|
- 2018
基于排队论的异构数据中心性能及能源管理策略
|
Abstract:
该文研究了怎样在一个数据中心内的几种具有不同处理能力的服务器之间,在消耗最小能量的同时根据等待时间保证性能要求。重点探讨了在给定基于等待时间的性能要求的前提下,使用动态开启/关闭一部分服务器的管理策略,实现最小化数据中心能耗的问题;使用排队论建立了数学模型来确定应开启的服务器的数目。实验结果表明,相比于不考虑服务器分组的调度策略,该方法可以减少能耗,其策略也为研究异构数据中心的能耗与性能的权衡提供了途径。
[1] | BROWN R E, BROWN R, MASANET E, et al. Report to congress on server and data center energy efficiency:Public law 109-431[R]. Ernest Orlando Lawrence Berkeley National Laboratory. Berkeley, USA:[s.n.], 2007. |
[2] | ROSSI F, XAVIER M, ROSE C, et al. E-eco:Performance-aware energy-efficient cloud data center orchestration[J]. Journal of Network and Computer Applications, 2017, 78:83-96. |
[3] | LI K. Optimal power allocation among multiple heterogeneous servers in a data center[J]. Sustainable Computing:Informatics and Systems, 2012, 2(1):13-22. |
[4] | INTEL CORP. Intel math kernel library 10.0-linpack[EB/OL].[2016-05-10]. http://www.intel.com/cd/software/products/asmo-na/eng/266857.htm,2007. |
[5] | GREENBERG A, HAMILTON J, MALTZ D A, et al. The cost of a cloud:Research problems in data center networks[J]. ACM SIGCOMM Computer Communication Review, 2008, 39(1):68-73. |
[6] | BENSON T, AKELLA A, MALTZ D. Network traffic characteristics of data centers in the wild[C]//Internet Measurement Conference (IMC). Melbourne, Australia:[s.n.], 2010. |
[7] | KIM J, CHANG H, JUNG Y, et al. Energy conservation effects of a multi-stage outdoor air enabled cooling system in a data center[J]. Energy and Buildings, 2017, 138:257-270. |
[8] | DYACHUK D, MAZZUCCO M. On allocation policies for power and performance[C]//11th ACM/IEEE International Conference on Grid Computing (Grid 2010)-Energy Efficient Grids, Clouds and Clusters Workshop. Brussels, Belgium:IEEE, 2010. |
[9] | GANDHI A, GUPTA V, HARCHOL-BALTER M, et al. Optimality analysis of energy-performance trade-off for server farm management[J]. Performance Evaluation, 2010, 67(11):1155-71. |
[10] | ZHENG X, CAI Y. Optimal server provisioning and frequency adjustment in server clusters[C]//IEEE 39th International Conference on Parallel Processing Workshops.[S.l.]:IEEE, 2010. |
[11] | GHAMKHARI M, MOHSENIAN-RAD H. Energy and performance management of green data centers:a profit maximization approach[J]. IEEE Transactions on Smart Grid, 2013, 4(2):1017-1025. |
[12] | GUENTER B, JAIN N, WILLIAMS C. Managing cost, performance and reliability tradeoffs for energy-aware serverprovisioning[C]//IEEE International Conference on Computer Communications.[S.l.]:IEEE, 2011. |
[13] | SCHWARTZ C, PRIES R, TRAN-GIA P. A queuing analysis of an energy-saving mechanism in data centers[C]//IEEE International Conference on Information Networking (ICOIN).[S.l.]:IEEE, 2012. |
[14] | WANG W, LUO J, SONG A, et al. Heterogeneity aware optimal power allocationin data center environments[J]. Pervasive Computing and the Networked World, 2013, 7719:513-528. |
[15] | DENG X, WU D, SHEN J, et al. Eco-aware online power management and load scheduling for green cloud datacenters[J]. IEEE Systems Journal, 2016, 10(1):78-87. |
[16] | ZHANG Q, SHI W. Energy-efficient workload placement in enterprise datacenters[J]. Computer, 2016, 49(2):46-52. |
[17] | XU G, DAI B, HUANG B, et al. Bandwidth-aware energy efficient flow scheduling with SDN in data center networks[J]. Future Generation Computer Systems, 2017, 68:163-174. |
[18] | MAZZUCCO M, DYACHUK D, DETERS R. Maximizing cloud providers revenues via energy aware allocation policies[C]//IEEE International Conference on Cloud Computing. Miami, Florida:IEEE, 2010. |