Thermal Aware Workload Scheduling in Datacenters

Kruidhof, R.K. (2016) Thermal Aware Workload Scheduling in Datacenters. Master's Thesis / Essay, Industrial Engineering and Management.

	Text Thermal-aware_workload_schedul_1.pdf - Published Version Restricted to RUG campus only Download (1MB)
	Text Toestemming.pdf - Other Restricted to Backend only Download (77kB)

Abstract

Over the last years there has been a growth in the amount of large-scale datacenters across the world. A large part of the total energy consumption of datacenters is used by the cooling equipment. One of the factors influencing the cooling efficiency of a datacenter is the workload distribution of jobs to individual servers, with respect to their heat generation. This research investigates two types of thermal-aware optimal control methods which are used to steer the temperature in the datacenter to a desired temperature which minimizes the energy costs. A feedback controller is used to control the workload distribution and supply temperature in order to minimize the energy costs. This controller is compared to an existing controller found in literature, which uses the linear-quadratic-regulator to control the workload distribution and a controller for the airflow. Both controllers are analysed and their similarities and differences are discussed. Also a direction for further research is proposed.

Item Type:	Thesis (Master's Thesis / Essay)
Degree programme:	Industrial Engineering and Management
Thesis type:	Master's Thesis / Essay
Language:	English
Date Deposited:	15 Feb 2018 08:27
Last Modified:	15 Feb 2018 08:27
URI:	https://fse.studenttheses.ub.rug.nl/id/eprint/15028

Actions (login required)

View Item