Implementing a Cell-Free 6G Distributed AI Network With the Use of Deep ML Under a Traditional Multi-Cell Mobile Network

The emergence of cell-free networks marks a transformative shift in wireless communication by eliminating rigid cell boundaries and addressing the challenges of dense environments. This study introduces a novel cell-free architecture that integrates advanced clustering algorithms such as Self-Organizing Maps (SOM), Gaussian Mixture Model (GMM), MeanShift, DBSCAN, and KMeans, with Belief-Desire-Intention extended (BDIx) agents for optimized resource allocation. Among the approaches, SOM demonstrates the highest performance, achieving superior clustering metrics and significantly improving network sum rate and energy efficiency, making it ideal for dense networks. The integration of BDIx agents further improves real-time decision-making for collaborative load balancing and resource distribution. Simulation results validate the framework’s alignment with 6G goals, offering a scalable, adaptive, and energy-efficient solution for modern wireless networks and high-bandwidth urban applications.