Dynamic power optimization of interactive systems

Power has become a major concern for mobile computing systems such as laptops and handheld, 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 interface 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 optimization. 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 measurements. Experiments show that using predicted user delays for DPM/DVS achieves an average of 21.9% system energy reduction with little sacrifice in user productivity or satisfaction.