The proposed framework does not optimize only computational speed, but also clarifies the trade-off among execution time, SINR, spectral efficiency, and fairness under dynamic uplink CF-mMIMO conditions, indicating that this architecture serves as an adaptable platform to evaluate dynamic uplink power distribution across CF-mMIMO networks.
Abstract
Dynamic uplink power allocation is a critical challenge in cell-free massive MIMO (CF-mMIMO) networks, where distributed access points (APs) jointly serve multiple user equipment (UEs) under mobility, time-varying propagation conditions, and strong inter-user interference. Conventional optimization-based methods can improve fairness or spectral efficiency, but they often require repeated numerical solving and are usually designed for a specific objective. Learning-based approaches can reduce online decision time after training; however, their effectiveness depends strongly on the reward design and the selected operating objective. In response to these challenges, we propose a Deep Hybrid Intelligent (DHI) architecture designed to evaluate dynamic uplink power management within cell-free massive MIMO environments. The framework uses Soft Actor-Critic (SAC) learning to generate continuous uplink transmit-power decisions and evaluates objective-specific configurations for fairness, signal-to-interference-plus-noise ratio (SINR) improvement, and spectral-efficiency enhancement. In addition, three optimization-based strategies, namely max-min fairness, max-product SINR optimization, and max-sum-rate maximization, are incorporated to analyze the trade-off among fairness, signal quality, throughput, and computational cost. Limited-memory Broyden-Fletcher-Goldfarb-Shanno with bound constraints (L-BFGS-B) optimization is employed for the max-product and max-sum-rate objectives, while the max-min strategy is evaluated through a fairness-oriented feasibility procedure. Simulation results show that the fairness-oriented configuration achieves the highest Jain’s fairness index, reaching 0.989 at 120 access points, whereas the sum-rate-oriented configuration provides stronger SINR and user-rate performance. The results also indicate execution-time reductions of 51.6%, 83.7%, and 85.0% for the evaluated max-min, max-product, and max-sum-rate strategies, respectively, compared with conventional optimization-based implementations. These execution-time gains are accompanied by a clear performance trade-off: the max-min strategy provides the strongest fairness behavior, the max-sum-rate strategy improves total spectral efficiency and user-rate performance, and the max-product strategy offers a balanced operating point between collective SINR improvement and user-service balance. Therefore, the proposed framework does not optimize only computational speed, but also clarifies the trade-off among execution time, SINR, spectral efficiency, and fairness under dynamic uplink CF-mMIMO conditions. These results indicate that this architecture serves as an adaptable platform to evaluate dynamic uplink power distribution across CF-mMIMO networks.
The seamless integration of non-terrestrial and terrestrial infrastructures is a key enabler for ubiquitous connectivity in next-generation (NG) wireless networks. We investigate a hybrid satellite-cell-free Massive MIMO system, where multiple low-Earth-orbit (LEO) satellites jointly serve users in unison with terrestrial access points (APs) under realistic imperfect channel state information and practical user association constraints. We first derive closed-form expressions of the uplink ergodic throughput by exploiting maximum ratio combining (MRC) for transmission over spatially correlated Rician fading channels. Our analysis reveals the characteristic impact of both user-satellite and user-AP association patterns on both the spectral efficiency and rate-fairness achieved. We then formulate an energy efficiency optimization problem under joint user association and power control. Since the problems are inherently NP-hard due to the binary nature of the user-association variables, we develop an improved Differential Evolution (IDE) framework that efficiently explores the feasible solutions in polynomial time. Numerical results validate our analysis and show that the proposed hybrid scheme substantially improves energy efficiency and network throughput. For large-scale scenarios, the DE framework provides practical user-satellite-AP association guidelines, enabling scalable performance gains.
