Efficient and Scalable ACO-Based Task Scheduling for Green Cloud Computing Environment

Cloud Computing has emerged as a popular technology that support computing on demand services by allowing users to follow the pay-per-use-on-demand model. Minimizing energy consumption in cloud systems has many benefits that enable green computing. Energy aware task scheduling in cloud to the users by service cloud providers has non negligible influences on optimal resources utilization and thereby on the cost benefit. The traditional algorithms for task scheduling are not well enough for cloud computing. In such environment, tasks should be efficiently scheduled such a way that the makespan is reduced. In this paper, we proposed a biologically inspired scheduling scheme, which is a based on a modified version of the ant colony optimization that aims at reducing the makespan time while ensuring load balancing among resources in order to enable green computing. Experiments of the proposed scheme in various scenario have been conducted in order to elaborate the impact of proposed models in the reduction of makespan. The obtained results demonstrate the effectiveness of the proposal in regards to the compared algorithms.