Search

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., Comment: 7 pages, 3 figures, 2nd International Workshop on Graph Neural Networking (GNNet '23)

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 \textit{Atom}, a neural traffic compression method that leverages spatial and temporal correlations present in network traffic. \textit{Atom} implements a customized spatio-temporal graph neural network design that effectively exploits both types of correlations simultaneously. The experimental results show that \textit{Atom} can outperform GZIP's compression ratios by 50\%-65\% on three real-world networks., Comment: 7 pages, 6 figures, 2nd International Workshop on Graph Neural Networking (GNNet '23)

Currently the state of the art network models are based or depend on Discrete Event Simulation (DES). While DES is highly accurate, it is also computationally costly and cumbersome to parallelize, making it unpractical to simulate high performance networks. Additionally, simulated scenarios fail to capture all of the complexities present in real network scenarios. While there exists network models based on Machine Learning (ML) techniques to minimize these issues, these models are also trained with simulated data and hence vulnerable to the same pitfalls. Consequently, the Graph Neural Networking Challenge 2023 introduces a dataset of captured traffic traces that can be used to build a ML-based network model without these limitations. In this paper we propose a Graph Neural Network (GNN)-based solution specifically designed to better capture the complexities of real network scenarios. This is done through a novel encoding method to capture information from the sequence of captured packets, and an improved message passing algorithm to better represent the dependencies present in physical networks. We show that the proposed solution it is able to learn and generalize to unseen captured network scenarios., Comment: 8 pages, 4 figures

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., Comment: 7 pages, 7 figures

Recently emerged Topological Deep Learning (TDL) methods aim to extend current Graph Neural Networks (GNN) by naturally processing higher-order interactions, going beyond the pairwise relations and local neighborhoods defined by graph representations. In this paper we propose a novel TDL-based method for compressing signals over graphs, consisting in two main steps: first, disjoint sets of higher-order structures are inferred based on the original signal --by clustering $N$ datapoints into $K\ll N$ collections; then, a topological-inspired message passing gets a compressed representation of the signal within those multi-element sets. Our results show that our framework improves both standard GNN and feed-forward architectures in compressing temporal link-based signals from two real-word Internet Service Provider Networks' datasets --from $30\%$ up to $90\%$ better reconstruction errors across all evaluation scenarios--, suggesting that it better captures and exploits spatial and temporal correlations over the whole graph-based network structure., Comment: Accepted as Oral at the Second Learning on Graphs Conference (LoG 2023). The recording of the talk can be found in https://www.youtube.com/watch?v=OcruIkiRkiU

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 ($38.0-85.7\%$)., Comment: 11 pages, 7 figures, 2 tables

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., Comment: IEEE Transactions on Cognitive Communications and Networking (2023). arXiv admin note: text overlap with arXiv:2109.01445

Wireless communications at the chip scale emerge as a interesting complement to traditional wire-based approaches thanks to their low latency, inherent broadcast nature, and capacity to bypass pin constraints. However, as current trends push towards massive and bandwidth-hungry processor architectures, there is a need for wireless chip-scale networks that exploit and share as many channels as possible. In this context, this work addresses the issue of channel sharing by exploring the design space of multi-channel Medium Access Control (MAC) protocols for chip-scale networks. Distinct channel assignment strategies for both random access and token passing are presented and evaluated under realistic traffic patterns. It is shown that, even with the improvements enabled by the multiple channels, both protocols maintain their intrinsic advantages and disadvantages., Comment: Accepted for lecture presentation at IEEE ISCAS 2023

The deployment of modern network applications is increasing the network size and traffic volumes at an unprecedented pace. Storing network-related information (e.g., traffic traces) is key to enable efficient network management. However, this task is becoming more challenging due to the ever-increasing data transmission rates and traffic volumes. In this paper, we present a novel method for network traffic compression that exploits spatial and temporal patterns naturally present in network traffic. We consider a realistic scenario where traffic measurements are performed at multiple links of a network topology using tools like SNMP or NetFlow. Such measurements can be seen as multiple time series that exhibit spatial and temporal correlations induced by the network topology, routing or user behavior. Our method leverages graph learning methods to effectively exploit both types of correlations for traffic compression. The experimental results show that our solution is able to outperform GZIP, the \textit{de facto} traffic compression method, improving by 50\%-65\% the compression ratio on three real-world networks., Comment: 11 pages, 14 figures

