Antonio de la Oliva

Jorge Martín-Pérez, Nuria Molner, Francesco Malandrino et al.

Open Radio Access Network (O-RAN) is an emerging paradigm, whereby virtualized network infrastructure elements from different vendors communicate via open, standardized interfaces. A key element therein is the RAN Intelligent Controller (RIC), an Artificial Intelligence (AI)-based controller. Traditionally, all data available in the network has been used to train a single AI model to be used at the RIC. This paper introduces, discusses, and evaluates the creation of multiple AI model instances at different RICs, leveraging information from some (or all) locations for their training. This brings about a flexible relationship between gNBs, the AI models used to control them, and the data such models are trained with. Experiments with real-world traces show how using multiple AI model instances that choose training data from specific locations improve the performance of traditional approaches following the hoarding strategy.

David Rico Menéndez, Pablo Picazo-Martínez, Antonio de la Oliva et al.

Emerging integrated sensing and communication (ISAC) applications require large volumes of data, but collecting such datasets in real networks is costly, time consuming, and often infeasible due to limited access to low level measurements. In this paper we present NextSense, an open and modular semi-synthetic data generation platform that consists of a 5G stack, a channel emulator, and an UE emulator. The platform allows users full customization on radio configuration, channel and mobility, and traffic profiles through an API and GUI, and produces multi-perspective outputs that combine symbol-level IQ samples, protocol traces, and key performance indicators across UE, RAN, and CN. This paper describes the NextSense's architecture, and validates its ability to act as a faithful proxy for real measurements in sensing use cases.

Carlos Barroso-Fernández, Alejandro Calvillo-Fernandez, Antonio de la Oliva et al.

The upcoming generations of wireless technologies promise an era where everything is interconnected and intelligent. As the need for intelligence grows, networks must learn to better understand the physical world. However, deploying dedicated hardware to perceive the environment is not always feasible, mainly due to costs and/or complexity. Integrated Sensing and Communication (ISAC) has made a step forward in addressing this challenge. Within ISAC, passive sensing emerges as a cost-effective solution that reuses wireless communications to sense the environment, without interfering with existing communications. Nevertheless, the majority of current solutions are limited to one technology (mostly Wi-Fi or 5G), constraining the maximum accuracy reachable. As different technologies work with different spectrums, we see a necessity in integrating more than one technology to augment the coverage area. Hence, we take the advantage of ISAC passive sensing, to present FAWN, a MultiEncoder Fusion-Attention Wave Network for ISAC indoor scene inference. FAWN is based on the original transformers architecture, to fuse information from Wi-Fi and 5G, making the network capable of understanding the physical world without interfering with the current communication. To test our solution, we have built a prototype and integrated it in a real scenario. Results show errors below 0.6 m around 84% of times.

Francesco Malandrino, Carla Fabiana Chiasserini, Nuria Molner et al.

The traditional approach to distributed machine learning is to adapt learning algorithms to the network, e.g., reducing updates to curb overhead. Networks based on intelligent edge, instead, make it possible to follow the opposite approach, i.e., to define the logical network topology em around the learning task to perform, so as to meet the desired learning performance. In this paper, we propose a system model that captures such aspects in the context of supervised machine learning, accounting for both learning nodes (that perform computations) and information nodes (that provide data). We then formulate the problem of selecting (i) which learning and information nodes should cooperate to complete the learning task, and (ii) the number of iterations to perform, in order to minimize the learning cost while meeting the target prediction error and execution time. After proving important properties of the above problem, we devise an algorithm, named DoubleClimb, that can find a 1+1/|I|-competitive solution (with I being the set of information nodes), with cubic worst-case complexity. Our performance evaluation, leveraging a real-world network topology and considering both classification and regression tasks, also shows that DoubleClimb closely matches the optimum, outperforming state-of-the-art alternatives.

Milan Groshev, Jorge Martín-Pérez, Kiril Antevski et al.

Edge & Fog computing have received considerable attention as promising candidates for the evolution of robotic systems. In this letter, we propose COTORRA, an Edge & Fog driven robotic testbed that combines context information with robot sensor data to validate innovative concepts for robotic systems prior to being applied in a production environment. In lab/university, we established COTORRA as an easy applicable and modular testbed on top of heterogeneous network infrastructure. COTORRA is open for pluggable robotic applications. To verify its feasibility and assess its performance, we ran set of experiments that show how autonomous navigation applications can achieve target latencies bellow 15ms or perform an inter-domain (DLT) federation within 19 seconds.