Interaction-Aware Energy Management for Wireless Network Cards Igor Crk, Mingsong Bi, Chris Gniady Department of Computer Science, University of Arizona Tucson, AZ 85704 icrk@cs.arizona.edu, mbi@cs.arizona.edu, gniady@cs.arizona.edu Abstract Wireless Network Interface Cards (WNICs) are part of every portable device, where efficient energy management plays a significant role in extending the device’s battery life. The goal of efficient energy management is to match the perfor- mance of the WNIC to the network activity shaped by a running application. In the case of interactive applications on mobile systems, network I/O is largely driven by user interactions. Current solutions either require application modifications or lack a sufficient context of execution that is crucial in making accurate and timely predictions. This pa- per proposes a range of user-interaction-aware mechanisms that utilize a novel approach of monitoring a user’s interac- tion with applications through the capture and classification of mouse events. This approach yields considerable improve- ments in energy savings and delay reductions of the WNIC, while significantly improving the accuracy, timeliness, and computational overhead of predictions when compared to existing state-of-the-art solutions. Categories and Subject Descriptors D.4.4 [Operating Systems]: Communications Management— Input/Output; Network Communication General Terms Design, Experimentation, Measurement, Performance 1. INTRODUCTION Mobile devices have become an everyday part of our life. We depend on them for our computation, communication, and entertainment. An ever-increasing demand for perfor- mance, functionality, and better user interfaces has resulted in the demand for longer battery life. However, as advances in battery technology continue to lag behind the demands placed upon the battery, power awareness has become an important consideration in the design of mobile systems. The challenge of designing energy efficient systems lies in Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. SIGMETRICS’08, June 2–6, 2008, Annapolis, Maryland, USA. Copyright 2008 ACM 978-1-60558-005-0/08/06 ...$5.00. understanding the role of user interaction in energy con- sumption and in providing an energy-performance schedule that adequately accommodates user demand. Furthermore, by understanding user interaction we can optimize system performance by tailoring it to a user’s patterns of interac- tion. Performance and energy consumption are tightly coupled where higher performance is usually achieved at the cost of increased power demand. However, the key observation is that higher power demand does not necessarily translate into an increase in energy consumption. For instance, hardware in a higher performance state may complete a particular task faster than the same hardware operating in a lower perfor- mance state. This reduces the time during which the entire system has to be on. On the other hand, a particular device may not be required by all tasks and so may be operated in a low performance state without a significant impact on the performance of the executing application. The challenge in designing efficient energy management mechanisms is to provide a energy/performance schedule that best matches the task at hand to transparently provide energy savings while satisfying the performance demand. Many energy management techniques have been proposed ranging from hardware optimizations all of the way to appli- cation transformation. However, most user interactions are still hidden from the existing approaches, which are unable to capture the context necessary for inferring what a user demands. Monitoring user interaction provides not only the necessary context of execution that was previously unavail- able to the predictors, but also enables timely predictions before the need for high performance arrives [2]. The timely transition of a device to a desired performance/energy level is critical to meet performance demand and achieve energy efficiency. In this paper, we show that the user interactions can be easily monitored and exploited to increase both the timeli- ness and accuracy of prediction mechanisms. More specif- ically, we apply user-interaction-based prediction to reduce energy consumption in Wireless Network Interface Cards (WNICs) while maintaining good performance levels. Sub- sequently, we propose and evaluate a range of prediction mechanisms that balance accuracy, energy consumption, and delay to provide energy efficient management of the WNIC. Each mechanism incorporates high-level contextual informa- tion about user’s activity to predict network access patterns and provide desired energy/performance levels. The idea is motivated by observing that network traffic (for interac- tive applications) usually follows a specific interaction with 371