Deep Reinforcement Learning-based Sum Rate Fairness Trade-off for Cell-Free mMIMO

The uplink of a cell-free massive multiple-input multiple-output with maximum-ratio combining (MRC) and zero-forcing (ZF) schemes are investigated. A power allocation optimization problem is considered, where two conflicting metrics, namely the sum rate fairness, jointly optimized. As there no closed-form expression for achievable in terms large scale-fading (LSF) components, fairness trade-off cannot be solved by using known convex methods. To alleviate this problem, we propose new approaches. For first approach, use-and-then-forget scheme utilized to derive rate. Then, iteratively through proposed sequential approximation (SCA) scheme. second exploit LSF coefficients as inputs twin delayed deep deterministic policy gradient (TD3), which efficiently solves non-convex problem. Next, complexity convergence properties analyzed. Numerical results demonstrate superiority approaches over conventional control algorithms minimum user both ZF MRC receivers. Moreover, TD3-based achieves better performance than SCA-based approach well fractional