Mikko A. Uusitalo

Akshay Jain, Sylvaine Kerboeuf, Sokratis Barmpounakis et al.

Previous generations of cellular communication, such as 5G, have been designed with the objective of improving key performance indicators (KPIs) such as throughput, latency, etc. However, to meet the evolving KPI demands and the ambitious sustainability targets for the Information and Communication Technology (ICT) industry, 6G will need to be designed differently. 6G will need to consider both the performance and sustainability targets for the various use cases it will serve. In addition, 6G will have various candidate technological enablers, making the design space of the system even more complex. Furthermore, due to the subjective nature of sustainability indicators, especially social sustainability, the literature still lacks clear methods to link them with technical enablers and 6G system design. Hence, in this article a novel method for 6G end-to-end (E2E) system design based on Knowledge graphs (KG) has been introduced. It considers as its input: the use case KPIs, use case sustainability requirements expressed as Key Values (KV) and KV Indicators (KVIs), the ability of the technological enablers to satisfy these KPIs and KVIs, the 6G system design principles defined in Hexa-X-II project, the maturity of a technological enabler and the dependencies between the various enablers. The KG method also introduces a novel approach for determining the key values addressed by a technological enabler. The effectiveness of the KG method was demonstrated by its application in designing the 6G E2E system for the cooperating mobile robot use case defined in the Hexa-X-II project, where 82 enablers were selected. Lastly, results from proof-of-concept demonstrations for a subset of the selected enablers have also been provided, which reinforce the efficacy of the KG method for designing a sustainable 6G system.

Dariush Salami, Ramin Hashemi, Parham Kazemi et al.

This paper presents a novel and sustainable approach for improving beam selection in 5G and beyond networks using transfer learning and Reinforcement Learning (RL). Traditional RL-based beam selection models require extensive training time and computational resources, particularly when deployed in diverse environments with varying propagation characteristics posing a major challenge for scalability and energy efficiency. To address this, we propose modeling the environment as a point cloud, where each point represents the locations of gNodeBs (gNBs) and surrounding scatterers. By computing the Chamfer distance between point clouds, structurally similar environments can be efficiently identified, enabling the reuse of pre-trained models through transfer learning. This methodology leads to a 16x reduction in training time and computational overhead, directly contributing to energy efficiency. By minimizing the need for retraining in each new deployment, our approach significantly lowers power consumption and supports the development of green and sustainable Artificial Intelligence (AI) in wireless systems. Furthermore, it accelerates time-to-deployment, reduces carbon emissions associated with training, and enhances the viability of deploying AI-driven communication systems at the edge. Simulation results confirm that our approach maintains high performance while drastically cutting energy costs, demonstrating the potential of transfer learning to enable scalable, adaptive, and environmentally conscious RL-based beam selection strategies in dynamic and diverse propagation environments.

Jaakko Pihlajasalo, Dani Korpi, Mikko Honkala et al.

In this paper, we propose a machine learning (ML) based physical layer receiver solution for demodulating OFDM signals that are subject to a high level of nonlinear distortion. Specifically, a novel deep learning based convolutional neural network receiver is devised, containing layers in both time- and frequency domains, allowing to demodulate and decode the transmitted bits reliably despite the high error vector magnitude (EVM) in the transmit signal. Extensive set of numerical results is provided, in the context of 5G NR uplink incorporating also measured terminal power amplifier characteristics. The obtained results show that the proposed receiver system is able to clearly outperform classical linear receivers as well as existing ML receiver approaches, especially when the EVM is high in comparison with modulation order. The proposed ML receiver can thus facilitate pushing the terminal power amplifier (PA) systems deeper into saturation, and thereon improve the terminal power-efficiency, radiated power and network coverage.