Experience-Centric Mobile Video Scheduling Through Machine Learning

Vikram Chandrasekhar,Yuqiang Heng,Jianzhong Zhang,Jinho Lee,Joonyoung Cho,Jeffrey G Andrews

doi:10.1109/access.2019.2933273

Abstract

Providing a high quality video streaming experience in a mobile data network via the ubiquitous HTTP Adaptive Streaming (HAS) protocol is challenging. This is largely because HAS traffic arrives as regular Internet Protocol (IP) packets, indistinguishable from those of other data services. This paper presents real-time network-based Machine Learning (ML) classifiers incurring low overhead and capable of (a) detecting the service type of different flows including HAS, and (b)detecting the player status for users with HAS flows. We utilize random forests , an ensemble classifier, relying only upon standard unencrypted packet headers. By applying the ML classifier outputs to derive scheduling metrics, we show how existing LTE base-station schedulers can improve video Quality-of-Experience (QoE) while incurring minimal overhead. For a simulated LTE cellular network, we present quantitative performance results that include misclassification errors. Our classification and scheduling framework is shown to provide an improved video QoE with tolerable impact on other non-video best effort services. These design insights can be applied to optimize video delivery in current and future wireless networks.

Highlights

Mobile data traffic continues to grow at a roughly 50% annual rate, mostly due to demand for video streaming services
2) PRIORITIZED SCHEDULING We present a simulated LTE base station scheduler that applies the Random Forest Classifiers (RFCs) outputs for prioritizing scheduling of HTTP Adaptive Streaming (HAS) users based on their detected player state
We present the results from multi-layer perceptron (MLP) for play state and resolution classification for initial model selection

Summary

Introduction

Mobile data traffic continues to grow at a roughly 50% annual rate, mostly due to demand for video streaming services. By 2022, streaming video and immersive multimedia traffic are projected to comprise 82% of all mobile data traffic at 225 EB per month [1]. This growth imposes significant challenges for mobile network operators (MNOs) and content providers, given their constrained bandwidth and infrastructure. Rather than capping video bit rates and intentionally limiting the video quality, Radio Access Networks (RANs) should implement a more holistic, user-experience based and end-to-end approach consisting of (a) deploying network upgrades, e.g. 5G, (b) bringing video content closer to the end user, for example, via edge-caching, (c) detecting. The focus of this paper is on the latter two topics

Objectives

Findings

Discussion

Conclusion