Unsupervised Learning for Scalable Downlink Power Control in Cell-Free Massive MIMO
In cell-free massive multiple-input multiple-output systems, downlink power control is essential to ensure uniformly high service quality across users. Existing methods range from centralized iterative approaches requiring global channel knowledge and supervised training, to simpler distributed strategies such as fractional power control that rely on local information but perform poorly in terms of fairness. This letter proposes an unsupervised, physics-informed framework that directly optimizes max-min fairness without requiring optimal labels or user position information. The method is inherently scalable in the number of user equipment, does not require retraining when the user population changes, and can be extended to achieve full scalability with respect to both access points and users. Numerical results show that it nearly doubles the worst-user spectral efficiency compared to existing scalable schemes.