Antonino Nespola

Optical fiber sensing on deployed cables is gaining significant interest as a means to enhance network integrity and expand environmental monitoring capabilities. To fully achieve these goals, sensing signals must coexist with data transmission. While phase and state-of-polarization analysis are promising candidates for this integration, their practical exploitation presents several challenges. Because these methods measure the integrated deformation along the entire cable, sensitivity is often limited by high environmental noise floors. Furthermore, event interpretation and localization require more sophisticated analytics than conventional distributed fiber sensing. Incorporating fiber sensing into standard network architectures also necessitates a novel telemetry management system capable of handling heterogeneous datasets, high data rates, and stringent synchronization requirements. We present progress on these aspects, based on multi-year analysis of fiber-sensing data collected in field environments. Our results confirm that integrated sensing achieves the sensitivity required to detect mid- and low-magnitude seismic events within a range of tens of kilometers from the fiber, holding the potential to support seismic monitoring services in terrestrial areas. Additionally, we demonstrate the detection and localization of anomalous vibrations and anthropogenic events and the development of an autonomous anomaly-detection tool suitable for real-time alerting. Finally, we outline the requirements for an advanced network management system designed to accommodate sensing alongside conventional telemetry, supporting the transition from proof-of-concept experiments to robust, large-scale applications.

The paradigm shift toward autonomous optical networking is transforming the transport layer into a widespread distributed sensing platform. However, traditional telemetry architectures, designed for low-frequency performance monitoring (typically sampled at 1 Hz or 15 min intervals), fail to meet the stringent requirements of physical sensing applications, which demand kHz-range sampling to capture seismic events by using indirect metrics such as state of polarization (SOP) rotations or the Jones rotation vector. This paper proposes a high-sampling-rate, open-source telemetry architecture designed to bridge this gap. Implemented as a containerized microservices stack orchestrated via Docker Compose, the framework leverages Apache Kafka to decouple high-velocity sensing streams from persistent storage, elevating raw sensor data to a “First-Class Citizen” for immediate consumption by AI/ML agents. This approach facilitates multi-modal sensor fusion by enabling the temporal correlation of heterogeneous metrics in real-time. We validate the architecture through an extensive experimental scalability analysis using a Monte Carlo approach. Results demonstrate that the system sustains a throughput of over 30,000 messages/s—approximately 15 times the requirement for high-fidelity sensing—while maintaining sub-second end-to-end latency ( <200ms ) in the optimal batching regime. These findings confirm the architecture’s suitability for critical early warning scenarios, enabling robust, low-latency intervention in disaggregated optical networks.

This study proposes a novel two-stage framework that integrates Digital Twin (DT) with Reinforcement Learning (RL) for failure prediction in optical communication networks. The framework focuses on optical amplifier failures, one of the most critical elements impacting network reliability. In the first stage, DTs are employed using the GNPy (Gaussian Noise model in Python) open-source optical network simulation framework to emulate amplifier behavior across diverse operational scenarios. This enables the generation of a comprehensive training dataset to train the Machine Learning (ML) model based on Long Short-Term Memory (LSTM). The LSTM model is able to achieve an accuracy of 98%. In the second stage, RL is applied to enhance the predictive accuracy to 99.5% and to improve the adaptability of the model. The LSTM model is rewarded for accurate predictions using external feedback, allowing it to iteratively refine its performance. This feedback-driven learning mechanism strengthens the robustness and decision-making capabilities of the model under dynamic network conditions. The proposed fine-tuning of the DT-based ML model using RL with external feedback enables proactive and adaptive fault management in optical networks.

This work presents a machine-learning framework for detecting and classifying independent and overlapping anomaly signatures in optical fiber infrastructure using state-of-polarization (SOP) dynamics. The framework exploits temporal variations of the Stokes parameters to characterize bending, tapping, shaking, and their simultaneous combinations. An experimentally collected dataset is used to evaluate multiple machine-learning models under realistic noise conditions representative of practical fiber monitoring environments. The results demonstrate that SOP-based features enable accurate identification of complex fiber disturbances, strengthening physical-layer monitoring and supporting the secure and reliable operation of next-generation optical networks.