Ngo Tran Anh Thu, Lo Hai Long, Le Duc Anh Vu et al.· IEEE Transactions on Communi...· 0 citations
Sixth-generation (6G) mobile communication poses unprecedented challenges for resource scheduling under personalized demands. Cell-free massive multiple-input multiple-output (CF-mMIMO), with its user-centric characteristics, has emerged as a key technology for satisfying personalized demands. However, faced with heterogeneous quality-of-service (QoS) requirements, existing reinforcement learning schemes are constrained by partial observability, making it difficult to balance overall system performance and personalized demands. Consequently, we propose a graph-embedded multi-agent deep deterministic policy gradient (G-MADDPG) scheme. Guided by personalized demands, proposed G-MADDPG formulates a maximization problem for system weighted sum spectral efficiency and introduces differentiated QoS penalties. In addition, graph neural networks (GNNs) are embedded into the policy learning and value estimation processes of reinforcement learning, endowing agents with enhanced structural reception and cooperative capabilities. Simulation results demonstrate that proposed G-MADDPG scheme outperforms existing benchmark schemes in both convergence speed and performance evaluation.
Yu-Heng An· 2026 8th International Confe...· 0 citations
Validation of the APG algorithm's resilience revealed that it outperformed benchmark algorithms in terms of energy efficiency and execution time, demonstrating its usefulness for challenging optimization tasks, particularly those involving bursty communication.
K. A. Bonsu, Ebenezer Baidoo Baidoo Bediako, K. Darkwah et al.· Applied Mathematics and Stat...· 0 citations
Cell-free massive multiple-input multiple-output (CF mMIMO) requires effective power control, but centralized processing relies on global instantaneous channel state information (CSI) and creates heavy fronthaul load. This letter focuses on low-overhead distributed power control under limited fronthaul capacity. We propose an information bottleneck (IB)-based policy that exchanges compact latent messages instead of raw local observations, and we train it using cluster-based federated learning to keep raw CSI local. The IB penalty provides an explicit information-rate proxy for online coordination, while robustness under imperfect CSI and data locality are evaluated as supporting effects rather than formal guarantees. Simulations show that the proposed method approaches a centralized benchmark with much lower effective overhead and stable behavior under channel estimation errors.
Yukun Ma, Jiayi Zhang, Zih-Yi Liu et al.· IEEE Wireless Communications...· 0 citations
We consider the downlink of a Rician-faded massive multiple-input-multiple-output multi-cell system, where each base station (BS) serves its user equipments (UEs) with assistance from cell-specific intelligent-reflecting surface (IRS). The BSs employ rate splitting multiple access (RSMA) protocol, and maximal-ratio transmission. We derive a closed-form spectral efficiency (SE) expression for this system, and use it to optimize its global energy efficiency (GEE) metric by jointly optimizing the BS transmit power and IRS phases. We develop novel low-complexity closed-form solution to optimize power by using Lagrangian dual, Quadratic and Dinkelbach transforms. We then optimize IRS phases by developing a novel generative diffusion model (GDM)-based deep reinforcement learning (DRL) framework. We numerically characterize, for the first time, the RSMA SE gains over spatial division multiple access in a multi-cell network. We also compare the impact of inter-cell and residual successive interference cancellation interference on the SE of a multi-cell system. We also show that our GDM-DRL framework provides much higher GEE than multiple state-of-the-art solutions.
Sourasis Chatterjee, C. R., Rohit Budhiraja· IEEE Transactions on Communi...· 0 citations
Cell-free massive MIMO with wireless fronthaul is a promising architecture for energy-efficient 6G networks, but the access and fronthaul links must then share the same scarce spectrum, and, under the fully centralized (option-8) functional split, the fronthaul rate is dictated by the finite quantization resolution used at the access points (APs). This paper develops a network energy-efficiency (EE) maximization framework for the uplink of such a system, jointly optimizing the integrated access and fronthaul (IAF) resource split, the adaptive per-AP quantization resolution, and the fronthaul powers, and treating the time-division (TD) and frequency-division (FD) operating modes in a unified manner. Each AP may be switched off (put to sleep) when it is not worth activating, so the resolution allocation is inherently coupled with AP selection. The resulting mixed-integer, nonconvex fractional program is solved by an alternating-optimization algorithm with per-block optimality guarantees---a closed-form optimal time split, bandwidth bisection, and optimal per-AP bit selection---that applies verbatim to both modes. While the design relies on the tractable additive quantization noise model, the reported performance is obtained end-to-end with the actual Lloyd--Max quantizers and a Bussgang decomposition-based achievable-rate bound.