Optimal Power Flow (OPF) is a very traditional research area within the power systems field that seeks for the optimal operation point of electric power plants, and which needs to be solved every few minutes in real-world scenarios. However, due to the nonconvexities that arise in power generation systems, there is not yet a fast, robust solution technique for the full Alternating Current Optimal Power Flow (ACOPF). In the last decades, power grids have evolved into a typical dynamic, non-linear and large-scale control system, known as the power system, so searching for better and faster ACOPF solutions is becoming crucial. Appearance of Graph Neural Networks (GNN) has allowed the natural use of Machine Learning (ML) algorithms on graph data, such as power networks. On the other hand, Deep Reinforcement Learning (DRL) is known for its powerful capability to solve complex decision-making problems. Although solutions that use these two methods separately are beginning to appear in the literature, none has yet combined the advantages of both. We propose a novel architecture based on the Proximal Policy Optimization algorithm with Graph Neural Networks to solve the Optimal Power Flow. The objective is to design an architecture that learns how to solve the optimization problem and that is at the same time able to generalize to unseen scenarios. We compare our solution with the DCOPF in terms of cost after having trained our DRL agent on IEEE 30 bus system and then computing the OPF on that base network with topology changes

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., Comment: This paper has been accepted for publication at IEEE/ACM Transactions on Networking 2023 (DOI: 10.1109/TNET.2023.3269983). \copyright 2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses

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 ($\approx$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., Comment: NOTE:This work has been accepted for presentation in the International Conference on Network and Service Management (CNSM)

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., Comment: 7 pages, 4 figures. arXiv admin note: text overlap with arXiv:2201.01144

The next generation of wireless networks is expected to tap into the terahertz (0.1--10 THz) band to satisfy the extreme latency and bandwidth density requirements of future applications. However, the development of systems in this band is challenging as THz waves confront severe spreading and penetration losses, as well as molecular absorption, which leads to strong line-of-sight requirements through highly directive antennas. Recently, reconfigurable intelligent surfaces (RISs) have been proposed to address issues derived from non-line-of-sight propagation, among other impairments, by redirecting the incident wave toward the receiver and implementing virtual-line-of-sight communications. However, the benefits provided by a RIS may be lost if the network operates at multiple bands. In this position paper, the suitability of the RIS paradigm in indoor THz scenarios for 6G is assessed grounded on the analysis of a tunable graphene-based RIS that can operate in multiple wideband transparency windows. A possible implementation of such a RIS is provided and numerically evaluated at 0.65/0.85/1.05 THz separately, demonstrating that beam steering and other relevant functionalities are realizable with excellent performance. Finally, the challenges associated with the design and fabrication of multi-wideband graphene-based RISs are discussed, paving the way to the concurrent control of multiple THz bands in the context of 6G networks., Comment: in IEEE Vehicular Technology Magazine, 2022

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., Comment: arXiv admin note: text overlap with arXiv:2110.01261

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., Comment: 5 pages, 5 figures

In the paper, we propose two models of Artificial Intelligence (AI) patents in European Union (EU) countries addressing spatial and temporal behaviour. In particular, the models can quantitatively describe the interaction between countries or explain the rapidly growing trends in AI patents. For spatial analysis Poisson regression is used to explain collaboration between a pair of countries measured by the number of common patents. Through Bayesian inference, we estimated the strengths of interactions between countries in the EU and the rest of the world. In particular, a significant lack of cooperation has been identified for some pairs of countries. Alternatively, an inhomogeneous Poisson process combined with the logistic curve growth accurately models the temporal behaviour by an accurate trend line. Bayesian analysis in the time domain revealed an upcoming slowdown in patenting intensity., Comment: This work has been submitted to Scientometrics and is under review process

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., Comment: 7 pages, 4 figures

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.

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.

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 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 seconds on average for topologies up to 100 edges., Comment: 12 pages, 9 figures

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.

