Hilbert Transform-Based Workload Prediction and Dynamic Frequency Scaling for Power-Efficient Video Encoding

With the popularity of mobile devices with embedded video cameras, real-time video encoding on hand-held devices becomes increasingly popular. Reducing the power consumption during real-time video encoding to suspend the battery life with the same encoding performance is very important to improve the quality of service. Although some workload estimation techniques have been developed for video decoding to reduce power consumption for video playback applications, they present inefficiency in being transferred to video encoding directly because the compressed information cannot be retrieved before encoding and the future input video content is often nondeterministic. In this paper, a workload estimation scheme targeting video encoding applications is proposed. Based on the definition of video encoding workload and the analysis of the features, a Hilbert transform-based workload estimation model is proposed to predict the overall variation trend in the encoding workload to overcome the workload fluctuations and the nondeterministic content variations, e.g., burst motion. The effectiveness of the proposed algorithm is demonstrated on two H.264/AVC encoders on PC and an embedded platform by encoding different video contents at different bit-rates. The proposed algorithm provides a negligible deadline missing ratio around 4.8%, which is much lower than the previous solutions, together with platform and content robustness. Compared with the previous solutions, the proposed algorithm provides up to 61.69% power reduction under the same performance constraint.