Real-Time Adaptive Intelligent Monitoring Through Privacy-Preserving Edge AI in Connected Enterprise Systems

Authors

  • A.V. Kalpana Department of Computer Science and Engineering, SRM Institute of Science & Technology, Chennai, India Author

DOI:

https://doi.org/10.64235/

Keywords:

Edge AI, Intelligent Monitoring, Privacy-Preserving AI, Connected Enterprise Systems, Real-Time Analytics, Adaptive Machine Learning, Federated Learning

Abstract

Connected enterprise systems increasingly depend on distributed sensors, industrial devices, edge gateways, cloud platforms,
enterprise applications, and communication networks to support real-time operations. Although this connectivity improves
visibility and operational efficiency, continuous monitoring generates substantial volumes of sensitive data and introduces
privacy, security, latency, and bandwidth challenges. Centralized cloud-based monitoring can create delays and increase exposure
when raw enterprise telemetry must be transmitted to remote platforms for analysis. This research proposes a real-time adaptive
intelligent monitoring framework based on privacy-preserving Edge Artificial Intelligence (AI). The framework performs
intelligent data processing close to data-generation points while incorporating privacy protection, adaptive machine learning,
secure communication, and cloud-edge coordination. Edge AI models continuously analyze device behavior, network activity,
application events, resource utilization, and operational telemetry to identify anomalies and emerging risks with low latency.
Privacy-preserving mechanisms, including local processing, federated learning, data minimization, and differential privacy, reduce
unnecessary exposure of sensitive information. An adaptive orchestration layer dynamically adjusts monitoring policies, model
configurations, and computational resources according to changing enterprise conditions. The proposed methodology combines
connected enterprise architecture design, multi-source telemetry generation, edge-based machine-learning development, privacy
mechanism integration, and experimental validation. Performance is evaluated using detection accuracy, latency, bandwidth
consumption, privacy protection, false-positive rate, energy efficiency, and adaptation effectiveness. The proposed framework
aims to provide scalable, responsive, privacy-aware, and intelligent monitoring for modern connected enterprise environments.

Downloads

Published

2026-09-16

How to Cite

Real-Time Adaptive Intelligent Monitoring Through Privacy-Preserving Edge AI in Connected Enterprise Systems. (2026). Journal of Cyber-Physical Security and Robotics, 2(03), 80-88. https://doi.org/10.64235/

Similar Articles

11-20 of 46

You may also start an advanced similarity search for this article.