Breaking down broadband nutrition labels

As part of the recently passed Infrastructure Investment and Jobs Act (Infrastructure Act) in the United States, Congress asked the Federal Communications Commission (FCC) to finalize rules that would require broadband Internet access service providers (ISPs) display a “label” that provides consumers with a simple layout that discloses prices, introductory rates, data allowances, broadband performance, management practices, and more.

A sample Broadband Nutrition Facts from the original 2016 FCC proposal.

While the idea of a label is not new (the original design dates from 2016), its inclusion in the Infrastructure Act has reinvigorated the effort to provide consumers with information sufficient to enable them to make informed choices when purchasing broadband service. The FCC invited the public to submit comments on the existing label, and explain how the Internet has changed since 2016. We’re sharing Cloudflare’s comments here as well to call attention to this opportunity to make essential information accessible, accurate, and transparent to the consumer. We encourage you to read our full comments. (All comments, from Cloudflare and others, are available for public consumption on the FCC website.)

Six years can change a lot of things, and the Internet is no exception. For example, Tiktok barely existed as a company at the start of 2016; now it is the most popular site in the world. The global population that uses the Internet increased from 3.4 billion people in 2016 to 5.2 billion in 2021, which represents a growth of 52%. According to Statista, users in 2015 spent around 5.5 hours with digital media; now users spend almost 8 hours with digital media. The amount of data consumed on the Internet in 2021 was 79 zettabytes, which is a number that is expected to more than double in only two years. Users are more dependent on the Internet now than ever before.

Users being more dependent on the Internet has been amplified during the pandemic. According to Pew Research, 90% of American adults say the Internet has been essential or important for them personally during the coronavirus outbreak. Forty percent of American adults say they used digital technology or the Internet in new or different ways compared with before the beginning of the outbreak. A home broadband connection is no longer primarily for recreation, but a necessity for equitable access to education, healthcare, and as of 2020, it’s now even essential for many employment opportunities.

With that dependency, though, comes a higher expectation of quality. In 2016, users were more tolerant of poor performance: they were just happy if their Internet worked. Furthermore, applications were typically less latency sensitive: things like VoIP and video chats were less prevalent than they are today. Nowadays, however, video chats are almost ubiquitous: we use them at work and at home with increasing frequency. If these applications are slow or perform poorly, it’s hugely impactful to the user experience. We think of it as “our Internet cutting out,” and we lose the engagement with whomever we’re talking to.

Our increased dependence on the Internet has in turn increased our expectations for good Internet performance.

Because the Internet has become more focused on performance in 2022, we believe that your Internet providers should disclose to you how good they are at providing a good experience for these applications that are now mission critical.

Previously, performance was measured by bandwidth, or the size of the pipe between you and what you want to access. However, bandwidth is much more widely available today than it was six years ago. Median download throughput increased from 39 Mbps in 2016 to 194 Mbps in 2021. This increase in throughput has opened up new uses of home Internet connections, and new opportunities to look holistically at the Quality of Experience (QoE) of home broadband. We believe that metrics beyond bandwidth such as latency and jitter (the variance in latency) have grown appreciably in importance and that should be reflected in policy going forward.

Transparency into broadband Internet performance isn’t just important to consumers, though. With more and more enterprises relying on the Internet to reach both customers and also employees, it has become a foundational part of the American economy. So many businesses rely on Cloudflare because they want their digital assets delivered to customers, partners, and employees quickly. Enterprises want to secure their network with our cloud because our edge services are physically close to users and can be reached with low latency. Performance is no longer a luxury — it is increasingly a necessity.

The FCC defined latency in 2016 as “the time it takes for a data packet to travel from one point to another in a network.” While technically true, the vagueness of this definition presents certain issues. The latency between two points could be arbitrary, or as is the case with current speed tests, measuring a path that is never traversed by consumers in daily Internet usage. To put it succinctly: we don’t know what is being measured or whether what’s measured reflects reality.

While there is ambiguity about what latency ISPs would show on their broadband label, Cloudflare, and other content providers, can see latency from the other side – from our edge servers that are serving websites to consumers. What we see is that rural states have higher latency than more dense states.

Figure 1: 50th percentile TCP Connect Time (ms) to Major Content Delivery Networks

*Alaska and Hawaii have TCP Connect times of 263ms and 160ms respectively. Data compiled by Cloudflare from the HTTP Resource Timings API‌‌

As an example, Cloudflare offers a browser isolation product that runs a web browser in our cloud, an application that is extremely sensitive to latency. To achieve these latencies, we’ve connected directly with 10,000 distinct networks across more than 270 global data center locations. We estimate that 95% of Internet users globally can reach Cloudflare-protected websites and services in under 50 milliseconds.

