Batch Arrival Multiserver Queue with State-Dependent Setup for Energy-Saving Data Center
Batch Arrival Multiserver Queue with State-Dependent Setup for Energy-Saving Data Center
复制标题
具有状态相关设置的批量到达多服务器队列,用于节能数据中心
DOI:
10.1007/978-981-15-5951-8_25
复制
发表时间:
2020
期刊:
影响因子:
--
通讯作者:
Phung-Duc Tuan
中科院分区:
文献类型:
--
作者:
Tamae Kawasaki;Takashi Seo;Phung-Duc Tuan
Queues with setup time are extensively studied because they have application in performance evaluation of power-saving data centers. In data centers, there are a huge number of servers which consume a large amount of energy. In the current technology, an idle server still consumes about 60% of the energy when it is busy. Thus, a simple way to save energy is to turn off idle servers. However, when there are some waiting jobs, we have to turn on the OFF servers in order to reduce the waiting time. A server needs some setup time to be active during which it consumes energy but cannot process jobs. Therefore, there exists a trade-off between power consumption and delay performance. Gandhi et al. (Eval Rev 38:48–50, 2010; Perform Eval 67:1123–1138, 2010) analyze this trade-off using an M/M/cqueue with staggered setup (one server in setup at a time). In this paper, using an alternative approach, we obtain generating functions for the joint stationary distribution of the number of active servers and that of jobs in the system for a more general model with batch arrivals and state-dependent setup time. We further obtain moments for the joint queue length. Numerical results reveal that under the same traffic intensity, the mean power consumption decreases with the mean batch size. One of the main theoretical contributions is a new conditional decomposition formula showing that the number of waiting customers under the condition that all servers are busy can be decomposed to the sum of two independent random variables with clear physical interpretation.
登录
查看更多内容
DOI:
10.1145/1870178.1870195
发表时间:
2010
期刊:
SIGMETRICS Perform. Evaluation Rev.
影响因子:
--
作者:
Anshul Gandhi;Mor Harchol;I. Adan
通讯作者:
I. Adan
DOI:
--
发表时间:
2011
期刊:
Allerton Conference on Communication, Control, and Computing
影响因子:
--
作者:
Anshul Gandhi;Mor Harchol
通讯作者:
Mor Harchol
影响因子:
3.6
作者:
M. Cromie;M. Chaudhry;W. Grassmann
通讯作者:
W. Grassmann
影响因子:
2.7
作者:
Paul J. Burke
通讯作者:
Paul J. Burke