The Internet is a research experiment that "escaped from the lab" to become a critical global communications infrastructure during our lifetimes. Over the past year of the COVID-19 pandemic, the Internet has supported friends and families staying in touch and supporting each other, remote work and learning, and the global collaboration of experts designing much-needed treatments and vaccines. As challenging as the past year (and more) has been, the Internet has made it possible for many important aspects of life, work, and culture to continue.
In March 2020, the Internet suddenly became a lifeline for people all over the world. Designed to withstand failures, attacks, and fluctuations in traffic, the Internet proved up to the task. Almost overnight, demand for Internet services grew dramatically, and shifted in both time and space. Many Internet service providers (ISPs) had network designs with spare capacity, deployed more bandwidth in critical locations, and relaxed bandwidth caps on low-income households. The Internet protocols, designed to adapt to changing conditions, were able to deliver reasonable service to many users by sharing the available resources dynamically.
As challenging as the past year (and more) has been, the Internet has made it possible for many important aspects of life, work, and culture to continue.
The following paper offers a detailed look at how Internet traffic changed during the COVID-19 pandemic. The paper is distinctive in analyzing traffic measurements from multiple networks—ISPs, three major Internet eXchange points (IXPs), a mobile provider, and a university network—across a long period of time. The combination of longitudinal data from multiple, diverse vantage points is truly unusual, and a testament to the large group of authors who worked with each other, their home institutions, and other stakeholders to acquire the measurement data.
The study shows how, as the spring 2020 lockdowns began, traffic surged for ISPs and IXPs while decreasing for mobile providers and university campuses. Residential traffic shifted quickly to having high loads during normal business hours. Normally dominated by download traffic, the volume of upstream traffic (from residential users to the Internet) increased even more dramatically due to interactive applications like videoconferencing. Other applications like video-on-demand streaming and online gaming increased, as users sought sources of news, education, and entertainment. People working from home also increased their use of Virtual Private Network (VPN) technologies for remote access to online resources within their companies and universities. The study also shows that traffic patterns changed throughout the year, with fluctuations caused by shifts in national lockdown strategies, vacation and holiday seasons, bouts of bad winter weather, and more.
While the Internet has been remarkably robust to the shifts in demand, the experiences of the past year offer valuable lessons for the future, including:
- The "digital divide" is more pronounced than ever, now that good Internet connectivity is critical for work, education, and medical information.
- Interactive applications, like video conferencing, are incredibly sensitive to even small fluctuations in network reliability and performance, leaving users frustrated.
- The enduring problems of Internet security and privacy become even more serious as attackers exploit vulnerabilities in popular applications as well as people's growing dependence on the Internet.
As the computer science community continues the important work of addressing these challenges, we should also redouble our efforts to collect and analyze the measurement data needed to understand Internet traffic, performance, and applications. With the Internet such an essential part of our daily lives, we can easily forget that no one person, company, country, or organization is truly in charge of making this "network of networks" hold together as one global infrastructure. We can only understand, and therefore improve, the Internet by observing how it responds under pressure from many locations.
To view the accompanying paper, visit doi.acm.org/10.1145/3465212
The Digital Library is published by the Association for Computing Machinery. Copyright © 2021 ACM, Inc.