Computer scientists at the University of Leicester have developed an innovative technology to manage the increasing demands on mobile networks caused by multiple users and the surge in Terahertz frequencies.
With the rapid expansion of IoT, this technology is not just poised to enhance the speed and power efficiency for mobile device users, but also to leverage the advantages of the forthcoming 6G mobile technologies.
The UK’s mobile telecommunications network is facing growing demands. Mobile UK estimates that twenty-five million devices are currently connected to mobile networks, a figure projected to soar to thirty billion by 2030. As IoT expands, the competition for network access is intensifying.
While state-of-the-art telecommunication technologies have been established for 5G, the increasing number of users and devices leads to slower connections and higher energy consumption. These systems often struggle with a self-interference issue that significantly impacts communication quality and efficiency. To address these challenges, a technique known as multicarrier-division duplex (MDD) has been introduced. This technique nearly eliminates self-interference in the network receiver in the digital domain, relying solely on fast Fourier transform (FFT) processing.
This project introduced a cutting-edge technology designed to optimise the assignment of subcarrier sets and the number of access point clusters, thereby enhancing communication quality across various networks. The team conducted simulations in a real-world industrial context, demonstrating that their technology outperforms existing methods. They achieved a 10% reduction in power consumption compared to other advanced technologies.
Professor Huiyu Zhou, Lead Principal Investigator from the University of Leicester School of Computing and Mathematical Sciences, commented: “Our technology makes 5G/6G systems more energy-efficient, with faster device selection and resource allocation. Users should experience quicker mobile communication, broader coverage, and reduced power demands.
“The University of Leicester is at the forefront of developing AI solutions for device selection and access point clustering. Specifically, reinforcement learning helps us swiftly and effectively identify optimal parameters for these wireless communication systems, saving power, resources, and labour. Without AI technologies, finding the best system settings and device selection parameters would be much more time-consuming.”
The team is now focusing on further optimising these technologies and reducing the computational complexity of the technique. The source code of the proposed method has been published and made available globally to promote research.
This study is part of the EU-funded 6G BRAINS project, which aims to develop an AI-driven self-learning platform. This platform will intelligently and dynamically allocate resources to enhance capacity and reliability, improve positioning accuracy, and reduce response latency for future industrial applications on a massive scale with varying demands.
There’s plenty of other editorial on our sister site, Electronic Specifier! Or you can always join in the conversation by commenting below or visiting our LinkedIn page.