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)., Comment: To appear at IEEE ICNP 2021

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., Comment: 7 pages, 4 figures, 1 table

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.

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., Comment: 6 pages, 4 figures

The reconfigurable intelligent surface is a promising technology for the manipulation and control of wireless electromagnetic signals. In particular, it has the potential to provide significant performance improvements for wireless networks. However, to do so, a proper reconfiguration of the reflection coefficients of unit cells is required, which often leads to complex and expensive devices. To amortize the cost, one may share the system resources among multiple transmitters and receivers. In this paper, we propose an efficient reconfiguration technique providing control over multiple beams independently. Compared to time-consuming optimization techniques, the proposed strategy utilizes an analytical method to configure the surface for multi-beam radiation. This method is easy to implement, effective and efficient since it only requires phase reconfiguration. We analyze the performance for indoor and outdoor scenarios, given the broadcast mode of operation. The aforesaid scenarios encompass some of the most challenging scenarios that wireless networks encounter. We show that our proposed technique provisions sufficient improvements in the observed channel capacity when the receivers are close to the surface in the indoor office environment scenario. Further, we report a considerable increase in the system throughput given the outdoor environment.

Graphene supports surface plasmon polaritons with comparatively slow propagation velocities in the THz region, which becomes increasingly interesting for future communication technologies. This ability can be used to realize compact antennas, which are up to two orders of magnitude smaller than their metallic counterparts. For a proper functionality of these antennas some minimum material requirements have to be fulfilled, which are presently difficult to achieve, since the fabrication and transfer technologies for graphene are still evolving. In this work we analyze available graphene materials experimentally and extract intrinsic characteristics at THz frequencies, in order to predict the dependency of the THz signal emission threshold as a function of the graphene relaxation time tau_r and the chemical potential mu_c., Comment: 2 pages, 1 table

Metasurfaces, the two-dimensional counterpart of metamaterials, have caught great attention thanks to their powerful capabilities on manipulation of electromagnetic waves. Recent times have seen the emergence of a variety of metasurfaces exhibiting not only countless functionalities, but also a reconfigurable response. Additionally, digital or coding metasurfaces have revolutionized the field by describing the device as a matrix of discrete building block states, thus drawing clear parallelisms with information theory and opening new ways to model, compose, and (re)program advanced metasurfaces. This paper joins the reconfigurable and digital approaches, and presents a metasurface that leverages the tunability of graphene to perform beam steering at terahertz frequencies. A comprehensive design methodology is presented encompassing technological, unit cell design, digital metamaterial synthesis, and programmability aspects. By setting up and dynamically adjusting a phase gradient along the metasurface plane, the resulting device achieves beam steering at all practical directions. The proposed design is studied through analytical models and validated numerically, showing beam widths and steering errors well below 10 degrees and 5% in most cases. Finally, design guidelines are extracted through a scalability analysis involving the metasurface size and number of unit cell states., Comment: 12 pages

Metasurfaces are envisaged to play a key role in next-generation wireless systems due to their powerful control over electromagnetic waves. The last decade has witnessed huge advances in this regard, shifting from static to programmable metasurfaces. The HyperSurface (HSF) paradigm takes one step further by integrating a network of controllers within the device with the aim of adding intelligence, connectivity, and autonomy. However, little is known about the traffic that this network will have to support as the target electromagnetic function or boundary conditions change. In this paper, we lay down the foundations of a methodology to characterize the workload of programmable metasurfaces and then employ it to analyze the case of beam steering HSFs. We observe that traffic is bursty and highly dependent on the position of the target. These results will enable the early-stage evaluation of intra-HSF networks, as well as the estimation of the system performance and cost.

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.

