Efficient PFD-Based Networking and Buffering Models for Improving Video Quality over Congested Links

Abstract

Video traffic over the Internet becomes increasingly popular and is expected to comprise the largest proportion of the traffic carried by wired and wireless networks. On the other hand, videos are usually compressed by exploiting spatial and temporal redundancy for the reason of increasing the number of video streams that can be simultaneously carried over links. Unfortunately, receiving high-quality video streaming over the Internet remains a challenge due to the packet loss encountered in the congested wired and wireless links. In addition, the problem is more apparent in wireless links due to not only employing limited system capacity, but also some of the major drawbacks of wireless networks, out of which the bandwidth limitations and link asymmetry which refers to the situation where the forward and reverse paths of a transmission have different channel capacities. Therefore, the wireless hops may be congested which result in dropping many video frames. Additionally, as a result of compressing videos, dependencies among frames and within a frame arise. Consequently, the overall video quality tends to be degraded dramatically. The main challenge is to support the growth of video traffic while keeping the perceived quality of the delivered videos high. In this paper, we extend our previous work concerning improving video traffic over wireless networks through professionally studying the dependencies between video frames and their implications on the overall network performance. In other words, we propose very efficient network and buffer models proportionately to novel algorithms that aim to minimize the cost of aforementioned possible losses by selectively discarding frames based on their contribution to picture quality, namely, partial and selective partial frame discarding policies considering the dependencies between video frames. The performance metrics that are employed to evaluate the performance of the proposed algorithms include the rate of non-decodable frames, peak signal-to-noise ratio, frameput, average buffer occupancy, average packet delay, as well as jitter. Our results are so promising and show significant improvements in the perceived video quality over what is relevant in the current literature. We do not end up to this extent, but rather the effect of producing different bit-stream rates by the FFMPEG codecs on aforementioned performance metrics has been extensively studied.