Multi-Failure Localization in High-Degree ROADM-based Optical Networks using Rules-Informed Neural Networks

TL;DR

This work tackles multi-failure localization in high-degree ROADM-based optical networks by introducing Rules-Informed Neural Networks (RINN), which combine threshold-based rules with a data-driven ANN to handle large intra-/inter-node fault sets. The method first uses rules-based reasoning to narrow the candidate faulty components via Optical Power Monitor (OPM) data, then employs a neural classifier on the suspected set to produce final fault localization with BCE-based training. Across simulations and a real 3-node testbed, RINN yields up to ~20% improvement in complete localization accuracy and maintains practical inference times around 4.14 ms, outperforming both rules-only and pure ANN baselines. The approach demonstrates strong potential for scalable, accurate multi-failure localization in complex ROADM deployments, with future work addressing topology generalization and data efficiency under limited supervision.

Abstract

To accommodate ever-growing traffic, network operators are actively deploying high-degree reconfigurable optical add/drop multiplexers (ROADMs) to build large-capacity optical networks. High-degree ROADM-based optical networks have multiple parallel fibers between ROADM nodes, requiring the adoption of ROADM nodes with a large number of inter-/intra-node components. However, this large number of inter-/intra-node optical components in high-degree ROADM networks increases the likelihood of multiple failures simultaneously, and calls for novel methods for accurate localization of multiple failed components. To the best of our knowledge, this is the first study investigating the problem of multi-failure localization for high-degree ROADM-based optical networks. To solve this problem, we first provide a description of the failures affecting both inter-/intra-node components, and we consider different deployments of optical power monitors (OPMs) to obtain information (i.e., optical power) to be used for automated multi-failure localization. Then, as our main and original contribution, we propose a novel method based on a rules-informed neural network (RINN) for multi-failure localization, which incorporates the benefits of both rules-based reasoning and artificial neural networks (ANN). Through extensive simulations and experimental demonstrations, we show that our proposed RINN algorithm can achieve up to around 20 higher localization accuracy compared to baseline algorithms, incurring only around 4.14 ms of average inference time.

Figures (20)

• Figure 1: An example of a ROADM with degree 4.
• Figure 2: A fully-connected high-degree ROADM node.
• Figure 3: A multi-fiber link between two ROADM nodes.
• Figure 4: Candidate OPM locations.
• Figure 5: An example of uniform OPM deployment.