As the current standardization for the 5G networks nears completion, work towards understanding the potential technologies for the 6G wireless networks is already underway. One of these potential technologies for the 6G networks are Reconfigurable Intelligent Surfaces (RISs). They offer unprecedented degrees of freedom towards engineering the wireless channel, i.e., the ability to modify the characteristics of the channel whenever and however required. Nevertheless, such properties demand that the response of the associated metasurface (MSF) is well understood under all possible operational conditions. While an understanding of the radiation pattern characteristics can be obtained through either analytical models or full wave simulations, they suffer from inaccuracy under certain conditions and extremely high computational complexity, respectively. Hence, in this paper we propose a novel neural networks based approach that enables a fast and accurate characterization of the MSF response. We analyze multiple scenarios and demonstrate the capabilities and utility of the proposed methodology. Concretely, we show that this method is able to learn and predict the parameters governing the reflected wave radiation pattern with an accuracy of a full wave simulation (98.8%-99.8%) and the time and computational complexity of an analytical model. The aforementioned result and methodology will be of specific importance for the design, fault tolerance and maintenance of the thousands of RISs that will be deployed in the 6G network environment., Comment: Submitted to IEEE OJ-COMS

Programmable metasurfaces have garnered significant attention as they confer unprecedented control over the electromagnetic response of any surface. Such feature has given rise to novel design paradigms such as Software-Defined Metamaterials (SDM) and Reconfigurable Intelligent Surfaces (RIS) with multiple groundbreaking applications. However, the development of programmable metasurfaces tailored to the particularities of a potentially broad application pool becomes a daunting task because the design space becomes remarkably large. This paper aims to ease the design process by proposing a methodology that, through a semi-analytical model of the metasurface response, allows to derive performance scaling trends as functions of a representative set of design variables. Although the methodology is amenable to any electromagnetic functionality, this paper explores its use for the case of beam steering at 26 GHz for 5G applications. Conventional beam steering metrics are evaluated as functions of the unit cell size, number of unit cell states, and metasurface size for different incidence and reflection angles. It is shown that metasurfaces 5$\lambda\times$5$\lambda$ or larger with unit cells of $\lambda/3$ and four unit cell states ensure good performance overall. Further, it is demonstrated that performance degrades significantly for angles larger than $\theta > 60^o$ and that, to combat this, extra effort is needed in the development of the unit cell. These performance trends, when combined with power and cost models, will pave the way to optimal metasurface dimensioning.

Recent years have seen the emergence of programmable metasurfaces, where the user can modify the EM response of the device via software. Adding reconfigurability to the already powerful EM capabilities of metasurfaces opens the door to novel cyber-physical systems with exciting applications in domains such as holography, cloaking, or wireless communications. This paradigm shift, however, comes with a non-trivial increase of the complexity of the metasurfaces that will pose new reliability challenges stemming from the need to integrate tuning, control, and communication resources to implement the programmability. While metasurfaces will become prone to failures, little is known about their tolerance to errors. To bridge this gap, this paper examines the reliability problem in programmable metamaterials by proposing an error model and a general methodology for error analysis. To derive the error model, the causes and potential impact of faults are identified and discussed qualitatively. The methodology is presented and exemplified for beam steering, which constitutes a relevant case for programmable metasurfaces. Results show that performance degradation depends on the type of error and its spatial distribution and that, in beam steering, error rates over 20% can still be considered acceptable.

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., Comment: 12 pages

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., Comment: 12 pages

Software-defined metasurfaces are electromagnetically ultra-thin, artificial components that can provide engineered and externally controllable functionalities. The control over these functionalities is enabled by the metasurface tunability, which is implemented by embedded electronic circuits that modify locally the surface resistance and reactance. Integrating controllers within the metasurface cells, able to intercommunicate and adaptively reconfigure it, thus imparting a desired electromagnetic operation, opens the path towards the creation of an artificially intelligent (AI) fabric where each unit cell can have its own sensing, programmable computing, and actuation facilities. In this work we take a crucial step towards bringing the AI metasurface technology to emerging applications, in particular exploring the wireless mm-wave intercell communication capabilities in a software-defined HyperSurface designed for operation is the microwave regime. We examine three different wireless communication channels within the landscape of the reflective metasurface: Firstly, in the layer where the control electronics of the HyperSurface lie, secondly inside a dedicated layer enclosed between two metallic plates, and, thirdly, inside the metasurface itself. For each case we examine the physical implementation of the mm-wave transponder nodes, we quantify communication channel metrics, and we identify complexity vs. performance trade-offs.

