José Suárez-Varela

Paul Almasan, Stefanos Bakirtzis, José Suárez-Varela et al.

Artificial intelligence-driven radio propagation models provide agile and robust solutions for mobile network operators in their effort to ensure the optimal performance of the wireless ecosystem and support its efficient expansion. In this paper, we introduce GRAPHWAVE, a neural graph-driven propagation solver hinging on the governing principles of ray tracing. The proposed model leverages a digitized version of the propagation environment to build a point cloud and extract an equivalent graph representation of the radio environment. By applying neural message passing over the equivalent graph, it allows the model to accurately infer radio-related quantities, e.g., received signal strength, in a three-dimensional environment. We showcase the use of GRAPHWAVE as a radio environment digital twin and we demonstrate that the model can learn from synthetic and real-world data while achieving low inference times.

Miquel Ferriol-Galmés, Jordi Paillisse, José Suárez-Varela et al.

Network models are an essential block of modern networks. For example, they are widely used in network planning and optimization. However, as networks increase in scale and complexity, some models present limitations, such as the assumption of Markovian traffic in queuing theory models, or the high computational cost of network simulators. Recent advances in machine learning, such as Graph Neural Networks (GNN), are enabling a new generation of network models that are data-driven and can learn complex non-linear behaviors. In this paper, we present RouteNet-Fermi, a custom GNN model that shares the same goals as Queuing Theory, while being considerably more accurate in the presence of realistic traffic models. The proposed model predicts accurately the delay, jitter, and packet loss of a network. We have tested RouteNet-Fermi in networks of increasing size (up to 300 nodes), including samples with mixed traffic profiles -- e.g., with complex non-Markovian models -- and arbitrary routing and queue scheduling configurations. Our experimental results show that RouteNet-Fermi achieves similar accuracy as computationally-expensive packet-level simulators and scales accurately to larger networks. Our model produces delay estimates with a mean relative error of 6.24% when applied to a test dataset of 1,000 samples, including network topologies one order of magnitude larger than those seen during training. Finally, we have also evaluated RouteNet-Fermi with measurements from a physical testbed and packet traces from a real-life network.

Guillermo Bernárdez, José Suárez-Varela, Albert López et al.

Current trends in networking propose the use of Machine Learning (ML) for a wide variety of network optimization tasks. As such, many efforts have been made to produce ML-based solutions for Traffic Engineering (TE), which is a fundamental problem in ISP networks. Nowadays, state-of-the-art TE optimizers rely on traditional optimization techniques, such as Local search, Constraint Programming, or Linear programming. In this paper, we present MAGNNETO, a distributed ML-based framework that leverages Multi-Agent Reinforcement Learning and Graph Neural Networks for distributed TE optimization. MAGNNETO deploys a set of agents across the network that learn and communicate in a distributed fashion via message exchanges between neighboring agents. Particularly, we apply this framework to optimize link weights in OSPF, with the goal of minimizing network congestion. In our evaluation, we compare MAGNNETO against several state-of-the-art TE optimizers in more than 75 topologies (up to 153 nodes and 354 links), including realistic traffic loads. Our experimental results show that, thanks to its distributed nature, MAGNNETO achieves comparable performance to state-of-the-art TE optimizers with significantly lower execution times. Moreover, our ML-based solution demonstrates a strong generalization capability to successfully operate in new networks unseen during training.

Guillermo Bernárdez, José Suárez-Varela, Xiang Shi et al.

Congestion Control (CC) plays a fundamental role in optimizing traffic in Data Center Networks (DCN). Currently, DCNs mainly implement two main CC protocols: DCTCP and DCQCN. Both protocols -- and their main variants -- are based on Explicit Congestion Notification (ECN), where intermediate switches mark packets when they detect congestion. The ECN configuration is thus a crucial aspect on the performance of CC protocols. Nowadays, network experts set static ECN parameters carefully selected to optimize the average network performance. However, today's high-speed DCNs experience quick and abrupt changes that severely change the network state (e.g., dynamic traffic workloads, incast events, failures). This leads to under-utilization and sub-optimal performance. This paper presents GraphCC, a novel Machine Learning-based framework for in-network CC optimization. Our distributed solution relies on a novel combination of Multi-agent Reinforcement Learning (MARL) and Graph Neural Networks (GNN), and it is compatible with widely deployed ECN-based CC protocols. GraphCC deploys distributed agents on switches that communicate with their neighbors to cooperate and optimize the global ECN configuration. In our evaluation, we test the performance of GraphCC under a wide variety of scenarios, focusing on the capability of this solution to adapt to new scenarios unseen during training (e.g., new traffic workloads, failures, upgrades). We compare GraphCC with a state-of-the-art MARL-based solution for ECN tuning -- ACC -- and observe that our proposed solution outperforms the state-of-the-art baseline in all of the evaluation scenarios, showing improvements up to $20\%$ in Flow Completion Time as well as significant reductions in buffer occupancy ($38.0-85.7\%$).

