Show simple item record

AuthorUddin, Md. Sihab
AuthorHossain, Md. Zahid
AuthorFahim, Shahriar Rahman
AuthorSarker, Subrata K.
AuthorBhuiyan, Erphan Ahmmad
AuthorMuyeen, S.M.
AuthorDas, Sajal K.
Available date2023-02-26T08:29:58Z
Publication Date2022
Publication NameEnergy Reports
ResourceScopus
URIhttp://dx.doi.org/10.1016/j.egyr.2022.07.163
URIhttp://hdl.handle.net/10576/40379
AbstractTransmission lines (TLs) of power networks are often encountered with a number of faults. To continue normal operation and reduce the damage due to the TL faults, it is a must to identify and classify faults as early as possible. In this paper, the design and development of an intelligent machine learning framework is presented to identify and classify faults in a power TL. The design of the proposed framework is done with the goal of reducing computational load and ensuring resilience against source noise, source impedance, fault strength, and sampling frequency variation. The design is carried out based on the selection of the optimal model parameters using a search optimization algorithm called GridSearchCV. The effectiveness of the proposed model is verified by testing the model on the IEC standard microgrid model in a MATLAB environment. The results show that the proposed model has more than ninety-nine per cent overall accuracy in the identification and classification of the TL faults. The results are also compared with some state-of-the-art approaches such as LSTM, RNN, DBN, DRL, and CNF to further examine the performance of the proposed framework. The comparison demonstrates that the proposed model outperforms other existing techniques in terms of accuracy, computational cost, and response speed. 2022 The Authors
SponsorThe publication of this article was funded by Qatar National Library .
Languageen
PublisherElsevier Ltd
SubjectFault diagnosis
Noise immunity
Optimized model
Supervised learning
Transmission line
Wavelet transform
TitleOn the protection of power system: Transmission line fault analysis based on an optimal machine learning approach
TypeArticle
Pagination10168-10182
Volume Number8
dc.accessType Open Access


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record