Bridging the Gap between QoE and QoS in Congestion Control - A Large-scale Mobile Web Service Perspective

Explore a conference talk from USENIX ATC '23 that delves into improving mobile web service performance through innovative congestion control techniques. Learn about Floo, a novel QoE-oriented congestion control selection mechanism designed to bridge the gap between Quality of Experience (QoE) and Quality of Service (QoS). Discover how this approach targets request completion time as a QoE metric and utilizes reinforcement learning to optimize congestion control algorithm selection in real-time. Gain insights into the implementation of Floo in a popular mobile web service application and its impressive results, demonstrating QoE improvements ranging from 14.3% to 52.7% in various network conditions.