Frequency Resource Management in 6G User-Centric CFmMIMO: A Hybrid Reinforcement Learning and Metaheuristic Approach

TL;DR

The paper tackles frequency resource allocation in 6G UC-CFmMIMO for vehicular networks, framing a multi-objective problem that maximizes spectral efficiency, minimizes interference, and preserves fairness under limited subband resources. A novel hybrid framework combining Aquila Optimizer (AO) with DDPG-based Actor-Critic RL is proposed, leveraging AO’s global search and RL’s adaptive learning, and is evaluated under realistic 3D channel conditions using QuaDRiGa. The approach is benchmarked against standalone AO and AC-RL, showing faster, more stable convergence and higher throughput (over $200$ bps/Hz) with a near-zero Gini fairness index (~0.02). Simulation studies reveal the framework’s robustness to varying UE density and subband counts, highlighting its potential for real-time, scalable spectrum management in dense, vehicle-centric networks. The work advances AI-driven resource allocation in UC-CFmMIMO by integrating frequency-aware modeling, realistic channels, and hybrid optimization to unlock practical 6G/V2X gains.

Abstract

As sixth-generation (6G) networks continue to evolve, AI-driven solutions are playing a crucial role in enabling more efficient and adaptive resource management in wireless communication. One of the key innovations in 6G is user-centric cell-free massive Multiple-Input Multiple-Output (UC-CFmMIMO), a paradigm that eliminates traditional cell boundaries and enhances network performance by dynamically assigning access points (APs) to users. This approach is particularly well-suited for vehicular networks, offering seamless, homogeneous, ultra-reliable, and low-latency connectivity. However, in dense networks, a key challenge lies in efficiently allocating frequency resources within a limited shared subband spectrum while accounting for frequency selectivity and the dependency of signal propagation on bandwidth. These factors make resource allocation increasingly complex, especially in dynamic environments where maintaining Quality of Service (QoS) is critical. This paper tackles these challenges by proposing a hybrid multi-user allocation strategy that integrates reinforcement learning (RL) and metaheuristic optimization to enhance spectral efficiency (SE), ensure fairness, and mitigate interference within shared subbands. To assess its effectiveness, we compare this hybrid approach with two other methods: the bio-inspired Aquila Optimizer (AO) and Deep Deterministic Policy Gradient (DDPG)-based Actor-Critic Reinforcement Learning (AC-RL). Our evaluation is grounded in real-world patterns and channel characteristics, utilizing the 3GPP-3D channel modeling framework (QuaDRiGa) to capture realistic propagation conditions. The results demonstrate that the proposed hybrid strategy achieves a superior balance among competing objectives, underscoring the role of AI-driven resource allocation in advancing UC-CFmMIMO systems for next-generation wireless networks.

Figures (12)

• Figure 1: Illustration of UC mMIMO clustering in a CF network architecture.
• Figure 2: Channel frequency responses of the 10 AP-UE pair links.
• Figure 3: DDPG-based RLM framework.
• Figure 4: Architecture of Actor and Critic deep neural networks (DNNs).
• Figure 5: Proposed HRLM framework.