Publications

2023

1. Enhancing 5G Radio Planning with Graph Representations and Deep Learning

   Paul Almasan, José Suárez-Varela, Andra Lutu, and 2 more authors

   In Proceedings of the 3rd ACM Workshop on 5G and Beyond Network Measurements, Modeling, and Use Cases, 2023

   Abs arXiv

   The roll out of new mobile network generations poses hard challenges due to various factors such as cost-benefit tradeoffs, existing infrastructure, and new technology aspects. In particular, one of the main challenges for the 5G deployment lies in optimal 5G radio coverage while accounting for diverse service performance metrics. This paper introduces a Deep Learning-based approach to assist in 5G radio planning by utilizing data from previous-generation cells. Our solution relies on a custom graph representation to leverage the information available from existing cells, and employs a Graph Neural Network (GNN) model to process such data efficiently. In our evaluation, we test its potential to model the transition from 4G to 5G NSA using real-world data from a UK mobile network operator. The experimental results show that our solution achieves high accuracy in predicting key performance indicators in new 5G cells, with a Mean Absolute Percentage Error (MAPE) <17% when evaluated on samples from the same area where it was trained. Moreover, we test its generalization capability over various geographical areas not included in the training, achieving a MAPE <19%. This suggests beneficial properties for achieving robust solutions applicable to 5G planning in new areas without the need of retraining.

2. Atom: Neural Traffic Compression with Spatio-Temporal Graph Neural Networks

   Paul Almasan, Krzysztof Rusek, Shihan Xiao, and 4 more authors

   In Proceedings of the 2nd on Graph Neural Networking Workshop 2023, 2023

   Abs arXiv

   Storing network traffic data is key to efficient network management; however, it is becoming more challenging and costly due to the ever-increasing data transmission rates, traffic volumes, and connected devices. In this paper, we explore the use of neural architectures for network traffic compression. Specifically, we consider a network scenario with multiple measurement points in a network topology. Such measurements can be interpreted as multiple time series that exhibit spatial and temporal correlations induced by network topology, routing, or user behavior. We present Atom, a neural traffic compression method that leverages spatial and temporal correlations present in network traffic. Atom implements a customized spatio-temporal graph neural network design that effectively exploits both types of correlations simultaneously. The experimental results show that Atom can outperform GZIP’s compression ratios by 50%–65% on three real-world networks.

2022

1. Deep reinforcement learning meets graph neural networks: Exploring a routing optimization use case

   Paul Almasan, José Suárez-Varela, Krzysztof Rusek, and 2 more authors

   Computer Communications, 2022

   Abs arXiv HTML

   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.

2. Digital Twin Network: Opportunities and Challenges

   Paul Almasan, Miquel Ferriol-Galmés, Jordi Paillisse, and 13 more authors

   2022

   Abs arXiv

   The proliferation of emergent network applications (e.g., AR/VR, telesurgery, real-time communications) is increasing the difficulty of managing modern communication networks. These applications typically have stringent requirements (e.g., ultra-low deterministic latency), making it more difficult for network operators to manage their network resources efficiently. In this article, we propose the Digital Twin Network (DTN) as a key enabler for efficient network management in modern networks. We describe the general architecture of the DTN and argue that recent trends in Machine Learning (ML) enable building a DTN that efficiently and accurately mimics real-world networks. In addition, we explore the main ML technologies that enable developing the components of the DTN architecture. Finally, we describe the open challenges that the research community has to address in the upcoming years in order to enable the deployment of the DTN in real-world scenarios.

3. Network Digital Twin: Context, Enabling Technologies, and Opportunities

   Paul Almasan, Miquel Ferriol-Galmés, Jordi Paillisse, and 13 more authors

   IEEE Communications Magazine, 2022

   Abs arXiv HTML

   The proliferation of emergent network applications (e.g., telesurgery, metaverse) is increasing the difficulty of managing modern communication networks. These applications entail stringent network requirements (e.g., ultra-low deterministic latency), which hinders network operators to manage their resources efficiently. In this article, we introduce the network digital twin (NDT), a renovated concept of classical network modeling tools whose goal is to build accurate data-driven network models that can operate in real-time. We describe the general architecture of the NDT and argue that modern machine learning (ML) technologies enable building some of its core components. Then, we present a case study that leverages a ML-based NDT for network performance evaluation and apply it to routing optimization in a QoS-aware use case. Lastly, we describe some key open challenges and research opportunities yet to be explored to achieve effective deployment of NDTs in real-world networks.

