Scheduling workflows with privacy protection constraints for big data applications on cloud

Abstract

Nowadays, business or scientific processes with massive big data in Cyber-Physical-Social environments are springing up in cloud. Cloud customers’ private information stored in cloud may be easily exposed and lead to serious privacy leakage issues in Cyber-Physical-Social environments. To avoid such issues, cloud customers’ privacy or sensitive data may be restricted to being processed by some specific trusted cloud data centers. Therefore, a new problem is how to schedule workflow with such data privacy protection constraints, while minimizing both execution time and monetary cost for big data applications on cloud. In this paper, we model such problem as a multi-objective optimization problem and propose a Multi-Objective Privacy-Aware workflow scheduling algorithm, named MOPA. It can provide cloud customers with a set of Pareto tradeoff solutions. The problem-specific encoding and population initialization are proposed in this algorithm. The experimental results show that our algorithm can obtain higher quality solutions when compared with other ones.