Reinforcement learning-based adaptive resource management of differentiated services in geo-distributed data centers
Reinforcement learning-based adaptive resource management of differentiated services in geo-distributed data centers
复制标题
DOI：
10.1109/iwqos.2017.7969161
复制
发表时间：
2017-06
期刊：
影响因子：
--
通讯作者：
Xiaojie Zhou;Kun Wang;Weijia Jia;M. Guo
中科院分区：
文献类型：
--
作者：
Xiaojie Zhou;Kun Wang;Weijia Jia;M. Guo
为了更好地提供服务和利用可再生能源，互联网服务提供商已经在地理上分散的位置建立了他们的数据中心。这些公司通过迁移虚拟机(VM)和自适应地分配服务器资源来平衡服务质量(Qos)收入和功耗。然而，现有的方法通过违反服务等级协议(SLA)来建模服务质量收益，并且忽略了网络通信成本和迁移时间。本文提出了一种基于强化学习的自适应资源管理算法，其目标是在服务质量收益和功耗之间取得平衡。该算法不需要假设资源需求的先验分布，在实际工作负载中具有较强的鲁棒性。该方法在三个方面优于已有的方法：1)直接用不同任务的差异化收益来模拟服务质量收益，而不是使用违反SLA的方法。2)对于地理位置分散的数据中心，考虑了迁移虚拟机的时间和网络通信成本。3)对强化学习算法的信息存储和随机行为选择进行了优化，实现了快速决策。实验表明，我们提出的算法比现有的算法具有更强的鲁棒性。此外，在非区分服务和区分服务下，该算法的功耗分别比现有算法提高了13.3%和9.6%。
For better service provision and utilization of renewable energy, Internet service providers have already built their data centers in geographically distributed locations. These companies balance quality of service (QoS) revenue and power consumption by migrating virtual machines (VMs) and allocating the resource of servers adaptively. However, existing approaches model the QoS revenue by service-level agreement (SLA) violation, and ignore the network communication cost and immigration time. In this paper, we propose a reinforcement learning-based adaptive resource management algorithm, which aims to get the balance between QoS revenue and power consumption. Our algorithm does not need to assume prior distribution of resource requirements, and is robust in actual workload. It outperforms other existing approaches in three aspects: 1) The QoS revenue is directly modeled by differentiated revenue of different tasks, instead of using SLA violation. 2) For geo-distributed data centers, the time spent on VM migration and network communication cost are taken into consideration. 3) The information storage and random action selection of reinforcement learning algorithms are optimized for rapid decision making. Experiments show that our proposed algorithm is more robust than the existing algorithms. Besides, the power consumption of our algorithm is around 13.3% and 9.6% better than the existing algorithms in non-differentiated and differentiated services.