Optimizing Power Control and Pilot Allocation in Cell-Free Massive MIMO via Deep Learning

Cell-free massive MIMO (CF-mMIMO) networks leverage seamless cooperation among numerous access points to serve a large number of users over the same time/frequency resources. This paper presents a novel multi-task learning approach aimed at mitigating inter-user interference and enhancing spectral efficiency, particularly in scenarios where the number of users far exceeds the available orthogonal pilots. Our proposed method entails the design and unsupervised training of a deep neural network (DNN), employing a custom loss function specifically tailored to perform joint power control and pilot assignment. Numerical results demonstrate that our algorithm outperforms existing power control and pilot assignment strategies in terms of achievable network throughput, minimum user rate, and per-user energy consumption.