Michail Kalntis, George Iosifidis, José Suárez-Varela et al.

While traditional handovers (THOs) have served as a backbone for mobile connectivity, they increasingly suffer from failures and delays, especially in dense deployments and high-frequency bands. To address these limitations, 3GPP introduced Conditional Handovers (CHOs) that enable proactive cell reservations and user-driven execution. However, both handover (HO) types present intricate trade-offs in signaling, resource usage, and reliability. This paper presents unique, countrywide mobility management datasets from a top-tier mobile network operator (MNO) that offer fresh insights into these issues and call for adaptive and robust HO control in next-generation networks. Motivated by these findings, we propose CONTRA, a framework that, for the first time, jointly optimizes THOs and CHOs within the O-RAN architecture. We study two variants of CONTRA: one where users are a priori assigned to one of the HO types, reflecting distinct service or user-specific requirements, as well as a more dynamic formulation where the controller decides on-the-fly the HO type, based on system conditions and needs. To this end, it relies on a practical meta-learning algorithm that adapts to runtime observations and guarantees performance comparable to an oracle with perfect future information (universal no-regret). CONTRA is specifically designed for near-real-time deployment as an O-RAN xApp and aligns with the 6G goals of flexible and intelligent control. Extensive evaluations leveraging crowdsourced datasets show that CONTRA improves user throughput and reduces both THO and CHO switching costs, outperforming 3GPP-compliant and Reinforcement Learning (RL) baselines in dynamic and real-world scenarios.

Muhammad Asad Ullah, Davi Brilhante, Luís Eduardo Partichelli Potrich et al.

Communication, Navigation, and Surveillance (CNS) is the backbone of the Air Traffic Management (ATM) and Unmanned Aircraft System (UAS) Traffic Management (UTM) systems, ensuring safe and efficient operations of modern and future aviation. Traditionally, the CNS is considered three independent systems: communications, navigation, and surveillance. The current CNS system is fragmented, with limited integration across its three domains. Integrated CNS (ICNS) is a contemporary concept implying that those systems are provisioned through the same technology stack. ICNS is envisioned to improve service quality, spectrum efficiency, communication capacity, navigation predictability, and surveillance capabilities. The 5G technology stack offers higher throughput, lower latency, and massive connectivity compared to many existing communication technologies. This paper presents our 5G ICNS vision and network architecture and discusses how 5G technology can support integrated CNS services using terrestrial and non-terrestrial networks. We also discuss key 5G radio access technologies for delivering integrated CNS services at low altitudes for Innovative Air Mobility (IAM) and Advanced Air Mobility (AAM) operations. Finally, we present relevant challenges and potential research directions for further studies.

David Pujol-Perich, José Suárez-Varela, Miquel Ferriol et al.

Recent years have seen the vast potential of Graph Neural Networks (GNN) in many fields where data is structured as graphs (e.g., chemistry, recommender systems). In particular, GNNs are becoming increasingly popular in the field of networking, as graphs are intrinsically present at many levels (e.g., topology, routing). The main novelty of GNNs is their ability to generalize to other networks unseen during training, which is an essential feature for developing practical Machine Learning (ML) solutions for networking. However, implementing a functional GNN prototype is currently a cumbersome task that requires strong skills in neural network programming. This poses an important barrier to network engineers that often do not have the necessary ML expertise. In this article, we present IGNNITION, a novel open-source framework that enables fast prototyping of GNNs for networking systems. IGNNITION is based on an intuitive high-level abstraction that hides the complexity behind GNNs, while still offering great flexibility to build custom GNN architectures. To showcase the versatility and performance of this framework, we implement two state-of-the-art GNN models applied to different networking use cases. Our results show that the GNN models produced by IGNNITION are equivalent in terms of accuracy and performance to their native implementations in TensorFlow.

