Transformer's Encoder-based 5G Transport Block Size (TBS) Prediction Model

This advanced and complex project implements an AI-powered optimization system for 5G Open RAN networks. Using machine learning and deep learning, the system optimizes network performance by detect…

Simple 5G RAN scheduler

A Framework for Safe and Accelerated Reinforcement Learning-based Radio Resource Management

A deep reinforcement learning framework for dynamic 5G resource allocation. This project uses Proximal Policy Optimization (PPO) with learnable priority weights to intelligently assign MAC layer re…

This project uses Deep Reinforcement Learning with Proximal Policy Optimization (PPO) to optimize network slicing in 5G/6G networks. It aims to improve dynamic resource allocation, Quality of Servi…

A offline scheduler based on time-triggered ethernet.

GitHub for the article Deep Reinforcement Learning for URLLC data management on top of scheduled eMBB traffic (Fabio Saggese, Luca Pasqualini, Marco Moretti, Andrea Abrardo)

Framework for learning handover algorithms using deep reinforcement learning.

This project optimizes handover management in 5G networks using Q-Learning to minimize handover failures and enhance QoS. It employs a dynamic grid-based system where an agent learns to ensure low …

Codes for paper "Knowledge-Assisted Deep Reinforcement Learning in 5G Scheduler Design: From Theoretical Framework to Implementation"

Repo for my srsRAN Project demonstration

A machine-learning-based DDoS detection and mitigation system using SDN. Built with Ryu and Mininet, it simulates network traffic, collects flow data, detects attacks via a Random Forest model, and…

An Anomaly-Based Intrusion Detection System (AIDS) built with a Random Forest classifier on the CICIOT23 dataset. This project automates the full ML pipeline to detect anomalous IoT network traffic…

To reproduce the results of the paper: Probabilistic Delay Forecasting in 5G Using Recurrent and Attention-Based Architectures

To reproduce the results of the paper: Data-Driven Latency Probability Prediction for Wireless Networks: Focusing on Tail Probabilities

A Differentiable Digital Twin of Distributed Link Scheduling for Contention-Aware Networking

Applying Reinforecement Learning Algortihms to perform traffic engineering using SDN

Automated traffic engineering using evolutionary optimization algorithms

[SIGCOMM’24] RedTE: A MARL-based distributed traffic engineering system,

This project is about the undergraduate thesis, the main idea is about route allocation algorithm.

Mitigating Routing Update Overhead for Traffic Engineering by Combining Destination-based Routing with Reinforcement Learning

Designed custom routing for network flows to minimize the collision problem between data center traffic using Mininet along with OpenVswitch.

Dissertation for Computer Science Tripos Part III (MEng) at the University of Cambridge. Associated code is in the gnn-routing repository.

Look-Ahead Reinforcement Learning: network traffic engineering with preventive load balancing

Traffic Engineering with Joint Link Weight and Segment Optimization

tools for SDN based Traffic Engineering

Code for ISSCC2019 paper《Traffic Matrix Prediction Based on Deep Learning for Dynamic Traffic Engineering》