Deep Learning Based Electricity Demand Forecasting in Different Domains

Imani, M.

doi:10.5829/ijee.2020.11.01.06

Document Type : Original Article

Author

M. Imani

Faculty of Electrical and Computer Engineering, Tarbiat Modares University, Tehran, Iran

https://doi.org/10.5829/ijee.2020.11.01.06

Abstract

Electricity demand forecasting is an important task in power grids. Most of researches on electrical load forecasting have been done in the time domain. But, the electrical time series has a non-stationary inherence that makes hard load prediction. Moreover, valuable information is hidden in the electrical load sequence which is not open in the time domain. To deal with these difficulties, a new electricity demand forecasting framework is proposed in this work. In the proposed framework, at first, a new feature space of electrical load sequence is composed. The provided domain involves complementary information about shape and variations of electrical load sequence. Then, the obtained load features are integrated with the original load values in time domain to allow a rich input for predictor. Finally, a powerful deep learning technique from the family of recurrent neural networks, named long-short term memory, is used to learn electricity demand from the provided features in single and hybrid domains. The following domains are investigated in this work: frequency, cepstrum, spectral centroid, spectral roll-off, spectral flux, energy, time difference, frequency difference, Gabor and collaborative representation. The experiments show that the use of time difference domain decreases the mean absolute percent error from 0.0332 to 0.0056.

Keywords

References

1. Sahay, K.B. and Rana, V., 2015. One hour ahead load forecast of PJM electricity market & UPPCL. In 2015 International Conference on Energy Economics and Environment, IEEE, pp. 1-6.

2. Ali, M., Adnan, M. and Tariq, M., 2019. Optimum control strategies for short term load forecasting in smart grids. International Journal of Electrical Power & Energy Systems, 113, pp.792-806.

3. Torabi, M., Hashemi, S., Saybani, M.R., Shamshirband, S. and Mosavi, A., 2019. A Hybrid clustering and classification technique for forecasting short‐term energy consumption. Environmental Progress & Sustainable Energy, 38(1), pp.66-76.

4. Quilumba, F.L., Lee, W.J., Huang, H., Wang, D.Y. and Szabados, R.L., 2014. Using smart meter data to improve the accuracy of intraday load forecasting considering customer behavior similarities. IEEE Transactions on Smart Grid, 6(2), pp.911-918.

5. Du, X., Bai, J. and Fan, Q., 2011. Study of the medium-long load forecasting based on the identical dimension addition grey model. In 2011 Second International Conference on Mechanic Automation and Control Engineering, IEEE, pp. 700-703.

6. Carmo, D.L., Souza, R.C. and Barbosa, C.R.H., 2020. Partial decomposition approach to generate load curve forecasting scenarios. International Journal of Electrical Power & Energy Systems, 115, p.105436.

7. Kumar, S., Mishra, S. and Gupta, S., 2016, February. Short term load forecasting using ANN and multiple linear regression. In 2016 Second International Conference on Computational Intelligence & Communication Technology, IEEE, pp. 184-186.

8. Liu, S.T., Huang, S.R. and Hsien, T.Y., 2005. Optimal identification of self-reunion multiple regression (SRMR) model based on regression function for short-term load forecasting. In 2005 International Power Engineering Conference, IEEE, pp. 1-46.

9. Wei, W., Yin, Q., Bai, Y., Bao, H., Fang, C. and Yang, J., 2013. Regional load forecasting method based on the S-curve power business expansion. In 2013 IEEE International Conference of IEEE Region 10, IEEE, pp. 1-4.

10. Matsumoto, T., Nakajima, Y., Saito, M., Sugi, J. and Hamagishi, H., 2001. Reconstructions and predictions of nonlinear dynamical systems: A hierarchical Bayesian approach. IEEE transactions on signal processing, 49(9), pp.2138-2155.

11. Taylor, J.W. and McSharry, P.E., 2007. Short-term load forecasting methods: An evaluation based on european data. IEEE Transactions on Power Systems, 22(4), pp.2213-2219.

