Paper: Large Scale “Speedtest” Experimentation in Mobile Broadband Networks
Abstract: Characterizing and evaluating the performance of Mobile Broadband (MBB) networks is a vital need for today’s societies. Testbed-based measurements are of great significance in this context, since they allow for controlled and longitudinal experimentation. Inthis work, we focus on “speed” as an important Quality of Service (QoS) indicator for MBB networks, and design and implementMONROE-Nettest, an open-source speedtest tool running as an Experiment as a Service (EaaS) on the Measuring Mobile Broad-band Networks in Europe (MONROE) testbed. We run an extensive longitudinal measurement campaign spanning 4 countries over 3 years, and provide our experiment results together with rich metadata as open data. We characterize the open dataset in detail, aswell as derive insights from it regarding the impact of network context, spatio-temporal effects, roaming, and mobility on networkperformance. We describe our experience with conducting speedtest measurements in MBB, and discuss the challenges associatedwith large scale testbed experimentation in operational MBB networks. Tackling one of the said challenges further, we design aMachine Learning (ML) based framework for minimizing data consumption through adaptive speedtest duration. We provide aproof of concept, called “Speedtest++”, using a part of our open dataset. Finally, we provide an overall discussion of how opendatasets such as ours can support MBB research, as well as describe our lessons learned, and comment on open challenges, in orderto serve as discussion points for future work.