Mobile operator and UK ISP Vodafone have teamed up with Nokia Bell Labs to conduct a “world’s first trial” of the “viability” of harnessing L4S (Low Latency, Low Loss, and Scalable Throughput) technology over passive optical networks (PON), which could “greatly improve” network latency times for internet activities like AR, video conferencing and multiplayer gaming, even during peak hours.
For those who don’t know. Latency is a measure of the time that it takes for a packet of data to travel from your computer to a remote server and then back again (ping). The delay is measured in milliseconds (e.g. 1000ms = 1 second) and modern broadband connections will often have an average latency of anything from around c.4ms to 40ms (what is normal for your connection will depend on lots of different factors – see below).
A faster score (shortest time) is always best for latency, although the times can be affected by various things, such as the performance of remote internet servers, the connection technology being used, network congestion at your ISP, peering / routing problems and the setup of your own home network etc. But generally speaking, consumers with PON based Fibre-to-the-Premises (FTTP) broadband connections can usually already expect some of the best latency times of c.2-10ms.
However, there’s always room for improvement, which is where the new IETF Internet standard, L4S, comes in as it could enable networks to simultaneously maintain high throughput and low latency. L4S is based on the knowledge that the root cause of queuing delay (i.e. when packets wait idly in buffers across the network, for instance in routers and modems, before being forwarded) is in the capacity-seeking congestion controllers of senders, not in the queue itself. L4S thus aims to transition away from congestion control algorithms that cause substantial queuing delay and instead adopt a new class of congestion controls, which seek capacity with very little queuing.
Nokia Bell Labs and Vodafone’s Fixed Access Center of Excellence recently performed the “world’s first demonstration” of L4S running over PON in Vodafone’s lab in Newbury, England. The demonstration was performed on an end-to-end fixed access network built with Nokia technology. It consisted of a broadband network gateway (BNG), a PON optical line terminal (OLT), multiple PON optical network terminals (ONTs) and WiFi access points.
The lab tests showed extremely low and consistent end-to-end latencies when travelling across every element of the network and without compromising network speeds. In the tests, Vodafone and Nokia Bell Labs measured consistent latencies of 1.05ms at local Ethernet ports running over a fully congested access network (BNG to ONT) when loading a website, and just 12.1ms when including a fully congested WiFi link as the final connection. The fact it was “fully congested” is a key point, since otherwise 12.1ms on FTTP and WiFi (if we assume it was Wi-Fi 6E or 7 kit) might not seem all that special.
Azimeh Sefidcon, Head of Network Systems and Security Research, Bell Labs at Nokia, said:
“These highly encouraging results show L4S will unshackle any real-time application that would normally be constrained by high latency. Videoconferencing, cloud-gaming, augmented reality and even the remote operations of drones would run flawlessly across the internet, without experiencing any significant queuing delays.”
Gavin Young, Head of Fixed Access Centre of Excellence at Vodafone, said:
“As a leading broadband provider, Vodafone aims to give customers a faster, more responsive, and reliable service unhindered by lag even during peak hours. L4S is an exciting technology with huge potential to achieve this goal, as well as deliver a more interactive and tactile internet experience for our customers.”
The announcement does make a point of referencing online video games, although it is worth remembering that the related netcode for such games is typically designed to work across multiple different types of connection, including significantly slower links. As such, there is often an element of diminishing returns, where past a certain point you won’t notice any particular difference (e.g. if you already have FTTP with extremely fast latency times then L4S isn’t necessarily going to have a very noticeable impact, unless your network is under a lot of strain).