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

The achievable transmission capacity of conventional optical fibre communication systems is limited by nonlinear distortions due to the Kerr effect and the difficulty in modulating the optical field to effectively use the available fibre bandwidth. In order to achieve a high information spectral density (ISD), while simultaneously maintaining transmission reach, multi-channel fibre nonlinearity compensation and spectrally efficient data encoding must be utilised. In this work, we use a single coherent super-receiver to simultaneously receive a DP-16QAM super-channel, consisting of seven spectrally shaped 10GBd sub-carriers spaced at the Nyquist frequency. Effective nonlinearity mitigation is achieved using multi-channel digital back-propagation (MC-DBP) and this technique is combined with an optimised forward error correction implementation to demonstrate a record gain in transmission reach of 85%; increasing the maximum transmission distance from 3190 km to 5890 km, with an ISD of 6.60 b/s/Hz. In addition, this report outlines for the first time, the sensitivity of MC-DBP gain to linear transmission line impairments and defines a trade-off between performance and complexity.

/pdf/spectrally-shaped-dp-16qam-super-channel-transmission-with-nc38guh83g.pdf

Spectrally shaped DP-16QAM super-channel transmission with multi-channel digital back-propagation.

In this work we detail the strategies adopted in the European research project IDEALIST to overcome the predicted data plane capacity crunch in optical networks. In order for core and metropolitan telecommunication systems to be able to catch up with Internet traffic, which keeps growing exponentially, we exploit the elastic optical networks paradigm for its astounding characteristics: flexible bandwidth allocation and reach tailoring through adaptive line rate, modulation formats, and spectral efficiency. We emphasize the novelties stemming from the flex-grid concept and report on the corresponding proposed target network scenarios. Fundamental building blocks, like the bandwidth-variable transponder and complementary node architectures ushering those systems, are detailed focusing on physical layer, monitoring aspects, and node architecture design.

/pdf/next-generation-elastic-optical-networks-the-vision-of-the-1u1b7hiwk5.pdf

Next generation elastic optical networks: The vision of the European research project IDEALIST

This work proposes a probabilistic shaping scheme for optical WDM systems, where nonlinear interference noise depends on the input optical signal power distribution. With $16$ -QAM, a white Gaussian channel analysis shows that the shaped constellation is able to achieve a reach improvement of up to $7\%$ , while split-step Fourier method simulations suggest that even higher gains are possible in practice. An example system is developed for a transmission distance around $3280$  km. A constellation mapping and a low-density parity-check code are developed for this regime to show a reach improvement of $7.1\%$ . These shaping schemes can also be extended to $64$ -QAM, where a reach improvement of over $10\%$ is expected.

Probabilistic 16-QAM Shaping in WDM Systems

Next-generation optical communication systems will continue to push the ( bandwidth · distance) product towards its physical limit. To address this enormous demand, the usage of digital signal processing together with advanced modulation formats and coherent detection has been proposed to enable data-rates as high as 400 Gb/s per channel over distances in the order of 1000 km. These technological breakthroughs have been made possible by full compensation of linear fiber impairments using digital equalization algorithms. While linear equalization techniques have already matured over the last decade, the next logical focus is to explore solutions enabling the mitigation of the Kerr effect induced nonlinear channel impairments. One of the most promising methods to compensate for fiber nonlinearities is digital back-propagation (DBP), which has recently been acknowledged as a universal compensator for fiber propagation impairments, albeit with high computational requirements. In this paper, we discuss two proposals to reduce the hardware complexity required by DBP. The first confirms and extends published results for non-dispersion managed link, while the second introduces a novel method applicable to dispersion managed links, showing complexity reductions in the order of 50% and up to 85%, respectively. The proposed techniques are validated by comparing results obtained through post-processing of simulated and experimental data, employing single channel and WDM configurations, with advanced modulation formats, such as quadrature phase shift keying (QPSK) and 16-ary quadrature amplitude modulation (16-QAM). The considered net symbol rate for all cases is 25 GSymbol/s. Our post-processing results show that we can significantly reduce the hardware complexity without affecting the system performance. Finally, a detailed analysis of the obtained reduction is presented for the case of dispersion managed link in terms of number of required complex multiplications per transmitted bit.

Erik Timmers

Papers

Reduced Complexity Digital Back-Propagation Methods for Optical Communication Systems