A hybrid genetic algorithm for scientific workflow scheduling in cloud environment
- PDF / 1,798,468 Bytes
- 16 Pages / 595.276 x 790.866 pts Page_size
- 78 Downloads / 204 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
A hybrid genetic algorithm for scientific workflow scheduling in cloud environment Hatem Aziza1 • Saoussen Krichen1 Received: 23 March 2019 / Accepted: 20 March 2020 Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Nowadays, we live an unprecedented evolution in cloud computing technology that coincides with the development of the vast amount of complex interdependent data which make up the scientific workflows. All these circumstances developments have made the issue of workflow scheduling very important and of absolute priority to all overlapping parties as the provider and customer. For that, work must be focused on finding the best strategy for allocating workflow tasks to available computing resources. In this paper, we consider the scientific workflow scheduling in cloud computing. The main role of our model is to optimize the time needed to run a set of interdependent tasks in cloud and in turn reduces the computational cost while meeting deadline and budget. To this end, we offer a hybrid approach based on genetic algorithm for modelling and optimizing a workflow-scheduling problem in cloud computing. The heterogeneous earliest finish time (HEFT), an heuristic model, intervenes in the generation of the initial population. Based on results obtained from our simulations using real-world scientific workflow datasets, we demonstrate that the proposed approach outperforms existing HEFT and other strategies examined in this paper. In other words, experiments show high efficiency of our proposed approach, which makes it potentially applicable for cloud workflow scheduling. For this, we develop a GA-based module that was integrated to the WorkflowSim framework based on CloudSim. Keywords Cloud computing Genetic algorithm Scientific workflow Workflow scheduling Deadline Budget
1 Introduction Over last few years, cloud computing (CC) has become an emerging research area. It is considered as the main model of distributed computing. It offers elastically scalable and highly available resources as a subscription-based service like utility computing [1] for executing scientific workflows (SWfs). The SWf (such as Montage, CyberShake, Epigenomics, LIGO and SIPHT) is a transposition of the general term of workflow in the experimental context, that is to say relating only to computational processes via complex data flows and control dependencies while & Hatem Aziza [email protected] Saoussen Krichen [email protected] 1
automating their implementations in appropriate resources [2]. Successful execution of SWf requires optimal use of resources. For that, the work must be focused on finding the best strategy for allocating workflow tasks to available computing resources. This is called workflow scheduling (WS). The WS aims at mapping and managing the execution of interdependent tasks by considering precedence constraints on shared resources [3]. This problem is known to be NP-Complete [3] due to its combinatorial aspe
Data Loading...
