ISSN (Online) : 2456 - 0774

Email : ijasret@gmail.com

ISSN (Online) 2456 - 0774


ELECTRICITY THEFT DETECTION USING MACHINE LEARNING
 

Abstract

Abstract: Power robbery is one of the serious issues of electric utilities. Such electricity theft produce financial loss to the utility companies. It is not possible to inspect manually such theft in large amount of data. For detecting such electricity theft introduces a gradient boosting theft detector (GBTD) based on the three latest gradient boosting classifiers (GBCs): extreme gradient boosting (XGBoost), categorical boosting (Cat Boost), and light gradient boosting method (LightGBM). XGBoost is one machine learning algorithm which gives high accuracy in less time. In this we apply pre-processing on smart meter data then does feature selection. Practical application of the proposed GBTD for theft detection by minimizing FPR and reducing data storage space and improving time-complexity of the GBTD classifiers which detect nontechnical loss (NTL) detection.
Keywords: Electricity data, , machine learning, XgBoost

Full Text PDF

IMPORTANT DATES 

Submit paper at ijasret@gmail.com

Paper Submission Open For October 2024
UGC indexed in (Old UGC) 2017
Last date for paper submission 30th October, 2024
Deadline Submit Paper any time
Publication of Paper Within 15-30 Days after completing all the formalities
Publication Fees  Rs.6000 (UG student)
Publication Fees  Rs.8000 (PG student)