Findings validate the efficacy of incorporating swarm intelligence into the 5G architectures as a viable and self-optimizing solution for the promotion of connectivity and signal power performance in the next-generation high-density wireless networks.
A Dual-Stage Multi-Time-Scale Temporal Attention-Based LSTM network (D-MTSTA-LSTM) has been architected, which effectively learns short- and long-term relationships in network trends, thereby precisely predicting optimal communication routes and associated power and spectrum allocation.
Simulation results position D3QN-PER as a strong candidate for deployment as a near-RT RIC xApp within the O-RAN architecture, advancing the vision of AI-native mobility management for 6G.
This work demonstrates the viability of RL for distributed resource management and provides a reproducible simulation toolkit to support further research in AI-driven wireless communication systems.
The proposed framework achieves 20-30% reduced latency, a 15-35% reduction in energy consumption, and an 18-28% throughput enhancement compared to existing methods, and ensures a wide improvement in reliability and adaptability in 5G V2X communication networks.
According to this study, PPO provides continuous action spaces with good training stability for AI models and its stable policy-learning capabilities make it suitable for next-generation communication systems.