Ebublio: Edge Assisted Multi-user 360-Degree Video Streaming

PubDate: April 2022

Teams: Chinese University of Hong Kong

Writers: Yili Jin; Junhua Liu; Fangxin Wang

PDF: Ebublio: Edge Assisted Multi-user 360-Degree Video Streaming

Abstract

Compared to traditional videos, streaming 360° videos is more difficult. We propose Ebublio, a novel intelligent edge caching framework consisting of a collaborative FoV prediction (CFP) module and a long-term tile caching optimization (LTO) module. The former integrates the features of video content, user trajectory, and other users’ records for combined prediction. The latter employs the Lyapunov framework and a subgradient optimization toward the optimal caching replacement policy. Our trace-driven evaluation further demonstrates the superiority of our framework, with about 42% improvement in FoV prediction, and 36% improvement in QoE under similar traffic consumption.