructure: A Survey on Recent Advances
Year: 2024
Type: article
Abstract: In cloud computing, load balancing is essential for maximizing system performance, guaranteeing availability, and optimizing resource use. Because of the growing complexity and scalability requirements of contemporary cloud settings, traditional static and dynamic load balancing algorithms sometimes find it difficult to adjust. Swarm Intelligence (SI) algorithms, inspired by the collective behavior of biological swarms, have emerged as effective meta-heuristic optimization techniques for task distribution and resource management. This survey explores the recent advancements in SI-based load balancing approaches, categorizing them into traditional and modern techniques. Traditional SI methods such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Ant Colony Optimization (ACO), Artificial Bee Colony (ABC), Grey Wolf Optimization (GWO), and BAT Algorithm offer improved efficiency but face challenges related to convergence speed and adaptability. To address these limitations, modern SI techniques like Whale Optimization Algorithm (WOA), Social Spider Algorithm (SSA), Dragonfly Optimization Algorithm (DOA), and Raven Roosting Optimization (RRO) incorporate adaptive strategies for enhanced scalability and dynamic task allocation. This research offers a thorough evaluation of different algorithms, contrasting their effectiveness, computational complexity, and practicality. The results show that cutting-edge SI techniques hold potential for flawless load balancing, quicker reaction times, and more effective utilization of cloud computing resources.
Author: Stefy Methew
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7217266180