APAlessandro Pacini

Alessandro Pacini

*This is an algorithmically generated author record based on publicly available information.

Alessandro Pacini has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Longitudinal power profile monitoring telemetry enabling self-healing optical networks

    by Alessandro Pacini, Fabien Boitier, Alix May, Vinod Bajaj, Andrea Sgambelluri, Alessio Giorgetti, Luca Valcarenghi, Patricia Layec

    Soft failures in optical networks pose a significant challenge, as their detection and localization are notoriously difficult. This often leads to suboptimal mitigation strategies being implemented before the root cause is identified. To address this, the longitudinal power monitoring (LPM) technique has gained significant attention in recent years. LPM leverages information from the coherent receiver to compute the power evolution along the optical path. This paper presents an architecture that integrates the power profile information retrieved from the receiver with the SDN controller. The result is a self-healing optical network capable of locating soft failures in its lightpaths and providing finely tuned reconfigurations to solve them. By developing an OpenConfig-compliant YANG model, we implemented a gNMI streaming mechanism to transmit power profile metrics every 1.5 s from the receiver to the SDN controller. This process utilizes two SDN applications that combine the received data at the controller to finalize the power profile computation and pinpoint the location of soft failures. The architecture’s effectiveness is demonstrated through two scenarios. In the first scenario, the SDN controller accurately identifies and resolves attenuation caused by VOAs strategically placed along a span. In the second scenario, the controller jointly examines the power profiles of two lightpaths to locate a faulty WSS that is causing attenuation in only one of them.


  • Open Access

    Hybrid-Hierarchical Synchronization for Resilient Large-Scale SDN Architectures

    by Alessandro Pacini, Davide Scano, Andrea Sgambelluri, Luca Valcarenghi, Alessio Giorgetti

    Interest in hierarchical Software-Defined Networking (SDN) controllers is growing recently due to their ability to address the challenges associated with the SDN paradigm, such as responsiveness and scalability. This design enables efficient domain control separation, which uses different child instances to manage large-scale networks. Parent controller computational resources can be dedicated to cross-domain decision making, exploiting network views provided by its children. In this context, the correctness of the process fully relies on the network view synchronization mechanism, which should be fast and resilient. This paper presents a hybrid synchronization model combining a hierarchical design with established resilient cluster mechanisms. In this way, high-level control over large-scale networks can be guaranteed even with failures affecting every level of the management plane. Specifically, two applications are developed for the ONOS controller to share topology events using low-latency channels from child clusters to parent clusters. The performance of both applications is measured under different cluster configurations, topology sizes and number of generated topology updates. The results show that the proposed approach offers high performance while being fully compliant with the platform for which it is designed. This makes the solution easily extendable to heterogeneous child controllers. In fact, events are propagated from children to parents using gRPC, achieving end-to-end latency of less than 10ms under normal conditions and 40-60ms under high-rate event conditions. Consistency of network views is also guaranteed by strong event ordering and delivery mechanisms. Failures are handled seamlessly at both cluster levels (i.e. parent and child controllers) with a maximum synchronization delay of 2 seconds, which is quickly recovered.


  • Open Access

    Managing Physical Distancing Through 5G and Accelerated Edge Cloud

    by Luca Valcarenghi, Alessandro Pacini, Justine Cris Borromeo, Silvia Fichera, Maria Gagliardi, Denise Amram, Vincenzo Lionetti

    Specific 5G Release 17 work items are dealing with critical medical applications. Moreover, the adoption of mobile health (m-health) and e-health has been accelerated by the COVID-19 pandemic. This paper first examines the requirements of critical medical applications that 5G is expected to support. Then it illustrates possible data protection, management, and privacy issues. Finally, it shows a first implementation of an m-health framework supporting physical distance management. Experimental results show that, by exploiting 5G connectivity and the computing capacity provided by an accelerated edge cloud, the proposed framework can detect physical distance violations faster than a user equipment (UE)-based implementation, while saving UE energy.


  • Learning Long- and Short-Term Temporal Patterns for ML-Driven Fault Management in Optical Communication Networks

    by Moises Felipe Silva, Alessandro Pacini, Andrea Sgambelluri, Luca Valcarenghi

    The deployment of 5G and network slicing has challenged the current network management requirements, triggering the need for programmable and software-driven architectures. Thus, automated real-time fault management for self-managed networks with machine learning and artificial intelligence at the forefront has become necessary. This is especially the case of optical communication systems, accountable for most of the data traffic worldwide. This study introduces the application of a novel failure detection and localization framework capable of forecasting failures in optical systems based on an unsupervised learning strategy. In this approach, the Long- and Short-term Time-series Network (LSTNet) is exploited for modeling the normal behavior of optical systems. Then, failure conditions are properly forecast without explicitly training the model for such cases, easing the data acquisition process. Later, forecast values and actual measurements from optical equipment are used to derive an outlier detection method to detect and locate failures to improve the decision-making process at the network orchestrator. Laboratory experiments comparing the proposed approach with the Recurrent and Long Short-Term Memory models in terms of failure detection and forecasting performance show that using the LSTNet reduces the mean squared errors in 95% for unseen data, indicating robustness and suitability for real-world environments.


  • Bringing Disaggregated Telemetry and ML to the Transceiver for Autonomic Signal Adaptation

    by M. Felipe Silva, A. Pacini, A. Sgambelluri, L. Valcarenghi, F. Paolucci

    Soft failure localization is performed at SDN transceiver agents with peer-to-peer optical telemetry and lightweight ML-based algorithm. Results on a real disaggregated testbed dataset show the effectiveness in terms of accuracy and computational complexity.

  • Tailoring Micro-solar Systems to Heterogeneous Wireless Sensor Networks

    by Stefano Calabrò, Roberto Gagliardi, Fausto Marcantoni, Matteo Micheletti, Alessandro Pacini, Andrea Piermarteri