Energy Efficient Scheduling of Scientific Workflows in Cloud Environment

Cloud computing makes utility computing possible with pay as you go model. It virtualizes the systems by polling and sharing the resources, thus we need to handle more than one workflow at the same time. Workflow is the standard to represent compute intensive applications in scientific and engineering domain. Hence, in this article, the authors presented the scheduling heuristic for multiple workflows running parallel in the cloud environment with the aim to reduce the energy consumption as it is one of the major concerns of cloud data centers along with the execution performance. In the proposed approach, first clustering is performed to minimize the energy consumption and execution time during communication corresponding to precedence constraint tasks. Then cluster are scheduled is on the best available energy efficient resources. Finally, DVFS is applied in order to reduce energy consumption further when the nodes are in the idle and communication stage. The simulation has been performed on CloudSim and the results show the reduction in energy consumption by up to 42%.

Download Full-text

PSO-COGENT: Cost and energy efficient scheduling in cloud environment with deadline constraint

Sustainable Computing Informatics and Systems ◽

10.1016/j.suscom.2018.06.002 ◽

2018 ◽

Vol 19 ◽

pp. 147-164 ◽

Cited By ~ 9

Author(s):

Mohit Kumar ◽

S.C. Sharma

Keyword(s):

Energy Efficient ◽

Cloud Environment ◽

Energy Efficient Scheduling ◽

Deadline Constraint

Download Full-text

Design of Energy Aware Scheduling Algorithm for Executing Scientific Workflows in Cloud

International Journal of Engineering and Advanced Technology - Regular Issue ◽

10.35940/ijeat.a2013.129219 ◽

2019 ◽

Vol 9 (2) ◽

pp. 1305-1311

Keyword(s):

Energy Efficient ◽

Virtual Machines ◽

Scheduling Algorithm ◽

Scientific Workflow ◽

Scientific Workflows ◽

Cloud Environment ◽

Scientific Applications ◽

Energy Aware ◽

Efficient Manner ◽

The Given

The usage of cloud computing and its resources for the execution of scientific workflow is a rapidly increasing demand. The Scientific applications are generally large in scale; even a single scientific workflow includes more number of complex tasks. Execution of these tasks can be made successful only by deploying it in the cloud virtual machines, because only cloud environment can only provide very large number of computing assets. In cloud, every processing resource is given as Virtual Machine. Any scientific workflow deployed in the cloud needs large number of virtual machines so; huge amount of computational energy is spent by the virtual machines to execute multifaceted scientific workflows. Hence there arises the need to utilize the cloud resources in an energy efficient way. Also, if the virtual machines are planned to schedule in an energy efficient manner there is an increase of makepsan of the workflow which is going to be an important parameter for completing the workflow within the deadline. So, the need for executing scientific workflows in energy efficient way with reduced makespan becomes a major issue among the researchers. It also becomes very challenging task to executing a scientific workflow in within the given deadline of a task in the given workflow. To address these issues, a new Energy Aware workflow scheduling algorithm is proposed and designed with improved makespan for the execution of different scientific applications in cloud environment.

Download Full-text