We present the design and numerical analysis of an asymmetric bow-tie vertical-cavity surface-emitting laser (ABT-VCSEL) that enables PAM-2 direct modulation up to 100 GHz. The device concept relies on photon-photon resonance (PPR) between laterally coupled modes, triggered by a structural asymmetry introduced via a hollowed dielectric mirror. This approach avoids the need for asymmetric pumping and probing while ensuring strong modal coupling under uniform carrier injection. A dynamical in-house suite, combining field-carrier interaction, electromagnetic, and thermal problems, is developed and discussed to evaluate device performance under realistic conditions. The simulation results predict a 3-dB bandwidth up to 70 GHz with low modulation swing, and open eye diagrams at 100 GHz PAM-2 modulation and 70 GHz PAM-4 modulation. The proposed ABT-VCSEL concept shows robustness against geometrical variations and ambient temperature when proper cavity detuning is applied, making it a promising candidate for next-generation ultra-fast short-reach interconnects.

Accurate estimation of Non-Linear Interference (NLI) is critical for optimizing ultra-wideband optical networks. This paper investigates the performance of Longitudinal Power Monitoring (LPM)-based NLI estimation, focusing on heterogeneous links. While LPM offers robust, link-agnostic estimation of Self-Channel Interference (SCI), it requires correction for Cross-Channel Interference (XCI) to fully assess NLI. Two correction approaches are compared: a simplified Gaussian Noise (GN)-model-based approximation and the more accurate Polynomial Closed-Form GN/EGN model (PCFM). Experimental validation is conducted over both homogeneous and heterogeneous links, including scenarios with unequal channel power, on two different modulation formats. Results show that while estimation accuracy decreases in complex scenarios, LPM-based methods still provide sufficiently reliable performance for practical optimization tasks, such as determining optimal launch power. These findings support the use of LPM-based NLI estimation as a promising tool for real-time network monitoring and digital twin modeling.

This work introduces an advanced comprehensive framework for predictive maintenance by integrating Digital Twin (DT) with multiple Deep Learning (DL) models with the aim of predicting amplifier failures in optical networks. Using GNPy (Gaussian Noise model in Python), an open source framework, a DT is created to emulate network behavior under both normal and failure conditions, enabling the generation of synthetic datasets representative of amplifier degradation fault scenarios. These datasets are used to train DL models based on Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and Long- and Short-Term Time-Series Networks (LSTNet). A comparative analysis shows that all models exhibit strong performance, with LSTM achieving an accuracy of 99% and LSTNet, CNN models closely following at 98% and 96% respectively, demonstrating the ability of these DL models to identify complex temporal and statistical patterns in network telemetry data, facilitating accurate prediction of early failures. This integrated solution provides a scalable and data-driven approach for proactive fault management, improving operational capabilities in optical transport networks.

Network Interface Cards (NICs) greatly evolved from simple basic devices moving traffic in and out of the network to complex heterogeneous systems offloading host CPUs from performing complex tasks on in-transit packets. These latter comprise different types of devices, ranging from NICs accelerating fixed specific functions (e.g., on-the-fly data compression/decompression, checksum computation, data encryption, etc.) to complex Systems-on-Chip (SoC) equipped with both general purpose processors and specialized engines (Smart-NICs). Similarly, Field Programmable Gate Arrays (FPGAs) moved from pure reprogrammable devices to modern heterogeneous systems comprising general-purpose processors, real-time cores and even AI-oriented engines. Furthermore, the availability of high-speed network interfaces (e.g., SFPs) makes modern FPGAs a good choice for implementing Smart-NICs. In this work, we extended the functionalities offered by an open-source NIC implementation (Corundum) by enabling time-aware traffic management in hardware, and using this feature to control the bandwidth associated with different traffic classes. By exposing dedicated control registers on the AXI bus, the driver of the NIC can easily configure the transmission bandwidth of different prioritized queues. Basically, each control register is associated with a specific transmission queue (Corundum can expose up to thousands of transmission and receiving queues), and sets up the fraction of time in a transmission window which the queue is supposed to get access the output port and transmit the packets. Queues are then prioritized and associated to different traffic classes through the Linux QDISC mechanism. Experimental evaluation demonstrates that the approach allows to properly manage the bandwidth reserved to the different transmission flows.