EnerGAN++: A Generative Adversarial Gated Recurrent Network for Robust Energy Disaggregation

被引:17
作者
Kaselimi M. [1 ]
Doulamis N. [1 ]
Voulodimos A. [2 ]
Doulamis A. [1 ]
Protopapadakis E. [1 ]
机构
[1] Department of Electrical and Computer Engineering, National Technical University of Athens, Zografou
[2] Department of Informatics and Computer Engineering, University of West Attica, Athens
来源
IEEE Open Journal of Signal Processing | 2021年 / 2卷
基金
欧盟地平线“2020”;
关键词
Convolutional neural networks; denoising autoencoders; energy disaggregation; generative adversarial networks; non-intrusive load monitoring; recurrent neural networks; robustness to noise; sequence-to-sequence learning;
D O I
10.1109/OJSP.2020.3045829
中图分类号
学科分类号
摘要
Energy disaggregation, namely the separation of the aggregated household energy consumption signal into its additive sub-components, bears resemblance to the signal (source) separation problem and poses several challenges, not only as an ill-posed problem, but also, due to unsteady appliance signatures, abnormal behaviour that is usually detected in appliances operation and the existence of noise in the aggregated signal. In this paper, we propose EnerGAN++, a model based on Generative Adversarial Networks (GAN) for robust energy disaggregation. We attempt to unify the autoencoder (AE) and GAN architectures into a single framework, in which the autoencoder achieves a non-linear power signal source separation. EnerGAN++ is trained adversarially using a novel discriminator, to enhance robustness to noise. The discriminator performs sequence classification, using a recurrent convolutional neural network to handle the temporal dynamics of an appliance energy consumption time series. In particular, the proposed architecture of the discriminator leverages the ability of Convolutional Neural Networks (CNN) in rapid processing and optimal feature extraction, among with the need to infer the data temporal character and time dependence. Experimental results indicate the proposed method's superiority compared to the current state of the art. © 2020 IEEE.
引用
收藏
相关论文
共 51 条
[1]  
Kaselimi M., Doulamis N., Voulodimos A., Protopapadakis E., Doulamis A., Context aware energy disaggregation using adaptive bidirectional LSTM models, IEEE Trans. Smart Grid, 11, 4, pp. 3054-3067, (2020)
[2]  
Kaselimi M., Doulamis N., Doulamis A., Voulodimos A., Protopapadakis E., Bayesian-optimized bidirectional LSTM regression model for non-intrusive load monitoring, Proc. IEEE Int. Conf. Acoust., Speech Signal Process., pp. 2747-2751, (2019)
[3]  
Murray D., Stankovic L., Stankovic V., Lulic S., Sladojevic S., Transferability of neural network approaches for low-rate energy disaggregation, Proc. IEEE Int. Conf. Acoust., Speech Signal Process., pp. 8330-8334, (2019)
[4]  
D'Incecco M., Squartini S., Zhong M., Transfer learning for nonintrusive load monitoring, IEEE Trans. Smart Grid, 11, 2, pp. 1419-1429, (2020)
[5]  
Barsim K., Streubel R., Yang B., An approach for unsupervised non-intrusive load monitoring of residential appliances, Proc. 2nd Int. Workshop Non-Intrusive Load Monit., pp. 1-5, (2014)
[6]  
Goodfellow I., Et al., Generative adversarial nets, Adv. Neural Inf. Process. Syst., pp. 2672-2680, (2014)
[7]  
Kaneko T., Ushiku Y., Harada T., Label-noise robust generative adversarial networks, Proc. IEEE Conf. Comput. Vis. Pattern Recognit., pp. 2467-2476, (2019)
[8]  
Creswell A., Bharath A.A., Inverting the generator of a generative adversarial network, IEEE Trans. Neural Netw. Learn. Syst., 30, 7, pp. 1967-1974, (2018)
[9]  
Kaselimi M., Voulodimos A., Protopapadakis E., Doulamis N., Doulamis A., Energan: A generative adversarial network for energy disaggregation, Proc. IEEE Int. Conf. Acoust., Speech and Signal Process., pp. 1578-1582, (2020)
[10]  
Kelly J., Knottenbelt W., Neural nilm: Deep neural networks applied to energy disaggregation, Proc. 2nd ACM Int. Conf. Embedded Syst. Energy-Efficient Built Environ., pp. 55-64, (2015)