• ISHAN DESAI
• NILESH CHOTHANI

Integrating Decentralized Power Generation Facilities (DPGFs) like Solar PV, Wind Power Generation, Microturbine etc, into Distribution Network (DN) has revolutionized Conventional Distribution Networks (CDN) into Modern Distribution Networks (MDN) but also introduces notable challenges in Fault Detection and Classification (FDC), an important part for Protection Coordination. Conventional Distribution Network protection schemes rely mainly on Overcurrent Protection (OCP), often fails to lodge bidirectional power flows, dynamic DPGF output and network topology transition that leads to delay or failure of fault isolation, increasing chances of potential system and equipment outages. This article discusses numerous Machine Learning (ML) based fault detection and identification approaches used as alternative solution for improving fault management scheme in modern distribution scheme. Key advantages along with challenges for different Machine Learning (ML) based methods are discussed. Article is concluded with suggestion for future research area and scope, highlighting role of machine learning in achieving reliable protection scheme for distribution network.

Machine Learning, Fault Detection, Fault Classification, Distribution Network, Decentralized Power Generation

"Machine Learning Approach for Detection and Classification of Faults in Distribution Network with Decentralized Power Generation Facilities", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.c226-c230, November-2025, Available :http://www.jetir.org/papers/JETIR2511228.pdf

"Machine Learning Approach for Detection and Classification of Faults in Distribution Network with Decentralized Power Generation Facilities", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppc226-c230, November-2025, Available at : http://www.jetir.org/papers/JETIR2511228.pdf