Optimization of CF-mMIMO Systems for the Coexistence between eMBB+ and mMTC+: From Analytical to GNN-Aided Designs

2026-05-27

AI Summary

This work addresses the challenge of uplink multiple access and resource sharing in cell-free massive MIMO systems under the coexistence of enhanced mobile broadband (eMBB+) and massive machine-type communications (mMTC+). The authors propose a non-orthogonal multiple access (NOMA)-based shared access scheme that leverages statistical channel state information (CSI) and finite blocklength information theory to derive achievable rates for both traffic types under imperfect CSI. An energy efficiency optimization problem is formulated and solved via sequential fractional programming. To tackle the resulting non-convex power control problem, they innovatively design a graph neural network (GNN) with multi-head attention to approximate the optimal solution, incorporating an augmented Lagrangian loss to enforce constraint satisfaction. This approach represents the first integration of finite blocklength analysis with statistical CSI in heterogeneous CF-mMIMO scenarios, achieving near-optimal energy efficiency with significantly reduced computational complexity.

Abstract

This paper investigates uplink multiple access for the coexistence of enhanced mobile broadband+ (eMBB+) and massive machine-type communications+ (mMTC+) in terminal-centric cell-free massive MIMO (CF-mMIMO) systems. We propose a non-orthogonal scheme in which low-rate mMTC+ transmissions are spread across the time-frequency grid shared with eMBB+ users, enabling efficient resource reuse. In the presence of imperfect channel state information, we derive closed-form expressions for the achievable rates of both services based solely on statistical channel knowledge. For mMTC+ devices, the analysis also incorporates finite blocklength (FBL) modeling to capture short-packet transmissions. To support heterogeneous service requirements, we formulate a power-control problem that maximizes the minimum energy efficiency of mMTC+ devices subject to quality-of-service constraints on eMBB+ users. The resulting nonconvex problem is solved via sequential fractional programming, accounting for both the Shannon and FBL regimes. To enable real-time operation, we further propose a graph neural network (GNN) with multi-head attention to approximate the model-based solution. Constraint satisfaction during training is enforced via an augmented Lagrangian loss. Numerical results demonstrate effective multiplexing of the two data services and show that the proposed GNN algorithm achieves near-optimal performance with a significantly lower computational complexity.

Problem

• CF-mMIMO
• eMBB+
• mMTC+
• coexistence
• uplink multiple access

Innovation

• cell-free mMIMO
• non-orthogonal multiple access
• finite blocklength
• graph neural network
• energy efficiency optimization