AUTHOR=Aziz Saddam , Irshad Muhammad , Haider Sami Ahmed , Wu Jianbin , Deng Ding Nan , Ahmad Sadiq 

TITLE=Protection of a smart grid with the detection of cyber- malware attacks using efficient and novel machine learning models

JOURNAL=Frontiers in Energy Research

VOLUME=Volume 10 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.964305

DOI=10.3389/fenrg.2022.964305

ISSN=2296-598X

ABSTRACT=False data injection (FDI) attacks regularly target smart grids. It is impossible to detect FDI attacks using current bad data detection methods. Machine learning is one method for detecting FDI attacks. Each of six supervised learning (SVM-FS) hybrid strategies is examined using six distinct boosting and feature selection (FS) methodologies. A smart grid dataset is used to evaluate the applicability of different technologies. Detection methods are compared based on how accurate they are in detecting specific threats. When supervised learning and hybrid methods are applied in a simulation exercise, classification algorithms used to detect FDI attacks perform better.