Uma arquitetura de aprendizagem profunda para desagregação de energia

• Eduardo Santos UFAL
• Cristopher Freitas UFAL
• André Aquino UFAL

Resumo

Desagregação de energia busca distinguir o consumo de energia elétrica de diferentes dispositivos ligados a um único canal, de forma não intrusiva a partir de um único ponto de medição. Aprendizagem profunda tem se mostrado promissora nesse campo, visto que já apresentam melhores resultados quando comparadas à modelos anteriores que não fazem o uso como o FHMM (Factorial Hidden Markov Model). Nesse trabalho, utilizamos a base da dados UK-DALE, na qual fizemos um pré-processamento e aplicamos uma rede neural com camadas convolucionais (CNN) para desagregação de energia. Dessa forma conseguimos uma melhora de 13.74% e 14.92% em média em duas métricas usadas em comparação à trabalhos anteriores.

Referências

Batra, N., Kelly, J., Parson, O., Dutta, H., Knottenbelt,W., Rogers, A., Singh, A., and Srivastava, M. (2014). Nilmtk: an open source toolkit for non-intrusive load monitoring. In Proceedings of the 5th international conference on Future energy systems, pages 265–276. ACM.

Bengio, Y. et al. (2009). Learning deep architectures for ai. Foundations and trends R in Machine Learning, 2(1):1–127.

Goodfellow, I., Bengio, Y., and Courville, A. (2016). Deep learning. MIT press.

Kelly, J. and Knottenbelt, W. (2015a). Neural nilm: Deep neural networks applied to energy disaggregation. In Proceedings of the 2nd ACM International Conference on Embedded Systems for Energy-Efficient Built Environments, pages 55–64. ACM.

Kelly, J. and Knottenbelt, W. (2015b). The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes. Scientific Data, 2(150007).

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 Jaakkola, T. (2012). Approximate inference in additive factorial hmms with application to energy disaggregation. In Artificial intelligence and statistics, pages 1472–1482.

Mauch, L. and Yang, B. (2015). A new approach for supervised power disaggregation by using a deep recurrent lstm network. In 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP), pages 63–67. IEEE.

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 Artificial Intelligence.

Sirojan, T., Phung, B., and Ambikairajah, E. (2018). Deep neural network based energy disaggregation. In 2018 IEEE International Conference on Smart Energy Grid Engineering (SEGE), pages 73–77. IEEE.

Tabatabaei, S. M., Dick, S., and Xu, W. (2017). Toward non-intrusive load monitoring via multi-label classification. IEEE Transactions on Smart Grid, 8(1):26–40.

Utgoff, P. E. and Stracuzzi, D. J. (2002). Many-layered learning. Neural Computation, 14(10):2497–2529.

Xiao, P. and Cheng, S. (2019). Neural network for nilm based on operational state change classification. arXiv preprint arXiv:1902.02675.

Zhang, C., Zhong, M., Wang, Z., Goddard, N., and Sutton, C. (2018). Sequence-to-point learning with neural networks for non-intrusive load monitoring. In Thirty-Second AAAI Conference on Artificial Intelligence.

Zhao, B., Stankovic, L., and Stankovic, V. (2015). Blind non-intrusive appliance load monitoring using graph-based signal processing. In 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP), pages 68–72. IEEE.

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