Abstract

Cloud computing environments face increasing challenges in efficient resource allocation due to dynamic workloads, heterogeneous resources, and varying quality of service requirements. This paper presents a novel hybrid algorithm combining particle swarm optimization (PSO) with genetic algorithms (GA) and reinforcement learning techniques to address resource allocation optimization in cloud computing platforms. The proposed Hybrid Adaptive Resource Allocation Algorithm (HARAA) incorporates multi-objective optimization considering computational cost, energy consumption, and service level agreements. Experimental validation on CloudSim simulator demonstrates superior performance with 42% improvement in resource utilization efficiency, 35% reduction in energy consumption, and 29% decrease in average response time compared to existing algorithms. The hybrid approach successfully balances trade-offs between performance optimization and cost minimization while maintaining high service quality standards.