Combining Deep Learning with Edge Computing in Improving Accessibility and Performance of E-Learning

Abstract

Through a descriptive analysis, this study investigates how to improve the performance and accessibility of e-learning systems integrating deep learning (DL) with edge computing (EC). The COVID-19 epidemic has exposed obstacles to real-time interactions and scalability in traditional cloud-based e-learning, including latency, bandwidth limitations, and privacy problems. Through utilizing deep learning's adaptability and edge computing's decentralized design, this study suggests a three-tier architecture (end-user devices, edge servers, and cloud clusters) to enhance security, minimize latency, and optimize data processing. Through a comparative analysis of cloud-based and edge-enabled systems, the study highlights the advantages of this hybrid approach, including faster response times, reduced network congestion, and enhanced privacy. The findings demonstrate the potential of edge-based deep learning to revolutionize e-learning by enabling personalized, real-time, and offline-capable educational experiences.