Impact of Network Dynamics on User's Video Quality: Analytical Framework and QoS Provision

Abstract

Abstract-We develop an analytical framework to investigate the impacts of network dynamics on the user perceived video quality. Our investigation stands from the end user's perspective by analyzing the receiver playout buffer. In specific, we model the playback buffer at the receiver by a 1 and 1 queue, respectively, with arbitrary patterns of packet arrival and playback. We then examine the transient queue length of the buffer using the diffusion approximation. We obtain the closed-form expressions of the video quality in terms of the start-up delay, fluency of video playback and packet loss, and represent them by the network statistics, i.e., the average network throughput and delay jitter. Based on the analytical framework, we propose adaptive playout buffer management schemes to optimally manage the threshold of video playback towards the maximal user utility, according to different quality-of-service requirements of end users. The proposed framework is validated by extensive simulations.Index Terms-Diffusion approximation, playout buffer, qualitydriven.

A Mobility-Aware and Quality-Driven Retransmission Limit Adaptation Scheme for Video Streaming over VANETs

“…The playback terminates when the buffer becomes empty again. According to [2], the average number of streaming freezes after t seconds and its variance can be approximated using diffusion approximation as follows:…”

“…Streaming of high quality video to fast-moving vehicles is a promising application which faces fundamental challenges attributed to the high mobility and dynamic nature of the network. In order to have a smooth playout, it is necessary to have enough packets in the playback buffer at the destination [2]. Robust video streaming applications must be able to tolerate link failures or deep link fading, which normally occur due to node mobility or the unwillingness of the user to share node resources in a multihop network [3].…”

Probabilistic analysis of buffer starvation in Markovian queues

“…The optimal QoE is achieved by configuring the start-up threshold in packets. Recently, the similar QoE issue is studied in the important works [5], [6], [7]. Liang et al [6] studies the bounds of startup delay, given the deterministic playout and arrival curves.…”

“…They further extend their method to consider the arrival process depicted by a two-state Markov chain. Luan et al [5] adopts diffusion approximation to investigate the time-dependent starvation behavior. Their technique is inadequate to provide insights on starvation in a media file with small number of units (in packets or chunks).…”

QoE Analysis of Media Streaming in Wireless Data Networks

“…Then, a probabilistic framework is proposed to compute the starvation probability and the playback interval based on Takács Ballot theorem [1]. In comparison with recent works [2][3][4][5], we consider a network with shared resource, instead of a single streaming session. The arrival process and the departure process do not work at the same granularity of jobs.…”