Rashmi S. Phasate
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Rashmi S. Phasate has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Asha Shendge
Department of Electrical and Electronics Engineering, Rover Engineering College, Perambalur, Tamil Nadu, India
2 shared publications - Bhupendra Kumar
G H Raisoni Institute of Engineering & Technology
2 shared publications - Jagdish Chaudhari
Nagpur Institute of Technology
2 shared publications
Latest Publications
- 23 January 2025
- Published by Springer Nature
- p. 273-281
Application of Random Forest Tree for Fault Identification in Microgrid
- 23 January 2025
- Published by Springer Nature
- p. 273-281
Application of Random Forest Tree for Fault Identification in Microgrid
- Open Access
- 4 April 2024
- Published by Science Research Society in Journal of Electrical Systems
- Vol. 20 (2s) , 323-331
Empirical Evaluation of Microgrid Fault Identification Models from a Statistical Perspective
Microgrid fault identification models are developed via integration of extensive data collection, pre-processing of collected data, current & voltage segmentation, feature representation, identification of variant feature sets, their classification & post-processing operations. Existing models that perform microgrid fault identification are either highly complex, or cannot be applied for heterogeneous fault types. Moreover, these models also showcase large variance in terms of their qualitative & quantitative performance levels. Due to these issues, it is difficult for researchers to identify optimum models for their performance-specific deployment use cases. To overcome these issues, a detailed review of different microgrid fault detection & mitigation models in needed, which can evaluate their performance in terms of qualitative & quantitative parameters. Thus, this text initially discusses characteristics of some of the recently proposed microgrid fault detection models in terms of their functional nuances, application specific advantages, deployment specific limitations, and context-specific future research scopes. After referring this discussion, it was observed that linear models that incorporate pattern recognition are highly useful for fault pre-emption and mitigation purposes. This text also compares these models in terms of their accuracy of detection, delay needed for fault identification, computational complexity, deployment cost, and scalability metrics.
- 4 April 2024
- Published by Science Research Society in Journal of Electrical Systems
- Vol. 20 (2s) , 323-331
Open AccessEmpirical Evaluation of Microgrid Fault Identification Models from a Statistical Perspective
Microgrid fault identification models are developed via integration of extensive data collection, pre-processing of collected data, current & voltage segmentation, feature representation, identification of variant feature sets, their classification & post-processing operations. Existing models that perform microgrid fault identification are either highly complex, or cannot be applied for heterogeneous fault types. Moreover, these models also showcase large variance in terms of their qualitative & quantitative performance levels. Due to these issues, it is difficult for researchers to identify optimum models for their performance-specific deployment use cases. To overcome these issues, a detailed review of different microgrid fault detection & mitigation models in needed, which can evaluate their performance in terms of qualitative & quantitative parameters. Thus, this text initially discusses characteristics of some of the recently proposed microgrid fault detection models in terms of their functional nuances, application specific advantages, deployment specific limitations, and context-specific future research scopes. After referring this discussion, it was observed that linear models that incorporate pattern recognition are highly useful for fault pre-emption and mitigation purposes. This text also compares these models in terms of their accuracy of detection, delay needed for fault identification, computational complexity, deployment cost, and scalability metrics.