Abstract
Efficient identification of the voltage sag sources is significant in the power quality studies. This paper presents a novel method for voltage sag source identification which performs automatic feature extraction and shows a superior performance regardless of the insufficient amount of training samples. In the proposed strategy, the input data are preprocessed and fetched into the feature extractor, which is designed based on the convolutional neural network. Then the weighted k-nearest neighbor classifier generates the identification results. In the training period, the few-shot learning technique is harnessed, and the siamese network is constructed such that the proposed model learns efficiently even with a small number of samples. The proposed scheme is implemented in Python and PyTorch framework. Case studies and comparisons with other methods are carried out on 700 samples of voltage sag events in Jiangsu Province, China. Experimental results show the superiority of the proposed method over other identification methods in the tested cases.
Highlights
In the last decades, voltage sag (VS) has been regarded as one of the most significant issues in power quality [1]
The identification of VS sources are carried out in three major stages: 1) the VS data that are captured by the power quality monitors are firstly loaded and transformed into the unified dimension which is accepted by the following feature extractor; 2) the convolutional neural network (CNN)-based network, which is trained in advance using the representation learning technique, produces an embedding vector for each recorded VS event; 3) each embedding vector is analyzed by the weighted k-nearest neighbors (WKNN)-based classifier, and the identification result is generated
An efficient method for the identification of VS events is introduced in this paper
Summary
Voltage sag (VS) has been regarded as one of the most significant issues in power quality [1]. The RMS-voltage transition and make use of the K-means clustering algorithm to distinguish different VS groups The methods in this group obviate the labor work of labeling input data. The methods of the last group generally require the specialists to manually recognize and label a sufficient number of monitored data of VS events for training purpose. The identification of VS sources are carried out in three major stages: 1) the VS data that are captured by the power quality monitors are firstly loaded and transformed into the unified dimension which is accepted by the following feature extractor; 2) the CNN-based network, which is trained in advance using the representation learning technique, produces an embedding vector for each recorded VS event; 3) each embedding vector is analyzed by the WKNN-based classifier, and the identification result is generated
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
