Q3 2023 Internet disruption summary

Cloudflare operates in more than 300 cities in over 100 countries, where we interconnect with over 12,500 network providers in order to provide a broad range of services to millions of customers. The breadth of both our network and our customer base provides us with a unique perspective on Internet resilience, enabling us to observe the impact of Internet disruptions.

We have been publishing these summaries since the first quarter of 2022, and over that time, the charts on Cloudflare Radar have evolved. Many of the traffic graphs in early editions of this summary were screenshots from the relevant traffic pages on Radar. Late last year, we launched the ability to download graphs, and earlier this year, to embed dynamic graphs, and these summaries have taken advantage of those capabilities where possible. Sharp-eyed readers may notice an additional evolution in some of the graphs below: yellow highlighting indicating an observed “traffic anomaly”. Identification of such anomalies, along with the ability to be notified about them, as well as a timeline enhancement (embedded below) to the Cloudflare Radar Outage Center, were launched as part of Birthday Week at the end of September. More information on these new features can be found in our announcement blog post.

As we have seen in previous quarters, Iraq pursued an aggressive plan of government-directed Internet shutdowns intended to prevent cheating on exams, and several other African countries implemented politically motivated shutdowns. Damage to several submarine cables, as well as planned maintenance to others, caused Internet disruptions across a number of countries during the third quarter. Natural disasters, including wildfires and an earthquake, caused issues with connectivity, as did power outages in multiple countries. An acknowledged cyberattack resulted in a major US university intentionally disconnecting from the Internet, while a number of other major Internet providers acknowledged problems on their networks without ever disclosing the root cause of those problems.

(Note that the Internet disruptions related to the Israel/Palestine conflict are not covered in this post, as they began on October 7 in Q4 of 2023. Disruptions related to this conflict are being tracked, with additional insights found on the Cloudflare blog and @CloudflareRadar on X/Twitter.)

Government directed

Because the Internet has become a critical communications tool, Internet shutdowns are often used by governments as a means of controlling communication both within a country and with the outside world. These government-directed shutdowns are imposed for a variety of reasons, including during periods of civil unrest and protests around elections, and as a deterrent against cheating during exams.

As we have discussed in past summaries, Internet shutdowns are used by some governments in an attempt to prevent cheating on national high school or baccalaureate exams. These shutdowns have a nationwide impact, and it isn’t clear whether they are ultimately successful at mitigating cheating. As we have also discussed in the past, such shutdowns frequently occur in Iraq, and that was certainly the case during the third quarter, with rounds of shutdowns occurring during all three months.

The first round of exam-related Internet shutdowns during the quarter in Iraq was a continuation of a set that started in June, and continued on into July, targeting cheating on 9th and 12th grade exams. On ten days between July 4 and July 17, Internet connectivity was shut down on AS203214 (HulumTele), AS59588 (ZAINAS-IQ), AS199739 (Earthlink), AS203735 (Capacities-LTD), AS51684 (ASIACELL), and AS58322 (Halasat) in Iraq (except for the Kurdistan Region) between 04:00 - 08:00 local time (01:00 - 05:00 UTC).

During the second week of August, several networks in the Kurdistan region of Iraq again implemented daily exam-related Internet shutdowns due to a second round of exams for 12th grade students. These shutdowns took place between 06:00 - 08:00 local time (03:00 - 05:00 UTC), and impacted AS21277 (Newroz Telecom), AS48492 (IQ-Online), and AS59625 (KorekTel) from August 6-13. These two hour shutdowns were similar to those seen in the region in June.

A second round of 9th grade exams in August drove a week of Internet shutdowns across Iraq (except the Kurdistan region) between August 21 and August 29. Connectivity was shut down between 04:00 - 08:00 local time (01:00 - 05:00 UTC) across the same networks impacted by the shutdowns implemented in July.

Following the second round of 9th grade exams in August, the second round of 12th grade exams in Iraq (except the Kurdistan region) occurred in September, and with these exams, came yet another round of Internet shutdowns. Impacting the same set of network providers as the previous two months, these shutdowns occurred between September 17-30. However, while they started at the same time (04:00 local time, 01:00 UTC), they were shorter than previous rounds, ending an hour earlier (07:00 local time, 04:00 UTC).

On July 31, following the arrest of the Senegalese opposition leader, the Senegalese Ministry of Communication, Telecommunications and the Digital Economy once again ordered the disconnection of mobile Internet connectivity in Senegal as shown in the communiqué below. These disruptions to mobile Internet access were visible on two of the four network providers within the country: AS37196 (Sudatel Senegal) and AS37649 (Tigo/Free).

