Advertisement

Neural Computing and Applications

, Volume 31, Issue 12, pp 8931–8953 | Cite as

Dilated residual attention network for load disaggregation

  • Min XiaEmail author
  • Wan’an Liu
  • Yiqing Xu
  • Ke Wang
  • Xu Zhang
Original Article
  • 76 Downloads

Abstract

Load disaggregation technology is a key technology to realize real-time nonintrusive load monitoring (NILM), and deep learning method has shown great promise for NILM. However, current load disaggregation models based on deep learning are prone to the problems of gradient disappearance and model degradation, and it is difficult to extract effective features from load time series. In order to solve these problems, a new dilated residual attention deep network is proposed for load disaggregation. The proposed model adopts residual learning to extract high-level load features, reduces the difficulty of network optimization and solves the problem of network gradient disappearance. Dilated convolution is introduced to increase the receptive field of convolution kernels, which solves the problem that long-load time-series data are difficult to be learned. Most important of all, the proposed bottom-up and top-down attention mechanism can effectively extract the features of the abrupt points in mains power, improve the accuracy of judging the on/off state of electrical appliances and at the same time improve the learning ability of electrical appliances with low usage. Experiments on WikiEnergy dataset and UK-DALE dataset show that the proposed method achieves more accurate load disaggregation tasks than existing studies, which is of great significance for realizing practical NILM.

Keywords

Load disaggregation Dilated convolution Residual learning Attention mechanism 

Notes

Acknowledgements

This work is supported in part by the National Natural Science Foundation of PR China (61773219), the Natural Science Foundation of Jiangsu (BK20161533), State Grid Corporation of China Project ‘Fundamental Theory of Dynamic Demand Response Control Based on Large-Scale Diversified Demand Side Resources.’

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.

