Skip to main content

Advertisement

Springer Nature Link
Log in

Non-intrusive load monitoring based on semi-supervised smooth teacher graph learning with voltage–current trajectory

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Non-intrusive load monitoring (NILM) is a novel and cost-effective technology for monitoring load electricity energy consumption detail. It can support the construction of “energy internet” and electricity consumption big data in smart cities, promote the construction of internet ecology, and support the dual carbon goal achieved. Recently, most current researchers have employed machine learning methods to make those inferences. As the most challenging problem in this specific field, the machine learning algorithms usually require a large pool of labeled observations and are poor in multi-state load identification. In this paper, we first design a semi-supervised learning backbone that leverages external and internal structural information to reduce the required labeling effort. Then, a smooth teacher graph based on semi-supervised learning model is proposed for multi-state load, the teacher graph helps the fusing of cluster become tighter and more effective for multi-state load signatures. Specifically, we use the color V–I trajectory to enhance the load signature’s uniqueness. Experiments in public datasets PLAID and WHITED show the performance of the proposed method. We find that our algorithm could outperform state-of-the-art results on these datasets.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21

Similar content being viewed by others

Explore related subjects

Discover the latest articles and news from researchers in related subjects, suggested using machine learning.

References

  1. Pérez-Lombard L, Ortiz J, Pout C (2008) A review on buildings energy consumption information. Energ Build 40(3):394–398

    Article  Google Scholar 

  2. Guzhov S, Krolin A(2018) Use of big data technologies for the implementation of energy-saving measures and renewable energy sources in buildings. In: 2018 Renewable Energies, Power Systems & Green Inclusive Economy (REPS-GIE), IEEE, 2018, pp 1–5

  3. Chakravarty P, Gupta A (2013) Impact of energy disaggregation on consumer behavior. In: Behaviour, Energy and Climate Chance Conference

  4. Ehrhardt-Martinez K, Donnelly KA, Laitner S et al (2010) Advanced metering initiatives and residential feedback programs: a meta-review for household electricity-saving opportunities. American Council for an Energy-Effcient Economy Washington, DC

  5. Hart GW (1992) Nonintrusive appliance load monitoring. Proc IEEE 80(12):1870–1891

    Article  Google Scholar 

  6. Liu B, Luan W, Yu Y (2017) Dynamic time warping based non-intrusive load transient identification. Appl Energy 195(1):634–645

    Article  Google Scholar 

  7. Zoha A, Gluhak A, Imran MA, Rajasegarar S (2012) Non-intrusive load monitoring approaches for disaggregated energy sensing: a survey. Sensors 12(12):16838–16866

    Article  Google Scholar 

  8. Figueiredo MB, Almeida AD, Ribeiro B (2011) An experimental study on electrical signature identification of non-intrusive load monitoring (nilm) systems. In: International Conference on Adaptive and Natural Computing Algorithms, Springer, pp 31–40

  9. De Baets L, Develder C, Dhaene T, Deschrijver D (2019) Detection of unidentified appliances in non-intrusive load monitoring using siamese neural networks. Int J Electrical Power Energy Syst 104:645–653

    Google Scholar 

  10. Hassan T, Javed F, Arshad N (2014) An empirical investigation of v–i trajectory based load signatures for non-intrusive load monitoring. IEEE Trans Smart Grid 5(2):870–878

    Article  Google Scholar 

  11. Mulinari BM, de Campos DP, da Costa CH, Ancelmo HC, Lazzaretti AE, Oroski E, Lima CR, Renaux DP, Pottker F, Linhares RR (2019) A new set of steadystate and transient features for power signature analysis based on vi trajectory. In: 2019 IEEE PES Innovative Smart Grid Technologies Conference-Latin America (ISGT Latin America), IEEE, pp 1–6

  12. Habetler TG, Harley RG, He D, Du L (2015) Electric load classification by binary voltage-current trajectory mapping. IEEE Trans Smart Grid 7(1):358–365

    Google Scholar 

  13. Liu Y, Wang X, You W (2018) Non-intrusive load monitoring by voltage-current trajectory enabled transfer learning. IEEE Trans Smart Grid 10(5):5609–5619

    Article  Google Scholar 

  14. S. Wang, H. Chen, L. Guo, D. Xu (2021) Non-intrusive load identification based on the improved voltage-current trajectory with discrete color encoding background and deep-forest classifier, Energy and Buildings 244:111043

    Article  Google Scholar 

  15. De Baets L, Ruyssinck J, Develder C, Dhaene T, Deschrijver D (2018) Appliance classification using vi trajectories and convolutional neural networks. Energy Build 158(1):32–36

    Article  Google Scholar 

  16. Jia D, Li Y, Du Z, Xu J, Yin B (2021) Non-intrusive load identification using reconstructed voltage-current images. IEEE Access 9:77349–77358

    Article  Google Scholar 

  17. Linh NV, Arboleya P (2019) Deep learning application to non-intrusive load monitoring. In IEEE Milan PowerTech, IEEE, pp 1–5

  18. Faustine A, Pereira L, Klemenjak C (2020) Adaptive weighted recurrence graphs for appliance recognition in non-intrusive load monitoring. IEEE Trans Smart Grid 12(1):398–406

    Article  Google Scholar 

  19. Makonin S, Popowich F, BaJi IV, Gill B, BaRtram L (2016) Exploiting hmm sparsity to perform online real-time nonintrusive load monitoring. Smart Grid, IEEE Trans 7(6):2575–2585

