I. Introduction
Cell-free massive multiple-input multiple-output (CFm-MIMO) performs multiuser multiple-input multiple-output (MIMO) communications across distributed antennas or access points (APs). Decentralizing the antennas improves channel orthogonality and provides higher rates than colocated antennas, thanks to the differences in path loss between the users [1]–[7]. The time-division duplex (TDD) based CFmMIMO system with a large number of distributed antennas cooperating to serve a fewer number of users has been proposed in [8]. The CFmMIMO provides uniformly good service throughout the area of coverage. However, an efficient uplink/downlink power control algorithm is essential for achieving uniformly good service to all the users. Power control in CFmMIMO is challenging in general because of the computational complexity involved in solving the non-convex max-min fairness maximization problem [8], [9]. Specifically, designing a computationally efficient power control algorithm for the downlink signal at the central processing unit (CPU) is very challenging for CFmMIMO because of the number of optimization parameters involved in the downlink power control [9].