| Issue |
E3S Web Conf.
Volume 139, 2019
Rudenko International Conference “Methodological problems in reliability study of large energy systems” (RSES 2019)
|
|
|---|---|---|
| Article Number | 01040 | |
| Number of page(s) | 5 | |
| DOI | https://doi.org/10.1051/e3sconf/201913901040 | |
| Published online | 16 December 2019 | |
The support vector machine application in the implementation of multidimensional relay protection
Nizhniy Novgorod State Technical University, Russia
* Corresponding author: dimok.93@mail.ru
Power engineering digital transformation, the use of different intelligent electronic devices (IEDs), high-speed communication protocols provide extensive opportunities for relay protection and automation systems modernization of power utilities. One of the most promising avenues of power engineering development is design of new protection devices, whose principles are based on the elements of artificial intelligence and machine learning. The article discusses the features of the application of one of the most common machine learning algorithms, the support vector machine, by the example of constructing a three-dimensional fault detector, which would serve to increase a transmission line stepped protection selectivity. The proposed fault detector has high recognition ability and ease of technical implementation as part of the protection IED.
© The Authors, published by EDP Sciences, 2019
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.