So while Cloudflare supports the FCC’s effort to increase understanding of cost and privacy of Internet Service Provider offerings and wants the labels to be expedited to provide real consumer value, we have suggestions to significantly augment the labels to provide a better view of how your Internet does at providing services to you. Standardizing technical measurements across the Internet is a big topic, and in some cases we suggest the FCC build stakeholder consensus on additional future changes to the label.

For the broadband performance section of the label, we recommended:

• Renaming “download speed” (and “upload”) to “throughput,” “bandwidth”, or “capacity.” We can’t deny “speed” has become conversationally interchangeable with throughput, but they aren’t the same. As the Internet continues to grow, “speed” will mean how fast the Internet is, which will be measured in latency and overall quality of service, not just throughput. The latter is simply the amount of bits a connection can handle in the downstream direction at any given time.

• Adding “jitter” to the label. With the pandemic-driven rise of video conferencing, jitter —the variation, or stability, of latency in an Internet connection—has become a common cause of issues. Found yourself saying “my Internet is cutting out” or “am I frozen? Oh, I’m back”? That’s likely jitter.

• Add methodological transparency and work towards standards for how latency, jitter, and packet loss are measured. Consumers should be able to make apples-to-apples comparisons between ISP offerings, but to do that,  a standard in how ISPs measure these numbers is needed. Rather than a hasty mandate from the FCC, our suggestion is to take the time to engage stakeholders on the best approaches.

The end goal of these recommendations is to make sure that standards on performance match the experiences users have on the Internet. Today, speed tests and other forms of Internet measurement often query endpoints that are embedded into ISP networks that don’t see any traffic beyond measurements, and this can produce misleading results that may lead users to think that their Internet experience is better than it actually is. If your measurements don’t follow the same paths and are treated the same as normal Internet traffic, your measurements will look better. We believe that performance measurements should closely approximate the user experience, so that you have the complete picture of how your Internet is performing.

However, network performance isn’t only about how well your provider takes bits from your device to where they need to go. Sometimes network performance can be impacted by network management techniques. Providers may institute techniques like traffic shaping, which will slow down traffic to and from specific high-bandwidth sites to ensure that other sites don’t see congestion and degraded performance. Other providers may implement bandwidth caps, where specific users who consume lots of data may be slowed down if they exceed a threshold, a technique commonly used for mobile networks.

To help address these issues, we recommended including policy level line-items in the network management section instead of merely a yes-or-no answer. For example, if an ISP slows traffic after a certain amount of data has been consumed in a month, that information should be accessible on the label itself.

For the privacy section of the label, our recommendation is that a link to a dense and rarely-read ISP privacy policy is not sufficient transparency into how an ISP will use subscribers’ data. We recommended a privacy section that gives consumers insight into:

• Collection and retention of information: The label should indicate whether the ISP collects and retains any information beyond what is strictly necessary to provide services to the subscriber, including web browsing history and location data, as well as how long that information is retained.

• Use of information: The label should indicate whether data collected by the ISP is used for purposes other than what is strictly necessary to provide the broadband service to the consumer, such as for advertising.

• Sharing of information: The label should indicate whether the ISP shares or sells the data collected, including location or browsing information data, with third parties.

• Opt out: The label should indicate whether the ISP provides options to opt-out of data use and sharing (whether the ISP receives consideration for such sharing).

• Security of information: The label should indicate whether the ISP provider has technical mechanisms in place to secure data from unauthorized access, including whether it encrypts metadata about a consumer’s browsing habits, and mechanisms in place to report breaches.

We also suggested that the FCC make the data presented in the label accessible in a machine-readable format for researchers and consumers.

We commend Congress for including broadband nutrition labels in the Infrastructure Investment and Jobs Act, and the FCC for moving quickly to implement the labels. The current broadband label, the product of years of work, will be a significant improvement over what we have now – nothing.

However, we don’t believe that the labels should stop there. While the labels from 2016 go a long way towards providing clarity into how much money users pay for their Internet and create a good standard for pricing, the Internet and the way people interact with it is so different now than it was six years ago. We need to ensure that we are representing the user experience to its fullest, as this will ensure that our Internet experience can continue to improve over the next six years and beyond.