Security-Aware Workflow Scheduling with Selective Task Duplication in Clouds
Xiaomin Zhu, Yabing Zha, Peng Jiao, Huangke Chen · 2016
High quality of security service is increasingly critical for cloud workflow applications. Unfortunately, most existing scheduling strategies disregard security requirements for workflows and do not adequately exploit idle time resulting in long makespan. To address this issue, in this paper, we firstly make comprehensive analysis to minimize tasks' start time and generate useful time slots for task duplications to further reduce makespan. Based on the analysis, we devise a novel security-aware workflow scheduling algorithm SAWS including two important phases: 1) task scheduling with selectively duplicating tasks to idle time slots, and 2) intermediate data encrypting by effectively exploiting tasks' slack times. Simulation experiments injecting randomly generated workfows and some real-world workflow traces are conducted to validate the superiority of our SAWS by comparing it with some baselines. The experimental results show that SAWS outperforms others in terms of makespan (up to 21%), monetary costs (up to 40%) and resource utilization (up to 35%).