As shown in the graphs below, the shutdowns began mid-morning local time, generally between 08:00 and 10:00, from July 31 through August 5, and ended early the next morning, generally between midnight and 02:00. The final shutdown on August 5 was an exception, ending at 22:00 local time on both networks. (Senegal is UTC+0, so the local times are the same as UTC.)

Following days of clashes between the federal military and local militia, mobile Internet connectivity was shut down in Amhara, Ethiopia. Cloudflare saw traffic to the region drop around 21:00 local time (18:00 UTC) on August 2. This is the second time that authorities have shut down mobile Internet connectivity in Amhara in 2023 — the first time was on April 6 after protests broke out following the federal government’s move to disband regional security forces. (Note that the country is no stranger to Internet shutdowns, as they have taken such action multiple times over the last several years.) Despite calls to restore connectivity, mobile Internet remained unavailable through the end of the third quarter, as seen in the figure below.

On August 26, following contentious presidential elections in Gabon, Internet connectivity was shut down in order to "prevent the spread of calls for violence". As shown in the figure below, traffic began to fall just before 17:00 local time (16:00 UTC), and remained at zero through approximately 07:30 local time (06:30 UTC) on August 30. Connectivity was restored hours after military officers seized power in the country, placing President Ali Bongo under house arrest and naming a new leader after the country’s election body announced Bongo had won a third term.

Cable cuts

On July 7, an X/Twitter post from Cameroon Telecommunications alerted subscribers to disruptions to voice and data services, with a subsequent post nearly six hours later noting that services had been re-established. Although these posts did not provide details on the cause of the disruption, a Facebook post from the operator included an attached communiqué explaining that “The optical fibre has been severed by road maintenance operations, causing major disruptions in the delivery of our services.” The figure below shows the impact of this fiber damage, with traffic from AS15964 (CAMNET-AS) dropping sharply around 11:30 local time (10:30 UTC), and returning to expected levels by 18:00 local time (17:00 UTC).

Damage to the Africa Coast to Europe (ACE) submarine cable disrupted Internet connectivity in Liberia on July 28. A Facebook post from the Liberia Telecommunications Authority (LTA) noted “The Liberia Telecommunications Authority(LTA) announces the temporary interruption of all nationwide Internet services due to the breakdown of the Africa Coast to Europe Cable in Ivory Coast.” and also highlighted that the ACE cable serves as the “sole source of internet connectivity between Europe and Liberia”. The figure below shows a near complete loss of traffic starting at 13:00 local time (13:00 UTC) and gradually recovering over the next several hours, returning to expected levels by 17:00 local time (17:00 UTC).

On August 6, the West African Cable System (WACS) and the South Atlantic 3 (SAT–3) undersea cables were damaged by an undersea landslide in the Congo Canyon, located at the mouth of the Congo River. The damage to the cables impacted Internet connectivity in Togo, Benin, Namibia, and the Republic of Congo (Brazzaville). Social media posts from Telecom Namibia and Canalbox Congo alerted subscribers that connectivity would be impacted as a result of the damage to the cables.

Cable repair ship CS Leon Thevenin was called upon to perform repairs, but it took several weeks for it to arrive at the site of the damage, and then additional time to perform the repairs, which were reportedly completed on September 6. Network operators in impacted countries were able to shift some traffic to alternate cables, such as Google’s Equiano cable, which went live in February 2023.

As such, the graphs below illustrate that there was not a complete loss of traffic for impacted countries. To that end, traffic in Togo appeared to recover several weeks before the cable repairs were completed. The full impact is harder to see in the graphs for Benin, Namibia, and the Republic of Congo (Brazzaville) because the selected timeframe is long enough to force data aggregation at a daily level, but it is clearly visible in graphs covering shorter periods of time (with data aggregation at an hourly level) during the weeks after the cable cut occurred.

Highlighting the interconnected nature of the Internet, fiber cuts in Uganda caused a brief Internet disruption for customers on MTN South Sudan (AS37594) on August 14, occurring between 13:00 - 15:00 local time (11:00 - 13:00 UTC), and impacting an estimated 438,000 users. An X/Twitter post from the provider that afternoon told subscribers “We sincerely apologize for the network issues experienced over the last couple of hours. It was due to multiple fiber cuts in Uganda.”

Cyberattack

On August 27, a “significant security concern” led the University of Michigan to shut down the Internet on the Ann Arbor, Flint and Dearborn campuses. Although the shutdown occurred at the start of the new school year, classes continued as scheduled, but an announcement posted by the University detailed the impact of disconnecting from the Internet, including potential delays in financial aid refunds and the unavailability of certain campus systems. The impact of the disconnection can be seen in the figure below, appearing as a significant drop in traffic starting just before 14:00 local time (18:00 UTC) on August 27, and lasting until just after 08:00 local time (12:00 UTC) on August 30 on AS36375 (UMICH-AS-5), the primary autonomous system used by the University of Michigan.

