- Joined
- Aug 20, 2006
- Messages
- 13,000
Researchers have developed a solution for reducing video rebuffering using machine learning: the system, dubbed “Pensieve,” figures out the optimal algorithm to use for delivering video at the best possible resolution while avoiding buffering breaks. Current systems employed on YouTube, Netflix, and similar sites have to make a trade-off between the quality of the video versus how often it has to rebuffer, but Pensieve utilizes AI that knows what works best in various conditions, potentially cutting rebuffering by up to 30 percent.
Pensieve doesn’t need a model or any existing assumptions about things like network speed. It represents an ABR algorithm as a neural network and repeatedly tests it in situations that have a wide range of buffering and network speed conditions. The system tunes its algorithms through a system of rewards and penalties. For example, it might get a reward anytime it delivers a buffer-free, high-resolution experience, but a penalty if it has to rebuffer. “It learns how different strategies impact performance, and, by looking at actual past performance, it can improve its decision-making policies in a much more robust way.”
Pensieve doesn’t need a model or any existing assumptions about things like network speed. It represents an ABR algorithm as a neural network and repeatedly tests it in situations that have a wide range of buffering and network speed conditions. The system tunes its algorithms through a system of rewards and penalties. For example, it might get a reward anytime it delivers a buffer-free, high-resolution experience, but a penalty if it has to rebuffer. “It learns how different strategies impact performance, and, by looking at actual past performance, it can improve its decision-making policies in a much more robust way.”