Controller-Assisted Adaptive Video Streaming Experimented in Cloud-Native ICN Platform

Abstract

Adaptive video streaming is a major factor in today's Internet traffic explosion, and Information-Centric Networking (ICN) is expected to be a promising solution for addressing the tradeoff between traffic reduction and QoE optimization. However, it is also reported that throughput fluctuations by in-network cache, which is an inherent feature of ICN, might have negative influence on streaming users' video quality. In this paper, we propose a controller-assisted adaptive video streaming framework in Information-Centric Networking (ICN) for application-oriented service provisioning. In this framework, our cache pruning mechanism (CPM) provides stable throughput performance and achieve high QoE of streaming users by eliminating “harmful” cached chunks. To flexibly perform CPM, we developed a CCNx-1.0 compliant controller, and experimented the framework in a cloud-native ICN platform to prove stable video streaming quality as cloud/edge services. We revealed that our proposed framework can substantially improve throughput and achieve high QoE performance through the real-world performance evaluation.