MPHC: Preserving Privacy for Workflow Execution in Hybrid Clouds

Abstract

Cloud computing has been developed in response to demand from companies seeking to deal with the execution cost of their complex distributed applications. Introducing the notion of hybrid clouds to the cloud computing paradigm brings out many challenges in resource provisioning for workflows. Hybrid clouds encounter the following two main obstacles in reaching their full potential: (1) customers' dissatisfaction due to the conflicting nature of the constraints (budget and deadline), and (2) exposure of customers' private data/jobs in hybrid cloud infrastructures. We believe that too little attention is paid to privacy issues for workflow scheduling under deadline constraint. Many algorithms exist to address the cost and time trade-off, however, they suffer from insufficient consideration of privacy. In this study, we present an algorithm that preserves privacy in scheduling of workflows, whilst still considering customers' deadlines and cost. We evaluated our approach using real workflows running on a private HTCondor-based hybrid cloud. Results were promising and demonstrated the efficiency of our approach in not only reducing the cost of executing workflows, but also satisfying both the privacy and deadline constraints of the submitted workflows.