All Projects
6GNetwork SlicingISAC

AI-Native 6G Network Architecture

Next-generation 6G networks require fundamentally new design paradigms where AI is not an add-on but a native component of every network layer. This project investigates how deep learning, reinforcement learning, and generative AI can be embedded into radio access, core, and edge layers to achieve self-optimizing, zero-touch networks capable of supporting diverse services from eMBB to URLLC and massive IoT simultaneously.

Research Objectives

  • Develop AI-native air interface designs that jointly optimize sensing and communication
  • Build dynamic network slicing engines using deep reinforcement learning for multi-tenant QoS
  • Design intelligent spectrum management and interference coordination for sub-THz bands
  • Investigate generative AI for network digital twin creation and what-if scenario planning

Methods & Techniques

  • Deep Reinforcement Learning (DRL) for resource allocation
  • Transformer-based models for wireless channel prediction
  • Multi-agent RL for distributed network slice management
  • Diffusion models for radio environment map generation

Interested in this research?

Get in touch to discuss collaboration or graduate opportunities.

Contact Dr. Hossain