4. Graph Neural Networks for Communication Networks: Context, Use Cases and Opportunities

   Jose Suarez-Varela, Paul Almasan, Miquel Ferriol-Galmes, and 8 more authors

   IEEE Network, 2022

   Abs arXiv HTML

   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.

5. ENERO: Efficient real-time WAN routing optimization with Deep Reinforcement Learning

   Paul Almasan, Shihan Xiao, Xiangle Cheng, and 3 more authors

   Computer Networks, 2022

   Abs arXiv HTML

   Wide Area Networks (WAN) are a key infrastructure in today’s society. During the last years, WANs have seen a considerable increase in network’s traffic and network applications, imposing new requirements on existing network technologies (e.g., low latency and high throughput). Consequently, Internet Service Providers (ISP) are under pressure to ensure the customer’s Quality of Service and fulfill Service Level Agreements. Network operators leverage Traffic Engineering (TE) techniques to efficiently manage the network’s resources. However, WAN’s traffic can drastically change during time and the connectivity can be affected due to external factors (e.g., link failures). Therefore, TE solutions must be able to adapt to dynamic scenarios in real-time. In this paper we propose Enero, an efficient real-time TE solution based on a two-stage optimization process. In the first one, Enero leverages Deep Reinforcement Learning (DRL) to optimize the routing configuration by generating a long-term TE strategy. To enable efficient operation over dynamic network scenarios (e.g., when link failures occur), we integrated a Graph Neural Network into the DRL agent. In the second stage, Enero uses a Local Search algorithm to improve DRL’s solution without adding computational overhead to the optimization process. The experimental results indicate that Enero is able to operate in real-world dynamic network topologies in 4.5 s on average for topologies up to 100 links.

6. Accelerating Deep Reinforcement Learning for Digital Twin Network Optimization with Evolutionary Strategies

   Carlos Güemes-Palau, Paul Almasan, Shihan Xiao, and 4 more authors

   In NOMS 2022-2022 IEEE/IFIP Network Operations and Management Symposium, 2022

   Abs arXiv HTML

   The recent growth of emergent network applications (e.g., satellite networks, vehicular networks) is increasing the complexity of managing modern communication networks. As a result, the community proposed the Digital Twin Networks (DTN) as a key enabler of efficient network management. Network operators can leverage the DTN to perform different optimization tasks (e.g., Traffic Engineering, Network Planning). Deep Reinforcement Learning (DRL) showed a high performance when applied to solve network optimization problems. In the context of DTN, DRL can be leveraged to solve optimization problems without directly impacting the real-world network behavior. However, DRL scales poorly with the problem size and complexity. In this paper, we explore the use of Evolutionary Strategies (ES) to train DRL agents for solving a routing optimization problem. The experimental results show that ES achieved a training time speed-up of 128 and 6 for the NSFNET and GEANT2 topologies respectively.

7. Fast Traffic Engineering by Gradient Descent with Learned Differentiable Routing

   Krzysztof Rusek, Paul Almasan, José Suárez-Varela, and 3 more authors

   In 2022 18th International Conference on Network and Service Management (CNSM), 2022

   Abs arXiv HTML

   Emerging applications such as the metaverse, telesurgery or cloud computing require increasingly complex operational demands on networks (e.g., ultra-reliable low latency). Likewise, the ever-faster traffic dynamics will demand network control mechanisms that can operate at short timescales (e.g., sub-minute). In this context, Traffic Engineering (TE) is a key component to efficiently control network traffic according to some performance goals (e.g., minimize network congestion). This paper presents Routing By Backprop (RBB), a novel TE method based on Graph Neural Networks (GNN) and differentiable programming. Thanks to its internal GNN model, RBB builds an end-to-end differentiable function of the target TE problem (MinMaxLoad). This enables fast TE optimization via gradient descent. In our evaluation, we show the potential of RBB to optimize OSPF-based routing (≈25% of improvement with respect to default OSPF configurations). Moreover, we test the potential of RBB as an initializer of computationally-intensive TE solvers. The experimental results show promising prospects for accelerating this type of solvers and achieving efficient online TE optimization.

2021

1. The Graph Neural Networking Challenge: A Worldwide Competition for Education in AI/ML for Networks

   José Suárez-Varela, Miquel Ferriol-Galmés, Albert López, and 21 more authors

   SIGCOMM Comput. Commun. Rev., Jul 2021

   Abs arXiv HTML

   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.

