Buffer Data-Driven Adaptation of Mobile Video Streaming Over Heterogeneous Wireless Networks

The development of the Internet of Things (IoT), cyber physical systems, and ubiquitous mobile terminals enable video content to be shared and consumed in new and innovative ways. Nonetheless, the stochastic and unpredictable nature of heterogeneous wireless networks with mobile clients presents a significant challenge to the increasing demand of quality of experience (QoE). In this paper, we study the problem of maximizing the user's QoE of viewing streaming video via automatic bitrate adaptation in heterogeneous wireless networks. To be specific, a stochastic optimization problem is first formulated by considering fundamental uncertainties of heterogeneous wireless networks (i.e., the stochastic throughput). A dynamic bitrate adaptation scheme is then designed based on the Lyapunov optimization framework. Our proposed scheme conducts video bitrate selection based on the current queue buffer state and real-time throughput, and is capable of balancing the tradeoff between a user's QoE and buffer occupation (i.e., memory utilization). The performance of our proposed scheme is investigated through a combination of extensive analysis, simulations, and experiments in a real-world testbed. Simulation results demonstrate that our scheme outperforms the baseline with regard to QoE and bandwidth utilization. In addition, the experimental results in real-world testbed validate the scheme's efficiency and practicality in real-world system.