An Edge AI-Driven IoT Framework for Automatic Power Factor Correction in Smart Industrial Power Systems
Fuente:
Zenodo
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Recurso digital |
| Lenguaje: | inglés |
| Publicado: |
Zenodo
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866901132352159744 |
|---|---|
| author | S. Gowtham Dr.V.Manimekalai |
| author_facet | S. Gowtham Dr.V.Manimekalai |
| contents | <p>Abstract<br>Power factor correction remains a significant challenge in modern industrial power systems due to the presence <br>of highly inductive and fluctuating loads. Poor power factor results in increased energy losses, reduced system <br>efficiency, and higher operational costs. Conventional correction methods based on mechanical or thyristor <br>switching provide limited intelligence and slower adaptability to dynamic load variations. This paper presents <br>the design and hardware implementation of an Edge AI-driven IoT framework for automatic power factor <br>correction in smart industrial environments. The proposed system utilizes voltage and current sensing modules <br>integrated with an ESP8266 controller to continuously monitor electrical parameters. Edge Artificial <br>Intelligence enables real-time local decision-making for optimal capacitor bank switching to compensate <br>reactive power effectively. IoT connectivity allows remote monitoring and data visualization through cloud <br>platforms. The developed system maintains near-unity power factor, minimizes harmonics, and optimizes <br>current consumption under varying load conditions. Experimental results demonstrate improved power quality, <br>faster response time, and enhanced energy efficiency compared to conventional APFC systems.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_18917878 |
| institution | Zenodo |
| language | eng |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | An Edge AI-Driven IoT Framework for Automatic Power Factor Correction in Smart Industrial Power Systems S. Gowtham Dr.V.Manimekalai Power Factor Correction Edge Artificial Intelligence Internet of Things (IoT) Smart Industrial Power Systems Reactive Power Compensation TinyML <p>Abstract<br>Power factor correction remains a significant challenge in modern industrial power systems due to the presence <br>of highly inductive and fluctuating loads. Poor power factor results in increased energy losses, reduced system <br>efficiency, and higher operational costs. Conventional correction methods based on mechanical or thyristor <br>switching provide limited intelligence and slower adaptability to dynamic load variations. This paper presents <br>the design and hardware implementation of an Edge AI-driven IoT framework for automatic power factor <br>correction in smart industrial environments. The proposed system utilizes voltage and current sensing modules <br>integrated with an ESP8266 controller to continuously monitor electrical parameters. Edge Artificial <br>Intelligence enables real-time local decision-making for optimal capacitor bank switching to compensate <br>reactive power effectively. IoT connectivity allows remote monitoring and data visualization through cloud <br>platforms. The developed system maintains near-unity power factor, minimizes harmonics, and optimizes <br>current consumption under varying load conditions. Experimental results demonstrate improved power quality, <br>faster response time, and enhanced energy efficiency compared to conventional APFC systems.</p> |
| title | An Edge AI-Driven IoT Framework for Automatic Power Factor Correction in Smart Industrial Power Systems |
| topic | Power Factor Correction Edge Artificial Intelligence Internet of Things (IoT) Smart Industrial Power Systems Reactive Power Compensation TinyML |
| url | https://doi.org/10.5281/zenodo.18917878 |