Abstract: Video streaming services are complex systems, and there are many things that can contribute to the quality of experience perceived by the end users. In this talk, we will break down a typical streaming system into stages and look into issues that could impact user experience. We will cover a broad range of topics, such as recent advancements in encoding technologies, traffic policers on the Internet, and CPU and memory limitations on TV devices. We will primarily focus on issues that video streaming practitioners encounter in production systems and discuss the current efforts to resolve these issues. We don't have all the answers yet, and that's the beauty of this intriguing field. 

 

Bio: Te-Yuan (T.-Y.) is a senior engineering manager at Netflix, leading the effort to improve playback quality through adaptive streaming and joint optimizations between Netflix’s content delivery networks, encoding technologies, and video players. T.-Y. received her PhD in Computer Science from Stanford in 2014 and her thesis, with no surprise, focused on video streaming. Her journey at Netflix started in 2013 first as an intern to verify her Ph.D. thesis in Netflix's production system, then as a software engineer and engineering manager to further improve Netflix's playback quality. After 11 years at Netflix, she continues to be humbled by so many new learnings about the video streaming system, the Internet, and ways for further improvement.