Search

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.

Graph neural networks (GNN) have shown outstanding applications in fields where data is essentially represented as graphs (e.g., chemistry, biology, and recommendation systems). In this vein, communication networks comprise many fundamental components that are naturally represented in a graph-structured manner (e.g., topology, routing, and signal interference). 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-world networks. As a result, these 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 their unprecedented generalization capabilities when applied to other networks and configurations unseen during training. This is a critical feature for achieving practical data-driven solutions for networking. This article starts with a brief tutorial on GNNs and some potential applications to communication networks. Then it presents two state-of-the-art GNN models respectively applied to wired and wireless networks. Lastly, it delves into the key open challenges and opportunities yet to be explored in this novel research area.

Programmable metasurfaces constitute an emerging paradigm, envisaged to become a key enabling technology for Reconfigurable Intelligent Surfaces (RIS) due to their powerful control over electromagnetic waves. The HyperSurface (HSF) paradigm takes one step further by embedding a network of customized integrated circuit (IC) controllers within the device with the aim of adding intelligence, connectivity, and autonomy. However, little is known about the traffic that the network needs to support as the target electromagnetic function or boundary conditions change. In this paper, the framework of a methodology is introduced to characterize the workload of programmable metasurfaces which is then used to analyze the beam steering HSFs. The workload characterization leads to many useful insights into traffic behavior, including the spatio-temporal load incurred and the HSF limitations in terms of fine-grained tracking of moving targets. It is observed that the traffic is inherently bursty with an uneven spatial distribution of load and that finer resolution comes at the cost of an increased but less bursty load. An indoor mobility model indicates reasonable signaling load on the deployed surfaces. Finally, a statistical analysis on the traffic patterns is performed, showing that the incoming traffic can be well represented by an ON-OFF model.

Recent years have seen the emergence of programmable metasurfaces, where the user can modify the electromagnetic (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.

In shared-memory multiprocessing, fine-grain synchronization is challenging because it requires frequent communication. As technology scaling delivers larger manycore chips, such pattern is expected to remain costly to support. In this paper, we propose to address this challenge by using on-chip wireless communication. Each core has a transceiver and an antenna to communicate with all the other cores. This environment supports very low latency global communication. Our architecture, called WiSync, uses a per-core Broadcast Memory (BM). When a core writes to its BM, all the other 100+ BMs get updated in less than 10 processor cycles. We also use a second wireless channel with cheaper transfers to execute barriers efficiently. WiSync supports multiprogramming, virtual memory, and context switching. Our evaluation with simulations of 128-threaded kernels and 64-threaded applications shows that WiSync speeds-up synchronization substantially. Compared to using advanced conventional synchronization, WiSync attains an average speedup of nearly one order of magnitude for the kernels, and 1.12 for PARSEC and SPLASH-2.

Energy-harvesting-enabled wireless sensor networks (EHE-WSN), despite their disruptive potential impact, still present several challenges precluding practical deployability. In particular, the low power density and random character of the ambient energy sources produce slow deep fadings in the energy that nodes harvest. Unfortunately, the capacity of the energy buffers is very limited, causing that, at some times, the node might interrupt its operation due to lack of stored energy. In this context, a general purpose framework for dimensioning the energy buffer is provided in this work. To achieve this, a dynamics-decoupled, multi-source capable energy model is presented, which can handle fast random patterns of the communications and the energy harvesting, while it can capture slow variations of the ambient energy in both time and space. By merging both dynamics, the model can more accurately evaluate the performance of the sensor node in terms of the energy storage capacity and to estimate the expected energy of the neighboring nodes. In order to evaluate the performance of the sensor node, a statistical unit for energy harvesting resources, referred as the Energy-Erlang (E2), has been defined. This unit provides a link between the energy model, the environmental harvested power and the energy buffer. The results motivate the study of the specific properties of the ambient energy sources before the design and deployment. By combining them in this general-purpose framework, electronics and network designers will have a powerful tool for optimizing resources in EHE-WSNs.

Nowadays, it is common to find multiple WLAN deployments coexisting in shared spaces. The resulting interference between transmissions represents an important source of performance degradation, specially those originating from hidden traffic. This note explores the relation between hidden traffic and packet losses, using renewal theory to show that losses constitute biased samples of hidden traffic. Building on the developed analytical model, the paper derives the optimal frame length that maximizes throughput in the presence of hidden traffic. The results are validated using an 802.11 WLAN in-lab setting.

Nanotechnology has allowed building nanomachines capable of performing simple tasks, such as sensing, data storage, and actuation. Nanonetworks, networks of nanomachines, will allow cooperation and information sharing among them, thereby greatly expanding the applications of nanotechnology in the biomedical, environmental, and industrial fields. One of the most promising paradigms to implement nanonetworks is diffusion-based molecular communication (DMC). In DMC, nanomachines transmit information by the emission of molecules that diffuse throughout the medium until they reach their destination. Most of the existing literature in DMC has focused on the analysis of its physical channel. In this work, the key differences of the physical channel of DMC with respect to the wireless electromagnetic channel are reviewed with the purpose of learning how they impact the design of networks using DMC. In particular, we find that the uniqueness of the physical channel of DMC will require revisiting most of the protocols and techniques developed for traditional wireless networks in order to adapt them to DMC networks. Furthermore, guidelines for the design of a novel network architecture for DMC networks, including fundamental aspects such as coding, medium access control, addressing, routing and synchronization, are provided.