Fatima Zohra Boudjella
Fatima Zohra Boudjella has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Boudjella Souhila
University of Mascara
2 shared publications - Hafidha Reriballah
University Ahmed Zabana of Rélizane
2 shared publications - Latifa Smail
University Center of El Bayadh
2 shared publications - Adnane Mouffak
Département des Sciences et Techniques, Faculté des Sciences et de Technologie, Université de Mascara Route de Mamounia, BP. 305 Mascara 29000 Algeria
1 shared publication - Ali Abderrazak Tadjeddine
LSETER Laboratory, Technology Institute, Nour Bachir University Center, El-Bayadh, Algeria
1 shared publication - Chaouch Djamel Eddine
University of Mustapha Stambouli, Mascara, Algeria
1 shared publication
Latest Publications
- Open Access
- 14 November 2026
- Published by Polskie Towarzystwo Diagnostyki Technicznej in Diagnostyka
- p. 1-16
Comparative analysis of raw and logarithmic feature representations for supervised machine learning-based transformer fault diagnosis using dissolved gas analysis
Early detection of transformer faults is essential for ensuring power system reliability, reducing maintenance costs, and preventing unexpected outages. Traditional dissolved gas analysis (DGA)-based diagnostic approaches often exhibit limited accuracy when handling complex fault conditions. To...
- 14 November 2026
- Published by Polskie Towarzystwo Diagnostyki Technicznej in Diagnostyka
- p. 1-16
Open AccessComparative analysis of raw and logarithmic feature representations for supervised machine learning-based transformer fault diagnosis using dissolved gas analysis
Early detection of transformer faults is essential for ensuring power system reliability, reducing maintenance costs, and preventing unexpected outages. Traditional dissolved gas analysis (DGA)-based diagnostic approaches often exhibit limited accuracy when handling complex fault conditions. To...
- Open Access
- 1 September 2026
- Published by Institute of Advanced Engineering and Science in International Journal of Power Electronics and Drive Systems (IJPEDS)
- Vol. 17 (3) , 1780-1793
Transformer fault diagnosis using dissolved gas analysis: a hybrid ensemble model with data preprocessing
Failures and guaranteed dependability of the electrical grid, early fault diagnosis in power transformers is essential. By examining gas ratios suggestive of faults, dissolved gas analysis (DGA) continues to be a vital component for transformer health monitoring. Using four preprocessing techniques raw data, min-max normalization, logarithmic transformation, and square root transformation; this study suggests a machine learning method for fault detection using DGA gas ratios (such as CH₄/H₂, C₂H₂/C₂H₄). Random forest (RF), support vector machines (SVM), gradient boosted trees (GBT), and a hybrid RF-GBT model that uses prediction fusion were the four supervised classifiers assessed. Performance was assessed using accuracy, precision, recall, f1-score, and Cohen's kappa. Experimental results show that the hybrid RF-GBT model with logarithmic transformation achieves the highest performance, with 94.93% accuracy and 92.37% Cohen's kappa, significantly outperforming individual classifiers. Data preprocessing, particularly logarithmic and square root transformations, enhances diagnostic robustness by mitigating feature skewness. This study underscores the importance of tailored preprocessing and ensemble methods for reliable transformer fault diagnosis.
- 1 September 2026
- Published by Institute of Advanced Engineering and Science in International Journal of Power Electronics and Drive Systems (IJPEDS)
- Vol. 17 (3) , 1780-1793
Open AccessTransformer fault diagnosis using dissolved gas analysis: a hybrid ensemble model with data preprocessing
Failures and guaranteed dependability of the electrical grid, early fault diagnosis in power transformers is essential. By examining gas ratios suggestive of faults, dissolved gas analysis (DGA) continues to be a vital component for transformer health monitoring. Using four preprocessing techniques raw data, min-max normalization, logarithmic transformation, and square root transformation; this study suggests a machine learning method for fault detection using DGA gas ratios (such as CH₄/H₂, C₂H₂/C₂H₄). Random forest (RF), support vector machines (SVM), gradient boosted trees (GBT), and a hybrid RF-GBT model that uses prediction fusion were the four supervised classifiers assessed. Performance was assessed using accuracy, precision, recall, f1-score, and Cohen's kappa. Experimental results show that the hybrid RF-GBT model with logarithmic transformation achieves the highest performance, with 94.93% accuracy and 92.37% Cohen's kappa, significantly outperforming individual classifiers. Data preprocessing, particularly logarithmic and square root transformations, enhances diagnostic robustness by mitigating feature skewness. This study underscores the importance of tailored preprocessing and ensemble methods for reliable transformer fault diagnosis.
- Open Access
- 1 June 2026
- Published by Institute of Advanced Engineering and Science in International Journal of Power Electronics and Drive Systems (IJPEDS)
- Vol. 17 (2)
Enhancing grid performance through coordinated SVC-TCSC operation with PV support: A case study on IEEE 30-bus system under progressive loading
Power systems face growing challenges of voltage instability, line congestion, and increased losses under rising demand. This study proposes a coordinated approach using two flexible AC transmission system (FACTS) devices: the static var compensator (SVC) and the thyristor controlled series capacitor (TCSC), together with photovoltaic (PV) generation, to enhance grid performance. The IEEE 30 bus test system is analyzed under normal and increased load conditions (5%, 10%, 15% load growth). Results show that coordinated SVC TCSC operation improves voltage profiles, reduces critical line loading by 14%, and lowers active and reactive losses by 10% and 23.8%, respectively, in the base case. Under a 15% load increase, integrating a 25 MW PV system with the coordinated FACTS restores the minimum voltage to 0.95 p.u., reduces line congestion by 27%, and decreases active and reactive losses by 35.5% and 53.5%. The combined FACTS PV strategy proves essential for maintaining stability and efficiency under high load growth. This integrated approach provides practical guidance for transmission operators toward resilient, loss aware, and renewable integrated smart grids.
- 1 June 2026
- Published by Institute of Advanced Engineering and Science in International Journal of Power Electronics and Drive Systems (IJPEDS)
- Vol. 17 (2)
Open AccessEnhancing grid performance through coordinated SVC-TCSC operation with PV support: A case study on IEEE 30-bus system under progressive loading
Power systems face growing challenges of voltage instability, line congestion, and increased losses under rising demand. This study proposes a coordinated approach using two flexible AC transmission system (FACTS) devices: the static var compensator (SVC) and the thyristor controlled series capacitor (TCSC), together with photovoltaic (PV) generation, to enhance grid performance. The IEEE 30 bus test system is analyzed under normal and increased load conditions (5%, 10%, 15% load growth). Results show that coordinated SVC TCSC operation improves voltage profiles, reduces critical line loading by 14%, and lowers active and reactive losses by 10% and 23.8%, respectively, in the base case. Under a 15% load increase, integrating a 25 MW PV system with the coordinated FACTS restores the minimum voltage to 0.95 p.u., reduces line congestion by 27%, and decreases active and reactive losses by 35.5% and 53.5%. The combined FACTS PV strategy proves essential for maintaining stability and efficiency under high load growth. This integrated approach provides practical guidance for transmission operators toward resilient, loss aware, and renewable integrated smart grids.