Generative Adversarial Model-Guided Deep Active Learning for Voltage Dip Labelling
Paper in proceedings, 2019

In many real applications, the ground truths of class labels from voltage dip sequences used for training a voltage dip classification system are unknown, and require manual labelling by human experts. This paper proposes a novel deep active learning method for automatic labelling of voltage dip sequences used for the training process. We propose a novel deep active learning method, guided by a generative adversarial network (GAN), where the generator is formed by modelling data with a Gaussian mixture model and provides the estimated probability distribution function (pdf) where the query criterion of the deep active learning method is built upon. Furthermore, the discriminator is formed by a support vector machine (SVM). The proposed method has been tested on a voltage dip dataset (containing 916 dips) measured in a European country. The experiments have resulted in good performance (classification rate 83% and false alarm 3.2%), which have demonstrated the effectiveness of the proposed method.

Semisupervised Training

Deep Learning

Voltage Dip

Generative-Discriminative Model

Deep Active Learning

Automatic Labelling

Author

Azam Bagheri

Luleå University of Technology

Irene Yu-Hua Gu

Chalmers, Electrical Engineering

Math H.J. Bollen

Luleå University of Technology

2019 IEEE Milan PowerTech

8810499

13th IEEE PowerTech 2019
Milan, Italy,

Areas of Advance

Energy

Subject Categories

Electrical Engineering, Electronic Engineering, Information Engineering

DOI

10.1109/PTC.2019.8810499

More information

Latest update

4/22/2020