Fire

In early August, a series of wildfires broke out in the state of Hawaii, predominantly on the island of Maui. The town of Lahaina was one of the hardest hit, with the fires killing nearly 100 people, as well as destroying homes, businesses, and infrastructure, causing power outages and disrupting Internet connectivity. The graph below shows traffic to Cloudflare from Lahaina dropping to near zero around 21:00 local time on August 7 (07:00 UTC on August 8), and remaining at minimal levels through August 30. Some recovery of Internet traffic can be seen through the end of September as cleanup and repairs progressed, and as wireless operators deployed temporary network assets in an effort to restore some service capacity.

Earthquake

At 23:11 local time on September 8 (22:11 UTC), a magnitude 6.8 earthquake occurred in Morocco, centered 79 kilometers (49 miles) southwest of Marrakesh. Nearly 3,000 deaths were reported as a result of the quake, and significant damage was reported, including the collapse of schools, houses, and historic buildings. Power outages and infrastructure damage also impacted Internet connectivity in the region, leading to largely localized disruptions.

The country-level graph below shows a nominal loss of traffic in Morocco after the earthquake, remaining slightly lower than expected for approximately four days. However, the impacts are more evident at a regional level, with the earthquake causing an immediate 64% drop in traffic in Marrkesh-Safi, a 64% loss in Souss-Massa, and a 49% decline in Casablanca-Settat. Peak traffic levels in these regions remained slightly lower than those seen in previous weeks for several days after the earthquake occurred.

Power outages

On July 27, a malfunction at a major Aqualectra Utility power distribution center resulted in 70% of neighborhoods in Curaçao losing power. The power outage resulted in an island-wide Internet disruption. As seen in the graph below, Internet traffic fell sharply at around 12:30 local time (16:30 UTC), remaining largely flat for approximately five hours before starting to recover around 17:30 local time (21:30 UTC). The start of the recovery aligns with the timing of a Facebook post made at 18:00 local time by Aqualectra Utility noting that “55% of Curaçao’s power supply has been restored.” The ongoing traffic increase is in line with additional neighborhoods having power restored, with traffic returning to expected levels by around 22:00 local time (2:00 UTC on July 28).

A widespread power outage in Brazil starting at 08:30 local time (11:30 UTC) on August 15 resulted in a nominal disruption to Internet traffic within the country. Although the power outage represented a loss of approximately 27% of the total electric load at the time it occurred, the impact to the country’s Internet traffic was much lower, as seen in the graph below. Traffic returned to expected levels by around 11:30 local time (14:30 UTC).

A “system disturbance” at 21:45 local time (18:45 UTC) on August 25 led to “loss of bulk power supply to various parts of the country” in Kenya, according to an X/Twitter post from Kenya Power. The impact of the power outage is visible in the graph below, with traffic dropping as power is lost. Subsequent updates from Kenya Power on August 26 (1, 2, 3) highlighted the progress made in restoring electricity across the country. Internet traffic from the country returned to expected levels by 03:00 on August 27 (00:00 UTC).

An 11-hour Internet disruption in French Guiana on August 27 was the result of a power outage caused by “a problem that occurred at the energy evacuation station which connects Petit-Saut to the Kourou-Saint-Laurent line”. The power outage caused a nationwide drop in Internet traffic between 11:00 local time (14:00 UTC) and 22:00 local time (01:00 UTC on August 28), visible in the graph below.

A fire at the Tunisian Company of Electricity and Gas power station in Rades, Ben Arous Governorate caused a widespread power outage in Tunisia, resulting in an Internet disruption starting at 01:00 local time (00:00 UTC) on September 20. Traffic remained lower than expected for approximately five hours, as shown in the graph below, in line with a published report that noted “The unexpected outage lasted for over four hours in some areas of the country.”

A September 21 Facebook post from The Barbados Light & Power Company Limited noted that the company was aware of an outage affecting customers, and that they were “working to promptly and safely restore power in the shortest time possible.” This outage resulted in a significant drop in Internet traffic from the country starting at 11:30 local time (15:30 UTC). A subsequent Facebook post from the utility company at 20:00 local time (00:00 UTC on September 22) noted that power had been restored to all customers. Ahead of full power restoration, Internet traffic had returned to expected levels around 17:00 local time (21:00 UTC).

Maintenance

La Guinéenne de la Large Bande, also known as GUILAB, is the company responsible for managing the capacity allocated to the country of Guinea on the Africa Coast to Europe (ACE) submarine cable. According to a (translation of the) communiqué posted by the company on Facebook, planned maintenance on the cable would be taking place between 22:00 on July 14 and 06:18 "sharp" on July 15 (22:00 on July 14 and 06:18 on July 15 UTC). This maintenance resulted in a complete Internet outage in Guinea, as seen in the graph below. It appears that the ACE submarine cable is Guinea’s sole international Internet connection, with no other backup submarine or terrestrial connectivity.

