Cross-Layer Effects on Training Neural Algorithms for Video Streaming

TL;DR

This paper investigates how cross-layer interactions and simulation environment details influence the training effectiveness of neural network-based adaptive streaming algorithms, highlighting the importance of environment fidelity and congestion control in performance.

Contribution

It reveals the impact of simulation environment implementation and congestion control algorithms on the training outcomes of neural ABR algorithms, emphasizing cross-layer effects.

Findings

Training performance varies with simulation environment details.

Congestion control algorithms affect neural ABR effectiveness.

Cross-layer interactions influence training success.

Abstract

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.