Recent emergence of metasurfaces has enabled the development of ultra-thin flat optical components through different wavefront shaping techniques at various wavelengths. However, due to the non-adaptive nature of conventional metasurfaces, the focal point of the resulting optics needs to be fixed at the design stage, thus severely limiting its reconfigurability and applicability. In this paper, we aim to overcome such constraint by presenting a flat reflective component that can be reprogrammed to focus terahertz waves at a desired point in the near-field region. To this end, we first propose a graphene-based unit cell with phase reconfigurability, and then employ the coding metasurface approach to draw the phase profile required to set the focus on the target point. Our results show that the proposed component can operate close to the diffraction limit with high focusing range and low focusing error. We also demonstrate that, through appropriate automation, the reprogrammability of the metamirror could be leveraged to develop compact terahertz scanning and imaging systems, as well as novel reconfigurable components for terahertz wireless communications., Comment: 10 pages, 5 figures, published in Scientific Reports (Nature)

Metasurfaces, the two-dimensional counterpart of metamaterials, have caught great attention thanks to their powerful control over electromagnetic waves. Recent times have seen the emergence of a variety of metasurfaces exhibiting not only countless functionalities, but also a reconfigurable or even programmable response. Reconfigurability, however, entails the integration of tuning and control circuits within the metasurface structure and, as this new paradigm moves forward, new reliability challenges may arise. This paper examines, for the first time, the reliability problem in programmable metamaterials by proposing an error model and a general methodology for error analysis. To derive the error model, the causes and potential impact of faults are identified and discussed qualitatively. The methodology is presented and instantiated for beam steering, which constitutes a relevant example for programmable metasurfaces. Results show that performance degradation depends on the type of error and its spatial distribution and that, in beam steering, error rates over 10% can still be considered acceptable.

Network modeling is a critical component for building self-driving Software-Defined Networks, particularly to find optimal routing schemes that meet the goals set by administrators. However, existing modeling techniques do not meet the requirements to provide accurate estimations of relevant performance metrics such as delay and jitter. In this paper we propose a novel Graph Neural Network (GNN) model able to understand the complex relationship between topology, routing and input traffic to produce accurate estimates of the per-source/destination pair mean delay and jitter. GNN are tailored to learn and model information structured as graphs and as a result, our model is able to generalize over arbitrary topologies, routing schemes and variable traffic intensity. In the paper we show that our model provides accurate estimates of delay and jitter (worst case $R^2=0.86$) when testing against topologies, routing and traffic not seen during training. In addition, we present the potential of the model for network operation by presenting several use-cases that show its effective use in per-source/destination pair delay/jitter routing optimization and its generalization capabilities by reasoning in topologies and routing schemes not seen during training., Comment: 12 pages

Ubiquitous multicore processors nowadays rely on an integrated packet-switched network for cores to exchange and share data. The performance of these intra-chip networks is a key determinant of the processor speed and, at high core counts, becomes an important bottleneck due to scalability issues. To address this, several works propose the use of mm-wave wireless interconnects for intra-chip communication and demonstrate that, thanks to their low-latency broadcast and system-level flexibility, this new paradigm could break the scalability barriers of current multicore architectures. However, these same works assume 10+ Gb/s speeds and efficiencies close to 1 pJ/bit without a proper understanding on the wireless intra-chip channel. This paper first demonstrates that such assumptions do not hold in the context of commercial chips by evaluating losses and dispersion in them. Then, we leverage the system's monolithic nature to engineer the channel, this is, to optimize its frequency response by carefully choosing the chip package dimensions. Finally, we exploit the static nature of the channel to adapt to it, pushing efficiency-speed limits with simple tweaks at the physical layer. Our methods reduce the path loss and delay spread of a simulated commercial chip by 47 dB and 7.3x, respectively, enabling intra-chip wireless communications over 10 Gb/s and only 3.1 dB away from the dispersion-free case., Comment: 12 pages, 10 figures. IEEE Transactions on Communications Journal, 2020

