IOT-ENABLED CONDITION MONITORING IN POWER TRANSFORMERS: A PROPOSED MODEL
DOI:
https://doi.org/10.63125/3me7hy81Keywords:
IoT, Power Transformers, Condition Monitoring, Edge Computing, Dissolved Gas Analysis (DGA)Abstract
The growing complexity and operational demands of modern electrical power systems have necessitated the adoption of intelligent, real-time monitoring solutions for critical grid assets such as power transformers. As these components age and loads increase, the integration of Internet of Things (IoT) technologies into condition monitoring systems has emerged as a pivotal strategy to enhance asset reliability, enable predictive maintenance, and minimize unplanned outages. This systematic review explores the current landscape of IoT-enabled condition monitoring in power transformers, synthesizing technological advances across sensor deployment, edge and cloud computing architectures, communication protocols, machine learning diagnostics, and cybersecurity frameworks. A total of 84 peer-reviewed articles, published between 2010 and 2024, were analyzed in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Key findings indicate a strong emphasis on thermal and gas-based sensors, with fiber-optic temperature sensors and dissolved gas analysis remaining the most dominant diagnostic tools. Edge computing and lightweight AI models are increasingly used to filter and process data in real time, while LoRaWAN and NB-IoT have emerged as the communication protocols of choice in remote substations. Furthermore, machine learning—particularly support vector machines, decision trees, CNNs, and LSTMs—has advanced from exploratory modeling to deployment-ready applications for fault classification and health indexing. Despite these advancements, significant gaps persist in the integration of cybersecurity protocols and adherence to regulatory standards, highlighting a critical need for secure and compliant system architectures. This review contributes a comprehensive and structured analysis of the state-of-the-art approaches in the field, providing insights for researchers, utility operators, and policymakers aiming to modernize power transformer management within the broader context of smart grid infrastructure.