Every new mobile communication generation comes with the emergence of novel applications and services. The fifth-generation (5G) is not an exception, its increased performance and flexibility are expected to provide support for a plethora of utilization scenarios, where the network can be tailored, in runtime, to the particular requirements of each use case. In particular, 5G is gaining the attention of different vertical industries as an enabler of Industry 4.0. However, adopting these technologies requires novel business models for delivering communication services. Moreover, 5G deployments are still in early stages, with novel functionalities expected to gradually emerge over the next few years. The 5GAIner laboratory provides a 5G experimentation en-vironment for the different stakeholders taking part in the 5G ecosystem. The goal is to facilitate vertical markets’ digital transition to 5G by providing an environment for easy inno-vation, development, and experimentation. In this context, the paper describes the existing infrastructure, provides some initial performance results, summarises the learned lessons, and outlines the expected evolution path.

Check out the paper here. 

The rapid increase in mobile network traffic has led to the dense deployment of network cells and the introduction of technologies such as massive Multiple-Input Multiple-Output (m-MIM O) to achieve high gain and spectral efficiency. However, these benefits come with a significant growth in Operational Expenditure (OPEX) and energy consumption, which remains a major challenge in beyond 5G and 6G networks. In this paper, we employ Deep Reinforcement Learning (DRL) techniques to efficiently switch off cells and mute MIMO antenna elements at some specific times to achieve a higher gain in terms of Energy Saving (ES) and the number of network changes without majorly affecting user satisfaction. Through extensive experiments, we demonstrate that our proposed method called Smart Energy Efficiency using DRL (SEEDRL) saves power by 8.99% and significantly reduces the number of ES state changes by 22.83% compared to its counterpart the threshold-based algorithm.

Check out the paper here.

5G technologies are considered a cornerstone of the advent of the next industrial revolution. Promising performance improvements, along with advanced features and assurances in terms of reliability, flexibility and isolation, are expected to enable the realization of diverse and novel use cases, fostering industrial automation with optimized production lines and manufacturing systems. This document shares the experience and knowledge using a 5G SA network for industrial applications. Concretely, the paper examines whether and how the available technology could fulfil the demanding industry requirements, namely in terms of isolation, flexibility and performance. This gap analysis revealed 5G QoS mechanisms as a key driver towards 5G for industry. Thus, a comprehensive analysis of the existing mechanisms and their impact on the network performance are presented, serving as a reality check of 5G SA Release 15 technologies. Although results showed promising possibilities to support industrial deployments, there is still a gap between what’s achievable and what is expected from 5G that will be gradually filled by the introduction of novel features in the upcoming releases. In general, the contributions and insights presented in this paper are considered to be valuable for industry, standards development organizations, manufacturers, and the wider 5G ecosystem. Moreover, this paper serves as a foundational component within a larger endeavour of automating network slicing mechanisms for industrial applications.

Check out the paper here. 

IMAGINE-B5G (Advanced 5G Open Platform for Large Scale Trials and Pilots across Europe) is an SNS Phase-1 Stream-D project which aims to implement an advanced and easily accessible end-to-end (E2E) B5G platform for large-scale trials and pilots providing a set of B5G applications, enabled by the integration of advanced 5G disrupting technologies. In this paper, we present the seven main vertical use cases targeted in IMAGINE-B5G along the four advanced 5G experimental facilities located in Norway, Spain, France, and Portugal. In addition, the onboarding of third parties (such as SMEs, industry, and researchers) for both vertical experiments and platform extensions through open calls is part of the IMAGINE-B5G road map. To that extent, we provide an overview of the 15 projects that were chosen for financing in the first open-call.

Check out the paper here. 

The proliferation of virtual reality (VR) interaction in the wake of the Metaverse trend will place an increasing number of applications and services into virtual environments (VEs). Over the recent years, interactions with the VE have been studied intensely, but very frequently, such interactions are focused on stationary users or users who leverage specialized contraptions to act in the VE (e.g., omni-directional treadmills). The free movement in the VE tends to be achieved by controller input, which creates a huge hurdle to enter and act in it in a natural manner. The target of this study is the translation of the natural walking motion from the real environment (RE) into the VE. In particular, we aim to explore to which extent redirected walking (RW) is achievable without being noticed by the users. Towards this goal, we test two RW methods, i.e., rotation gain and curvature gain. According to the responses of the participants in our study, we find that there is a statistically significant difference with 90% confidence between the levels of gains for rotation gain. On the other hand, levels of gains for curvature gain are not noticeable (i.e., no statistically significant difference is observed).

Check out the paper here. 

Fifth Generation (5G) networks are becoming the norm in the global telecommunications industry, and Mobile Network Operators (MNOs) are currently deploying 5G alongside their existing Fourth Generation (4G) networks. In this paper, we present results and insights from our large-scale measurement study on commercial 5G Non Standalone (NSA) deployments in a European country. We leverage the collected dataset, which covers two MNOs in Rome, Italy, to study network deployment and radio coverage aspects, and explore the performance of two use cases related to enhanced Mobile Broadband (eMBB) and Ultra-Reliable Low Latency Communication (URLLC). We further leverage a machine learning (ML)-based approach to model the Dual Connectivity (DC) feature enabled by 5G NSA. Our data-driven analysis shows that 5G NSA can provide higher downlink throughput and slightly lower latency compared to 4G. However, performance is influenced by several factors, including propagation conditions, system configurations, and handovers, ultimately highlighting the need for further system optimization. Moreover, by casting the DC modeling problem into a classification problem, we compare four supervised ML algorithms and show that a high model accuracy (up to 99%) can be achieved, in particular, when several radio coverage indicators from both access networks are used as input. Finally, we conduct analyses towards aiding the explainability of the ML models.

Check out the paper here.