Scale- and Context-Aware Convolutional Non-Intrusive Load Monitoring

Non-intrusive load monitoring addresses the challenging task of decomposing the aggregate signal of a household's electricity consumption into appliance-level data without installing dedicated meters. By detecting load malfunction and recommending energy reduction programs, cost-effective non-intrusive load monitoring provides intelligent demand-side management for utilities and end users. In this paper, we boost the accuracy of energy disaggregation with a novel neural network structure named scale- and context-aware network, which exploits multi-scale features and contextual information. Specifically, we develop a multi-branch architecture with multiple receptive field sizes and branch-wise gates that connect the branches in the sub-networks. We build a self-attention module to facilitate the integration of global context, and we incorporate an adversarial loss and on-state augmentation to further improve the model's performance. Extensive simulation results tested on open datasets corroborate the merits of the proposed approach, which significantly outperforms state-of-the-art methods.

[1]  Wonjong Rhee,et al.  Subtask Gated Networks for Non-Intrusive Load Monitoring , 2018, AAAI.

[2]  G. W. Hart,et al.  Nonintrusive appliance load monitoring , 1992, Proc. IEEE.

[3]  Charles A. Sutton,et al.  Sequence-to-point learning with neural networks for nonintrusive load monitoring , 2016, AAAI.

[4]  Vladimir Stankovic,et al.  On a Training-Less Solution for Non-Intrusive Appliance Load Monitoring Using Graph Signal Processing , 2016, IEEE Access.

[5]  Fuchun Sun,et al.  HyperNet: Towards Accurate Region Proposal Generation and Joint Object Detection , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Zhaoxiang Zhang,et al.  Scale-Aware Trident Networks for Object Detection , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[7]  Lina Stankovic,et al.  Transferability of Neural Network Approaches for Low-rate Energy Disaggregation , 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[8]  Bernt Schiele,et al.  Generative Adversarial Text to Image Synthesis , 2016, ICML.

[9]  Aaron C. Courville,et al.  Improved Training of Wasserstein GANs , 2017, NIPS.

[10]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[11]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[12]  Abhinav Gupta,et al.  Non-local Neural Networks , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[13]  Jun Hu,et al.  Convolutional Sequence to Sequence Non-intrusive Load Monitoring , 2018, The Journal of Engineering.

[14]  拓海 杉山,et al.  “Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告 , 2017 .

[15]  Abhay Gupta,et al.  Is disaggregation the holy grail of energy efficiency? The case of electricity , 2013 .

[16]  Yi-Hsuan Yang,et al.  MidiNet: A Convolutional Generative Adversarial Network for Symbolic-Domain Music Generation , 2017, ISMIR.

[17]  Ricardo Silva,et al.  Scaling Factorial Hidden Markov Models: Stochastic Variational Inference without Messages , 2016, NIPS.

[18]  Francesco Piazza,et al.  Unsupervised algorithms for non-intrusive load monitoring: An up-to-date overview , 2015, 2015 IEEE 15th International Conference on Environment and Electrical Engineering (EEEIC).

[19]  Yuichi Yoshida,et al.  Spectral Normalization for Generative Adversarial Networks , 2018, ICLR.

[20]  Yann LeCun,et al.  Energy-based Generative Adversarial Networks , 2016, ICLR.

[21]  Han Zhang,et al.  Self-Attention Generative Adversarial Networks , 2018, ICML.

[22]  Nigel H. Goddard,et al.  Non-Intrusive Load Monitoring with Fully Convolutional Networks , 2018, ArXiv.

[23]  Vladlen Koltun,et al.  Multi-Scale Context Aggregation by Dilated Convolutions , 2015, ICLR.

[24]  Charles A. Sutton,et al.  VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning , 2017, NIPS.

[25]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[26]  Jack Kelly,et al.  The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes , 2014, Scientific Data.

[27]  Mohammad Shahidehpour,et al.  An Overview of Non-Intrusive Load Monitoring: Approaches, Business Applications, and Challenges , 2018, 2018 International Conference on Power System Technology (POWERCON).

[28]  J. Zico Kolter,et al.  REDD : A Public Data Set for Energy Disaggregation Research , 2011 .

[29]  Léon Bottou,et al.  Wasserstein Generative Adversarial Networks , 2017, ICML.

[30]  Yann LeCun,et al.  Energy-based Generative Adversarial Network , 2016, ICLR.

[31]  Jack Kelly,et al.  Neural NILM: Deep Neural Networks Applied to Energy Disaggregation , 2015, BuildSys@SenSys.

[32]  Thomas S. Huang,et al.  Generative Image Inpainting with Contextual Attention , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[33]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[34]  Martin Wagner,et al.  Enhancing neural non-intrusive load monitoring with generative adversarial networks , 2018 .

[35]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[36]  Mario Berges,et al.  Unsupervised disaggregation of appliances using aggregated consumption data , 2011 .

[37]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[38]  Alex Rogers,et al.  An unsupervised training method for non-intrusive appliance load monitoring , 2014, Artif. Intell..

[39]  Jitendra Malik,et al.  Hypercolumns for object segmentation and fine-grained localization , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Bin Yang,et al.  A new approach for supervised power disaggregation by using a deep recurrent LSTM network , 2015, 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[41]  Tommi S. Jaakkola,et al.  Approximate Inference in Additive Factorial HMMs with Application to Energy Disaggregation , 2012, AISTATS.

[42]  Alex Rogers,et al.  Non-Intrusive Load Monitoring Using Prior Models of General Appliance Types , 2012, AAAI.

[43]  Shu Liu,et al.  Path Aggregation Network for Instance Segmentation , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.