Just a few days later, planned maintenance to another submarine cable took Palau, an island country in the western Pacific, completely offline for several days. According to a press release from the Palau National Communications Corporation (PNCC) posted to their Facebook page, “BSCC (Belau Submarine Cable Corporation) has been notified that an emergency repair will be undertaken on the SEA – US cable network in Guam from Tuesday, July 18th 7:00 a.m. Palau time, and expected to be completed 5:00 p.m. Saturday, July 22nd. … For safety reasons, repairs can only be undertaken when the cable is not powered. Since BSCC’s Palau Cable Network No 1 connects to SEA – US for onward transport to Guam, BSCC will be unable to provide service for the duration of the repair. BSCC will be unable to provide any international connectivity for Palau. The only available international connection will be via PNCC satellite connection, which will provide limited capacity compared to normal cable service.”

The graph below shows that Cloudflare did not see any appreciable traffic from Palau’s backup satellite connection during the duration of the repairs, as traffic dropped to zero at 07:00 local time on July 18 (22:00 UTC on July 17), and remained there until around 18:00 local time on July 21 (09:00 UTC), as the repairs were completed earlier than expected. A PNCC press release confirmed this early completion, noting “PNCC is pleased to inform the public that Internet and Mobile Data services for our customers have been restored, due to the early completion today of the emergency repairs on the SEA-US Submarine Cable System, our main off-island internet connection.”

Unspecified issues

At 14:03 Eastern Time (18:03 UTC) on August 17, the X/Twitter support account for Spectrum, a brand of US-based Internet service provider Charter Communications, posted a statement that noted “We are aware of an outage affecting customers in Alabama, Georgia and Tennessee. We apologize for the inconvenience and are working to resolve as quickly as possible. Thank you.” The graphs below show the varied impacts to traffic seen from Spectrum (AS20115) across the listed states, as well as Texas, which wasn’t initially cited by Spectrum as having an issue, though customers quickly called it out.

A near complete outage was observed in Tennessee between 12:30 - 14:00 local time (17:30 - 19:00 UTC), while a brief drop in traffic at 12:00 local time (17:00 UTC) and quick recovery ahead of another drop at 13:30 local time (18:30 UTC) was seen in Alabama. Georgia also saw an initial drop in traffic at 13:00 local time (17:00 UTC) ahead of a larger fall at 14:30 local time (18:30 UTC), while traffic from Texas only experienced a decline at 13:30 local time (18:30 UTC). Traffic volumes from all four impacted states recovered within several hours — approximately three hours after the initial post, Spectrum’s support account stated “We have received confirmation repairs have been completed and services have been restored to affected customers in the Alabama, Georgia and Tennessee area.”

On September 12, satellite Internet service provider SpaceX Starlink experienced a brief but complete outage. The graph below shows traffic from AS14593 (SPACEX-STARLINK) dropping at 23:15 UTC, but quickly recovering, returning to normal within 90 minutes. At 00:33 UTC on September 13, Starlink shared an X/Twitter post stating “Starlink is currently in a network outage, and we are actively implementing a solution. We appreciate your patience, we'll share an update once this issue is resolved” and just over an hour later, posted “The network issue has been fully resolved”.

During the evening (UTC) of September 19, numerous complaints could be found on social media about a nationwide outage across the United Kingdom on Sky Broadband (AS5607). A sharp drop in traffic from Sky Broadband can be seen in the graph below starting at 21:00 UTC, but a full outage did not appear to have taken place. Traffic volumes below expected levels lasted until approximately 01:00 UTC on September 20. While the issue was acknowledged by Sky’s support account on X/Twitter, no root cause for the disruption was ever provided.

As we’ve noted in past quarterly summaries, this report is intended as a summary overview of observed disruptions, and not an exhaustive or complete list of issues that have occurred during the quarter. Some disruptions not covered here were visible in our data, but never acknowledged by the impacted provider, while others were reported by industry colleagues based on their measurement methodologies, but not clearly obvious in our traffic graphs.

As we indicated above, the Cloudflare Radar Outage Center now includes information on observed traffic anomalies as well as verified outages. Interested users can subscribe to notifications for both anomalies and outages — our blog post includes more information on how to do so.

Visit Cloudflare Radar for additional insights around Internet disruptions. Follow us on social media at @CloudflareRadar (Twitter), https://noc.social/@cloudflareradar (Mastodon), and radar.cloudflare.com (Bluesky), or contact us via email.