Edge–Cloud Integrated Framework for Real-Time Predictive Maintenance in Cyber–Physical Systems
Year: 2025
Type: article
Abstract: Real-time predictive maintenance (PdM) in cyber–physical systems (CPS) is essential for ensuring operational efficiency, reducing unplanned downtime, and optimizing industrial asset utilization. Integrating edge and cloud computing provides a scalable framework for processing large volumes of sensor data while enabling low-latency fault detection and decision-making. This study proposes an edge–cloud integrated framework for PdM in CPS, emphasizing real-time data acquisition, preprocessing, machine learning-based anomaly detection, and predictive analytics. Performance evaluation considers system latency, prediction accuracy, and computational efficiency. Comparative analyses of edge-only, cloud-only, and hybrid frameworks demonstrate the advantages of edge–cloud integration. Graphical illustrations highlight model performance under different architectures and failure prediction timelines. Challenges, implementation strategies, and future research directions are also discussed.
Authors: Awais Rehman, Gul Naz
Language: English
Topic: IoT and Edge/Fog Computing
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W7220567109
