Gen AI for Real- Time Traffic Prediction and Autoscaling in Cloud Computing Education 4.0
Abstract
The rise of Education 4.0 has brought the growing need for intelligent, adaptive cloud-based learning environments that can manage variable traffic and resource demands efficiently in real-time. This paper will introduce a generative AI -driven model to take advantage of enhancements in real-time traffic prediction and auto-scaling in cloud computing platforms to meet the needs of Education 4.0. This framework picks up a pattern in network traffic and foretells surges in demand by using GAN s so that proactive resource allocation can be done and the system's scalability can be improved. Our proposed approach combines AI-based predictions with an optimized autoscaling strategy, which dynamically adjusts cloud resources according to predicted traffic fluctuations. Experimental tests provide promising results regarding improvement in traffic prediction accuracy, resource usage optimization, and latency reduction toward achieving improved performance and reliable digital education services. The contribution goes to developing an agile, scalable cloud infrastructure that can support personalized and continuous learning according to the adaptive and data-driven goals of Education 4.0. Future work will refine prediction models and explore advanced auto scaling algorithms for further optimization.