On the use of Image-Based Feature Extraction for Non-Intrusive Load Monitoring: : A Comparative Analysis of Techniques and Window Sizes

Juan Salin Corrêa; Ricardo Augusto Souza Fernandes

doi:10.22456/2175-2745.150978

Authors

Juan Salin Corrêa Universidade de São Paulo (USP) https://orcid.org/0000-0002-1901-802X
Ricardo Augusto Souza Fernandes Universidade de São Paulo (USP) https://orcid.org/0000-0003-2361-6505

DOI:

https://doi.org/10.22456/2175-2745.150978

Keywords:

convolutional neural network, recurrence plot, gramian angular field, non-intrusive load monitoring

Abstract

The techniques of Non-Intrusive Load Monitoring (NILM) aim to label or disaggregate loads into time series of electrical energy consumption, mainly in the context of residential consumers, considering the optimization of electricity usage in demand response programs. In this sense, many researches have been developed with different methodologies of consumption time series transformation into images, which consider different window sizes. Thus, this work compares and analyzes different transformation techniques for window sizes ranging from 1 to 10 minutes, verifying how the Convolutional Neural Network models behave for different loads from the UK-DALE (The United Kingdom - Domestic Appliance-Level Electricity dataset). Through the proposed methodology, it was possible to obtain f1-scores higher than 90% for three of the five considered loads, demonstrating the robustness of the time-series transformation into images.

Downloads

Download data is not yet available.

References

[1] FONSECA, A. L. da; CHVATAL, K. M.; FERNANDES, R. A. Thermal comfort maintenance in demand response programs: A critical review. Renewable and Sustainable Energy Reviews, Elsevier, v. 141, p. 110847, 2021.

[2] DARBY, S. Energy feedback in buildings: improving the infrastructure for demand reduction. Building Research & Information, Informa UK Limited, v. 36, n. 5, p. 499–508, out. 2008. ISSN 1466-4321.

[3] HART, G. Nonintrusive appliance load monitoring. Proceedings of the IEEE, v. 80, n. 12, p. 1870–1891, 1992.

[4] LI, M. et al. Dynamic time warping optimization-based non-intrusive load monitoring for multiple household appliances. International Journal of Electrical Power & Energy Systems, Elsevier BV, v. 159, p. 110002, ago. 2024. ISSN 0142-0615.

[5] AGUIAR, E. L. de et al. ST-NILM: A wavelet scattering-based architecture for feature extraction and multilabel classification in NILM signals. IEEE Sensors Journal, Institute of Electrical and Electronics Engineers (IEEE), v. 24, n. 7, p. 10540–10550, abr. 2024. ISSN 2379-9153.

[6] WENNINGER, M. et al. Recurrence plot spatial pyramid pooling network for appliance identification in non-intrusive load monitoring. In: 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA). [S.l.]: IEEE, 2021. p. 108–115.

[7] LIANG, J. et al. Load signature study—part I: Basic concept, structure, and methodology. IEEE Transactions on Power Delivery, v. 25, n. 2, p. 551–560, 2009.

[8] CAVALCA, D. L.; FERNANDES, R. A. S. Recurrence plots and convolutional neural networks applied to nonintrusive load monitoring. In: 2020 IEEE Power Energy Society General Meeting (PESGM). [S.l.: s.n.], 2020. p. 1–5.

[9] KIM, H.; LIM, S. Temporal patternization of power signatures for appliance classification in NILM. Energies, v. 14, n. 10, 2021.

[10] LANGEVIN, A. et al. Energy disaggregation using variational autoencoders. Energy and Buildings, v. 254, p. 111623, 2022.

[11] ZHANG, B. et al. GT-NILM: A generative, transferable non-intrusive load monitoring system based on conditional diffusion models and convolutional neural networks. IEEE Transactions on Consumer Electronics, Institute of Electrical and Electronics Engineers (IEEE), p. 1–1, 2025. ISSN 1558-4127.

[12] WANG, J.; CHENG, L. An improved YOLOv8-XGBoost load rapid identification method based on multi-feature fusion. International Journal of Electrical Power & Energy Systems, Elsevier BV, v. 166, p. 110573, maio 2025. ISSN 0142-0615.

[13] MARWAN, N. et al. Recurrence plots for the analysis of complex systems. Physics Reports, v. 438, p. 237–329, 2007.

[14] ECKMANN, J.-P.; KAMPHORST, S. O.; RUELLE, D. Recurrence plots of dynamical systems. Europhys. Letters, v. 4, n. 9, p. 973–977, 1987.

[15] GRABEN, P. b. et al. Optimal estimation of recurrence structures from time series. EPL (Europhysics Letters), v. 114, n. 3, p. 38003, 2016.

[16] KELLY, J.; KNOTTENBELT, W. The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes. Scientific Data, v. 2, n. 150007, 2015.