In this blog series, we looked at how artificial intelligence (AI) and machine learning (ML) are transforming operations into fiber broadband networks that can sense, think and act. In this blog we look at the application of digital twins.
When internet speeds are not as advertised
What you see isn’t always what you get when it comes to internet speeds. Although a user may subscribe to a 200 Mb/s service, in reality the speed will often fluctuate throughout the day depending on what is happening on the network. For example, on November 8, 2023, the highly anticipated release of Call of Duty: Modern Warfare III saw a massive spike of 25.1 Tbps across Virgin Media’s UK network. These types of activities can cause speeds to drop dramatically during peak hours. And with approximately 1.5 billion PC and console gamers in the world1, and approximately 5,000 new games released on major platforms every year2, traffic congestion is a daily hazard.
This can be frustrating for subscribers and a concern for operators as regulators develop monitoring programs to measure broadband performance and better protect consumers. The US Federal Communications Commission has defined a testing framework to confirm that services funded by the Connect America Fund (CAF) meet basic performance standards. The FCC requires that at least 80 percent of network speed measurements be 80 percent of the required speeds.
By scoring well on these metrics, operators have a strong position in the market, as consumers want the assurance that their internet connection meets advertised performance levels.
So it’s not something you want to leave to chance.
Optimizing performance with digital twins
Leaving luck aside, operators leave a lot of space in the fiber access network, which ensures that at least one PON user can download at full speed during peak hours. This approach is simple but limited and overly conservative. It means that PON networks are largely underutilized, tying up capital and resources without delivering full value.
Meet the digital twin and a far superior way to optimize network capacity.
A digital network twin is broadly understood as a digital representation of a real network with which it is synchronized. Digital twins represent the next step in network simulation software: using real-time links to physical network entities for monitoring and control, integrating big data analytics and AI, and offering flexible user interactions and what-if predictions.
Digital twins have the potential to revolutionize networking capabilities and operations. This can improve scheduling decisions, validate configurations, speed troubleshooting, and assist in taking corrective action. This article from Nokia Bell Labs explains all the benefits of digital twins and here we will look at how a digital twin can improve both the strategic and operational aspects of PON capacity management.
Improvement of PON capacity planning
Digital, twin-based capacity planning predicts congestion risks much more accurately and focuses more on Quality of Experience (QoE) than traditional capacity planning. It avoids overly conservative service definitions and PON configurations, allowing network operators to increase PON usage – with up to 33 percent higher peak rates or doubling the number of users – without increasing the risk of speed test failures.
For strategic capacity planning, the digital twin enables “what-if” analysis. What is the impact if we increase the split ratio? What if a (multi-)gigabit service is introduced? The digital twin can also assess the impact of future traffic growth and determine when to upgrade to a new PON technology.
For operational capacity management, the digital twin monitors congestion levels and calculates the probability of speed test success for all PONs in the network, eliminating the need for real speed tests that are disruptive. This allows operators to verify that adding a user to the PON or upgrading a user to a higher service level is feasible without compromising the success of the speed test (and meeting the 80 to 80 percent requirement). The digital twin can do more than validate a service request in advance; it can even suggest which PON to add a user to or predict the fastest speed that can be offered without risking PON congestion.
In summary, the digital twin provides operators with valuable insights into their PON networks, allowing them to make informed decisions about capacity planning and management. This results in increased PON usage, improved network performance and a better user experience.
Make sure to download the whitepaper to understand all the ways AI/ML transform the operation of fiber optic networks. Also take a look at the Nokia Altiplano access controllerthe domain controller that brings advanced intelligence to the fixed access domain, which was awarded the #1 network automation platform for broadband access networks worldwide in 2024.
Sources
1. Newzoo Global Games Market Report 2023
2. Game World Observer
