Impact of the COVID-19 pandemic on the Internet latency: a large-scale study

TL;DR

This study analyzes the impact of the COVID-19 lockdown on Internet latency using large-scale RIPE Atlas measurements from Italy and broader Europe. It introduces two data pipelines, AMD and UDMD, and a latency decomposition framework to separate queuing from fixed path delays, aggregating results into 30-minute buckets to quantify variable latency via metrics like r_min, r_avg, and r_max. The findings show substantial increases in latency variability during lockdown, particularly in the evenings and weekends, with content-delivery traffic (e.g., YouTube) and IPv6 often exhibiting greater fluctuations. The results also reveal country-specific differences in Europe, AS-path changes, and mixed packet-loss behavior, underscoring the complex, heterogeneous resilience of regional networks and the importance of large-scale, operator-agnostic measurements for informing network management during crises.

Abstract

The COVID-19 pandemic dramatically changed the way of living of billions of people in a very short time frame. In this paper, we evaluate the impact on the Internet latency caused by the increased amount of human activities that are carried out on-line. The study focuses on Italy, which experienced significant restrictions imposed by local authorities, but results about Spain, France, Germany, Sweden, and the whole of Europe are also included. The analysis of a large set of measurements shows that the impact on the network can be significant, especially in terms of increased variability of latency. In Italy we observed that the standard deviation of the average additional delay -- the additional time with respect to the minimum delay of the paths in the region -- during lockdown is ~3-4 times as much as the value before the pandemic. Similarly, in Italy, packet loss is ~2-3 times as much as before the pandemic. The impact is not negligible also for the other countries and for the whole of Europe, but with different levels and distinct patterns.

Figures (14)

• Figure 1: Main characteristics of the Italian and European paths.
• Figure 2: Italian AMs, from raw data to aggregated values (scales on the $y$ axis are different).
• Figure 3: $d$ and $r$ values in measurements with both source and target in Italy. The dashed vertical lines correspond to lockdown events. The two gray areas correspond to W1 and W2.
• Figure 4: $r$ in measurements from Italy to the rest of Europe and vice-versa. The dashed vertical lines correspond to lockdown events. The two gray areas correspond to W1 and W2.
• Figure 5: Packet loss in measurements with both source and target in Italy.