Wireless Network-on-Chip (WNoC) appears as a promising alternative to conventional interconnect fabrics for chip-scale communications. The study of the channel inside the chip is essential to minimize latency and power. However, this requires long and computationally-intensive simulations which take a lot of time. We propose and implement an analytical model of the EM propagation inside the package based on ray tracing. This model could compute the electric field intensity inside the chip reducing the computational time several orders of magnitude with an average mismatch of only 1.7 dB., Comment: Poster presentation in IEEE Wireless Communications and Networking Conference (WCNC) 2018

Wireless Network-on-Chip (WNoC) appears as a promising alternative to conventional interconnect fabrics for chip-scale communications. WNoC takes advantage of an overlaid network composed by a set of millimeter-wave antennas to reduce latency and increase throughput in the communication between cores. Similarly, wireless inter-chip communication has been also proposed to improve the information transfer between processors, memory, and accelerators in multi-chip settings. However, the wireless channel remains largely unknown in both scenarios, especially in the presence of realistic chip packages. This work addresses the issue by accurately modeling flip-chip packages and investigating the propagation both its interior and its surroundings. Through parametric studies, package configurations that minimize path loss are obtained and the trade-offs observed when applying such optimizations are discussed. Single-chip and multi-chip architectures are compared in terms of the path loss exponent, confirming that the amount of bulk silicon found in the pathway between transmitter and receiver is the main determinant of losses., Comment: To be presented 12th IEEE/ACM International Symposium on Networks-on-Chip (NOCS 2018); Torino, Italy; October 2018

Recent trends in networking are proposing the use of Machine Learning (ML) techniques for the control and operation of the network. In this context, ML can be used as a computer network modeling technique to build models that estimate the network performance. Indeed, network modeling is a central technique to many networking functions, for instance in the field of optimization, in which the model is used to search a configuration that satisfies the target policy. In this paper, we aim to provide an answer to the following question: Can neural networks accurately model the delay of a computer network as a function of the input traffic? For this, we assume the network as a black-box that has as input a traffic matrix and as output delays. Then we train different neural networks models and evaluate its accuracy under different fundamental network characteristics: topology, size, traffic intensity and routing. With this, we aim to have a better understanding of computer network modeling with neural nets and ultimately provide practical guidelines on how such models need to be trained., Comment: 7 pages, 7 figures

Wireless on-chip communication is a promising candidate to address the performance and efficiency issues that arise when scaling current Network-on-Chip (NoC) techniques to manycore processors. A Wireless Network-on-Chip (WNoC) can serve global and broadcast traffic with ultra-low latency even in thousand-core chips, thus acting as a natural complement of conventional and throughput-oriented wireline NoCs. However, the development of Medium Access Control (MAC) strategies needed to efficiently share the wireless medium among the increasing number of cores remains as a considerable challenge given the singularities of the environment and the novelty of the research area. In this position paper, we present a context analysis describing the physical constraints, performance objectives, and traffic characteristics of the on-chip communication paradigm. We summarize the main differences with respect to traditional wireless scenarios, to then discuss their implications on the design of MAC protocols for manycore WNoCs, with the ultimate goal of kickstarting this arguably unexplored research area., Comment: To appear in IEEE Communications Magazine

Tunable metasurfaces are ultra-thin, artificial electromagnetic components that provide engineered and externally adjustable functionalities. The programmable metasurface, the HyperSurFace, concept consists in integrating controllers within the metasurface that interact locally and communicate globally to obtain a given electromagnetic behaviour. Here, we address the design constraints introduced by both functions accommodated by the programmable metasurface, i.e., the desired metasurface operation and the unit cells wireless communication enabling such programmable functionality. The design process for meeting both sets of specifications is thoroughly discussed. Two scenarios for wireless intercell communication are proposed. The first exploits the metasurface layer itself, while the second employs a dedicated communication layer beneath the metasurface backplane. Complexity and performance trade-offs are highlighted.

Pull-based ID/LOC split protocols, such as LISP (RFC6830), retrieve mappings from a mapping system to encapsulate and forward packets. This is done by means of a control-plane channel. In this short paper we describe three attacks against this channel (Denial-of-Service and overflowing) as well as the against the local cache used to store such mappings. We also provide a solution against such attacks that implements a per-source rate-limiter using a Count-Min Sketch data-structure.