Power Versus Quality Trade-offs for Adaptive Real-Time Applications

Electronic devices are expected to accommodate evermore complex functionality. Portable devices, such as mobile phones, have experienced a rapid increase in functionality, while at the same time being constrained by the amount of energy that may be stored in their batteries. Dynamic Voltage and Frequency Scaling (DVFS) is a common technique that is used to trade processor speed for a reduction in power consumption. Adaptive applications can reduce their output quality in exchange for a reduction in their execution time. This exchange has been shown to be useful for meeting temporal constraints, but its usefulness for reducing energy/power consumption has not been investigated. In this paper, we present a technique that uses existing DVFS methods to trade a quality decrease for lower power/energy consumption through an intermediary reduction in execution time. Our technique achieves this while meeting soft and/or hard time/energy/power constraints. We demonstrate the applicability of our technique on an adaptive H.263 decoder application, running on a predictable hardware platform that is prototyped on an FPGA. We further contribute an experimental evaluation of the H.263 decoder's scalable mechanisms, in their ability to trade quality for temporal/energy/power. From experimentation, we show that our quality trading technique is able to achieve up to a 45% increase in the number of frames decoded for the same amount of energy, in comparison to frequency scaling alone, but with a quality reduction of up to 22dB Peak Signal-to-Noise Ratio (PSNR).