Generative Adversarial Model-Guided Deep Active Learning for Voltage Dip Labelling

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.

[1]  Yang Wu,et al.  Meta-Learning Transferable Active Learning Policies by Deep Reinforcement Learning , 2018, ArXiv.

[2]  Ab Halim Abu Bakar,et al.  Strategy to enhance the low-voltage ride-through in photovoltaic system during multi-mode transition , 2017 .

[3]  Irene Yu-Hua Gu,et al.  Signal processing of power quality disturbances , 2006 .

[4]  Daphne Koller,et al.  Support Vector Machine Active Learning with Applications to Text Classification , 2000, J. Mach. Learn. Res..

[5]  Trevor Darrell,et al.  Active Learning with Gaussian Processes for Object Categorization , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[6]  C. Bishop.  Mixture density networks , 1994 .

[7]  Ran El-Yaniv,et al.  Online Choice of Active Learning Algorithms , 2003, J. Mach. Learn. Res..

[8]  Hsuan-Tien Lin,et al.  Active Learning by Learning , 2015, AAAI.

[9]  G. Moschopoulos,et al.  Voltage Sag Impact on Wind Turbine Tower Vibration , 2007, 2007 IEEE Power Engineering Society General Meeting.

[10]  Axel Brando Guillaumes,et al.  Mixture density networks for distribution and uncertainty estimation , 2017 .

[11]  Math Bollen,et al.  Different methods for classification of three-phase unbalanced voltage dips due to faults , 2003 .

[12]  Taghi M. Khoshgoftaar,et al.  Deep learning applications and challenges in big data analytics , 2015, Journal of Big Data.

[13]  Sethuraman Panchanathan,et al.  Batch Mode Active Sampling Based on Marginal Probability Distribution Matching , 2013, ACM Trans. Knowl. Discov. Data.

[14]  Shouxiang Wang,et al.  A novel deep learning method for the classification of power quality disturbances using deep convolutional neural network , 2019, Applied Energy.

[15]  Math Bollen,et al.  A Robust Transform-Domain Deep Convolutional Network for Voltage Dip Classification , 2018 .

[16]  Math Bollen.  Characterisation of voltage sags experienced by three-phase adjustable-speed drives , 1997 .

[17]  Ian J. Goodfellow,et al.  NIPS 2016 Tutorial: Generative Adversarial Networks , 2016, ArXiv.

[18]  Shaogang Gong,et al.  Finding Rare Classes: Adapting Generative and Discriminative Models in Active Learning , 2011, PAKDD.

[19]  Chih-Jen Lin,et al.  Probability Estimates for Multi-class Classification by Pairwise Coupling , 2003, J. Mach. Learn. Res..

[20]  Sethuraman Panchanathan,et al.  Batch mode active sampling based on marginal probability distribution matching , 2012, TKDD.