KI-5G (AI-based Ressource Allocation for private 5G Networks)

Duration: 01.03.2021 - 29.02.2024
Project Leader:
Prof. Dr.-Ing Horst Hellbrück
Staff: Dipl.-Ing. Fabian John

Background

AI is a key technology that has the potential to have a lasting impact or change entire industries.

The Smart Service World Innovation Report shows that mobile and dynamic wireless networks are finding ever-increasing use in industry and medical care to respond quickly to changing environmental parameters. A new solution approach is the 5G mobile network, which also provides local installations, so-called private 5G networks. In addition to the frequency bands, as already with LTE, in the range from 600MHz to 6GHz, 5G also opens up completely new frequency bands above 24GHz with new challenges. The complex tasks and dynamic network configurations place increased demands on the performance, reliability, and distribution of available communication resources. Therefore, using AI methods is one way to distribute the communication resources better and make the highly dynamic system more reliable.

KI-5G

Objective

The project's goal is to optimize private 5G networks with AI solutions so that AI-enriched transmission protocols improve dynamic system behavior and reliability is increased. Resource allocation by established allocation algorithms (e.g., a division of time or frequency range, by distinguishable codes or location-dependent) can be optimally tailored to the requirements of 5G applications with AI algorithms' help. AI solutions have not yet been deployed in mobile networks. Preliminary research has shown that AI methods are suitable for estimating process sequences in advance or making predictions. This makes it possible to launch critical processes in a more targeted manner when needed and optimize communication. The effectiveness of this support is being demonstrated in a test field in Schleswig-Holstein.

Funded project by Schleswig-Holstein