Date of Award
Doctor of Philosophy (PhD)
Dr. Hesham Ali
In the context of the big picture as energy demands rise due to growing economies and growing populations, there will be greater emphasis on sustainable supply, conservation, and efficient usage of this vital resource. Even at a smaller level, the need for minimizing energy consumption continues to be compelling in embedded, mobile, and server systems such as handheld devices, robots, spaceships, laptops, cluster servers, sensors, etc. This is due to the direct impact of constrained energy sources such as battery size and weight, as well as cooling expenses in cluster-based systems to reduce heat dissipation. Energy management therefore plays a paramount role in not only hardware design but also in user-application, middleware and operating system design. At a higher level Datacenters are sprouting everywhere due to the exponential growth of Big Data in every aspect of human life, the buzz word these days is Cloud computing. This dissertation, focuses on techniques, specifically algorithmic ones to scale down energy needs whenever the system performance can be relaxed. We examine the significance and relevance of this research and develop a methodology to study this phenomenon.
Specifically, the research will study energy-aware resource reservations algorithms to satisfy both performance needs and energy constraints. Many energy management schemes focus on a single resource that is dedicated to real-time or nonreal-time processing. Unfortunately, in many practical systems the combination of hard and soft real-time periodic tasks, a-periodic real-time tasks, interactive tasks and batch tasks must be supported. Each task may also require access to multiple resources. Therefore, this research will tackle the NP-hard problem of providing timely and simultaneous access to multiple resources by the use of practical abstractions and near optimal heuristics aided by cooperative scheduling. We provide an elegant EAS model which works across the spectrum which uses a run-profile based approach to scheduling. We apply this model to significant applications such as BLAT and Assembly of gene sequences in the Bioinformatics domain. We also provide a simulation for extending this model to cloud computing to answers “what if” scenario questions for consumers and operators of cloud resources to help answers questions of deadlines, single v/s distributed cluster use and impact analysis of energy-index and availability against revenue and ROI.
Pawaskaw, Sachin S., "Energy Awareness and Scheduling in Mobile Devices and High End Computing" (2013). Student Work. 2886.
Files over 3MB may be slow to open. For best results, right-click and select "save as..."