Optimizing data transmission in 6G software defined networks using deep reinforcement learning for next generation of...

Area of Science:

• Computer Science
• Telecommunications Engineering

Background:

• Virtual Reality (VR) demands high bandwidth and low latency for optimal user experience.
• Emerging 6G technologies, including Software-Defined Networking (SDN) and resource slicing, are crucial for meeting these demands.
• Efficient network resource management is paramount for satisfactory VR data transmission.

Purpose of the Study:

• To propose a VR-based SDN system model for 6G networks.
• To investigate the integration of Deep Reinforcement Learning (DRL) for dynamic network resource balancing.
• To enhance VR data transmission by minimizing latency and maximizing data rates.

Main Methods:

• Development of a VR-based SDN system model for 6G cellular networks.
• Integration of Deep Reinforcement Learning (DRL) for intelligent resource management.
• Utilizing resource slicing for services like enhanced Mobile Broadband (eMBB) and Ultra-Reliable Low Latency Communications (URLLC).

Main Results:

• DRL-based strategies demonstrated considerable improvements in resource management.
• Significant enhancements in achievable data rates were observed.
• A notable reduction in communication latency was achieved in dynamic and large-scale networks.

Conclusions:

• The proposed VR-based SDN system with DRL effectively manages network resources for VR transmission in 6G.
• This approach offers a streamlined solution for efficient VR video delivery.
• DRL integration provides a competitive advantage in performance, data rate, and latency reduction.