An efficient pattern analysis-based event detection and fault localisation model for reliable power transmission system
by Arunkumar Patil; T. Ananthapadmanaba; A.D. Kulkarni; N. Mohan
International Journal of Smart Grid and Green Communications (IJSGGC), Vol. 1, No. 4, 2018

Abstract: The exponential rise of power demands across socio-industrial applications has motivated academia-industries to develop optimal power quality assurance to meet the requirements. The use of synchrophasor information-based event detection has always been a potential solution to ensure controllability of the power systems; however assessing the gigantic real-time phasor information is often an intricate task. On the contrary, accurate and timely data (feature) extraction and event detection are a must for decision purposes. Recently, the robustness of the soft computing techniques, particularly data mining and pattern classification approaches have gained significant attention for large sale data analysis and classification. With this motivation, in this paper we have developed a multi-stage intelligent soft computing model for event detection and fault localisation using the pattern classification algorithms named, J48, naïve Bayes and K-NN. The developed algorithm is verified with IEEE test systems. The overall results affirm the suitability of K-NN-based event detection and fault localisation model for real time purposes.

Online publication date: Mon, 01-Oct-2018

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Smart Grid and Green Communications (IJSGGC):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email