LAUSR

Edge computing provides the potential to improve users’ Quality of Experience (QoE) in ever-increasing video delivery. However, existing edge-based solutions cannot fully utilize the edge computing power and storage capacity. This paper proposes VIdeo Super-resolution and CAching (VISCA), an edge-assisted adaptive video streaming solution, which integrates super-resolution and edge caching to improve users’ QoE. We design a novel edge-based ABR algorithm that makes bitrate and video chunk source decisions by considering network conditions, QoE objectives, and edge resource availability jointly. VISCA utilizes super-resolution to enhance the cached low-quality video at the edge. The super-resolution models used are trained for the most popular videos only in order to achieve quality improvements with a fraction of the computation. A novel cache strategy is also adopted to maximize caching efficiency. To assess the performance of VISCA, an implemented prototype of VISCA was deployed in synthetic and real network contexts. Compared with the existing video streaming solutions, VISCA improves video quality by 28.2%-251.2% and reduces rebuffering time by 16.1%-95.6% in all considered scenarios.