Hamid Latif-Martínez, José Suárez-Varela, Albert Cabellos-Aparicio et al.

Detecting anomalies on network traffic is a complex task due to the massive amount of traffic flows in today's networks, as well as the highly-dynamic nature of traffic over time. In this paper, we propose the use of Graph Neural Networks (GNN) for network traffic anomaly detection. We formulate the problem as contextual anomaly detection on network traffic measurements, and propose a custom GNN-based solution that detects traffic anomalies on origin-destination flows. In our evaluation, we use real-world data from Abilene (6 months), and make a comparison with other widely used methods for the same task (PCA, EWMA, RNN). The results show that the anomalies detected by our solution are quite complementary to those captured by the baselines (with a max. of 36.33% overlapping anomalies for PCA). Moreover, we manually inspect the anomalies detected by our method, and find that a large portion of them can be visually validated by a network expert (64% with high confidence, 18% with mid confidence, 18% normal traffic). Lastly, we analyze the characteristics of the anomalies through two paradigmatic cases that are quite representative of the bulk of anomalies.

Stefanos Bakirtzis, Paul Almasan, José Suárez-Varela et al.

Differentiable ray tracing has recently challenged the status quo in radio propagation modelling and digital twinning. Promising unprecedented speed and the ability to learn from real-world data, it offers a real alternative to conventional deep learning (DL) models. However, no experimental evaluation on production-grade networks has yet validated its assumed scalability or practical benefits. This leaves mobile network operators (MNOs) and the research community without clear guidance on its applicability. In this paper, we fill this gap by employing both differentiable ray tracing and DL models to emulate radio coverage using extensive real-world data collected from the network of a major MNO, covering 13 cities and more than 10,000 antennas. Our results show that, while differentiable ray-tracing simulators have contributed to reducing the efficiency-accuracy gap, they struggle to generalize from real-world data at a large scale, and they remain unsuitable for real-time applications. In contrast, DL models demonstrate higher accuracy and faster adaptation than differentiable ray-tracing simulators across urban, suburban, and rural deployments, achieving accuracy gains of up to 3 dB. Our experimental results aim to provide timely insights into a fundamental open question with direct implications on the wireless ecosystem and future research.

José Suárez-Varela, Andra Lutu

Mobile network operators (MNOs) manage Radio Access Networks (RANs) with massive amounts of cells over multiple radio generations (2G-5G). To handle such complexity, operations teams rely on monitoring systems, including anomaly detection tools that identify unexpected behaviors. In this paper, we present c-ANEMON, a Contextual ANomaly dEtection MONitor for the RAN based on Graph Neural Networks (GNNs). Our solution captures spatio-temporal variations by analyzing the behavior of individual cells in relation to their local neighborhoods, enabling the detection of anomalies that are independent of external mobility factors. This, in turn, allows focusing on anomalies associated with network issues (e.g., misconfigurations, equipment failures). We evaluate c-ANEMON using real-world data from a large European metropolitan area (7,890 cells; 3 months). First, we show that the GNN model within our solution generalizes effectively to cells from previously unseen areas, suggesting the possibility of using a single model across extensive deployment regions. Then, we analyze the anomalies detected by c-ANEMON through manual inspection and define several categories of long-lasting anomalies (6+ hours). Notably, 45.95% of these anomalies fall into a category that is more likely to require intervention by operations teams.

Miquel Ferriol-Galmés, Krzysztof Rusek, José Suárez-Varela et al.

Network modeling is a fundamental tool in network research, design, and operation. Arguably the most popular method for modeling is Queuing Theory (QT). Its main limitation is that it imposes strong assumptions on the packet arrival process, which typically do not hold in real networks. In the field of Deep Learning, Graph Neural Networks (GNN) have emerged as a new technique to build data-driven models that can learn complex and non-linear behavior. In this paper, we present \emph{RouteNet-Erlang}, a pioneering GNN architecture designed to model computer networks. RouteNet-Erlang supports complex traffic models, multi-queue scheduling policies, routing policies and can provide accurate estimates in networks not seen in the training phase. We benchmark RouteNet-Erlang against a state-of-the-art QT model, and our results show that it outperforms QT in all the network scenarios.

