Download PDFOpen PDF in browser

Electricity Theft Detection Using Machine Learning

EasyChair Preprint no. 9676

3 pagesDate: February 7, 2023


Electricity robbery is one of the predominant issues of electric powered utilities. Such power robbery produces monetary loss to the software agencies. It isn't always viable to check out manually such robbery in massive quantity of records. For detecting such power robbery introduces a Gradient Boosting Robbery Detector(GBTD) primarily based totally on the 3 present day Gradient Boosting Classifiers (GBCs): intense gradient boosting (XG Boost), specific boosting (Cat Boost), and mild gradient boosting method (Light). XGBoost is one system getting to know set of rules which offers excessive accuracy in less time. In this we practice preprocessing on clever meter records then does characteristic choice. Practical utility of the proposed GBTD for robbery detection through minimizing FPR and lowering records garage area and enhancing time complexity of the GBTD classifiers which come across nontechnical loss (NTL) detection.

Keyphrases: Artificial Intelligence, Classification, deep learning, feature extraction, Object evaluation, OCR set of rules, recognition

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
  author = {Prof. Shubham R. Bhandari and Anuja Kulkarni and Ruchika Zodage and Purva Sutar},
  title = {Electricity Theft Detection Using Machine Learning},
  howpublished = {EasyChair Preprint no. 9676},

  year = {EasyChair, 2023}}
Download PDFOpen PDF in browser