Using user interface event information in dynamic voltage scaling algorithms

Abstract

Increasingly, mobile computers use dynamic voltage scaling (DVS) to reduce CPU voltage and speed and thereby increase battery life. To determine how to change voltage and speed when responding to user interface events, we analyze traces of real user workloads. We evaluate a new heuristic for inferring when user interface tasks complete and find it is more efficient and nearly as effective as other approaches. We compare DVS algorithms and find that for a given performance level, the PACE algorithm uses the least energy and the Stepped algorithm uses the second least. We find that different types of user interface event (mouse movements, mouse clicks, and keystrokes) trigger tasks with significantly different CPU use, suggesting one should use different speeds for different event types. We also find differences in CPU use between categories of the same event type, e.g., between pressing spacebar and pressing enter, and between events of different applications. Thus, it is better to predict task CPU use based solely on tasks of the same category and application. However, energy savings from such improved predictions are small.