AI-Based Predictive Analytics for Enhancing Performance in Edge Computing

Abstract

Edge computing has emerged as a transformative paradigm for real-time data processing, reducing latency and enhancing system efficiency across various domains. However, the performance of edge environments is often constrained by resource limitations, dynamic workloads, and network uncertainties. This paper explores AI-based predictive analytics as a solution to optimize performance in edge computing by leveraging machine learning and deep learning techniques to forecast resource demands, mitigate network congestion, and enhance workload scheduling. By integrating AI-driven models, edge nodes can proactively allocate resources, balance computational loads, and improve response times, ultimately enhancing system reliability and scalability. The study also examines the role of federated learning in maintaining data privacy while optimizing model performance across distributed edge devices. Experimental evaluations demonstrate that AI-powered predictive analytics significantly reduces processing delays and energy consumption while improving overall efficiency. The findings highlight the potential of AI in revolutionizing edge computing by enabling intelligent, adaptive, and selfoptimizing infrastructures.