References

  1. 1.
    Wan Z, Li J, Gao Y (2018) Monitoring and diagnosis process of abnormal consumption on smart power grid. Neural Comput Appl 30(1):21–28CrossRefGoogle Scholar
  2. 2.
    Ridi A, Gisler C, Hennebert J (2014) A survey on intrusive load monitoring for appliance recognition. In: 2014 22nd international conference on pattern recognition, pp 3702–3707Google Scholar
  3. 3.
    Hart GW (1992) Nonintrusive appliance load monitoring. Proc IEEE 80(12):1870–1891CrossRefGoogle Scholar
  4. 4.
    Miyasawa A, Fujimoto Y, Hayashi Y (2019) Energy disaggregation based on smart metering data via semi-binary nonnegative matrix factorization. Energy Build 183:547–558CrossRefGoogle Scholar
  5. 5.
    Ma YJ, Zhai MY (2018) A non-intrusive load decomposition algorithm for residents. Neural Comput Appl.  https://doi.org/10.1007/s00521-018-3862-x CrossRefGoogle Scholar
  6. 6.
    Paterakis NG, Erdinc O, Bakirtzis AG, Catalão JPS (2015) Optimal household appliances scheduling under day-ahead pricing and load-shaping demand response strategies. IEEE Trans Ind Inf 11(6):1509–1519CrossRefGoogle Scholar
  7. 7.
    Islam B, Baharudin Z, Nallagownden P (2017) Development of chaotically improved meta-heuristics and modified bp neural network-based model for electrical energy demand prediction in smart grid. Neural Comput Appl 28(s1):877–891CrossRefGoogle Scholar
  8. 8.
    Lee WK, Fung GSK, Lam HY, Chan FHY, Lucente Mark (2004) Exploration on load signatures. In: International conference on electrical engineering (ICEE), vol 152Google Scholar
  9. 9.
    Amara F, Agbossou K, Dubé Y, Kelouwani S, Cardenas A, Hosseini SS (2019) A residual load modeling approach for household short-term load forecasting application. Energy Build 187(15):132–143CrossRefGoogle Scholar
  10. 10.
    Lin Y-H, Tsai M-S (2014) Development of an improved time-frequency analysis-based nonintrusive load monitor for load demand identification. IEEE Trans Instrum Meas 63(6):1470–1483MathSciNetCrossRefGoogle Scholar
  11. 11.
    Chang H-H, Lin L-S, Chen N, Lee W-J (2013) Particle-swarm-optimization-based nonintrusive demand monitoring and load identification in smart meters. IEEE Trans Ind Appl 49(5):2229–2236CrossRefGoogle Scholar
  12. 12.
    Gou J, Guo WP, Wang C, Luo W (2017) A multi-strategy improved particle swarm optimization algorithm and its application to identifying uncorrelated multi-source load in the frequency domain. Neural Comput Appl 28(7):1635–1656CrossRefGoogle Scholar
  13. 13.
    Piga D, Cominola A, Giuliani M, Castelletti A, Rizzoli AE et al (2016) Sparse optimization for automated energy end use disaggregation. IEEE Trans Control Syst Technol 24(3):1044–1051CrossRefGoogle Scholar
  14. 14.
    Ahmadi H, Martı JR (2015) Load decomposition at smart meters level using eigenloads approach. IEEE Trans Power Syst 30(6):3425–3436CrossRefGoogle Scholar
  15. 15.
    Kim H, Marwah M, Arlitt M, Lyon G, Han J (2011) Unsupervised disaggregation of low frequency power measurements. In: Proceedings of the 2011 SIAM international conference on data mining, pp 747–758. SIAMGoogle Scholar
  16. 16.
    Zoha A, Gluhak A, Nati M, Imran MA (2013) Low-power appliance monitoring using factorial hidden Markov models. In: IEEE eighth international conference on intelligent sensors, sensor networks and information processing, pp. 527–532. IEEEGoogle Scholar
  17. 17.
    Kolter JZ, Batra S, Ng AY (2010) Energy disaggregation via discriminative sparse coding. In: Advances in neural information processing systems, pp 1153–1161Google Scholar
  18. 18.
    Deb C, Frei M, Hofer J, Schlueter A (2019) Automated load disaggregation for residences with electrical resistance heating. Energy Build 182:61–74CrossRefGoogle Scholar
  19. 19.
    Hassan T, Javed F, Arshad N (2014) An empirical investigation of VI trajectory based load signatures for non-intrusive load monitoring. IEEE Trans Smart Grid 5(2):870–878CrossRefGoogle Scholar
  20. 20.
    Tsai M-S, Lin Y-H (2012) Modern development of an adaptive non-intrusive appliance load monitoring system in electricity energy conservation. Appl Energy 96:55–73CrossRefGoogle Scholar
  21. 21.
    Saitoh T, Osaki T, Konishi R, Sugahara K (2010) Current sensor based home appliance and state of appliance recognition. SICE J Control Meas Syst Integr 3(2):86–93CrossRefGoogle Scholar
  22. 22.
    Lin Y-H, Tsai M-S (2014) Non-intrusive load monitoring by novel neuro-fuzzy classification considering uncertainties. IEEE Trans Smart Grid 5(5):2376–2384CrossRefGoogle Scholar
  23. 23.
