Multi-head deep Q-learning for continuous beamforming with selective MC-CDMA operation in V2X highway communications

Area of Science:

• Wireless Communication Systems
• Network Engineering
• Artificial Intelligence in Communications

Background:

• Dynamic Vehicle-to-Everything (V2X) networks require robust communication for high-speed vehicular links.
• Existing Orthogonal Frequency Division Multiplexing (OFDM) systems face challenges in reliability and scalability in dense V2X deployments.
• Fast-varying channel conditions and mobility effects necessitate adaptive communication strategies.

Purpose of the Study:

• To propose an integrated framework for large-scale dynamic V2X communication networks.
• To enhance signal robustness, reliability, and scalability in complex propagation environments.
• To improve adaptive performance under fast-varying conditions using advanced modulation and AI.

Main Methods:

• Implementation of a resource block-based Multi-Carrier Code Division Multiple Access (MC-CDMA) modulation scheme.
• Development of a custom code mapper and resource element (RE) allocator for interference-aware transmission.
• Application of a Deep Reinforcement Learning (DRL) model, specifically a physics-inspired Deep Q-Learning (DQL) strategy with a force-arm-based mechanism, for joint beam tracking and channel condition adaptation.

Main Results:

• The MC-CDMA scheme demonstrated extended-range coverage and superior reliability and scalability compared to OFDM.
• The DRL-based beam tracking effectively corrected misalignment caused by mobility and Doppler effects.
• Significant improvements were observed in bit error rate (BER), bitrate stability, handover smoothness, and spectral efficiency.
• The system with a large-scale antenna array ensured continuous beam tracking, outperforming conventional RL techniques.

Conclusions:

• The proposed integrated framework offers a scalable and adaptive solution for future 6G-enabled V2X deployments.
• The combination of MC-CDMA and DRL-based beam tracking provides robust link quality essential for high-speed vehicular communication.
• The system's performance highlights its potential to address the demanding requirements of advanced V2X communication networks.