Cross-Layer Effects on Training Neural Algorithms for Video Streaming
This work addresses the reliability of training methods for video streaming algorithms, highlighting dependencies that could affect real-world deployment, but it is incremental as it builds on existing systems like Pensieve.
The paper investigates how the performance of neural network-based adaptive bit rate (ABR) algorithms for video streaming depends on the simulated training environment and congestion control algorithms, revealing cross-layer effects that influence algorithm effectiveness.
Nowadays Dynamic Adaptive Streaming over HTTP (DASH) is the most prevalent solution on the Internet for multimedia streaming and responsible for the majority of global traffic. DASH uses adaptive bit rate (ABR) algorithms, which select the video quality considering performance metrics such as throughput and playout buffer level. Pensieve is a system that allows to train ABR algorithms using reinforcement learning within a simulated network environment and is outperforming existing approaches in terms of achieved performance. In this paper, we demonstrate that the performance of the trained ABR algorithms depends on the implementation of the simulated environment used to train the neural network. We also show that the used congestion control algorithm impacts the algorithms' performance due to cross-layer effects.