    Smith DV, Shahriar MS (2013) A context aware sound classifier applied to prawn feed monitoring and energy disaggregation. Knowl-Based Syst 52:21–31CrossRefGoogle Scholar
  24. 24.
    Chang H-H, Lian K-L, Su Y-C, Lee W-J (2014) Power-spectrum-based wavelet transform for nonintrusive demand monitoring and load identification. IEEE Trans Ind Appl 50(3):2081–2089CrossRefGoogle Scholar
  25. 25.
    Guo Z, Wang ZJ, Kashani A (2015) Home appliance load modeling from aggregated smart meter data. IEEE Trans Power Syst 30(1):254–262CrossRefGoogle Scholar
  26. 26.
    Bouhouras AS, Gkaidatzis PA, Panagiotou E, Poulakis N, Christoforidis GC (2019) A NILM algorithm with enhanced disaggregation scheme under harmonic current vectors. Energy Build 183:392–407CrossRefGoogle Scholar
  27. 27.
    Perez KX, Cole WJ, Rhodes JD, Ondeck A, Webber M, Baldea M, Edgar TF (2014) Nonintrusive disaggregation of residential air-conditioning loads from sub-hourly smart meter data. Energy Build 81:316–325CrossRefGoogle Scholar
  28. 28.
    Zhang H, Ji Y, Huang W, Liu L (2018) Sitcom-star-based clothing retrieval for video advertising: a deep learning framework. Neural Comput Appl.  https://doi.org/10.1007/s00521-018-3579-x CrossRefGoogle Scholar
  29. 29.
    Ji Y, Zhang H, Wu QMJ (2018) Salient object detection via multi-scale attention CNN. Neurocomputing 322:130–140CrossRefGoogle Scholar
  30. 30.
    Chang H-H, Yang H-T, Lin C-L (2007) Load identification in neural networks for a non-intrusive monitoring of industrial electrical loads. In: International conference on computer supported cooperative work in design, Springer, Berlin, pp 664–674Google Scholar
  31. 31.
    Kelly J, Knottenbelt W (2015) Neural NILM: deep neural networks applied to energy disaggregation. In: Proceedings of the 2nd ACM international conference on embedded systems for energy-efficient built environments, ACM, Cambridge, pp 55–64Google Scholar
  32. 32.
    Bonfigli R, Felicetti A, Principi E, Fagiani M, Squartini S, Piazza F (2018) Denoising autoencoders for non-intrusive load monitoring: improvements and comparative evaluation. Energy Build 158:1461–1474CrossRefGoogle Scholar
  33. 33.
    Zhang C, Zhong M, Wang Z, Goddard N, Sutton C (2016) Sequence-to-point learning with neural networks for nonintrusive load monitoring. arXiv preprint arXiv:1612.09106
  34. 34.
    Zhang H, Li J, Ji Y, Yue H (2016) Understanding subtitles by character-level sequence-to-sequence learning. IEEE Trans Ind Inf 13(2):616–624CrossRefGoogle Scholar
  35. 35.
    Liu B, Liu Q, Zhu Z, Zhang T, Yang Y (2019) MSST-ResNet: deep multi-scale spatiotemporal features for robust visual object tracking. Knowl-Based Syst 164:235–252CrossRefGoogle Scholar
  36. 36.
    Wang B, Cao G, Shang Y, Zhou L, Zhang Y, Li X (2018) Single-column CNN for crowd counting with pixel-wise attention mechanism. Neural Comput Appl.  https://doi.org/10.1007/s00521-018-3810-9 CrossRefGoogle Scholar
  37. 37.
    Kelly J, Knottenbelt W (2015) The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes. Sci Data 2:150007CrossRefGoogle Scholar
  38. 38.
    He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778Google Scholar
  39. 39.
    Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167
  40. 40.
    Srivastava RK, Greff K, Schmidhuber J (2015) Highway networks. arXiv preprint arXiv:1505.00387
  41. 41.
    Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: CVPR, vol 1, p 3Google Scholar
  42. 42.
    LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436CrossRefGoogle Scholar
  43. 43.
    Katsuki F, Constantinidis C (2014) Bottom-up and top-down attention: different processes and overlapping neural systems. The Neurosci 20(5):509–521Google Scholar
  44. 44.
    Buschman TJ, Miller EK (2007) Top-down versus bottom-up control of attention in the prefrontal and posterior parietal cortices. Science 315(5820):1860–1862CrossRefGoogle Scholar
  45. 45.
    Wang F, Jiang M, Qian C, Yang S, Li C, Zhang H, Wang X, Tang X (2017) Residual attention network for image classification. arXiv preprint arXiv:1704.06904
  46. 46.
    Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. arXiv preprint arXiv:1511.07122
  47. 47.
    Yu F, Koltun V, Funkhouser TA (2017) Dilated residual networks. In: CVPR, vol 2, p 3Google Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2019

Authors and Affiliations

  1. 1.Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment TechnologyNanjing University of Information Science and TechnologyNanjingChina
  2. 2.College of Information Science and TechnologyNanjing Forestry UniversityNanjingChina
  3. 3.China Electric Power Research InstituteNanjingChina

Personalised recommendations