This paper presents new learning-based, energy-delay-aware power control strategies for the uplink of dynamic cell-free (CF) massive multiple-input multiple-output (MIMO) networks. We first propose a new algorithm to adaptively select an appropriate set of multi-antenna access points (APs) to serve each user at any time instant. A multi-level hidden Markov model (HMM) is constructed to predict the trajectory of a user and forecast the changing set of serving APs for the user over time. Given the selected, time-changing sets of serving APs, we also formulate a new multi-objective power control problem to minimize a weighted sum of the energy and delay costs of the users. By employing Bernoulli bandit learning (BBL) and Gaussian bandit learning (GBL), two new energy-delay-aware power control strategies are developed to adapt unpredictable channel dynamics, minimize the energy-delay costs online, and remain effective over a long time even when sharp changes occur in the channels. Numerical results demonstrate that the new predictive selection of serving APs and the new learning-based energy-delay-aware power control policies can significantly improve the reliability of uplink transmissions in dynamic CF massive MIMO networks, as compared to state-of-the-art static oracle solutions.

In this paper, we investigate a power control of uplink connection in Heterogeneous Cloud-Radio Access Network (H-CRAN). Our main objective is to optimize Online Energy-Efficiency (OEE) from the users' perspective. Firstly, a realistic and new model of the Long-Term Evolution (LTE) user device's power consumption is proposed. This model includes the power used for operating modes and signal processing of mobile devices during the uplink data transmission. Secondly, the optimization problem is formulated by maximizing the OEE function subject to each user's quality-of-service (QoS) and a power constraint. Then, we allocate online power for the OEE by jointly optimizing the Macro Base Station (MBS) users and small cell Radio Remote Heads (RRHs) users. Furthermore, the Online Frank-Wolfe (OFW) method is adopted to obtain the optimal solution for the formulated OEE optimization problem. The regret metric is derived to describe the performance of the OFW. Finally, numerical results validate the accuracy of the proposed power model and demonstrate the superiority of the proposed method compared to the benchmark.