Optics InfoBase is the Optical Society's online library for flagship journals, partnered and copublished journals, and recent proceedings from OSA conferences.

Autonomous network management is crucial for Fifth Generation (5G) and Beyond 5G (B5G) networks, where a constantly changing environment is expected and network configuration must adapt accordingly. Modeling tools are required to predict the impact on performance (packet and delay loss) when new traffic demands arrives and when changes in routing paths are applied in the network. Mathematical analysis and network simulators are techniques for modeling networks but both have limitations, as the former provides low accuracy and the latter requires high execution times. To overcome these limitations, machine learning (ML) algorithms, and more specifically, graph neural networks (GNNs), are proposed for network modeling due to their ability to capture complex relationships from graph-like data while predicting network properties with high accuracy and low computational requirements. However, one of the main issues when using GNNs is their lack of generalization capability to larger networks, i.e., when trained in small networks (in number of nodes, paths length, links capacity), the accuracy of predictions on larger networks is poor. This paper addresses the GNN generalization problem by the use of fundamental networking concepts. Our solution is built from a baseline GNN model called RouteNet (developed by Barcelona Neural Networking Center-Universitat Politècnica de Catalunya (BNN-UPC)) that predicts the average delay in network paths, and through a number of simple additions significantly improves the prediction accuracy in larger networks. The improvement ratio compared to the baseline model is 101, from a 187.28% to a 1.828%, measured by the Mean Average Percentage Error (MAPE). In addition, we propose a closed-loop control context where the resulting GNN model could be potentially used in different use cases.

In this article, a new model to simulate different failure propagation scenarios in GMPLS-based networks is proposed. Several types of failures and malfunctions may spread along the network following different patterns (hardware failures, natural disasters, accidents, configuration errors, viruses, software bugs, etc.). The current literature presents several models for the spreading of failures in general networks. In communication networks, a failure affects not only nodes but also the connections passing through those nodes. The model in this article takes into account GMPLS node failures, affecting both data and control planes. The model is tested by simulation using different types of network topologies. In addition, a new method for the classification of network robustness is also introduced.

As a potential solution to the compact routing problem, geometric routing has been proven to be both simple and heuristically effective. These routing schemes assign some (virtual) coordinates in a metric space to each network vertex through the process called embedding. By forwarding packets to the closest neighbor to the destination, they ensure a completely local process with the routing table bounded in size by the maximum vertex degree. In this letter, we present an embedding of any finite connected graph into a metric space generated by algebraic groups, and we prove that it is greedy (guaranteed packet delivery). Then, we present a specialized compact routing scheme relying on this embedding for scale-free graphs. Evaluation through simulation on several Internet topologies shows that the resulting stretch remains below the theoretical upper bounds.

Water scarcity and droughts are an increasing issue in many parts of the world. In the context of urban water systems, the transition to circularity may imply wastewater treatment and reuse. Planning and assessment of water reuse projects require decision-makers evaluating the cost and benefits of alternative scenarios. Manual or semi-automatic approaches are still common practice for planning both drinking and reclaimed water distribution networks. This work illustrates a decision support tool that, based on open data sources and graph theory coupled to greedy optimization algorithms, is able to automatically compute the optimal reclaimed water network for a given scenario. The tool provides not only the maximum amount of served reclaimed water per unit of invested cost, but also the length and diameters of the pipes required, the location and size of storage tanks, the population served, and the construction costs, i.e., everything under the same architecture. The usefulness of the tool is illustrated in two different but complementary cities in terms of size, density, and topography. The construction cost of the optimal water reclaimed network for a city of approximately 100,000 inhabitants is estimated to be in the range of €0.17–0.22/m³ (for a payback period of 30 years).