Abstract

Edge computing, combined with machine learning (ML), is emerging as a transformative paradigm for handling the data deluge generated by the Internet of Things (IoT) devices. Traditional cloud computing is often inadequate for the low-latency, high-throughput demands of IoT applications, especially in real-time analytics. By processing data locally at the edge of the network, edge computing reduces latency, enhances privacy, and alleviates the bandwidth burden on centralized cloud servers. The integration of ML algorithms into edge devices further augments the decision-making process by enabling real-time data analytics, improving operational efficiency, and delivering immediate insights. This paper explores the synergy between edge computing, ML, and IoT, discussing how real-time data analytics at the edge can transform industries such as smart cities, healthcare, and industrial automation. We also present challenges, future directions, and practical applications of machine learning-based real-time analytics for edge computing in IoT ecosystems