A deep-unfolded APG framework that maps iterative APG updates onto a finite number of neural network layers, where parameters such as step sizes and penalty coefficients are learned from data to reduce the computational complexity and runtime of APG.
Abstract
This paper investigates energy efficiency (EE) maximization for the downlink of cell-free massive multiple-input multiple-output systems under quality-of-service and per-access point power constraints. We first derive closed-form gradient expressions of the objective function with respect to the power allocation coefficients, and then propose an accelerated projected gradient (APG) approach to solve this problem. To reduce the computational complexity and runtime of APG, we propose a deep-unfolded APG framework that maps iterative APG updates onto a finite number of neural network layers, where parameters such as step sizes and penalty coefficients are learned from data. The proposed approach produces power allocation solutions through a fixed number of gradient-based updates without the need for line search or manual parameter tuning. Numerical results show that the method achieves EE performance comparable to the iterative APG approach while requiring significantly lower computational cost, with up to a 30-fold reduction in floating-point operations under the considered system settings.
Tri-hybrid multiple-input multiple-output architectures have recently emerged as a promising enabler for next-generation wireless systems, as they potentially provide enhanced design flexibility without a proportional increase in hardware cost or power consumption. However, the resulting triple-domain coupling renders beamforming optimization challenging and computationally demanding. This paper develops a fast tri-hybrid beamforming framework for multiuser downlink systems employing dynamic metasurface antennas (DMAs). Based on the equivalence between weighted sum-rate maximization and weighted sum-minimum mean square error minimization, an iterative algorithm is first derived under per-DMA input power constraints, with all update equations available in closed form, but convergence inherently remains slow. To enable real-time operation, the algorithm is further unfolded into a trainable finite-iteration architecture using graph neural networks that ensure permutation equivariance and support varying numbers of users. Trained on ray-tracing channel data, the unfolded method achieves comparable or higher system sum-rates while reducing runtime by more than an order of magnitude. The method also demonstrates strong scalability, robustness, and generalization across various environments.
Pinjun Zheng, Md. Jahangir Hossain, Anas Chaaban· 0 citations
A unified optimization framework that integrates Dinkelbach fractional programming, a rigorously derived weighted minimum mean square error (WMMSE) reformulation, second-order cone programming (SOCP), and Riemannian manifold optimization within a provably convergent alternating structure is developed.
I. Hburi, A. Abdulameer, N. Abbas et al.· Journal of Communications So...· 0 citations
A network energy-efficiency (EE) maximization framework for the uplink of acell-free massive MIMO with wireless fronthaul, 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 and frequency-division operating modes in a unified manner.
Jointly optimizing base station beamforming and reconfigurable intelligent surface (RIS) phase shifts in integrated sensing and communication (ISAC) systems under strict sensing constraints presents a challenging non-convex problem. Conventional algorithms suffer from high complexity, while penalty-based deep learning struggles to guarantee strict constraint satisfaction. To address this, we propose a novel penalty-free unsupervised Graph Neural Network (GNN) framework. Crucially, we introduce a beam decomposition and reconstruction layer that projects beamforming vectors into the sensing subspace and its orthogonal complement. By separating and scaling the sensing-aligned and orthogonal components, this mechanism theoretically guarantees 100% satisfaction of sensing signal-to-noise ratio and total power constraints without hyperparameter tuning. Simulation results demonstrate that the proposed approach ensures strict sensing performance guarantee and outperforms both traditional iterative algorithms and penalty-based baselines in sum-rate, while maintaining ultra-low inference time across different RIS sizes, thereby enabling real-time scalability.
This paper investigates the sum-rate maximization problem for downlink rate-splitting multiple access (RSMA) systems equipped with pattern-reconfigurable fluid antennas (PRFA). Two PRFA models are developed: a deployable discrete-selection PRFA (DS-PRFA) model with finite predefined radiation modes, and an idealized continuous-optimization PRFA (CO-PRFA) model based on spherical harmonic expansion that serves as a performance upper bound. The sum-rate maximization problem is formulated by jointly optimizing digital, analog, and antenna-domain precoders along with RSMA power allocation. To solve this non-convex problem, we propose alternating optimization algorithms based on the weighted minimum mean square error (WMMSE) transformation and block coordinate descent with per-antenna decoupling. For DS-PRFA optimization, closed-form solutions are derived, while for CO-PRFA optimization, a preconditioned Riemannian conjugate gradient method is developed on the spherical manifold. Simulation results under the considered settings show that the proposed tri-hybrid RSMA framework with PRFA improves sum-rate performance compared with conventional hybrid precoding, where the CO-PRFA provides an idealized upper benchmark compared with practical DS-PRFA due to the more flexible reconfigurability.
Yijin Pan, Yifeng Ji, Anzheng Tang et al.· IEEE Open Journal of the Com...· 0 citations
A nonconvex energy cost minimization problem is introduced by considering a user-specific energy cost ratio coefficient that explicitly balances UE-AP energy consumption according to heterogeneous device energy states and a double-loop framework combining successive convex approximation and alternating direction method of multipliers is developed.
Kai Dong, Lei Wang, S. Vorobyov et al.· IEEE Transactions on Wireles...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
