An Ensemble Rate Adaptation Framework for Dynamic Adaptive Streaming Over HTTP

TL;DR

This paper introduces an ensemble framework for DASH rate adaptation that combines multiple methods and dynamically selects the best one to enhance user QoE amid fluctuating network conditions.

Contribution

It proposes a novel ensemble framework with method pool and controller, improving QoE by selecting optimal rate adaptation methods in real-time.

Findings

Achieves higher QoE than existing methods in simulations.

Effectively adapts to changing network environments.

Outperforms state-of-the-art rate adaptation techniques.

Abstract

Rate adaptation is one of the most important issues in dynamic adaptive streaming over HTTP (DASH). Due to the frequent fluctuations of the network bandwidth and complex variations of video content, it is difficult to deal with the varying network conditions and video content perfectly by using a single rate adaptation method. In this paper, we propose an ensemble rate adaptation framework for DASH, which aims to leverage the advantages of multiple methods involved in the framework to improve the quality of experience (QoE) of users. The proposed framework is simple yet very effective. Specifically, the proposed framework is composed of two modules, i.e., the method pool and method controller. In the method pool, several rate adap tation methods are integrated. At each decision time, only the method that can achieve the best QoE is chosen to determine the bitrate of the requested video segment. Besides, we also propose two strategies for switching methods, i.e., InstAnt Method Switching, and InterMittent Method Switching, for the method controller to determine which method can provide the best QoEs. Simulation results demonstrate that, the proposed framework always achieves the highest QoE for the change of channel environment and video complexity, compared with state-of-the-art rate adaptation methods.