Abstract: A method of assessing a signal to identify particular signal characteristics comprises application of machine learning to multi-dimensional histograms derived from multi-tap sampling of the signal. The signal is sampled from at least two tap points to retrieve a sample set, and the at least two tap points are adapted to retrieve distinct samples from the signal, such as time spaced samples or spectrally distinct samples. Multiple sample sets are retrieved from the signal over time. The at least two dimensional histogram is built from the joint probability distribution of the plurality of sample sets. A machine learning algorithm then processes the multi-dimensional histogram, and is trained to predict a value of at least one characteristic of the signal.

Abstract: Monitoring an optical signal comprises sampling the optical signal from two or more distinct tap points to retrieve a sample set. Multiple such sample sets are obtained over time. A joint probability distribution or phase portrait of the sample sets is assessed for indications of optical signal quality. The tap distinction can be polarization, for example to determine OSNR, or frequency. The tap distinction can be a time delay, which can enable diagnostic differentiation between multiple impairments, such as OSNR, dispersion, PMD, jitter, Q, and the like. Machine learning algorithms are particularly suitable for such diagnosis, particularly when provided a two dimensional histogram of sample density in the phase portrait.

Abstract: A method and device for determining in-band noise of an optical signal. The optical signal is split to produce two optical signal components, of distinct polarisation, such that the respective noise component in each signal component is uncorrelated. The optical signal components are converted to the electrical domain to produce electrical signal components. The signal component powers are equalised either in the optical domain or the electrical domain. The equalised electrical signal components are then subtracted together to cancel the correlated portions of the signal components (e.g. the data signal), such that only uncorrelated signal components (e.g. noise) are output for measurement.

Abstract: Monitoring an optical signal comprises sampling the optical signal from two or more distinct tap points to retrieve a sample set. Multiple such sample sets are obtained over time. A joint probability distribution or phase portrait of the sample sets is assessed for indications of optical signal quality. The tap distinction can be polarisation, for example to determine OSNR, or frequency. The tap distinction can be a time delay, which can enable diagnostic differentiation between multiple impairments, such as OSNR, dispersion, PMD, jitter, Q, and the like. Machine learning algorithms are particularly suitable for such diagnosis, particularly when provided a two dimensional histogram of sample density in the phase portrait.

Abstract: A method and device for determining in-band noise of an optical signal. The optical signal is split to produce two optical signal components, of distinct polarisation, such that the respective noise component in each signal component is uncorrelated. The optical signal components are converted to the electrical domain to produce electrical signal components. The signal component powers are equalised either in the optical domain or the electrical domain. The equalised electrical signal components are then subtracted together to cancel the correlated portions of the signal components (e.g. the data signal), such that only uncorrelated signal components (e.g. noise) are output for measurement.