期刊
FRONTIERS OF COMPUTER SCIENCE
卷 9, 期 6, 页码 875-886出版社
HIGHER EDUCATION PRESS
DOI: 10.1007/s11704-015-4592-1
关键词
cloud computing; software-defined networking; data center; service migration; QoS
类别
资金
- National Natural Science Foundation of China [61303252, 61173061, 61472039, 71201120]
- National Key Technology RD Program [2012BAH01B03]
Cloud computing as an emerging technology promises to provide reliable and available services on demand. However, offering services for mobile requirements without dynamic and adaptive migration may hurt the performance of deployed services. In this paper, we propose MAMOC, a cost-effective approach for selecting the server and migrating services to attain enhanced QoS more economically. The goal of MAMOC is to minimize the total operating cost while guaranteeing the constraints of resource demands, storage capacity, access latency and economies, including selling price and reputation grade. First, we devise an objective optimal model with multi-constraints, describing the relationship among operating cost and the above constraints. Second, a normalized method is adopted to calculate the operating cost for each candidate VM. Then we give a detailed presentation on the online algorithm MAMOC, which determines the optimal server. To evaluate the performance of our proposal, we conducted extensive simulations on three typical network topologies and a realistic data center network. Results show that MAMOC is scalable and robust with the larger scales of requests and VMs in cloud environment. Moreover, MAMOC decreases the competitive ratio by identifying the optimal migration paths, while ensuring the constraints of SLA as satisfying as possible.
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