Abstract

In optical networks, failure localization is essential to stable operation and service restoration. Several approaches have been presented to achieve accurate failure localization of nodes and inter-nodes. However, due to increasing traffic and demand for flexibility, the reconfigurable optical add/drop multiplexer (ROADM) is evolving towards a multi-degree architecture. Therefore, each ROADM is composed of multiple devices, which makes intra-node failures become more complex. In this context, intra-node failure localization can effectively reduce the pressure on network operators to further find specific devices. In this work, we redefine the intra-/inter-node failure model for multi-degree ROADM-based optical networks and propose a suspect fault screen assisted graph aggregation network (SFS-GRN) for intra-/inter-node failure localization. The SFS is responsible for screening out suspect fault devices from all devices and reducing the number of candidate devices. The GRN is used to analyze these monitoring data from an optical performance monitoring (OPM) node and network wide and to determine the most likely failure device. The proposed scheme is evaluated in a nine-node simulated network and three-node testbed network. Extensive results show that the SFS-GRN achieves higher accuracy compared with existing methods under different percentages of OPM deployment, numbers of service requests, and failure types. The SFS can remove more than 98% of devices, which is beneficial to further detection and repair for network operators. Moreover, the proposed strategy takes about 10 ms to detect a potential failure, and it has the potential to be applied to a real scenario.

© 2023 Optica Publishing Group

Digital-twin-assisted meta learning for soft-failure localization in ROADM-based optical networks

Ruikun Wang, Jiawei Zhang, Zhiqun Gu, Memedhe Ibrahimi, Bojun Zhang, Francesco Musumeci, Massimo Tornatore, and Yuefeng Ji
J. Opt. Commun. Netw. 16(7) C11-C19 (2024)

Multiple attention mechanisms-driven component fault location in optical networks with network-wide monitoring data

Chuidian Zeng, Jiawei Zhang, Ruikun Wang, Bojun Zhang, and Yuefeng Ji
J. Opt. Commun. Netw. 15(7) C9-C19 (2023)

Machine learning framework for timely soft-failure detection and localization in elastic optical networks

Sadananda Behera, Tania Panayiotou, and Georgios Ellinas
J. Opt. Commun. Netw. 15(10) E74-E85 (2023)

Machine-learning-based soft-failure localization with partial software-defined networking telemetry

Kayol S. Mayer, Jonathan A. Soares, Rossano P. Pinto, Christian E. Rothenberg, Dalton S. Arantes, and Darli A. A. Mello
J. Opt. Commun. Netw. 13(10) E122-E131 (2021)

Dimensioning networks of ROADM cluster nodes

Hamid Mehrvar, Shiqiang Li, and Eric Bernier
J. Opt. Commun. Netw. 15(8) C166-C178 (2023)