Dynamic Power Optimization of Interactive Systems_zhong04vlsidesign

Dynamic Power Optimization of Interactive Systems_zhong04vlsidesign

Info iconThis preview shows pages 1–2. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Dynamic Power Optimization of Interactive Systems Lin Zhong and Niraj K. Jha Department of Electrical Engineering Princeton University Princeton, NJ 08544 { lzhong, jha } @ee.princeton.edu Abstract — Power has become a major concern for mo- bile computing systems such as laptops and handhelds, on which a significant fraction of software usage is interactive instead of computation-intensive. An analysis shows that over 90% of system energy and time is spent waiting for user input. Such idle periods provide vast opportunities for dynamic power management (DPM) and voltage scaling (DVS) techniques to reduce system energy. The user inter- face is in charge of system-user interaction. It often has a priori knowledge about how the user and system interact at a given moment. In this work, we propose to utilize such a priori knowledge and theories from the field of Psychology to predict user delays. We show that such delay predictions can be combined with DPM/DVS for aggressive power op- timization. We verify the effectiveness of our methodologies using usage traces collected on a personal digital assistant (PDA) and a system power model based on accurate mea- surements. Experiments show that using predicted user de- lays for DPM/DVS achieves an average of 21.9% system energy reduction with little sacrifice in user productivity or satisfaction. I. Introduction Power has become a dominant concern for mobile com- puting systems. While previous power management tech- niques were mostly concerned with computation-intensive and reactive applications, we are more interested in inter- active applications that are ubiquitous on modern mobile computing systems. In this work, we analyze the power characteristics of in- teractive systems, and employ the user interface informa- tion, history, and Psychology theories to predict user delays during system-user interaction. We show that such delay predictions can be utilized by DPM/DVS techniques to re- duce system energy consumption very effectively. As far as we know, this is the first work that addresses power op- timization of interactive systems from the perspective of system-user interaction. Unlike other works, in which en- ergy reduction is reported only for the processor, we report energy reduction for the whole system. The paper is organized as follows. After discussing back- ground and related work in Section II, we detail the model we employ for system-user interaction in Section III. User- delay models based on Psychological theories and history are proposed in Sections IV and V, respectively. We show how DPM/DVS techniques can take advantage of predicted user delays to save energy in Section VI. We then present our benchmarks and experimental results in Section VII....
View Full Document

This note was uploaded on 09/01/2009 for the course CSE CS-699 taught by Professor Prf.p.bhaduri during the Spring '09 term at Indian Institute of Technology, Guwahati.

Page1 / 7

Dynamic Power Optimization of Interactive Systems_zhong04vlsidesign

This preview shows document pages 1 - 2. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online