On QoE-Aware Traffic Management for Real-time, Interactive Video with Time-variant Spatial Complexity

Abstract: We analyzed spatial complexity, defined as the relationship between the required bitrate and a corresponding picture Quality of Experience (QoE) metric, for realistic, long, real-time, interactive video clips. Apart from variation across different content types, e.g., game genres, we discovered time-variability within a clip from second to second, and explored the ramifications for traffic management. We introduced utility as an elegant way to manage resource sharing preferences. Our analysis of resource sharing methods shows that frequent QoE-aware reallocation has significant performance advantages compared to static rate allocation, even in case the latter is based on rich information about long-term average spatial complexity. We have also shown that utility-based resource allocation has clear advantages over methods targeting equal QoE allocation, it increases the average QoE, while it still controls the worst case QoE.