Efficient hybrid multi objective optimization algorithms for enhancing the performance of task scheduling in cloud environment

Abstract

Cloud computing is an evolution of supercomputing and provides various services ranging from resource provisioning to job completion. Internet-based parallel and distributed computing models are used to set up the cloud environment and it is one of the most reliable paradigms in computing technology. The common services rendered by cloud computing are SaaS, PaaS, IaaS. The major goal of cloud computing is servicing user tasks with optimization. The virtual machine plays a key role in the cloud environment with respect to work allocation and completion. Efficient scheduling of tasks promises increased Quality of Service (QoS). The common and important QoS expected while dealing with task scheduling is obtaining Minimum Makespan and Energy consumption which requires some optimal algorithms and solutions. currently, task scheduling problems have been addressed using various meta-heuristic algorithms such as Firefly Algorithm (FA), Ant Colony Optimization (ACO) and Genetic Algorithm (GA). Also, the local and global based searches are imbalanced and thus lead to premature convergence with an increased computational cost. Hence to atta `in the optimal solutions for these problems, two approaches for task Scheduling were proposed. A new Local Pollination based Grey Wolf Optimization Algorithm for Task Scheduling (LPGWO-TS) has been proposed for optimal task scheduling in a heterogeneous cloud environment. The proposed LPGWO algorithm is an amalgamation of the Flower Pollination and Grey Wolf Optimization Algorithm. This aims at finding the right resource to hand over the task during task scheduling.The convergence time is reduced at the final iteration based on the explorations in early iterations newline