IPA-DASH: Intelligent Proactive Adaptation for DASH Video Streaming at 5G Network Edge

Edge computing has been determined as a key feature for achieving low-latency performance in 5G networks. It enables application servers to be deployed next to base stations, thus offering services without experiencing Internet delays or congestion. Thanks to the O-RAN (Open Radio Access Network) architecture, the edge server can obtain RAN information at run time and employ it to enhance the quality of edge-based services. In this work, we develop a proactive adaptation solution, designated as IPA-DASH (Intelligent Proactive Adaptation for Dynamic Adaptive Streaming over HTTP), for DASH video streaming services. By utilizing the radio access information for each UE (User Equipment), IPA-DASH applies deep reinforcement learning to estimate the best video quality at present, while enabling video segment reselection along with an in-band, low-overhead segment cancellation method. This allows IPA-DASH to proactively adapt video streaming before its quality suffers, in contrast to conventional video adaptation solutions that reactively adapt video streaming based solely on application-layer performance. These solutions have no access to radio access conditions, so the adaptation is triggered after the video quality degrades. We implement and evaluate IPA-DASH on both a simulator and an emulated 5G edge platform. The results demonstrate that IPA-DASH outperforms other video adaptation solutions, achieving gains of 1.1% to 55.6% in terms of average QoE (Quality of Experience) and reducing rebuffering time by 35.0% to 97.3%.