CaFTRA: Frequency-Domain Correlation-Aware Feedback-Free MIMO Transmission and Resource Allocation for 6G and Beyond

2025-12-03

AI Summary

To address the excessive uplink overhead, limited spectral efficiency, and poor cross-scenario adaptability inherent in feedback-based MIMO transmission for 6G, this paper proposes CaFTRA—an AI-native feedback-free MIMO transmission and resource allocation framework. Methodologically, CaFTRA introduces, for the first time, a learnable query-driven Transformer network that directly predicts channel state information (CSI) from user geographical coordinates, accurately capturing frequency-domain correlation without explicit feedback. It further integrates a low-complexity, many-to-one resource allocation algorithm grounded in matching theory to jointly optimize multi-base-station and multi-resource-block assignments. Simulation results demonstrate that CaFTRA achieves stable matching within a limited number of iterations, significantly improving both spectral efficiency and user fairness. Compared to 5G benchmark schemes, it delivers substantial performance gains across diverse scenarios.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Mixture of Experts (MoE)

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Personalized, context-aware and across-device search

Abstract

The fundamental design of wireless systems toward AI-native 6G and beyond is driven by the need for ever-increasing demand of mobile data traffic, extreme spectral efficiency, and adaptability across diverse service scenarios. To overcome the limitations posed by feedback-based multiple-input and multiple-output (MIMO) transmission, we propose a novel frequency-domain Correlation-aware Feedback-free MIMO Transmission and Resource Allocation (CaFTRA) framework tailored for fully-decoupled radio access networks (FD-RAN) to meet the emerging requirements of AI-Native 6G and beyond. By leveraging artificial intelligence (AI), CaFTRA effectively eliminates real-time uplink feedback by predicting channel state information (CSI) based solely on user geolocation. We introduce a Learnable Queries-driven Transformer Network for CSI mapping from user geolocation, which utilizes multi-head attention and learnable query embeddings to accurately capture frequency-domain correlations among resource blocks (RBs), thereby significantly improving the precision of CSI prediction. Once base stations (BSs) adopt feedback-free transmission, their downlink transmission coverage can be significantly expanded due to the elimination of frequent uplink feedback. To enable efficient resource scheduling under such extensive-coverage scenarios, we apply a low-complexity many-to-one matching theory-based algorithm for efficient multi-BS association and multi-RB resource allocation, which is proven to converge to a stable matching within limited iterations. Simulation results demonstrate that CaFTRA achieves stable matching convergence and significant gains in spectral efficiency and user fairness compared to 5G, underscoring its potential value for 6G standardization efforts.

Problem

• Eliminates real-time uplink feedback using AI and geolocation-based CSI prediction
• Enhances CSI prediction accuracy by capturing frequency-domain correlations among resource blocks
• Enables efficient multi-BS association and resource allocation for expanded downlink coverage

Innovation

• AI predicts CSI from user geolocation without feedback
• Transformer network captures frequency-domain correlations among resource blocks
• Matching theory algorithm enables efficient multi-BS resource allocation