ARTEMIS: Adaptive Bitrate Ladder Optimization for Live Video Streaming
Talkat 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI '24) · 2024-04-16..04-18·
summary
System implements a cloud service that advertises a mega manifest of many candidate bitrate-resolution pairs, collects CDN logs and encoder quality metrics, and solves a per-timeslot optimizer to pick an Optimal Temporary Ladder (OTL) which the encoder uses to produce only a small subset. Real-world and trace-driven experiments show a 25% reduction in encoding computation, 18% lower end-to-end latency, and about 11% QoE improvement versus existing industry ladders, while remaining encoder- and client-agnostic.
AI-written summary · about
chapters (7)
- 0:00Introduction to Artimis
- 0:36Live streaming pipeline
- 2:00ABR limitations
- 4:31Mega manifest approach
- 7:29Optimization framework
- 10:28Evaluation and results
- 13:21Conclusion
related talks
26mBandwidth Ballet: Optimizing Video Performance for Web Maestros
22mProviding better video experiences for the next billion users.
17mContent Aware Encoding for low latency live streaming encoders using deep learning
19mLow Latency Live from a Different Vantage Point
41m8K Codec Low-Latency Livestreaming, and AI Streaming
10mGoing Beyond Bitrate: Adaptation Based on Video Context
16mCDN Challenges of HTTP-based Low Latency Live Streaming Delivery
14mSynchronized horizontal and vertical video without compromises