Coherent optical orthogonal frequency division multiplexing (CO-OFDM) has attracted a lot of interest in optical fiber communications due to its simplified digital signal processing (DSP) units, high spectral-efficiency, flexibility, and tolerance to linear impairments. However, CO-OFDM’s high peak-to-average power ratio imposes high vulnerability to fiber-induced non-linearities. DSP-based machine learning has been considered as a promising approach for fiber non-linearity compensation without sacrificing computational complexity. In this paper, we review the existing machine learning approaches for CO-OFDM in a common framework and review the progress in this area with a focus on practical aspects and comparison with benchmark DSP solutions.

Single section quantum dash (QDash) mode locked lasers (MLL) can provide a flat and broadband optical frequency comb with low energy consumption, operational simplicity and large-scale low-cost production possibilities. MLL longitudinal modes can be employed as single carriers with a regular spectral spacing in a dense wavelength division multiplexing (DWDM) link, making them promising components for next generation DWDM transceivers. However, individual modes of a MLL suffer from relatively high phase noise while high capacity coherent transmission requires carriers with low phase noise. Optical feedback, which is a well-known method to reduce the linewidth of a single mode laser, can be used to stabilize comb lasers. This paper reports on the investigation of phase noise properties of comb lines delivered from a single section QDash MLL under optical feedback and shows that each MLL longitudinal mode optical linewidth can be drastically narrowed. It enables coherent transmission with extended link budget over 50 km at Tbit/s line rates.

We experimentally demonstrate the world’s first field-programmable gate-array-based real-time fiber nonlinearity compensator (NLC) using sparse K-means++ machine learning clustering in an energy-efficient 40-Gb/s 16-quadrature amplitude modulated self-coherent optical system. Our real-time NLC shows up to 3 dB improvement in Q-factor compared to linear equalization at 50 km of transmission.

We demonstrate detailed characterization results of a hybrid InP-TriPleX photonic integrated tunable laser based on silicon nitride microring resonators. A tuning range of 50 nm across the C-band, side-mode suppression ratio (SMSR) >50 dB, high output power (~10 dBm), linewidth of<;80 kHz across the whole tuning range, and μs switching speed are achieved. The delayed self-heterodyne (DSH) method is used for the linewidth measurement, the lowest linewidth can be achieve is ~35 kHz. The FM noise spectrum is also measured to show the 1/f noise and white noise characterization. Furthermore, the device demonstrates performance comparable with commercial external cavity lasers in 64-QAM coherent system.

Coherent fiber-optic communication systems are limited by the Kerr-induced nonlinearity. Benchmark optical and digital nonlinearity compensation techniques are typically complex and tackle deterministic-induced nonlinearities. However, these techniques ignore the impact of stochastic nonlinear distortions in the network, such as the interaction of fiber nonlinearity with amplified spontaneous emission from optical amplification. Unsupervised machine learning clustering (e.g., K-means) has recently been proposed as a practical approach to the blind compensation of stochastic and deterministic nonlinear distortions. In this work, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm is employed, for the first time, for blind nonlinearity compensation. DBSCAN is tested experimentally in a 40 Gb/s 16 quadrature amplitude-modulated system at 50 km of standard single-mode fiber transmission. It is shown that at high launched optical powers, DBSCAN can offer up to 0.83 and 8.84 dB enhancement in Q-factor when compared to conventional K-means clustering and linear equalisation, respectively.

We theoretically analyze the phase noise transfer issue between the pump and the wavelength-converted idler for a nondegenerate four-wave mixing (FWM) scheme, as well as study the vector theory in nonlinear semiconductor optical amplifiers (SOAs), in order to design a polarization-insensitive wavelength conversion system employing dual co-polarized pumps. A tunable sampled grating distributed Bragg reflector (SG-DBR) pump laser has been utilized to enable fast wavelength conversion in the sub-microsecond timescale. By using the detailed characterization of the SGDBR laser, we discuss the phase noise performance of the SGDBR laser. Finally, we present a reconfigurable SOA-based all-optical wavelength converter using the fast switching SGDBR tunable laser as one of the pump sources and experimentally study the wavelength conversion of the single polarization quadrature phase shift keying (QPSK) and polarization multiplexed (Pol-Mux) QPSK signals at 12.5-Gbaud. A wide tuning range (>10 nm) and less than 50 ns and 160 ns reconfiguration time have been achieved for the wavelength conversion system for QPSK and PM-QPSK signals, respectively. The performance under the switching environment after the required reconfiguration time is the same as the static case when the wavelengths are fixed.