Skip to content

AMELkhdfjd/Deep_Q_Learning_5G

Repository files navigation

Deep_Q_Learning_5G

Intelligent resource placement in an ultra-reliable 5G Core network

Today, with a rapid rise in the number of devices connected via the internet, emerging 5G networks plan to foster new network services. This generation promises to bring upheaval to the telecoms sector and totally transform the user experience.

Ultra-reliable low-latency communications (URLLC) is a new feature to be considered for fifth-generation systems. This feature is essential to support the critical applications envisaged. These applications require that messages, which are generally short packets, are exchanged between a source and a destination with a high level of reliability and in a short period of time. With this in mind, the allocation of available resources in the 5G Core network while optimizing URLLC service constraints becomes paramount.

This work proposes an approach encompassing intelligent and efficient resource allocation mechanisms for network slicing in the 5G core network after a study of the different techniques available in the literature. A solution based on deep reinforcement learning has been introduced. The new approach takes into account URLLC service requirements in terms of reliability and latency, focusing on the core network. The results show that the proposed method has proven its effectiveness in managing resource allocation in the 5G network while optimizing the requirements cited.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages