Sustainable Cloud Encoding for Adaptive Bitrate Streaming over CDNs
Cong Wang, Michael Zink · 2019
Video streaming is the most popular application on today's Internet. Millions of people around the globe access video contents using various end user devices, such as smart phones, tablets, laptops, and TVs. To meet the requirements of different end user devices and variable network conditions, videos need to be encoded into different quality versions before delivery to the clients. Such large-scale encoding tasks consume significant amounts of energy. In this paper, we investigate to what extent the realtime video encoding clouds can be powered by renewable energy sources. We show that video encoding tasks are suitable for execution on clouds that are powered by a combination of renewable and grid energy sources. With the use of our power management policies, grid energy usage can be reduced by 73-83%, which leads to electricity cost reductions of 14-28% compared to unlimited non-renewable power.