🤖 AI Summary
In the 5G era, mobile network performance exhibits significant heterogeneity, with users commonly experiencing high latency, low throughput, and unstable connectivity—necessitating independent, cross-carrier evaluation. Method: This study presents the first large-scale, third-party assessment of mobile network performance—latency, throughput, and connection stability—based on real-world traffic data collected globally from a distributed commercial CDN infrastructure. We integrate statistical analysis with spatiotemporal modeling to characterize geographic and carrier-specific performance variations. Contribution/Results: We find that minimum latency is highly location-stable (enabling robust anomaly detection); only 5% of users consistently achieve sub-20 ms latency, while 60% experience throughput below 50 Mb/s; the best observed latency reaches as low as 6 ms. These findings establish a novel empirical paradigm and benchmark for objective, operator-agnostic mobile network quality evaluation.
📝 Abstract
The web experience using mobile devices is important since a significant portion of the Internet traffic is initiated from mobile devices. In the era of 5G, users expect a high-performance data network to stream media content and for other latency-sensitive applications. In this paper, we characterize mobile experience in terms of latency, throughput, and stability measured from a commercial, globally-distributed CDN. Unlike prior work, CDN data provides a relatively neutral, carrier-agnostic perspective, providing a clear view of multiple and international providers. Our analysis of mobile client traffic shows mobile users sometimes experience markedly low latency, even as low as 6 ms. However, only the top 5% users regularly experience less than 20 ms of minimum latency. While 100 Mb/s throughput is not rare, we show around 60% users observe less than 50 Mb/s throughput. We find the minimum mobile latency is generally stable at a specific location which can be an important characteristic for anomaly detection.