Optimized Resource Integration and Global Architecture for Mobile Infrastructure for 6G
Open-Source code
The research conducted within the ORIGAMI project produces open-source code that is crucial for validating the findings and conclusions presented in the associated publications.
The code used in the project can be accessed below, linked to the corresponding publications where they were employed.
Source code of DUNE: Distributed Inference in the User Plane
de Andres Hernandez, David; BÜTÜN, BEYZA. 2025.
The deployment of Machine Learning (ML) models in the user plane, enabling line-rate in-network inference, significantly reduces latency and improves the scalability of cases like traffic monitoring. We propose DUNE, a novel framework that realizes for the first time a user plane inference that is distributed across the multiple devices that compose the programmable network.
Related to
DUNE: Distributed Inference in the User Plane
.
Risk-Aware Continuous Control with Neural Contextual Bandits. v1.0
CloudRIC is a system that meets specific reliability targets in 5G FEC processing while sharing pools of heterogeneous processors among DUs, which leads to more cost- and energy-efficient vRANs. The details of the solution are presented in https://doi.org/10.1145/3636534.3649381. As described therein, CloudRIC exploits data-driven models of Logical Processing Units. This repository includes the LPU models of an Intel Xeon Gold 6240R CPU and of an NVIDIA GPU V100 and the tools to replicate the results presented in the paper.
Related to
CloudRIC: Open Radio Access Network (O-RAN) Virtualization with Shared Heterogeneous Computing
.
We use cookies...
We only use Google Analytics cookies to provide us with information about how our website is used. You can find out more about the cookies we use in our Privacy Policy.
