Abstract

The fifth-generation (5G) network has revolutionized wireless communication with its promise of ultra-high-speed data transfer, reduced latency, and massive connectivity. However, one of the critical challenges remains efficient resource allocation, especially in Peer-to- Peer (P2P) communications during data transmission. In traditional centralized systems, resource allocation is handled by a base station, but P2P communication in 5G networks can help minimize network congestion and improve resource utilization by directly connecting users. This paper investigates a novel approach to resource allocation in P2P communications, optimizing data transmission through dynamic resource assignment strategies. The method utilizes machine learning algorithms to predict traffic patterns and demand, adjusting resource distribution in real-time to ensure fair and efficient bandwidth allocation. The proposed system prioritizes users based on the Quality of Service (QoS) requirements and the network's current load. The simulation results show that this approach improves throughput by 30%, reduces latency by 25%, and increases overall system efficiency by 18%. In comparison to conventional methods, the proposed model achieves better load balancing and minimizes data packet loss. The system's effectiveness was validated through extensive simulations in a 5G testbed, highlighting its scalability and adaptability in high-density user environments. The results demonstrate that P2P communications, when combined with smart resource allocation, can play a pivotal role in realizing the full potential of 5G networks for data transmission.

Authors

Pattem Sampath Kumar¹, Poomagal Adhinarayanan²
Malla Reddy College of Engineering, India¹, Sri Ramachandra Institute of Higher Education and Research, India²

Keywords

5G Networks, Peer-to-Peer Communication, Resource Allocation, Data Transmission, Machine Learning