Fast Short-Term Electrical Load Forecasting under High Meteorological Variability with a Multiple Equation Time Series Approach

Authors: Charline David, Alexandre Blondin Massé, Arnaud Zinflou

Abstract:

We present a multiple equation time series approach for the short-term load forecasting applied to the electrical power load consumption for the whole Quebec province, in Canada. More precisely, we take into account three meteorological variables — temperature, cloudiness and wind speed —, and we use meteorological measurements taken at different locations on the territory. Our final model shows an average MAPE score of 1.79% over an 8-years dataset.

Keywords: Short-term load forecasting, special days, time series, multiple equations, parallelization, clustering.

References:

[1] M. Grenier, “Short-term load forecasting at hydro-qu´ebec trans´energie,” in 2006 IEEE Power Engineering Society General Meeting. IEEE, 2006, pp. 5–pp.
[2] J. R. Cancelo, A. Espasa, and R. Grafe, “Forecasting the electricity load from one day to one week ahead for the spanish system operator,” International Journal of forecasting, vol. 24, no. 4, pp. 588–602, 2008.
[3] A. E. Clements, A. Hurn, and Z. Li, “Forecasting day-ahead electricity load using a multiple equation time series approach,” European Journal of Operational Research, vol. 251, no. 2, pp. 522–530, 2016.
[4] M. Rafiei, T. Niknam, J. Aghaei, M. Shafie-Khah, and J. P. Catal˜ao, “Probabilistic load forecasting using an improved wavelet neural network trained by generalized extreme learning machine,” IEEE Transactions on Smart Grid, vol. 9, no. 6, pp. 6961–6971, 2018.
[5] C. Feng and J. Zhang, “Assessment of aggregation strategies for machine-learning based short-term load forecasting,” Electric Power Systems Research, vol. 184, p. 106304, 2020.
[6] M. Santamouris, C. Cartalis, A. Synnefa, and D. Kolokotsa, “On the impact of urban heat island and global warming on the power demand and electricity consumption of buildings—a review,” Energy and buildings, vol. 98, pp. 119–124, 2015.
[7] V. Kondaiah, B. Saravanan, P. Sanjeevikumar, and B. Khan, “A review on short-term load forecasting models for micro-grid application,” The Journal of Engineering, 2022.
[8] S. Maldonado, A. Gonz´alez, and S. Crone, “Automatic time series analysis for electric load forecasting via support vector regression,” Applied Soft Computing, vol. 83, p. 105616, 2019.
[9] J. Wang and J. Hu, “A robust combination approach for short-term wind speed forecasting and analysis–combination of the arima (autoregressive integrated moving average), elm (extreme learning machine), svm (support vector machine) and lssvm (least square svm) forecasts using a gpr (gaussian process regression) model,” Energy, vol. 93, pp. 41–56, 2015.
[10] H. S. Hippert, C. E. Pedreira, and R. C. Souza, “Neural networks for short-term load forecasting: A review and evaluation,” IEEE Transactions on power systems, vol. 16, no. 1, pp. 44–55, 2001.
[11] X. Zhang and J. Wang, “A novel decomposition-ensemble model for forecasting short-term load-time series with multiple seasonal patterns,” Applied Soft Computing, vol. 65, pp. 478–494, 2018.
[12] M. Aouad, H. Hajj, K. Shaban, R. A. Jabr, and W. El-Hajj, “A cnn-sequence-to-sequence network with attention for residential short-term load forecasting,” Electric Power Systems Research, vol. 211, p. 108152, 2022.
[13] C. Feng, M. Sun, and J. Zhang, “Reinforced deterministic and probabilistic load forecasting via q-learning dynamic model selection,” IEEE Transactions on Smart Grid, vol. 11, no. 2, pp. 1377–1386, 2019.
[14] R.-J. Park, K.-B. Song, and B.-S. Kwon, “Short-term load forecasting algorithm using a similar day selection method based on reinforcement learning,” Energies, vol. 13, no. 10, p. 2640, 2020.
[15] D. Wu, C. Cui, and B. Boulet, “Residential short-term load forecasting via meta learning and domain augmentation,” in IFIP International Workshop on Artificial Intelligence for Knowledge Management. Springer, 2021, pp. 184–196.
[16] W. Lin, D. Wu, and B. Boulet, “Spatial-temporal residential short-term load forecasting via graph neural networks,” IEEE Transactions on Smart Grid, vol. 12, no. 6, pp. 5373–5384, 2021.
[17] G. Joshi, R. Walambe, and K. Kotecha, “A review on explainability in multimodal deep neural nets,” IEEE Access, vol. 9, pp. 59 800–59 821, 2021.
[18] R. Ramanathan, R. Engle, C. W. Granger, F. Vahid-Araghi, and C. Brace, “Short-run forecasts of electricity loads and peaks,” International journal of forecasting, vol. 13, no. 2, pp. 161–174, 1997.
[19] H. Spliid, “A fast estimation method for the vector autoregressive moving average model with exogenous variables,” Journal of the American Statistical Association, vol. 78, no. 384, pp. 843–849, 1983.
[20] R. E. Huschke et al., “Glossary of meteorology,” 1959.
[21] J. Mabille, S. Corlay, and W. Vollprecht, “xtensor: A C++ library for multi-dimensional arrays with broadcasting and lazy computing,” 2016, https://github.com/xtensor-stack/xtensor.git.
[22] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay, “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
[23] X. Y. Stella and J. Shi, “Multiclass spectral clustering,” in Computer Vision, IEEE International Conference on, vol. 2. IEEE Computer Society, 2003, pp. 313–313.
[24] T. Zhang, R. Ramakrishnan, and M. Livny, “Birch: an efficient data clustering method for very large databases,” ACM sigmod record, vol. 25, no. 2, pp. 103–114, 1996.
[25] D. Sculley, “Web-scale k-means clustering,” in Proceedings of the 19th international conference on World wide web, 2010, pp. 1177–1178.
[26] T. Williams, C. Kelley, and many others, “Gnuplot 5.2.8: An interactive plotting program,” http://gnuplot.sourceforge.net/, December 2019.