期刊
IEEE SYSTEMS JOURNAL
卷 16, 期 3, 页码 4232-4242出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSYST.2021.3122126
关键词
Quality of service; Cloud computing; Scheduling; Processor scheduling; Real-time systems; Training; Trajectory; Adversarial imitation learning; cloud computing; deep reinforcement learning (DRL); job scheduling; quality of service (QoS); real-time jobs
类别
资金
- Fundamental Research Funds for the Central Universities [2021MS017]
- National Science Foundation of China [61902222]
- Taishan Scholar Youth Program of Shandong Province [tsqn201909109]
- Science Foundation Ireland [SFI/12/RC/2289P2]
The article discusses utilizing a deep adversarial imitation reinforcement learning (AIRL) framework to address the scheduling of time-sensitive cloud jobs, aiming to maximize job successful rate and reduce job response time. Experimental results demonstrate that AIRL generally outperforms existing cloud job scheduling approaches across different real-time workload and computing resource configurations.
Although cloud computing is one of the promising technologies for online business services, how to schedule real-time cloud jobs with high quality of service (QoS) is still challenging current techniques. With the advancing of machine learning, deep reinforcement learning (DRL) has demonstrated its outstanding capability in dispatching time-sensitive tasks. However, the reinforced rewards in DRL are typically unavailable until the completion of the scheduling for all the jobs. Considering the fact that the trajectory of jobs in cloud is always long, current DRL-based solutions will meet challenges in finding the trajectories with high rewards, and thus would have issues such that the finally trained scheduling policy is suboptimal. To improve the problem, in this article, we propose a more advanced approach called a deep adversarial imitation reinforcement learning (AIRL) framework for scheduling time-sensitive cloud jobs. Specifically, we focus on scheduling user requests in a way to maximize job successful rate along with a significant reduction on job response time. We present the detailed design of our method, and our experimental results demonstrate that AIRL can generally outperform the existing cloud job scheduling approaches, including the DRL-based method, in the presence of different real-time workload and computing resource configurations.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据