<?xml version="1.0" encoding="UTF-8"?><ns2:project xmlns:ns1="http://gtr.rcuk.ac.uk/gtr/api" xmlns:ns2="http://gtr.rcuk.ac.uk/gtr/api/project" xmlns:ns3="http://gtr.rcuk.ac.uk/gtr/api/fund" xmlns:ns4="http://gtr.rcuk.ac.uk/gtr/api/person" xmlns:ns5="http://gtr.rcuk.ac.uk/gtr/api/project/outcome" xmlns:ns6="http://gtr.rcuk.ac.uk/gtr/api/organisation" ns1:created="2026-06-03T15:52:43Z" ns1:href="http://gtr.ukri.org/gtr/api/projects/729A3AF0-5C0E-49AB-924A-FDFA655C1546" ns1:id="729A3AF0-5C0E-49AB-924A-FDFA655C1546"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/persons/FE293E4C-A088-47C3-9931-74E32D511A92" ns1:rel="PM_PER"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/951B480E-1484-4A77-BB57-23DBEED87A0C" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/951B480E-1484-4A77-BB57-23DBEED87A0C" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2026-04-29T23:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/4F46955F-1A89-4EDC-A1BF-BB64A3F81A31" ns1:rel="FUND" ns1:start="2025-11-01T00:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">10172284</ns2:identifier></ns2:identifiers><ns2:title>RAIOS – RAN AI Optimisation: Secure and Open Source</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Fast Start Response</ns2:grantCategory><ns2:leadFunder>Innovate UK</ns2:leadFunder><ns2:abstractText>This project will develop and demonstrate a new, AI-enabled approach to optimising and securing Open RAN (Radio Access Network) mobile networks, making advanced 5G technology more accessible and cost-effective for smaller telecoms providers, including those supporting logistics, events, manufacturing, and other industrial sectors.

Open RAN technology allows mobile network operators to mix and match equipment from different vendors, reducing costs and increasing flexibility. However, today's Open RAN solutions are still complex to optimise and expensive to deploy, particularly when using cutting-edge AI capabilities such as xApps and rApps hosted on a RAN Intelligent Controller (RIC). These tools can improve performance (e.g. coverage, capacity, reliability), but they are typically designed for large operators with significant resources.

This project, led by Aerix and its partners, builds on previous successful work through the Liverpool 5G High Density Demand (HDD) project, which created a fully open and synchronised 5G lab environment. The team will now extend this platform by integrating open-source AI tools, including Large Language Models (LLMs), into the Open RAN control layer.

To support testing and safe deployment of these AI tools, the project will also use a dynamic &amp;quot;digital twin&amp;quot; platform: an interactive simulation of a real-world 5G network environment. Developed by CGA Simulation, this tool allows engineers to visualise how AI systems make decisions, safely test network changes in advance, and understand how performance could be improved in real time. It also enables collaboration between human operators and AI, building trust and improving explainability.

The project will also explore how AI can enhance network security. An open-source AI-based &amp;quot;sentinel&amp;quot; will monitor the network for unusual activity, help detect potential cyber threats, and enforce secure access policies, building on UK government Zero Trust security principles.

Together, these innovations will help make 5G networks smarter, more efficient, and more secure, while lowering the barriers to entry for UK SMEs and community operators. The results of the project will be tested in a lab environment, with potential for future exploration in live venues such as the M&amp;amp;S Bank Arena in Liverpool, offering a clear &amp;quot;lab-to-venue&amp;quot; route to real-world impact in post-project phases.

This project supports UK ambitions to lead in advanced connectivity and create more secure, flexible, and affordable telecoms infrastructure for the future.</ns2:abstractText></ns2:project>