A LEARNING FRAMEWORK TO IMPROVE VIDEO QOE IN HTTP ADAPTIVE STREAMING SDN FOR DELIVERING LIVE CONTENT

摘要

HTTP (Hyper Text Transport Protocol) adaptive streaming techniques suffers from start-up latencies and video stallswhich impair Video Quality of Experience (QoE). We deal with these issues in 4 steps: i) we analyze the advantages of variable bitrate encoded streams on Adaptive Bit Rate (ABR) streaming and assess the impact of chunk sizes on video quality and scenecomplexity; ii) we propose a novel machine learning framework through a Gaussian Mixture model k-means clustering to isolatevideo stall events, the Machine Learning Pipeline runs these Support Vector Machines (SVM) algorithms to accurately predict theoccurrence and duration of video stalls; iii) we employ Software Defined Networking (SDN) based OpenFlow controller todynamically switch, re-prioritize tracks and chunk sizes across tracks to improve the overall Video QoE; iv) we further optimizethis through an intelligent prediction of video stall occurrence and stall duration in accordance with network traffic conditions andscene complexity without compromising video quality.