Introduction Introduction
This addresses the question of whether the PingER data can identify the impact of COVID-19 on the Internet. According to https://thrivenextgen.com/covid-19-impact-on-internet-performance/ Most Internet Service Providers (ISPs) oversubscribe their bandwidth and networks as typical inbound and outbound traffic are bursty and often don’t sustain high levels on a continuous basis. Fortunately, most of the larger National Providers have had sufficient time to prepare for the impact of COVID-19 and plan for the possibility of business workloads shifting to the home. Regardless of this capacity planning, Internet traffic patterns are about to change drastically based on schools across the country opting for virtual learning and business work from home migrations. Also, Time Magazine April 5/ April 15, 2020, reports that "traffic worldwide is up 35%...Demand is highest in the evening in the past two weeks, says networking firm Century Link."
...
Results by region, country and by host
Asia
E Asia
Middle East (to be analyzed)
South Asia (to be analyzed)
...
PingER was originally set up for monitoring connections between High Energy Physics (HEP) sites that were mainly at National Labs and Universities in the US, Canada, Europe, and Japan. Thus these regions tend to have hosts that are mainly Research or Educational (R&E). As a result, for the above regions, most hosts being R&E monitored were and still are involved in Research and Education and have high-performance network links from organizations such as: Canarie, ESnet, Internet2, GEANT, DFN etc. Such network connections have sufficient capacity to accommodate changes in traffic patterns. These networks are deliberately well provisioned to enable research and explore the future etc.
as opposed to public network links. Thus looking at the overall performance for a country in these regions there is little evidence of the impact of Covid-19 interventions, See, for example, the analysis for Spain and Italy, two countries that were badly impacted by Covid-19. Also, see the UK.
On the other hand, almost all hosts monitored in Africa (apart from 3 in the Republic of South Africa), and South America (apart from some in Brazil and Argentina) are on public networks that are probably engineered to be good enough for the typical traffic, and thus more likely to be impacted by unexpected changes in traffic patterns caused by Covid-19 interventions.
The types of interventions that we may expect to make noticeable changes in Internet traffic patterns, and possible changes in ping jitter due to changes in path utilization, include:
- Lockdowns;
- Closing/suspending schools, colleges, sporting events, public meetings etc;
- Thus we might expect to see impacts on hosts at universities. However, as pointed out by Wade Hong of Carleton University "Due to the students in residence being asked to vacate for social distancing. With many university LMSes (Learning Management Systems) now cloud-based, and the use of cloud media services for streaming of recorded content, the potential bottlenecks have moved from the institution to these services."
- Imposing a curfew;
- Calling a state of emergency;
- It is probable that the increases in cases and deaths that are publicized will result in changed behaviors and people voluntarily sheltering in place working from home etc. however we do not regard this as an intervention.
The typical impacts are:
- A sustained (for a week or more) significant increase or decrease in IPDV values for some or all hosts in the country correlated with an intervention that may be expected to change traffic patterns.
- A change in the difference in the weekday vs the weekend performance (bear in mind all times are UTC) correlated with an intervention.
- An increase or decreases decrease in the variability day to day of the IPDV
To get a better idea of the overall impact we looked in more detail at 18 26 major countries in Africa that included over 40 hosts.76 monitored hosts in Southern Africa (Top Level Domains: ZA, LS, BW, NM), East Africa (BI, ER, ET, KY, MG, ML, MZ, RW, SD, TZ, UG, ZM, ZW), and Central Africa (AO, CM, CD, GA)
- There are 10 hosts (1 host in Mozambique, 2 in Botswana, 1 in Cameroon, 1 in Eritrea, 1 in Ethiopia, 1 in Sudan, 1 in Tanzania, 1 in the Republic of South Africa, and 1 in Zambia) that had insufficient PingER data to draw any conclusions.
- We could find no interventions of the above kind for Burundi (2 hosts), and Mozambique (4 hosts).
- Three hosts had high speed (TENET) connections
- Of the remaining 57 hosts:
- 17 had immediately recognizable IPDV changes within a week of the start of an intervention,
- 9 had associated changes that required further investigation (typically averaging the IPDV for a period of 14 days before and after the interventions)
- there were 3 high performance connected (TENET) hosts
- the remaining 31 either had no significant (i.e. to be significant the IPDV needed to have a difference that lasted for at least a week) changes or the change did not match an intervention.
- We categorized the remaining hosts into the site's purpose, i.e. gov (13 hosts), net (10 hosts), com (15 hosts), edu (17 hosts), org (1 host)
The breakdown of host category versus IPDV changes is below.
Gov Net Com Edu Org Total Strong 3 3 4 7 0 17 Medium 4 0 2 3 0 9 Unclear 7 7 9 7 1 31 Total 14 10 15 17 1 57
Possible Future work
Add data for South Asia.Summarize
Analyze more countries in Africa and South America.
References
Spread sheets:
- PingER daily IPDV from SLAC to over 700 hosts in over 155 countries
- Correlations between Covid-19 interventions and PingER IPDV changes.
- PingER daily IPDV versus Covid-19 interventions summary
the success by country in finding hosts with IPDV performance changes correlating with interventions in Africa and South America.