Abstract—Distribution transformers play a critical role in ensuring uninterrupted power supply, yet their performance is often compromised by undetected internal faults and oil degradation. This paper presents the development and validation of an intelligent, low-cost, and real-time monitoring and fault diagnosis system for distribution transformers by integrating Internet of Things (IoT) technologies with Artificial Intelligence (AI)-based classification algorithms. The system employs wireless sensors to continuously monitor key operational parameters, including temperature, light intensity, and oil level, with data transmitted via ZigBee modules to a central LabVIEW interface and secure cloud platform for real-time visualization, control, and remote access. To ensure reliable communication, the proposed framework incorporates robust data transmission protocols and minimal latency for continuous monitoring. For intelligent fault classification, Decision Tree (DT) and Multi-Layer Perceptron (MLP) classifiers were used. Experimental results demonstrate that the DT model achieved a training accuracy of 95.9% and testing accuracy of 94.5%, outperforming MLP with 94.9% and 90.9%, respectively. The DT classifier also yielded superior F1−Score (0.931) and specificity (0.954) across multiple transformer oil condition classes. The results confirm the effectiveness of the proposed hybrid IoT-AI solution in reliably detecting and classifying oil condition anomalies for timely maintenance actions and operational safety. The system offers a scalable and cost-effective alternative to conventional Supervisory Control and Data Acquisition (SCADA) and PLC-based monitoring, with potential for integration into predictive maintenance frameworks for smart grid applications. 

Keywords—distribution transformer, Internet of Things (IoT), oil monitoring, machine learning

Cite: Faraqid Qasim Mohammed, Yassine Aydi, and Mohamed Abid, “IoT-Enabled Wireless Communication Monitoring and Fault Diagnosis for Transformer Oil Condition Using Machine Learning," Journal of Communications, vol. 21, no. 1, pp. 149-162, 2026.

Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).