Graduate Exam Abstract

Brad Donohoo

M.S. Final
March 23, 2012, 1:00 PM
ECE Conference Room - C101B Engineering
Machine Learning Techniques and Algorithms for Energy Optimization in Mobile Embedded Systems

Abstract: Mobile smartphones and other portable battery operated embedded systems (PDAs, tablets) are pervasive computing devices that have emerged in recent years as essential instruments for communication, business, and social interactions. While performance, capabilities, and design are all important considerations when purchasing a mobile device, battery lifetime is one of the most desirable attributes. Battery technology and capacity has improved over the years, but it still cannot keep pace with the power consumption demands of today’s mobile devices. Until a new battery technology is discovered, this key limiter has led to a strong research emphasis on extending battery lifetime by minimizing energy consumption, primarily using software optimizations. This thesis presents two strategies that attempt to optimize mobile device energy consumption with negligible impact on user perception and quality of service (QoS). The first strategy, is an application and user interaction aware middleware framework that takes advantage of user idle time between interaction events of the foreground application to optimize CPU and screen backlight energy consumption. The framework dynamically classifies mobile device applications based on their received interaction patterns, then invokes a number of different power management algorithms to adjust processor frequency and screen backlight levels accordingly. The second strategy proposes the usage of machine learning techniques to learn a user’s mobile device usage pattern pertaining to spatiotemporal and device contexts, and then predict energy-optimal data and location interface configurations. By learning where and when a mobile device user uses certain power-hungry interfaces (3G, WiFi, and GPS), the techniques, which include variants of linear discriminant analysis, linear logistic regression, non-linear logistic regression, and k-nearest neighbor, are able to dynamically turn off unnecessary interfaces at runtime in order to save energy.

Adviser: Sudeep Pasricha
Co-Adviser: N/A
Non-ECE Member: N/A
Member 3: Charles Anderson, Computer Science
Addional Members: Anura P. Jayasumana, Electrical and Computer Engineering,N/A

B. K. Donohoo, C. Ohlsen, S. Pasricha, “AURA: An Application and User Interaction Aware Middleware Framework for Energy Optimization in Mobile Devices ” In ICCD ‘11, pp. 168-174, Oct. 2011.

B. K. Donohoo, C. Ohlsen, S. Pasricha, C. Anderson, “Exploiting Spatiotemporal and Device Contexts for Energy-Efficient Mobile Embedded Systems,” Accepted for publication in DAC ’12, Jun. 2012.

Program of Study: