BT takes a deep dive into hollow-core fibre

BT has been experimenting with hollow-core fibre to understand how it could benefit its network. The results are promising.

Professor Andrew Lord“We are looking at all the use cases and it is a bit early to say which one is the killer one but they are all interesting,” says Professor Andrew Lord, BT’s head of optical network research.

“There are so many parameters [of hollow-core fibre] and all seem to be slightly or vastly better than single-mode fibre,” says Neil Parkin, optical networks research manager at BT.

The service provider is working with hollow-core fibre start-up, Lumenisity, and 5G software networking specialist, Mavenir.

Hollow-core fibre

Hollow-core fibre is not new. Several firms pursued the technology in the early 2000s but the technology failed to be adopted and the firms folded.

BT Labs is investigating the fibre anew because the optical loss performance of Lumenisity's fibre has improved greatly in recent years.

“Hollow-core fibre might have been interesting for devices but if it carries on [progressing], it looks like it will be useful in the network,” says Lord.

Standard optical fibre uses a solid glass core surrounded by cladding. The core has a higher refractive index than the cladding which confines the light to the core. But being glass, the speed of the light in the core is two-thirds that of the fundamental speed of light.

Hollow-core fibre, in contrast, uses an air-based core. Data sent along the fibre travels at a speed approaching that of the fundamental speed of light, some 50 per cent faster than traditional fibre. In terms of latency, this corresponds to a 30 per cent reduction.

Hollow-core fibre is thus ideal for applications where getting data to the destination as quickly as possible is key.

Companies such as OFS Fitel and Lumenisity, a University of Southampton spin-off, now offer hollow-core fibre commercially.

Hollow-core fibre typically is based on a photonic bandgap design. This results in multi-mode transmission in the core such that the fibre must be designed to filter the higher-order modes. In contrast, Lumenisity uses what it calls a nested, anti-resonant nodule fibre (NANF) design that is inherently single-mode.

"We are probably the first telco to have this hollow-core NANF design," says Parkin.

Optical performance merits

The flagship optical performance benefit of hollow-core fibre is its low latency. In addition to high-frequency trading, BT believes the lower latency will benefit 5G deployments.

The optical loss of standard fibre is 0.20dB/km while the loss of Lumensity’s fibre on a spool is 0.28dB/km. But the loss rises to 1dB/km when the hollow-core fibre is cabled for deployment.

“The loss, although worse than single-mode fibre, has a trajectory that suggests it has the potential to be much better,” says Lord. “With a fibre loss potentially down to 0.1dB/km, then you have got something disruptive for all kind of systems.”

The fibre could have an even lower loss because no impurities exist in a hollow core. But challenges remain in the fibre's manufacturing and there is the optical loss associated with the light’s interaction with the glass structures around the air core.

Another benefit of an air-based core and that there is no dispersion and non-linearity, and that implies better core networks or networks where the optical transceivers used could be simpler and cheaper.

Hollow-core fibre also has a significantly better thermal stability (some 20x) such that it varies far less with temperature. That equates to a much lower jitter around latency benefitting applications where timing is key.

Use cases

The main application of hollow-core fibre to date is high-frequency trading where its low latency gives a trader's financial transactions an edge.

BT is exploring hollow-core fibre’s potential for other networking applications, especially when it could deliver an optical loss lower than traditional fibre. “Could there be places in the network where it replaces a standard fibre or is maybe used alongside it?” says Lord.

BT Labs has been testing a 10km hollow-core cable and has been looking at its use for 5G fronthaul, working alongside Mavenir and Lumenisity.

The operator is also investigating 400-gigabit dense wavelength-division multiplexing (DWDM) using the OIF 400ZR standard as well as quantum key distribution (QKD) for secure data transfer.

5G fronthaul

BT is a proponent of Open RAN and is interested in using the fibre for 5G fronthaul to reduce costs.

There is a certain latency budget associated with fronthaul and BT is modelling what can be done by trading the latency associated with the fibre with that of the radio processing equipment. The lower latency of hollow-core fibre promises to extend the eCPRI link between the remote radio head and the central office where the signal processing occurs.

"Ultimately you are trying to lower the cost of 5G," says Parkin.

BT will publish its 5G work at ECOC later this year. "At a high level, it all works; you can go further for the same latency," says Parkin.

Lord adds that since fronthaul links do not span great distances, BT may not need to wait for Lumenisity to reduce the fibre's loss further.

"It might be good enough now," says Lord. "Then it becomes a question of the manufacturability of the fibre."

ZR optics

The 400ZR coherent standard serves data centre interconnect applications for distances up to 120km. The high ZR module volumes that data centre operators will drive means BT is keen to benefit from the technology.

BT wants to determine if 400ZR optical modules combined with hollow-core fibre will enable transmissions over greater distances. "Does hollow-core help with the ZR performance, the fact that it has lower non-linearity and lower dispersion?" says Lord.

Lord says dispersion has always been viewed as useful as it limits the effect of non-linearities in single-mode fibre. But to compensate for dispersion requires a coherent digital signal processor (DSP).

But hollow-core fibre has no non-linearities and so high dispersion is no longer needed. "Maybe we don't need the coherent DSP anymore or we don't need as much," says Lord.

ZR does use a coherent DSP but if it goes further distances, BT could use it in its core network.

"Does hollow-core enable us to build a very different architecture where ZR is everywhere?" says Lord.

Quantum key distribution (QKD)

The third use case BT has explored is QKD which involves the sharing of a key between endpoints for secure communications. The issue with quantum encryption is the distances involved since QKD is limited by the fibre's loss.

A certain number of keys are sent each second and most disappear in the loss of the fibre, says Lord. This is a limitation of QKD since what is required are intermediate 'trusted nodes' along the link, spaced a few tens of kilometres apart, to get the key to the destination.

If the loss of hollow-core is reduced to 0.1dB/km the number of trusted nodes needed would be halved.

Non-linearity of standard fibre is 'a killer' if quantum is integrated with conventional 100-gigabit transmissions.

"The hundred gigabit is not quantum but has masses of photons and they get in the way," says Lord. "They generate noise photons in the quantum channels via the RAMAN effect."

To exclude them from these channels requires high-quality optical filters. Since hollow-core fibre doesn't experience the RAMAN effect, co-existence of classical and quantum channels is much easier, says Lord. A single fibre could then be used for both channels.

Work status

BT Labs' says its remit of applied research means the work with start-up Lumenisity is exactly what it is meant to be doing.

"It doesn't mean that BT is about to buy a whole load of this fibre but we think this is added value that BT can have in having a strong research department to explore all of these disruptive ideas," says Lord.

BT has finished the initial phase of the experimentation with hollow-core fibre. "We have reached the point where we understand the fibre very well," says Lord. "It is very promising but who knows what is happening next."

BT’s Asif Iqbal will present a paper discussing ZR optics over hollow-core fibre at OFC while BT will publish more of its hollow-core fibre work at ECOC later this year.

And were BT to adopt the technology, would it even announce it? Not necessarily, says Lord.