A smart energy and reliability aware scheduling algorithm for workflow execution in DVFS-enabled cloud environment

The energy consumption is one of the major concerns addressed by recent researches in the green cloud environment. As a result, to decrease the enormous increase in energy consumption, one of the most promising scheduling techniques used nowadays is the Dynamic Voltage Frequency Scaling (DVFS) techn...

Full description

Saved in:
Bibliographic Details
Published in:Future generation computer systems Vol. 112; pp. 431 - 448
Main Authors: Hassan, Hadeer A., Salem, Sameh A., Saad, Elsayed M.
Format: Journal Article
Language:English
Published: Elsevier B.V 01.11.2020
Subjects:
DAG workflow
DVFS-enabled
Energy efficient
Green cloud computing
Heterogeneous system
Reliability
Task scheduling algorithm
Heterogeneous system
Task scheduling algorithm
Reliability
DAG workflow
DVFS-enabled
Energy efficient
Green cloud computing
ISSN:0167-739X, 1872-7115
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The energy consumption is one of the major concerns addressed by recent researches in the green cloud environment. As a result, to decrease the enormous increase in energy consumption, one of the most promising scheduling techniques used nowadays is the Dynamic Voltage Frequency Scaling (DVFS) technique. DVFS reduces energy consumption by lowering the processors’ frequency for virtual machines (VMs); this results in an increase in the occurrence of errors during the execution of the workflow, which decreases the reliability of the system. As a consequence, this paper addresses the DVFS problem by proposing a new Smart Energy and Reliability Aware Scheduling algorithm (SERAS) for workflow execution in the cloud environment. The SERAS approach split the target deadline of workflow across tasks. Afterward, the proposed algorithm decreases the frequency of processors for VMs using the DVFS technique without missing the tasks’ deadline. As a consequence, the SERAS algorithm allocates the tasks to the most appropriate VMs with suitable frequencies levels while guaranteeing both the reliability and the completion time requirement of green cloud systems. To vindicate the effectiveness of the SERAS algorithm in real-world applications, we carried out a series of experiments on four real workflows generated using a scientific toolkit. Also, we performed comprehensive experiments with recent researches. The results showed that the SERAS algorithm outperforms its competitors while keeping both the reliability and completion time requirements. Furthermore, the estimated time complexity and average execution time show the applicability of the SERAS algorithm compared with their competitors. •A proposed reliable Energy-aware scheduling algorithm for workflow execution.•Fault detection and correction using checkpointing with rollback recovery criterion are applied.•A reduction of 30% to 50% in energy consumption and speed up to 97% faster than other competitors are achieved.•Benchmarking using CloudSim simulator for cloud computing environment.•CyberShake, Montage, Sipht, and Epigenomics for benchmarking real domain problems.
ISSN:0167-739X
1872-7115
DOI:10.1016/j.future.2020.05.040