Energy-Efficient and Scalable Architectures for Cell-Free Massive MIMO in 6G

About the Project

The sixth generation (6G) of wireless networks is expected to deliver ultra-reliable, high-capacity, and energy-efficient connectivity across diverse environments. Cell-Free Massive MIMO (CF-mMIMO), where large numbers of distributed access points (APs) jointly serve users without fixed cell boundaries, has emerged as a key enabler of this vision. However, ultra-dense CF-mMIMO systems face critical challenges including high coordination overhead, fronthaul limitations, and excessive energy consumption.

This PhD project aims to design AI-enabled, scalable, and energy-efficient CF-mMIMO architectures tailored for 6G networks. By applying advanced machine learning techniques such as reinforcement learning, federated learning, and graph neural networks, the project will enable intelligent clustering, distributed beamforming, and dynamic power control. The research will explore trade-offs between performance, energy use, and system complexity, supporting deployment within Open RAN (O-RAN) frameworks.

The successful candidate will develop novel algorithms and evaluate them using realistic simulations and channel models, contributing to the design of next-generation wireless systems that are both high-performing and sustainable.