Uma proposta de desagregação de energia baseada no Modelo Oculto de Markov
Abstract
The energy disaggregation allows us to separate the aggregate energy consumption of a household into its contributing appliances. In this work, we used an energy disaggregation method based on the building of Hidden Markov Models that describes the power demand of appliances and we proposed the use of Baum-Welch algorithm to the parameter estimation for the refrigerator and washing machine model. Each model was obtained and evaluated using the Tracebase and REDD Dataset. The results presents a general model for each appliance, which were constructed using until 7 training instances, so that the metrics presents a better convergence. Lastly, each model was adjusted to disaggregate the energy.
Keywords:
Aprendizagem de Máquina, Inteligência Artificial, Matemática Computacional
References
Hart, G. W. (1992). Nonintrusive appliance load monitoring. Proceedings of the IEEE, 80(12):1870–1891.
Kim, H., Marwah, M., Arlitt, M., Lyon, G., and Han, J. (2011). Unsupervised disaggregation of low frequency power measurements. In Proceedings of the 2011 SIAM international conference on data mining, pages 747–758. SIAM.
Kolter, J. Z. and Johnson, M. J. (2011). Redd: A public data set for energy disaggregation research. In Workshop on data mining applications in sustainability (SIGKDD), San Diego, CA, volume 25, pages 59–62.
Kong, W., Dong, Z. Y., Ma, J., Hill, D. J., Zhao, J., and Luo, F. (2016). An extensible approach for non-intrusive load disaggregation with smart meter data. IEEE Transactions on Smart Grid, 9(4):3362–3372.
Kwak, Y., Hwang, J., and Lee, T. (2018). Load disaggregation via pattern recognition: A feasibility study of a novel method in residential building. Energies, 11(4):1008.
Lam, H. Y., Fung, G., and Lee, W. (2007). A novel method to construct taxonomy electrical appliances based on load signaturesof. IEEE Transactions on Consumer Electronics, 53(2):653–660.
Parson, O., Ghosh, S., Weal, M., and Rogers, A. (2012). Non-intrusive load monitoring using prior models of general appliance types. In Twenty-Sixth AAAI Conference on Articial Intelligence.
Parson, O., Ghosh, S., Weal, M., and Rogers, A. (2014). An unsupervised training method for non-intrusive appliance load monitoring. Articial Intelligence, 217:1–19.
Reinhardt, A., Baumann, P., Burgstahler, D., Hollick, M., Chonov, H., Werner, M., and Steinmetz, R. (2012). On the accuracy of appliance identication based on distributed load metering data. In 2012 Sustainable Internet and ICT for Sustainability (SustainIT), pages 1–9. IEEE.
Sammut, C. and Webb, G. I. (2011). Encyclopedia of machine learning. Springer Science & Business Media.
Schreiber, J. (2017). Pomegranate: fast and exible probabilistic modeling in python. The Journal of Machine Learning Research, 18(1):5992–5997.
Stamp, M. (2017). Introduction to machine learning with applications in information security. Chapman and Hall/CRC.
Kim, H., Marwah, M., Arlitt, M., Lyon, G., and Han, J. (2011). Unsupervised disaggregation of low frequency power measurements. In Proceedings of the 2011 SIAM international conference on data mining, pages 747–758. SIAM.
Kolter, J. Z. and Johnson, M. J. (2011). Redd: A public data set for energy disaggregation research. In Workshop on data mining applications in sustainability (SIGKDD), San Diego, CA, volume 25, pages 59–62.
Kong, W., Dong, Z. Y., Ma, J., Hill, D. J., Zhao, J., and Luo, F. (2016). An extensible approach for non-intrusive load disaggregation with smart meter data. IEEE Transactions on Smart Grid, 9(4):3362–3372.
Kwak, Y., Hwang, J., and Lee, T. (2018). Load disaggregation via pattern recognition: A feasibility study of a novel method in residential building. Energies, 11(4):1008.
Lam, H. Y., Fung, G., and Lee, W. (2007). A novel method to construct taxonomy electrical appliances based on load signaturesof. IEEE Transactions on Consumer Electronics, 53(2):653–660.
Parson, O., Ghosh, S., Weal, M., and Rogers, A. (2012). Non-intrusive load monitoring using prior models of general appliance types. In Twenty-Sixth AAAI Conference on Articial Intelligence.
Parson, O., Ghosh, S., Weal, M., and Rogers, A. (2014). An unsupervised training method for non-intrusive appliance load monitoring. Articial Intelligence, 217:1–19.
Reinhardt, A., Baumann, P., Burgstahler, D., Hollick, M., Chonov, H., Werner, M., and Steinmetz, R. (2012). On the accuracy of appliance identication based on distributed load metering data. In 2012 Sustainable Internet and ICT for Sustainability (SustainIT), pages 1–9. IEEE.
Sammut, C. and Webb, G. I. (2011). Encyclopedia of machine learning. Springer Science & Business Media.
Schreiber, J. (2017). Pomegranate: fast and exible probabilistic modeling in python. The Journal of Machine Learning Research, 18(1):5992–5997.
Stamp, M. (2017). Introduction to machine learning with applications in information security. Chapman and Hall/CRC.
Published
2020-10-26
How to Cite
FONTES, Igor; FREITAS, Cristopher; DOS SANTOS, Eduardo; AQUINO, Andre.
Uma proposta de desagregação de energia baseada no Modelo Oculto de Markov. In: REGIONAL SCHOOL ON COMPUTING OF BAHIA, ALAGOAS, AND SERGIPE (ERBASE), 20. , 2020, Arapiraca-AL.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2020
.
p. 21-30.