José Suárez-Varela, Paul Almasan, Miquel Ferriol-Galmés et al.

Graph neural networks (GNN) have shown outstanding applications in many fields where data is fundamentally represented as graphs (e.g., chemistry, biology, recommendation systems). In this vein, communication networks comprise many fundamental components that are naturally represented in a graph-structured manner (e.g., topology, configurations, traffic flows). This position article presents GNNs as a fundamental tool for modeling, control and management of communication networks. GNNs represent a new generation of data-driven models that can accurately learn and reproduce the complex behaviors behind real networks. As a result, such models can be applied to a wide variety of networking use cases, such as planning, online optimization, or troubleshooting. The main advantage of GNNs over traditional neural networks lies in its unprecedented generalization capabilities when applied to other networks and configurations unseen during training, which is a critical feature for achieving practical data-driven solutions for networking. This article comprises a brief tutorial on GNNs and their possible applications to communication networks. To showcase the potential of this technology, we present two use cases with state-of-the-art GNN models respectively applied to wired and wireless networks. Lastly, we delve into the key open challenges and opportunities yet to be explored in this novel research area.

Miquel Ferriol-Galmés, José Suárez-Varela, Krzysztof Rusek et al.

Graph Neural Networks (GNN) have shown a strong potential to be integrated into commercial products for network control and management. Early works using GNN have demonstrated an unprecedented capability to learn from different network characteristics that are fundamentally represented as graphs, such as the topology, the routing configuration, or the traffic that flows along a series of nodes in the network. In contrast to previous solutions based on Machine Learning (ML), GNN enables to produce accurate predictions even in other networks unseen during the training phase. Nowadays, GNN is a hot topic in the Machine Learning field and, as such, we are witnessing great efforts to leverage its potential in many different fields (e.g., chemistry, physics, social networks). In this context, the Graph Neural Networking challenge 2021 brings a practical limitation of existing GNN-based solutions for networking: the lack of generalization to larger networks. This paper approaches the scalability problem by presenting a GNN-based solution that can effectively scale to larger networks including higher link capacities and aggregated traffic on links.

Guillermo Bernárdez, José Suárez-Varela, Albert López et al.

Traffic Engineering (TE) is a basic building block of the Internet. In this paper, we analyze whether modern Machine Learning (ML) methods are ready to be used for TE optimization. We address this open question through a comparative analysis between the state of the art in ML and the state of the art in TE. To this end, we first present a novel distributed system for TE that leverages the latest advancements in ML. Our system implements a novel architecture that combines Multi-Agent Reinforcement Learning (MARL) and Graph Neural Networks (GNN) to minimize network congestion. In our evaluation, we compare our MARL+GNN system with DEFO, a network optimizer based on Constraint Programming that represents the state of the art in TE. Our experimental results show that the proposed MARL+GNN solution achieves equivalent performance to DEFO in a wide variety of network scenarios including three real-world network topologies. At the same time, we show that MARL+GNN can achieve significant reductions in execution time (from the scale of minutes with DEFO to a few seconds with our solution).

David Pujol-Perich, José Suárez-Varela, Albert Cabellos-Aparicio et al.

The last few years have seen an increasing wave of attacks with serious economic and privacy damages, which evinces the need for accurate Network Intrusion Detection Systems (NIDS). Recent works propose the use of Machine Learning (ML) techniques for building such systems (e.g., decision trees, neural networks). However, existing ML-based NIDS are barely robust to common adversarial attacks, which limits their applicability to real networks. A fundamental problem of these solutions is that they treat and classify flows independently. In contrast, in this paper we argue the importance of focusing on the structural patterns of attacks, by capturing not only the individual flow features, but also the relations between different flows (e.g., the source/destination hosts they share). To this end, we use a graph representation that keeps flow records and their relationships, and propose a novel Graph Neural Network (GNN) model tailored to process and learn from such graph-structured information. In our evaluation, we first show that the proposed GNN model achieves state-of-the-art results in the well-known CIC-IDS2017 dataset. Moreover, we assess the robustness of our solution under two common adversarial attacks, that intentionally modify the packet size and inter-arrival times to avoid detection. The results show that our model is able to maintain the same level of accuracy as in previous experiments, while state-of-the-art ML techniques degrade up to 50% their accuracy (F1-score) under these attacks. This unprecedented level of robustness is mainly induced by the capability of our GNN model to learn flow patterns of attacks structured as graphs.

