Machine Learning-Based Model to Enhance Smart Grid Reliability
Bhushan Prataprao Patil
, Salunkhe Umakant Manohar , Marathe Sushant Sanjay , Patil Jayesh Navnit , Bhavsar Rushikesh Rajendra, Patil Ashwin Sanjay
The electrical power system is a complex network of interconnected components that can experience disturbances or electrical faults. One challenging task is to detect these faults and determine their underlying causes. In this paper, a new approach using semi-supervised machine learning techniques is presented for fault detection and classification on transmission lines. The approach employs Decision Tree (DT), Random Forest (RF), Logistic Regression and SVM classifiers, which are designed to analyze and classify different types of faults. To extract relevant information from the fault current and voltage signals, a technique called Discrete Wavelet Transform (DWT) is applied for feature extraction. The Decision Tree classifier makes decisions based on constructing an optimal classification tree. It uses a set of rules to determine the most appropriate fault classification. The Random Forest and Logistic Regression also contribute to the fault analysis process. To evaluate the performance of the proposed system, various datasets are used. The results obtained from the two classifiers are compared based on their accuracy. This helps identify the most suitable technique for fault analysis in the given context. This paper presents an innovative approach to classify faults in transmission lines using machine learning techniques. By applying the Decision Tree, Random Forest, and Logistic Regression, along with the feature extraction capabilities of the Discrete Wavelet Transform. The Random Forest and Decision Tree improve the accuracy and effectiveness of fault analysis in the electrical power system
"Machine Learning-Based Model to Enhance Smart Grid Reliability", IJSDR - International Journal of Scientific Development and Research (www.IJSDR.org), ISSN:2455-2631, Vol.8, Issue 6, page no.433 - 436, June-2023, Available :https://ijsdr.org/papers/IJSDR2306063.pdf
Volume 8
Issue 6,
June-2023
Pages : 433 - 436
Paper Reg. ID: IJSDR_207140
Published Paper Id: IJSDR2306063
Downloads: 000347036
Research Area: Engineering
Country: -, -, India
ISSN: 2455-2631 | IMPACT FACTOR: 9.15 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 9.15 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJSDR(IJ Publication) Janvi Wave