    Article  Google Scholar 

  20. Yasin A, Khan SA (2018) Unsupervised event detection and onoff pairing approach applied to nilm. In: 2018 international conference on frontiers of information technology (FIT), IEEE,pp 123–128

  21. Srinivasarengan K, Goutam Y, Chandra MG, Kadhe S (2013) A framework for non intrusive load monitoring using bayesian inference. In: 2013 Seventh International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing, IEEE, pp 427–432

  22. Jia R, Gao Y, Spanos CJ (2015) A fully unsupervised non-intrusive load monitoring framework, in: 2015 IEEE international conference on smart grid communications (SmartGridComm), IEEE, pp 872–878

  23. Haykin S (2000) Unsupervised adaptive filtering, volume I: Blind Source Separation. New York, NY, USA: Wiley

  24. Li D, Dick S (2018) Residential household non-intrusive load monitoring via graph-based multi-label semi-supervised learning. IEEE Trans Smart Grid 10(4):4615–4627

    Article  Google Scholar 

  25. Li D, Dick S (2017) A graph-based semi-supervised learning approach towards household energy disaggregation. In: 2017 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), IEEE, pp 1–7

  26. Barsim KS, Yang B (2015) Toward a semi-supervised non-intrusive load monitoring system for event-based energy disaggregation. In: 2015 IEEE global conference on signal and information processing (GlobalSIP), IEEE, pp 58–62

  27. Yang Y, Zhong J, Li W, Gulliver TA, Li S (2020) Semisupervised multilabel deep learning based nonintrusive load monitoring in smart grids. IEEE Trans Industr Inf 16(11):6892–6902

    Article  Google Scholar 

  28. Luo Y, Zhu J, Li M, Ren Y, Zhang B (2018) Smooth neighbors on teacher graphs for semi-supervised learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 8896–8905

  29. Matindife L, Sun Y, Wang Z (2021) Image-based mains signal disaggregation and load recognition. Compl Intell Syst 7(2):901–927

    Article  Google Scholar 

  30. Liang J, Ng SK, Kendall G, Cheng JW (2010) Load signature study-part i: Basic concept, structure, and methodology. IEEE Trans Power Deliver 25(2):551–560

    Article  Google Scholar 

  31. Wang AL, Chen BX, Wang CG, Hua D (2018) Non-intrusive load monitoring algorithm based on features of v–i trajectory. Electric Power Syst Res 157:134–144

    Article  Google Scholar 

  32. Oliver A, Odena A, Raffel C, Cubuk E, Goodfellow I (2018) Realistic evaluation of semi-supervised learning algortihms. In: International conference on Learning Representations, pp 1–15

  33. LeCun Y, Bengio Y, Hinton G (2015) Deep learning, nature 521(7553):436–444

    Article  Google Scholar 

  34. Gao J, Giri S, Kara EC, Bergés M (2014) PLAID: A public dataset of high-resoultion electrical appliance measurements for load identification research. In: Proc. 1st ACM Conf. Embedded Syst. Energy Efficient Build., pp 198–199

  35. Kahl M, Haq A, Kriechbaumer T (2016) WHITED—A worldwide household and industry transient energy data set. In: Proc. 3rd Int. Workshop Non Intrusive Load Monitor. (NILM), pp 1–4

  36. Kohavi R et al. (1995) A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Ijcai, vol. 14. Montreal, Canada, pp 1137–1145

  37. Gillis JM, Morsi WG (2016) Non-intrusive load monitoring using semi-supervised machine learning and wavelet design. IEEE Trans Smart Grid 8(6):2648–2655

    Article  Google Scholar 

  38. Sadeghianpourhamami N, Ruyssinck J, Deschrijver D, Dhaene T, Develder C (2017) Comprehensive feature selection for appliance classification in nilm. Energy Build 151:98–106

    Article  Google Scholar 

  39. He K, Stankovic L, Jing L, Stankovic V (2018) Non-intrusive load disaggregation using graph signal processing. IEEE Trans Smart Grid 9(3):1739–1747

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by National Natural Science Foundation of China (U1908213). Colleges and Universities in Hebei Province Science Research Program (QN2020504). The Fundamental Research Funds for the Central UniversitiesN2223001.

Author information

Authors and Affiliations

  1. School of Computer and Communication Engineering, Northeastern University at Qinhuangdao, Qinhuangdao, 066004, China

    Yinghua Han, Keke Li & Hantong Feng

  2. School of Control Engineering, Northeastern University at Qinhuangdao, Qinhuangdao, 066004, China

    Qiang Zhao

Authors
  1. Yinghua Han
    View author publications

    You can also search for this author inPubMed Google Scholar

  2. Keke Li
    View author publications

    You can also search for this author inPubMed Google Scholar

  3. Hantong Feng
    View author publications

    You can also search for this author inPubMed Google Scholar

  4. Qiang Zhao
    View author publications

    You can also search for this author inPubMed Google Scholar

Corresponding author

Correspondence to Keke Li.

Ethics declarations

Conflict of interest

The author declare that they have no conflict of interest.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Han, Y., Li, K., Feng, H. et al. Non-intrusive load monitoring based on semi-supervised smooth teacher graph learning with voltage–current trajectory. Neural Comput & Applic 34, 19147–19160 (2022). https://doi.org/10.1007/s00521-022-07508-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-022-07508-7

Keywords