Can I read Scaling UPF Instances with DRL in 5G/6G on EtoBox?

Scaling UPF Instances with DRL in 5G/6G by Tech Tronie is a document available to read on EtoBox.

What is Scaling UPF Instances with DRL in 5G/6G about?

This document proposes using deep reinforcement learning (DRL) to scale user plane function (UPF) instances in the 5G/6G core. It investigates applying DRL for scaling UPF instances that are packaged in Kubernetes containers. The authors formulate a threshold-based reward function and adapt the proximal policy optimization algorithm for DRL scaling. They also apply a support vector machine classifier to address issues from a stochastic DRL policy. Simulation results show the DRL approach outperforms Kuberne

Author

Tech Tronie

Language

EN