DQL-based Time Division Duplex Configuration Optimization Technique in 5G New Radio

Abstract

Emerging 5G and 6G networks demand high bandwidth, ultra-low latency, and adaptable traffic management to facilitate serviceswhich are transitioning to balanced uplink traffic from heavily downlink-dependent traffic. In contrast to 4G Time Division Duplex (TDD),which uses static Uplink/Downlink (UL/DL) configurations, 5GNR enables dynamic modification of defined procedures for the best possiblepattern design. In order to optimize TDD pattern selection in 5G New Radio (NR) networks, this paper suggests a Deep Q Learning (DQL)architecture. It was created to model important network characteristics, including as user equipment (UE) density, interference, and uplinkand downlink traffic loads. Optimizing uplink (UL) and downlink (DL) slot designs is essential for 5G networks based on TDD in orderto satisfy dynamic traffic needs while preserving low latency and high throughput. A DQL method that learns to modify UL-DL configurationsin response to real-time traffic patterns is presented in this study. The DQL agent is trained in a simulated 5G environment to maximizea reward function that combines latency reduction and throughput gain. The DQL-based approach’s performance is evaluated incomparison to a static 4:4 UL-DL configuration baseline. The suggested paradigm dramatically increases network performance and lowerslatency, according to experimental data. In particular, the DQL agent outperforms the baseline by more than 95% in throughput and50% in latency, demonstrating its promise for intelligent and flexible slot scheduling in TDD systems of the future.