Deep Mixture of Experts Network for Resource Optimization in Aerial-Terrestrial CF-mMIMO Systems under URLLC

2026-05-14

AI Summary

This work addresses the limitations of conventional approaches in low-altitude 6G ultra-reliable low-latency communication (URLLC), which suffer from poor spectral and energy efficiency and struggle to meet stringent latency constraints. To overcome these challenges, the paper proposes an integrated space-air-ground cell-free massive MIMO architecture, co-designed with a Transformer-based channel prediction network (CP-Net), a deep mixture-of-experts network (MoE-Net), and a weighted gating network (WT-Net). The framework incorporates a channel quality-aware prediction mechanism and leverages a multi-objective expert model with an adaptive fusion strategy to dynamically accommodate heterogeneous user requirements. Experimental results demonstrate that the proposed method significantly enhances both spectral and energy efficiency while effectively satisfying the stringent latency and reliability demands of URLLC.

Abstract

As a critical component of sixth-generation (6G) wireless networks, ultra-reliable and low-latency communication (URLLC) is expected to support real-time and reliable information exchange in low-altitude environments. However, achieving URLLC often incurs significant resource overhead, including increased bandwidth consumption, higher transmit power, and denser access point (AP) deployment, which pose significant challenges to both spectral efficiency (SE) and energy efficiency (EE). Besides, existing iterative optimization algorithms are computationally intensive and struggle to meet the latency requirements of URLLC. To address these challenges, we propose a hybrid aerial-terrestrial cell-free massive MIMO (CF-mMIMO) network to support diverse services, along with a channel prediction network and a deep mixture of experts (MoE) network for uplink optimization. First, we design a channel prediction network (CP-Net) to mitigate channel aging caused by high-mobility user equipment (UE). CP-Net employs three Transformer-based sub-networks for aged channel state information (CSI) prediction, while a channel quality-aware loss function is introduced to improve the prediction accuracy of weak links. Based on the predicted CSI, we develop a deep MoE network (MoE-Net) for power allocation comprising three expert models targeting different objectives. Then, we introduce a weighted gating network (WT-Net) to learn an efficient adaptive combination of expert outputs. The proposed framework better captures heterogeneous UE requirements and improves communication performance under URLLC constraints. Numerical results demonstrate the effectiveness of the proposed method.

Problem

• URLLC
• CF-mMIMO
• resource optimization
• spectral efficiency
• energy efficiency

Innovation

• Mixture of Experts
• Channel Prediction
• Cell-Free mMIMO
• URLLC
• Transformer