Abstract:

Abstract Data center workload allocation and resource utilization have been challenged by rising cloud service demand. Load balancing ensures resource allocation, response time reduction, and system performance optimization. This paper proposes bio-inspired hybrid load-balancing for cloud based physical servers. The suggested load balancing method uses ACO and PSO algorithms. The “Ant Colony Optimization” (ACO) method mimics ants foraging to find the best pathways, whereas the Particle Swarm Optimization (PSO) approach explores the search space like a swarm. Integrating the methodologies should improve load balance and convergence. We developed a novel performance assessment method that considers reaction time, throughput, resource usage, and energy consumption to evaluate the suggested strategy. Load balancing methods typically ignore energy efficiency and focus on a limited set of performance criteria. This paper presents a unique assessment tool to analyze the suggested approach's performance and energy efficiency. In a simulated cloud data center environment, the proposed algorithms and other parallel research methods are tested with a proposed QoS metric. The bio-inspired hybrid load balancing algorithm outperforms traditional algorithms in response time, SLA violation, VM migrations, and efficiency. The evaluation shows that energy efficiency in load balancing choices has significant economic and environmental benefits. This work advances cloud data center load balancing. The paper provides a bio-inspired hybrid technique and a complete performance evaluation strategy. The suggested cloud method optimizes resource efficiency, reaction time, and system performance. The evaluation approach also helps decision-makers balance load based on performance and energy efficiency criteria.

Keywords: