hrcak mascot   Srce   HID

Tehnički vjesnik, Vol.25 No.5 Listopad 2018.

Izvorni znanstveni članak
https://doi.org/10.17559/TV-20170317203817

Non-Intrusive Electrical Load Monitoring System Applying Neural Networks with Combined Steady-State Electrical Variables

Diana Racines   ORCID icon orcid.org/0000-0001-9455-4984 ; Department of Electrical and Electronics Engineering, Universidad del Norte, Km 5 vía Puerto Colombia, Barranquilla, Colombia
John E. Candelo   ORCID icon orcid.org/0000-0002-9784-9494 ; Department of Electrical Energy and Automation, Universidad Nacional de Colombia, Cra. 80 No 65–223, Medellín, Colombia
Johny Montaña   ORCID icon orcid.org/0000-0002-9999-2366 ; Department of Electrical Engineering, Universidad Técnica Federico Santa María, Valparaíso, Chile

Puni tekst: engleski, pdf (1 MB) str. 1321-1329 preuzimanja: 38* citiraj
APA 6th Edition
Racines, D., Candelo, J.E. i Montaña, J. (2018). Non-Intrusive Electrical Load Monitoring System Applying Neural Networks with Combined Steady-State Electrical Variables. Tehnički vjesnik, 25 (5), 1321-1329. https://doi.org/10.17559/TV-20170317203817
MLA 8th Edition
Racines, Diana, et al. "Non-Intrusive Electrical Load Monitoring System Applying Neural Networks with Combined Steady-State Electrical Variables." Tehnički vjesnik, vol. 25, br. 5, 2018, str. 1321-1329. https://doi.org/10.17559/TV-20170317203817. Citirano 17.12.2018.
Chicago 17th Edition
Racines, Diana, John E. Candelo i Johny Montaña. "Non-Intrusive Electrical Load Monitoring System Applying Neural Networks with Combined Steady-State Electrical Variables." Tehnički vjesnik 25, br. 5 (2018): 1321-1329. https://doi.org/10.17559/TV-20170317203817
Harvard
Racines, D., Candelo, J.E., i Montaña, J. (2018). 'Non-Intrusive Electrical Load Monitoring System Applying Neural Networks with Combined Steady-State Electrical Variables', Tehnički vjesnik, 25(5), str. 1321-1329. doi: https://doi.org/10.17559/TV-20170317203817
Vancouver
Racines D, Candelo JE, Montaña J. Non-Intrusive Electrical Load Monitoring System Applying Neural Networks with Combined Steady-State Electrical Variables. Tehnički vjesnik [Internet]. 2018 [pristupljeno 17.12.2018.];25(5):1321-1329. doi: https://doi.org/10.17559/TV-20170317203817
IEEE
D. Racines, J.E. Candelo i J. Montaña, "Non-Intrusive Electrical Load Monitoring System Applying Neural Networks with Combined Steady-State Electrical Variables", Tehnički vjesnik, vol.25, br. 5, str. 1321-1329, 2018. [Online]. doi: https://doi.org/10.17559/TV-20170317203817

Sažetak
This paper presents a full electrical load identification model that considers steady-state parameters obtained easily from low-cost residential smart meters. The model was developed using neural networks including combinations of real power, current, impedance and admittance variables to identify the best input parameters. The monitoring model was improved by training one neural network to identify changing events and another neural network to identify the load state. The proposed model was tested using two different groups of residential loads: residential appliances measured in the laboratory and a public database of electrical measurements. The results show that the impedance model and a feedforward neural network achieved the best performance to characterise the load. In addition, when combining the different input parameters, those that consider impedance as an input parameter produced better results. The output provides simultaneous information about the operation state of all the loads before and after an event occurs.

Ključne riječi
energy efficiency; load characterization; neural networks; non-intrusive load monitoring method; smart meters

Hrčak ID: 207429

URI
https://hrcak.srce.hr/207429

Posjeta: 73 *