On the Experimental Assessment of QUIC and Congestion Control Schemes in Cellular Networks

With the growth of the internet, current transport protocols are being re-evaluated to deal with traffic growth. QUIC is an evolving transport-layer protocol that has been developed to reduce Web latency, integrate security features, and enable a high-quality experience for mobile users. However, few systematic experimental studies have been carried out to evaluate users' service in a realistic mobile environment. In this work, we describe the design of experiments with QUIC and HTTP/3, which is based on QUIC, also considering benchmarks and variants in QUIC's implementations. We report our measurements collected from real mobile networks with the pan-European MONROE platform. Using data from the application, transport, and network layers in different wireless environments, we experimentally investigate and compare the performance of QUIC and HTTP/3 for static and mobile cellular users of several networks across Europe. Initial results show that QUIC-based operations are advantageous in case of users that move, and they are also strongly affected by the congestion control algorithm chosen for QUIC.