Skip to main content

Ciena uses machine learning to create Liquid Spectrum

OFC 2017, LOS ANGELES – Ciena is introducing new capabilities that “empower network operators to tune, control and dynamically adjust optical capacity in an on-demand world”, which go under the umbrella of “Liquid Spectrum”.

At first glance it sounds like just another software-defined networking (SDN) story, when in fact there’s some very cool technology buried in Ciena’s announcement.

Helen Xenos, director of portfolio marketing for Ciena, hints at what it does. “At its core, Liquid Spectrum is about mining and using available system margin – a changing variable over the life of the network – to gain optical capacity on-demand, improved reach for a specific channel, or increased service availability,” she wrote on Ciena’s corporate blog.

In fact, Ciena has used machine learning to wring the last ounce of performance out of an optical link. Liquid Spectrum doesn’t just automate the existing network, it optimises the physical properties of the underlying network.

Maurice O’Sullivan, Ciena’s senior director optical systems engineering, presented an overview of how it works at an OFC 2017 Workshop on Sunday titled “Will Machine Learning and Big Data Analytics Relieve Us from the Complexity of System and Network Engineering?” (into which this reporter stumbled out of curiosity).

Programmable coherent transponders, like those based on Ciena’s Wavelogic coherent processor family, come armed with a range of modulation formats. For any given reach, the modem capacity is truncated to the highest available value from the selection. Or to put it another way, as the reach increases the corresponding channel capacity falls in a step-wise fashion. As a result, unless the system is operating on the edge of a step, some system margin has to be thrown away.

One way to avoid throwing away margin would be to reduce the size of the step, but too many speeds would be difficult to manage, and would not be compatible with existing service rates. There’s another way to achieve near-continuous tuning: optimising the optical signal-to-noise ratio (OSNR) by adjusting the power of neighbouring channels (to reduce interference). Ciena calls this “neighbourhood power provisioning”.

For instance, if all channels in a link had insufficient OSNR to support 250G, reducing the power on alternate groups of channels so they still had enough margin to carry 200G, but not more, would have the effect of boosting the OSNR on remaining channels to a level that can now support 250G. (Lower power in neighbouring channels equals less interference). Thus, the overall capacity of the link is increased.

It’s a neat concept, but this kind of optimisation is not trivial. This is where the smarts of Ciena’s latest Wavelogic AI coherent processor are required (see Ciena embeds network monitoring in next-generation coherent chipset). O’Sullivan described how supervised machine learning is used to calibrate the system – because the effect of system nonlinearities cannot easily be calculated. Machine learning gives a more accurate result.

Software control via Ciena’s Blue Planet software is required to exploit these new capabilities. In its initial introduction, Liquid Spectrum will feature several advanced applications. The “Bandwidth Optimizer” uses customer-defined service policies and suggests the ideal capacity, hardware configuration and spectral placement for any channel, across any network path. “Liquid Restoration” adjusts the deployed coherent optical capacity as needed to route affected services across any available path in the network. And “Wave-Line Synchronizer” accelerates service provisioning, reduces manual provisioning steps and eliminates associated human errors across multi-vendor optical deployments.

Combined, Ciena says these new capabilities result in a better way to design networks, with an optical system that can “understand its existing level of performance and have the intelligence to perform a self-optimisation, selecting from a list of modulation formats for each transponder in the network and maximising the capacity that can be achieved at any moment, autonomously.”

Ciena’s WaveLogic Ai and Blue Planet Manage Control and Plan (MCP) – two key elements of Liquid Spectrum – will be available in the second quarter of 2017. Liquid Spectrum and its initial software applications are slated for delivery by the end of this year.



Read more about:


Media Partners