José Suárez-Varela, Miquel Ferriol-Galmés, Albert López et al.

During the last decade, Machine Learning (ML) has increasingly become a hot topic in the field of Computer Networks and is expected to be gradually adopted for a plethora of control, monitoring and management tasks in real-world deployments. This poses the need to count on new generations of students, researchers and practitioners with a solid background in ML applied to networks. During 2020, the International Telecommunication Union (ITU) has organized the "ITU AI/ML in 5G challenge'', an open global competition that has introduced to a broad audience some of the current main challenges in ML for networks. This large-scale initiative has gathered 23 different challenges proposed by network operators, equipment manufacturers and academia, and has attracted a total of 1300+ participants from 60+ countries. This paper narrates our experience organizing one of the proposed challenges: the "Graph Neural Networking Challenge 2020''. We describe the problem presented to participants, the tools and resources provided, some organization aspects and participation statistics, an outline of the top-3 awarded solutions, and a summary with some lessons learned during all this journey. As a result, this challenge leaves a curated set of educational resources openly available to anyone interested in the topic.

Miquel Ferriol-Galmés, José Suárez-Varela, Pere Barlet-Ros et al.

Recent advances in Machine Learning (ML) have shown a great potential to build data-driven solutions for a plethora of network-related problems. In this context, building fast and accurate network models is essential to achieve functional optimization tools for networking. However, state-of-the-art ML-based techniques for network modelling are not able to provide accurate estimates of important performance metrics such as delay or jitter in realistic network scenarios with sophisticated queue scheduling configurations. This paper presents a new Graph-based deep learning model able to estimate accurately the per-path mean delay in networks. The proposed model can generalize successfully over topologies, routing configurations, queue scheduling policies and traffic matrices unseen during the training phase.

Paul Almasan, José Suárez-Varela, Krzysztof Rusek et al.

Deep Reinforcement Learning (DRL) has shown a dramatic improvement in decision-making and automated control problems. Consequently, DRL represents a promising technique to efficiently solve many relevant optimization problems (e.g., routing) in self-driving networks. However, existing DRL-based solutions applied to networking fail to generalize, which means that they are not able to operate properly when applied to network topologies not observed during training. This lack of generalization capability significantly hinders the deployment of DRL technologies in production networks. This is because state-of-the-art DRL-based networking solutions use standard neural networks (e.g., fully connected, convolutional), which are not suited to learn from information structured as graphs. In this paper, we integrate Graph Neural Networks (GNN) into DRL agents and we design a problem specific action space to enable generalization. GNNs are Deep Learning models inherently designed to generalize over graphs of different sizes and structures. This allows the proposed GNN-based DRL agent to learn and generalize over arbitrary network topologies. We test our DRL+GNN agent in a routing optimization use case in optical networks and evaluate it on 180 and 232 unseen synthetic and real-world network topologies respectively. The results show that the DRL+GNN agent is able to outperform state-of-the-art solutions in topologies never seen during training.

Krzysztof Rusek, José Suárez-Varela, Paul Almasan et al.

Network modeling is a key enabler to achieve efficient network operation in future self-driving Software-Defined Networks. However, we still lack functional network models able to produce accurate predictions of Key Performance Indicators (KPI) such as delay, jitter or loss at limited cost. In this paper we propose RouteNet, a novel network model based on Graph Neural Network (GNN) that is able to understand the complex relationship between topology, routing, and input traffic to produce accurate estimates of the per-source/destination per-packet delay distribution and loss. RouteNet leverages the ability of GNNs to learn and model graph-structured information and as a result, our model is able to generalize over arbitrary topologies, routing schemes and traffic intensity. In our evaluation, we show that RouteNet is able to predict accurately the delay distribution (mean delay and jitter) and loss even in topologies, routing and traffic unseen in the training (worst case MRE=15.4%). Also, we present several use cases where we leverage the KPI predictions of our GNN model to achieve efficient routing optimization and network planning.