Optimal Data Placement for Scientific Workflows in Cloud

The deployment of datasets in the heterogeneous cloud computing has received increasing attention in current research. However, due to their large sizes and the existence of private scientific datasets, finding an optimal data placement strategy remains a persistent problem. The primary goal of this work is to discover an optimum placement while satisfying the security demand (SD) at the lowest cost. To effectively address this problem, a security-based optimal workflow scheduling (OWS) is proposed for privacy-aware applications over data. During negotiation, the user can submit the SD to the cloud. This work is initialized with list-based heuristics with Particle Swarm Hybridized Red Deer (PSRD). The proposed system can assign tasks for the scientific workflow in the cloud according to the virtual machine (VM). The results show that the workflow schedule provides better security yielding good makespan than the conventional methods with minimum iteration suited for a cloud environment.