A STUDY OF ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING TECHNIQUES FOR TRAFFIC MANAGEMENT IN SCALABLE METAVERSE SYSTEMS

Abstract

Explosive growth of Metaverse created new problems with virtual traffic management, now unheard of, which require new creative solutions to provide scalability, effectiveness and user happiness. This work investigates the use of machine learning (ML) and artificial intelligence (AI) approaches for traffic control in a scalable Metaverse system. The research addresses the virtual environment space where the complexity is growing, rendering the conventional methods of traffic management unusable. It is problem-based. The purpose of this research is to implement real time adaptive systems with the use of ML and AI to manage the dynamic, and diverse quality of traffic to be seen in the Metaverse. The literature analysis is done in depth and then follows the creation and use of AI/ML models for resource allocation, traffic prediction, congestion management. The results show the typical latency minimization rate, resource consumption maximization, and user experience improvement of these methods. Finally, the paper notes that further research is needed while advising that in order to keep up with the evolving demands of the Metaverse, innovation must continue. Along with providing more information to the stored corpus on the AI/ML applications in the virtual world, this research provides developers and policy makers with useful insights.