Artificial intelligence (AI) methods in optical networks: A comprehensive survey

Artificial intelligence (AI) is an extensive scientific discipline which enables computer systems to solve problems by emulating complex biological processes such as learning, reasoning and self-correction. This paper presents a comprehensive review of the application of AI techniques for improving performance of optical communication systems and networks. The use of AI-based techniques is first studied in applications related to optical transmission, ranging from the characterization and operation of network components to performance monitoring, mitigation of nonlinearities, and quality of transmission estimation. Then, applications related to optical network control and management are also reviewed, including topics like optical network planning and operation in both transport and access networks. Finally, the paper also presents a summary of opportunities and challenges in optical networking where AI is expected to play a key role in the near future.

Artificial Intelligence (AI) Methods in Optical Networks: A Comprehensive Survey

In this paper, tools from machine learning community, such as Bayesian filtering and expectation maximization parameter estimation, are presented and employed for laser amplitude and phase noise characterization. We show that phase noise estimation based on Bayesian filtering outperforms conventional time-domain approach in the presence of moderate measurement noise. Additionally, carrier synchronization based on Bayesian filtering, in combination with expectation maximization, is demonstrated for the first time experimentally.

Application of Machine Learning Techniques for Amplitude and Phase Noise Characterization

We present a simple method to accurately measure the frequency noise power spectrum of lasers. It relies on creating the beat note between two lasers, capturing the corresponding signal in the time domain, and appropriately postprocessing the data to derive the frequency noise power spectrum. In contrast to methods already established, it does not require stabilization of the laser to an optical reference, i.e., a second laser, to an optical cavity or to an atomic transition. It further omits a frequency discriminator and hence avoids bandwidth limitation and nonlinearity effects common to high-resolution frequency discriminators.

Accurate frequency noise measurement of free-running lasers

The phase noise characteristics and laser stabilization time of a tunable laser under both static and fast switching operation is characterized using a dynamic linewidth measurement technique which employs a digital intradyne coherent receiver. The measurement technique utilizes a time domain frequency estimator to characterize the laser phase noise and also analyses the separate noise contributions to the overall laser linewidth. The performance of the measurement technique is validated using a phase noise emulator and a low linewidth (10kHz) external cavity laser. The dynamic stabilization time, in terms of instantaneous frequency and linewidth, of a fast switching tunable DSDBR laser is subsequently investigated and we demonstrate that a minimum linewidth for a DSDBR laser can be realized within 50ns of a wavelength switching event in a 5-channel 50GHz spaced WDM system.

Dynamic linewidth measurement technique using digital intradyne coherent receivers

In this letter, we present a novel approach to measure the Lorentzian linewidth of a laser source. The approach is based on a heterodyne detection scheme, such as may be implemented in a coherent optical receiver for data communications, using both in-phase and quadrature information of the optical field. In contrast to previously published works, this approach does not suffer from modulation effects on the laser output.

Laser Linewidth Estimation by Means of Coherent Detection

We review real-time and off-line processing techniques for the proto-typing of a digital coherent receiver.

Real-time prototypes for digital coherent receivers

From 1-symbol delayed self-homodyne detected NRZ-DQPSK signals we derive four metrics, which allow for characterization of specific transmitter parameter misalignments. The presented approach does not only rely on interference constellation diagrams but incorporates reconstructing the transmitted optical field.

S. Wiese

Papers

Laser Linewidth Estimation by Means of Coherent Detection

Real-time prototypes for digital coherent receivers

QPSK transmitter characterization and reconstruction of optical field by 1 symbol delayed self-homodyne detection