文献类型：期刊文献

英文题名：Handling hierarchy in cloud data centers: A Hyper-Heuristic approach for resource contention and energy-aware Virtual Machine management

作者：Zhang, Jiayin[1];Yu, Huiqun[1];Fan, Guisheng[1];Li, Zengpeng[1];Xu, Jin[1];Li, Jun[2]

机构：[1]East China Univ Sci & Technol, 130 Meilong Rd, Shanghai 200237, Peoples R China;[2]VMware, 3401 Hillview Ave, Palo Alto, CA 94304 USA

年份：2024

卷号：249

外文期刊名：EXPERT SYSTEMS WITH APPLICATIONS

收录：;EI(收录号：20240915623464);WOS:【SCI-EXPANDED(收录号:WOS:001188010200001)】；

基金：This work was partially supported by the National Natural Science Foundation of China No. 62372174, the Natural Science Foundation of Shanghai (No. 21ZR1416300) , the Capacity Building Project of Local Universities Science and Technology Commission of Shanghai Municipality (No. 22010504100) , the Research Programme of National Engineering Laboratory for Big Data Distribution and Exchange Technologies, and the Shanghai Municipal Special Fund for Promoting High Quality Development (No. 2021-GYHLW-01007) .

语种：英文

外文关键词：Hierarchical data center; Virtual Machine management; Hyper-Heuristic; Game-Theory; Resource contention; Energy efficiency

摘要：For cloud data centers, a performant yet energy -efficient operation is critical for service quality and experience. The growing demand for cloud -based services has led to the development of large-scale hierarchical data center structures, characterized by horizontal expansion and vertical hierarchy, leading to challenges in managing Virtual Machines (VM) at a granular level. The hierarchical arrangement can increase the risk of deployment failures, often stemming from inadequate computational resources on physical hosts, even when the clusterlevel resources seem sufficient. While substantial work has gone into managing VMs at the physical host level, there remains a dearth of research under hierarchical data center configurations. To fill the research gap, we address the hierarchy in cloud data centers with a novel two -stage approach named VMM-HHGT, aiming at suppressing VM deployment failures, while balancing the energy consumption and computation resource contention. VMM-HHGT comprises a Hyper -Heuristic -assisted broker (VMM-HH), which can learn the workload patterns and hardware configurations to generate cluster -selection heuristics. An offline training process is incorporated for continuous heuristic evolution with zero overhead on decision -making. Besides, a Game -Theory -assisted hypervisor (GT) is designed for inter -host live VM migration for fine-grained balancing of energy consumption and resource contention. Extensive experiments with traces from real -world VMware data centers show that VMM-HHGT achieves a higher deployment success rate compared to the state-of-the-art approaches, with a well -situated performance in energy consumption and resource contention.