The speed with which the Covid-19 pandemic took hold did not allow for network operators to lay huge amounts of extra fiber to cope with the high bandwidth spikes caused by lockdowns and work-from-home policies. Other means of coping were implemented, from calling in specialist technology suppliers to optimize traffic management, to operators rallying together to agree on widespread bit-rate reductions across streaming platforms.
US cableco Comcast is one operator which turned to artificial intelligence to address the bandwidth crunch, bringing forward some of its projects to develop capacity forecasting capabilities using AI/ML above a layer of network automation features.
The world’s largest cable operator is crediting its inhouse-developed Comcast Octave software for managing traffic spikes as high as 60% and adding 35Tbps of peak capacity to regional networks during March and April, according to a recent interview with VentureBeat.
At the time that lockdowns were being imposed in parts of the USA, Octave had only been deployed to part of the network. The new situation warranted radical measures as a team of 25 Octave engineers worked 7-day weeks to accelerate the deployment process. It worked, according to Comcast execs, bringing a 36% capacity increase to subscribers.
Octave is built on top of Comcast’s Smart Network Platform, which automates network functions to reduce the frequency and duration of network outages, cutting outage times from hours to minutes. At the heart of the Smart Network Platform is a machine learning tool called NetIQ that makes thousands of measurements on the core network every hour to monitor service degradation. NetIQ detects core network issues in minutes rather than hours – reducing the average from 90 minutes down to five minutes.
Only by having a grasp on core network issues can Octave then do its thing – which is both to identify when network modems are not using bandwidth efficiently, and to make this bandwidth available ahead of time.
Octave monitors some 4,000 telemetry data points on 50m network modems every 20 minutes, tweaking speed and capacity accordingly based on oodles of data points that only an AI-based platform could monitor, let alone act upon before an issue has even occurred.
Comcast says it uses telemetry and automation to operate equipment without manual interference from engineers – mitigating issues before degradation is allowed to hit the network.
Of course, it helps that Comcast has its own content delivery network (CDN) too, part of $12bn in network investments made since 2017, the majority of which has gone towards 33,331 new route miles of fiber optic cable to allow for doubling capacity every 2.5 years, according to Jan Hofmeyr, chief network officer at the Comcast Technology Center in Philadelphia
It is typical for Tier 1 providers like Comcast to have inhouse CDNs, often supported by mainstream CDNs, giving them extra control of what is delivered and how it is delivered. Since lockdowns came in, we have seen more companies going all-out on cloud infrastructure and exploring the possibilities of the network edge, as well as techniques like peer-to-peer networking.
Lockdowns have also highlighted how building a residential ISP network in a dense metropolitan area is a wildly different prospect from building a residential ISP network in a sparsely populated rural area. Some ISPs build their networks with a substantial amount of excess capacity, while others do not, with Comcast clearly falling into the former category – much to the envy of many smaller service providers.
Inevitably, what goes up, must come down – and this week evidence emerged for the first time showing that SVoD viewing has tailed off since lockdowns began easing. Netflix registered a 4% dip in viewing time, with Amazon Prime suffering a slump of 12% from the heights of April and May. It comes after the likes of Netflix, Amazon Prime Video, YouTube, Disney+, Apple TV+, Facebook and many more all committed to bit-rate squeezes earlier this year to help ease the traffic load.
Certainly, more ISPs will wish they had the resources to weather the storm, and while many will be funneling capex into fiber, others will be looking for a more software-centric, AI-based approach like Octave.