Integration of High-Frequency and Harmonic Measurements from Open-Source Meters into NILMTK Datasets |
|
C. Rodriguez-Navarro(1), F. Portillo(1), I. Robalo(1), L. Castro-Santos(2), A. Filgueira-Vizoso(3), F. G. 1. Departamento de Ingeniería, Escuela Superior de Ingeniería, Universidad de Almería, La Cañada de San Urbano, Almería (Spain) 2. Departamento de Enxeñaría Naval e Industrial, Centro de Investigación en Tecnoloxías Navais e Industriais (CITENI), Escola Politécnica de Enxeñaría de Ferrol, Universidade da Coruña 3. Departamento de Química, Centro de Investigación en Tecnoloxías Navais e Industriais (CITENI), Escola Politécnica de Enxeñaría de Ferrol,
2026-06-27 |
 |
Abstract
This work presents a methodology for generating datasets compatible with the Non-Intrusive Load Monitoring Toolkit (NILMTK) using measurements from open-source smart meters: OpenZmeter (oZm) and Open Multi Power Meter (OMPM). The purpose is to advance research on Non-Intrusive Load Monitoring by enabling detailed analysis of energy disaggregation and power quality. The main challenge is integrating data sources with extended timestamps and high-frequency electrical harmonics into the standardised NILMTK format. To solve this, custom data converters were developed for different versions of oZm (with and without harmonic support) and for OMPM (without harmonics). These converters transform HDF5/CSV data into NILMTK-compatible HDF5 structures, including up to ten electrical variables and conversion of 13-digit timestamps. Datasets with harmonic support provide 150 additional measurements of harmonics up to the 50th order. Modifications to NILMTK components enable recognition of these new formats. Results demonstrate the feasibility of extending NILMTK for advanced analysis in power-quality and energy-efficiency research.Key words: Dataset generation, Non-Intrusive Load Monitoring, NILMTK framework, Open-source smart meters, Power quality analysis.
Published in: Renewable Energies, Environment
& Power Quality Journal (REE&PQJ) |
|
| ISSUE: Vol. 26. No.3 | Pages: 385-390 |
| E-ISSN: 3020-531 X | Date of Current Version: 2026-06-27 |
| REF: 355-26 | Issue Date: 2026-07-15 |
| DOI:10.24084/reepqj26-355 | Publisher: AEDERMACP/ EA4EPQ |
References
[1] Juliano Souza, ‘Non-Intrusive Load Monitoring (NILM): An Introduction and practical example.’, https://www.linkedin.com/pulse/non-intrusive-load-monitoring-nilm-introduction-practical-souza-rpy4f/. Accessed: Mar. 11, 2025. [Online]. Available: https://www.linkedin.com/pulse/non-intrusive-load-monitoring-nilm-introduction-practical-souza-rpy4f/
[2] B. Nipun, K. Jack, P. Oliver, D. Haimonti, and K. William, ‘NILMTK: An Open Source Toolkit for Non-intrusive Load Monitoring’, Apr. 2014, doi: 10.1145/2602044.2602051.
[3] J. Kelly et al., ‘NILMTK v0.2: A non-intrusive load monitoring toolkit for large scale data sets’, in BuildSys 2014 - Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings, Association for Computing Machinery, Nov. 2014, pp. 182–183. doi: 10.1145/2674061.2675024.
[4] E. Viciana, A. Alcayde, F. G. Montoya, R. Baños, and F. Manzano-Agugliaro, ‘An open hardware design for internet of things power quality and energy saving solutions’, Sensors , vol. 19, no. 3, Feb. 2019, doi: 10.3390/s19030627.
[5] C. Rodríguez-Navarro, F. Portillo, F. Martínez, F. Manzano-Agugliaro, and A. Alcayde, ‘Development and Application of an Open Power Meter Suitable for NILM’, Inventions, vol. 9, no. 1, p. 2, Dec. 2023, doi: 10.3390/inventions9010002.
[6] R. Kukunuri et al., ‘NILMTK-Contrib: Towards reproducible state-of-the-art energy disaggregation’. [Online]. Available: https://github.com/nilmtk/buildsys2019-paper-notebooks
[7] J. Z. Kolter and M. J. Johnson, ‘REDD: A Public Data Set for Energy Disaggregation Research’, Cambridge, 2011. Accessed: Aug. 29, 2025. [Online]. Available: http://redd.csail.mit.edu/
[8] P. Oliver, F. Grant, H. April, B. Nipun, and K. Jack, ‘Dataport and NILMTK: A building data set designed for non-intrusive load monitoring.’, IEEE, 2015, Accessed: Apr. 21, 2022. [Online]. Available: https://ieeexplore.ieee.org/abstract/document/7418187/keywords
[9] S. Makonin, F. Popowich, L. Bartram, B. Gill, and I. V. Bajic, ‘AMPds: A Public Dataset for Load Disaggregation and Eco-Feedback Research.’, IEEE Electrical Power.
[10] C. Beckel, W. Kleiminger, R. Cicchetti, T. Staake, and S. Santini, ‘The ECO data set and the performance of non-intrusive load monitoring algorithms’, in BuildSys 2014 - Proceedings of the 1st ACM Conference on Embedded Systems for Energy-Efficient Buildings, Association for Computing Machinery, Nov. 2014, pp. 80–89. doi: 10.1145/2674061.2674064.
[11] A. Monacchi, D. Egarter, W. Elmenreich, S. D’Alessandro, and A. M. Tonello, ‘GREEND: An energy consumption dataset of households in Italy and Austria’, in 2014 IEEE International Conference on Smart Grid Communications, SmartGridComm 2014, 2015. doi: 10.1109/SmartGridComm.2014.7007698.
[12] C. Rodriguez-Navarro, ‘PhD thesis Explore the horizons of unbundling electricity consumption and emissions: innovations in hardware (OZM and OMPM) and open-source software’, Almeria, Oct. 2025. Accessed: Oct. 30, 2025. [Online]. Available: https://dialnet.unirioja.es/servlet/tesis?codigo=394849
|