Optimal control for energy-aware server farms
Loading...
URL
Journal Title
Journal ISSN
Volume Title
School of Electrical Engineering |
Doctoral thesis (article-based)
| Defence date: 2018-10-26
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Authors
Date
2018
Major/Subject
Mcode
Degree programme
Language
en
Pages
109 + app. 107
Series
Aalto University publication series DOCTORAL DISSERTATIONS, 167/2018
Abstract
In many cases, services hosted in server farms are designed to be highly available and fault tolerant in the presence of randomly varying traffic, which often translates into over-provisioning of the server farms targeting peak demand periods. Consequently, the servers spend a substantial amount of time in low utilization range, which also happens to be the range in which servers are far less energy efficient. Moreover, even when completely idle, servers still consume a large portion of their peak power. However, servers cannot be simply switched off to save energy for two main reasons. First, any energy saving obtained by switching servers off comes at the expense of reduced performance due to the setup delay required to switch servers back to an operational state. Furthermore, servers are rarely completely idle since dispatching policies are often designed in such a way that the workload is evenly distributed across the server farm, resulting in low but non-zero utilization during off-peak demand periods. Thus, a coordinated control approach needs to be devised to achieve energy savings by consolidating workload and placing unused servers in low-power states while still providing good performance. This thesis studies the energy-performance trade-off by applying queueing theoretic methods and by formulating the trade-off as a multi-objective optimization problem. Single-server models are first analyzed and the mean response time and mean power consumption metrics are derived. Compound cost functions are defined from these metrics and the control variables that minimize these cost functions are optimized. For such cost functions, it is shown under very general assumptions that in a single-server queue there is no gain from delaying the decision to switch off the server upon becoming idle. Instead the optimal decision is either to switch off immediately or never switch off. Server farms are modeled as parallel queueing systems with each server belonging to either a baseline or reserve group of servers. Energy-aware dispatching and power-control policies are developed so that the reserve servers are placed in a low-power state whenever possible. To this end, the dispatching decisions are studied by formulating the problem as a Markov Decision Process, and the resulting system is solved using the Policy Iteration method to construct a near-optimal dispatching policy. More simple, heuristic power-control and dispatching policies are also proposed to reduce the energy consumption of a server farm without compromising the performance.Description
Supervising professor
Manner, Jukka, Prof., Aalto University, Department of Communications and Networking, FinlandThesis advisor
Aalto, Samuli, Dr., Aalto University, Department of Communications and Networking, FinlandLassila, Pasi, Dr., Aalto University, Department of Communications and Networking, Finland
Keywords
energy-aware server farms, queueing systems with setup delay, energy-performance trade-off, cost-performance trade-off
Other note
Parts
-
[Publication 1]: Misikir Eyob Gebrehiwot, Samuli Aalto, Pasi Lassila. Optimal energy-aware control policies for FIFO servers. Performance Evaluation, 103, 41-59, 2016.
DOI: 10.1016/j.peva.2016.06.003 View at publisher
-
[Publication 2]: Misikir Eyob Gebrehiwot, Samuli Aalto, Pasi Lassila. Energy-aware SRPT server with batch arrivals: Analysis and optimization. Performance Evaluation, 115, 92-107, 2017.
DOI: 10.1016/j.peva.2017.07.003 View at publisher
-
[Publication 3]: Misikir Eyob Gebrehiwot, Samuli Aalto, Pasi Lassila. Energy-performance trade-off for processor sharing queues with setup delay. Operations Research Letters, 44, 101-106, 2016.
DOI: 10.1016/j.orl.2015.12.004 View at publisher
-
[Publication 4]: Misikir Eyob Gebrehiwot, Samuli Aalto, Pasi Lassila. Energy-aware server with SRPT scheduling: Analysis and optimization. In 13th International Conference on Quantitative Evaluation of Systems (QEST), Quebec, Canada, 107-122, 2016.
DOI: 10.1016/j.peva.2017.07.003 View at publisher
-
[Publication 5]: Misikir Eyob Gebrehiwot, Samuli Aalto, Pasi Lassila. Optimal sleep-state control of energy-aware M/G/1 queues. In 8th International Conference on Performance Evaluation Methodologies and Tools, Bratislava, Slovakia, 82-89, 2014.
DOI: 10.4108/icst.Valuetools.2014.258149 View at publisher
-
[Publication 6]: Misikir Eyob Gebrehiwot, Samuli Aalto, Pasi Lassila. Near-optimal policies for energy-aware task assignment in server farms. In TAPEMS workshop, 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID), Madrid, Spain, 1017-1026, 2017.
DOI: 10.1109/CCGRID.2017.112 View at publisher
-
[Publication 7]: Misikir Eyob Gebrehiwot, Samuli Aalto, Pasi Lassila. Energy efficient load balancing in web server clusters. In Ph.D. Workshop on Modelling Communication Networks, 29th International Teletraffic Congress (ITC), Genoa, Italy, 13-18, 2017.
DOI: 10.23919/ITC.2017.8065804 View at publisher
-
[Publication 8]: Misikir Eyob Gebrehiwot, Samuli Aalto, Pasi Lassila. Energy-aware control of server farms. In 39th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), Opatija, Croatia, 748-753, 2016.
DOI: 10.1109/MIPRO.2016.7522240 View at publisher
- [Errata file]: Errata of publication 3 and 4