Combining Improvements in Uplink AI-RAN

2026-10-05

AI Summary

This study addresses the insufficient exploration of joint behaviors among 6G physical-layer AI features in realistic multi-cell deployments. To this end, it proposes a hybrid simulation framework integrating link-level and system-level evaluations to assess the synergistic performance of AI-driven uplink receivers, power control, and link adaptation. Methodologically, a mirrored data augmentation strategy is designed to decouple receiver performance from scheduling scale, while deep learning-aided MIMO receivers are integrated with deep reinforcement learning algorithms. Experimental results demonstrate that, compared with non-AI baselines, the proposed approach improves average uplink user throughput by approximately 27%. These findings effectively validate the complementary gains between PHY- and MAC-layer AI features and confirm the feasibility of their joint deployment in future networks.

Abstract

One of the major transformative factors in 6G will be the integration of Artificial Intelligence (AI) to become a native part of Radio Access Network (RAN). While most physical-layer AI features have so far been evaluated in isolation using link-level simulations, their combined behavior in a realistic multi-cell, multi-UE deployment has remained largely unexplored. In this paper, we present system-level performance results when multiple uplink AI features are enabled together, achieved by integrating accurate link-level and system-level simulators. To infer state-of-the-art deep-learning-aided Multiple Input Multiple Output (MIMO) receivers under the dynamic allocations produced by a realistic uplink scheduler, we propose a mirrored data augmentation method that decouples receiver performance from scheduled allocation size. In addition to these Physical Layer (PHY) receiver features, we combine several recent advances in deep reinforcement learning to train uplink power control and link adaptation that outperform a heuristic baseline and further boost the gains obtainable from the AI receiver alone. The system-level results show that the combined AI features improve the mean uplink user throughput by roughly 27% compared to a non-AI baseline, confirming that the individual PHY and Medium Access Control (MAC) AI features provide complementary gains when deployed jointly.

Problem

• AI-RAN
• 6G
• uplink
• system-level performance
• multi-cell

Innovation

• AI-RAN
• Mirrored Data Augmentation
• Deep Reinforcement Learning
• System-level Simulation
• Deep-learning-aided MIMO