2. Towards Real-Time Routing Optimization with Deep Reinforcement Learning: Open Challenges

   Paul Almasan, José Suárez-Varela, Bo Wu, and 3 more authors

   In 2021 IEEE 22nd International Conference on High Performance Switching and Routing (HPSR), Jul 2021

   Abs arXiv HTML

   The digital transformation is pushing the existing network technologies towards new horizons, enabling new applications (e.g., vehicular networks). As a result, the networking community has seen a noticeable increase in the requirements of emerging network applications. One main open challenge is the need to accommodate control systems to highly dynamic network scenarios. Nowadays, existing network optimization technologies do not meet the needed requirements to effectively operate in real time. Some of them are based on hand-crafted heuristics with limited performance and adaptability, while some technologies use optimizers which are often too time-consuming. Recent advances in Deep Reinforcement Learning (DRL) have shown a dramatic improvement in decision-making and automated control problems. Consequently, DRL represents a promising technique to efficiently solve a variety of relevant network optimization problems, such as online routing. In this paper, we explore the use of state-of-the-art DRL technologies for real-time routing optimization and outline some relevant open challenges to achieve production-ready DRL-based solutions.

3. Results and Achievements of the ALLIANCE Project: New Network Solutions for 5G and Beyond

   Davide Careglio, Salvatore Spadaro, Albert Cabellos, and 11 more authors

   Applied Sciences, Jul 2021

   Abs PDF

   Leaving the current 4th generation of mobile communications behind, 5G will represent a disruptive paradigm shift integrating 5G Radio Access Networks (RANs), ultra-high-capacity access/metro/core optical networks, and intra-datacentre (DC) network and computational resources into a single converged 5G network infrastructure. The present paper overviews the main achievements obtained in the ALLIANCE project. This project ambitiously aims at architecting a converged 5G-enabled network infrastructure satisfying those needs to effectively realise the envisioned upcoming Digital Society. In particular, we present two networking solutions for 5G and beyond 5G (B5G), such as Software Defined Networking/Network Function Virtualisation (SDN/NFV) on top of an ultra-high-capacity spatially and spectrally flexible all-optical network infrastructure, and the clean-slate Recursive Inter-Network Architecture (RINA) over packet networks, including access, metro, core and DC segments. The common umbrella of all these solutions is the Knowledge-Defined Networking (KDN)-based orchestration layer which, by implementing Artificial Intelligence (AI) techniques, enables an optimal end-to-end service provisioning. Finally, the cross-layer manager of the ALLIANCE architecture includes two novel elements, namely the monitoring element providing network and user data in real time to the KDN, and the blockchain-based trust element in charge of exchanging reliable and confident information with external domains.

2020

1. RouteNet: Leveraging Graph Neural Networks for Network Modeling and Optimization in SDN

   Krzysztof Rusek, José Suárez-Varela, Paul Almasan, and 2 more authors

   IEEE Journal on Selected Areas in Communications, Jul 2020

   Abs arXiv HTML

   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.

2019

1. Challenging the Generalization Capabilities of Graph Neural Networks for Network Modeling

   José Suárez-Varela, Sergi Carol-Bosch, Krzysztof Rusek, and 4 more authors

   In Proceedings of the ACM SIGCOMM 2019 Conference Posters and Demos, Jul 2019

   Abs HTML PDF

   Today, network operators still lack functional network models able to make accurate predictions of end-to-end Key Performance Indicators (e.g., delay or jitter) at limited cost. Recently a novel Graph Neural Network (GNN) model called RouteNet was proposed as a cost-effective alternative to estimate the per-source/destination pair mean delay and jitter in networks. Thanks to its GNN architecture that operates over graph-structured data, RouteNet revealed an unprecedented ability to learn and model the complex relationships among topology, routing and input traffic in networks. As a result, it was able to make performance predictions with similar accuracy than resource-hungry packet-level simulators even in network scenarios unseen during training. In this demo, we will challenge the generalization capabilities of RouteNet with more complex scenarios, including larger topologies.

2. Towards More Realistic Network Models Based on Graph Neural Networks

   Arnau Badia-Sampera, José Suárez-Varela, Paul Almasan, and 3 more authors

   In Proceedings of the 15th International Conference on Emerging Networking EXperiments and Technologies, Jul 2019

   Abs HTML PDF

   Recently, a Graph Neural Network (GNN) model called RouteNet was proposed as an efficient method to estimate end-to-end network performance metrics such as delay or jitter, given the topology, routing, and traffic of the network. Despite its success in making accurate estimations and generalizing to unseen topologies, the model makes some simplifying assumptions about the network, and does not consider all the particularities of how real networks operate. In this work we extend the architecture of RouteNet to support different features on forwarding devices, specifically we focus on devices with variable queue sizes, and we experimentally evaluate the accuracy of the extended RouteNet architecture.