Heuristic algorithms for task scheduling in Cloud Computing using Combined Particle Swarm Optimization and Bat Algorithms

Abstract The rapid growth in demand for computing power has led to a shift towards a cloud-based model relying on virtual data centers. In order to meet the demand of cloud computing clients, cloud service providers need to maintain service quality parameters at optimum levels. This paper presents a hybrid algorithm dubbed PSOBAT-Greedy, which is expected to reduce cost and time while enhancing the efficiency of resources. The main idea behind the newly proposed algorithm is to find an optimal weight for local and global search using Range and Tuning functions as an important solution overcoming various problems in task scheduling and provide the right response within an acceptable time. The new hybrid algorithm is less time-consuming and costly than the other two algorithms. As compared to particle swarm optimization (PSO) algorithm and combined particle swarm optimization and bat algorithm (PSOBat), resource efficiency improves by 15% and 5%, respectively. Keywords: Quality of Service, Cloud Computing, Particle Swarm Optimization, Bat Algorithm