5 August 2024 in IEEE Transactions on Wireless Communications
In the rapidly advancing field of Underwater Acoustic Communication (UAC), channel prediction remains a major challenge, exacerbated by the complicated nature of ocean environments. This paper introduces an innovative Multi-Task Learning (MTL) framework for time-varying Underwater Acoustic (UWA) channel prediction. By decomposing the high-dimensional Channel Impulse Response (CIR) prediction into interconnected tasks, the proposed framework leverages a Shared Feature Learning (SFL) layer, capturing intricate dependencies underlying UWA channels. To validate its efficacy, we conducted thorough evaluations, leveraging real-world data from two distinct at-sea experiments conducted in Wuyuan Bay, China. A comprehensive comparative study of various configurations for the SFL layer, ranging from commonly used Recurrent Neural Network (RNN)-based models to the more advanced transformer structure, further underscores the flexibility and broad applicability of our MTL framework for handling various challenging UWA environments.
25 July 2025 in Journal of Optical Communications and Networking
Accurate modeling of the gain spectrum in erbium-doped fiber amplifiers (EDFAs) is essential for optimizing optical network performance, particularly as networks evolve toward multi-vendor solutions. In this work, we propose a generalized few-shot transfer learning architecture based on a semi-supervised self-normalizing neural network (SS-NN) that leverages internal EDFA features—such as VOA input/output power and attenuation—to improve gain spectrum prediction. Our SS-NN model employs a two-phase training strategy comprising unsupervised pre-training with noise-augmented measurements and supervised fine-tuning with a custom-weighted MSE loss. Furthermore, we extend the framework with transfer learning (TL) techniques that enable both homogeneous (same-feature space) and heterogeneous (different-feature sets) model adaptation across booster, pre-amplifier, and ILA EDFAs. To address feature mismatches in heterogeneous TL, we incorporate a covariance matching loss to align second-order feature statistics between the source and target domains. Extensive experiments conducted across 26 EDFAs in the COSMOS and Open Ireland testbeds demonstrate that the proposed approach significantly reduces the number of measurement requirements on the system while achieving lower mean absolute errors and improved error distributions compared to benchmark methods.
19 December 2025 in Journal of Optical Communications and Networking
Scalable and efficient methods for predicting optical transmission performance using machine learning (ML) and cascaded learning (CL) are investigated in metro multi-span optical networks. We extend the CL framework beyond multi-span power spectrum prediction to enable accurate estimation of optical signal-to-noise (OSNR) and generalized signal-to-noise (GSNR) under dynamic channel loading, integrating cascaded component models for end-to-end (E2E) optical link performance prediction. To mitigate error accumulation inherent in cascaded predictions, additional E2E optical link measurements and models are incorporated. To ensure scalability, component-level models for erbium-doped fiber amplifier (EDFA) gain and noise figure are pre-trained prior to deployment. We demonstrate that the data collection effort for pre-training the EDFA model can be reduced to only 5.5% of the original training set through transfer learning. Furthermore, Gaussian noise (GN)-based analytical models are leveraged to assist in the training of ML-based models for fiber loss and nonlinear impairments. The proposed approach is evaluated under four distinct optical link configurations. On a five-span system comprising six EDFAs, the method achieves a mean absolute error of 0.22 and 0.13 dB for OSNR prediction of background channels and GSNR prediction for 400 GbE channels, respectively.
27 January 2026 in Journal of Optical Communications and Networking
We perform a field trial of end-to-end transmission of heterogeneous signals: digital coherent optical (DCO) channels up to 600 Gbps and analog radio-over-fiber (ARoF) carriers at 60 GHz (mmWave) and 210 GHz (sub-THz), across the HEAnet live production metro network, leveraging optical spectrum-as-a-service and a laboratory-based passive optical network. We then perform wavelength-dependent performance characterization of ARoF carriers across the 50 GHz ITU-T channel grid within the C-band, measuring the pre-FEC bit-error rate (BER). The channel whose BER lies within the acceptable FEC threshold is selected as the optimum spectral slot for co-launching ARoF with background WDM traffic. This analysis enables optimization of the spectrum allocation, enhancing performance, throughput, and spectral efficiency, and shows the seamless coexistence of analog and digital traffic services.
8 May 2025 in Journal of Optical Communications and Networking
With the growing demand for high-bandwidth, low-latency applications, optical spectrum as a service (OSaaS) is of interest for flexible bandwidth allocation within elastic optical networks (EONs) and open line systems (OLSs). While OSaaS facilitates transparent connectivity and resource sharing among users, it raises concerns over potential network vulnerabilities due to shared fiber access and inter-channel interference, such as fiber nonlinearity and amplifier-based crosstalk. These challenges are exacerbated in multi-user environments, complicating the identification and localization of service interferences. To reduce system disruptions and system repair costs, it is beneficial to detect and identify such interferences in a timely manner. Addressing these challenges, this paper introduces a machine learning (ML)-based architecture for network operators to detect and attribute interferences to specific OSaaS users while being blind to the users’ internal spectrum details. Our methodology leverages available coarse power measurements and operator channel performance data, bypassing the need for internal user information of wide-band shared spectra. Experimental studies conducted on a 190 km optical line system in the Open Ireland testbed, with three OSaaS users, demonstrate the model’s capability to accurately classify the source of interferences, achieving a classification accuracy of 90.3%.