Sub-Band Full Duplex Resource Allocation: A Predictive Deep Reinforcement Learning Approach

TL;DR

This paper introduces a predictive deep reinforcement learning framework for dynamic sub-band allocation in SBFD systems, improving spectrum efficiency and traffic management by forecasting traffic and adapting resource allocation in real-time.

Contribution

It combines a hybrid Bi-LSTM traffic forecasting model with a DDQN-based resource allocation strategy, a novel integration for SBFD systems.

Findings

High accuracy in traffic pattern prediction

Effective adaptation of UL/DL split ratios

Enhanced spectrum utilization and reduced queue buildup

Abstract

This paper presents a predictive deep learning framework for dynamic sub-band allocation in Sub-Band Full Duplex (SBFD) systems, addressing the challenge of balancing uplink (UL) and downlink (DL) performance under highly dynamic traffic conditions. The key contribution lies in integrating a hybrid Bidirectional Long Short-Term Memory (Bi-LSTM) model for traffic forecasting with a Double Deep Q-Network (DDQN) for real-time resource allocation. Using both predicted traffic and current queue states, the proposed system enables proactive scheduling based on traffic demand. Evaluation results show that the prediction model achieves high accuracy in capturing bursty traffic patterns, while the DDQN agent effectively adapts UL/DL split ratios according to traffic variations. The framework improves spectrum utilization, reduces queue buildup, and avoids inefficient static configurations. The proposed approach demonstrates that combining predictive intelligence with reinforcement learning significantly enhances the efficiency and adaptability of SBFD systems, making it a strong candidate for autonomous resource management in future 6G networks.