Enhancing the optimization of resource distribution for eMMB and URLLC services within 5G wireless network architectures

Abstract

The complex dilemma of resource allocation and management in the 5G network priority system, particularly for eMBB and URLLC services, is a pressing and critical issue that necessitates comprehensive research and strategic actions to enhance the performance and user experience of modern digital communications. This situation urgently requires the development of innovative spectrum sharing strategies, prioritization methods, and adaptive algorithms to cope with real-time fluctuations in network conditions. The fusion of machine learning and artificial intelligence can significantly enhance these methods by predicting traffic trends and proactively adjusting resources, ensuring that both eMBB and URLLC services meet their respective quality of service standards. This paper introduces a Q-learning-based particle swarm optimization algorithm for efficient resource allocation techniques. The implementation of edge computing can further alleviate some of these challenges by performing data processing close to the user, thereby reducing latency and improving the response time of URLLC applications while meeting the high throughput requirements of eMBB.