期刊
ADVANCES IN KNOWLEDGE DISCOVERY AND DATA MINING, PAKDD 2020, PT II
卷 12085, 期 -, 页码 906-917出版社
SPRINGER INTERNATIONAL PUBLISHING AG
DOI: 10.1007/978-3-030-47436-2_68
关键词
Job scheduling; Cluster scheduling; Deep reinforcement learning; Actor critic
类别
资金
- National Science Foundation [CCF-1718336, CNS-1817094]
Efficient job scheduling on data centers under heterogeneous complexity is crucial but challenging since it involves the allocation of multi-dimensional resources over time and space. To adapt the complex computing environment in data centers, we proposed an innovative Advantage Actor-Critic (A2C) deep reinforcement learning based approach called A2cScheduler for job scheduling. A2cScheduler consists of two agents, one of which, dubbed the actor, is responsible for learning the scheduling policy automatically and the other one, the critic, reduces the estimation error. Unlike previous policy gradient approaches, A2cScheduler is designed to reduce the gradient estimation variance and to update parameters efficiently. We show that the A2cScheduler can achieve competitive scheduling performance using both simulated workloads and real data collected from an academic data center.
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