12. El Desouky, A.A. and El Kateb, M.M., 2000. Hybrid adaptive techniques for electric-load forecast using ANN and ARIMA. IEE Proceedings-Generation, Transmission and Distribution, 147(4), pp.213-217.

13. Vrablecová, P., Ezzeddine, A.B., Rozinajová, V., Šárik, S. and Sangaiah, A.K., 2018. Smart grid load forecasting using online support vector regression. Computers & Electrical Engineering, 65, pp.102-117.

14. Jiang, H., Zhang, Y., Muljadi, E., Zhang, J.J. and Gao, D.W., 2016. A short-term and high-resolution distribution system load forecasting approach using support vector regression with hybrid parameters optimization. IEEE Transactions on Smart Grid, 9(4), 3341-3350.

15. Perfumo, C., Braslavsky, J.H. and Ward, J.K., 2014. Model-based estimation of energy savings in load control events for thermostatically controlled loads. IEEE Transactions on Smart Grid, 5(3), pp.1410-1420.

16. Srinivasan, D., Tan, S.S., Chang, C.S. and Chan, E.K., 1998. Practical implementation of a hybrid fuzzy neural network for one-day-ahead load forecasting. IEE Proceedings-Generation, Transmission and Distribution, 145(6), pp.687-692.

17. Mota, L.T.M., Mota, A.A. and Morelato, A., 2007. Load behaviour prediction under blackout conditions using a fuzzy expert system. IET Generation, Transmission & Distribution, 1(3), pp.379-387.

18. Nose-Filho, K., Lotufo, A.D.P. and Minussi, C.R., 2011. Short-term multinodal load forecasting using a modified general regression neural network. IEEE Transactions on Power Delivery, 26(4), pp.2862-2869.

19. Quan, H., Srinivasan, D. and Khosravi, A., 2013. Short-term load and wind power forecasting using neural network-based prediction intervals. IEEE Transactions on Neural Networks and Learning Systems, 25(2), pp.303-315.

20. Samet, H., Reisi, M. and Marzbani, F., 2019. Evaluation of neural network-based methodologies for wind speed forecasting. Computers & Electrical Engineering, 78, pp.356-372.

21. Bebis, G. and Georgiopoulos, M., 1994. Feed-forward neural networks. IEEE Potentials, 13(4), pp.27-31.

22. Shao, H., 2008. Delay-dependent stability for recurrent neural networks with time-varying delays. IEEE Transactions on Neural networks, 19(9), pp.1647-1651.

23. Wang, S., Wang, X., Wang, S. and Wang, D., 2019. Bi-directional long short-term memory method based on attention mechanism and rolling update for short-term load forecasting. International Journal of Electrical Power & Energy Systems, 109, pp.470-479.

24. Alawe, I., Ksentini, A., Hadjadj-Aoul, Y. and Bertin, P., 2018. Improving traffic forecasting for 5G core network scalability: A Machine Learning approach. IEEE Network, 32(6), pp.42-49.

25. Kaur, A. and Singh, A., 2016. Power-Normalized Cepstral Coefficients (PNCC) for Punjabi Automatic Speech Recognition using phone based modelling in HTK. In 2016 2nd International Conference on Applied and Theoretical Computing and Communication Technology, IEEE, pp. 372-375.

26. Theodoridis, S. and Koutroumbas, K., 2010. Pattern recognition & Matlab intro. Academic Press, Inc..

27. Commission for Energy Regulation (CER) Smart Metering Project, 2009-2010 Dataset, Electricity Customer Behaviour Trial, 1st Edition. Irish Social Science Data Archive. SN: 0012-00. www.ucd.ie/issda/CER-electricity, 2012.

Iranica Journal of Energy & Environment

Deep Learning Based Electricity Demand Forecasting in Different Domains

References

References

Volume 11, Issue 1
March 2020
Pages 33-39

Deep Learning Based Electricity Demand Forecasting in Different Domains

References

References

Volume 11, Issue 1March 2020Pages 33-39

Volume 11, Issue 1
March 2020
Pages 33-39