Multivariate time series forecasting for electricity consumption using machine learning methods

Hadiqa Basit; Nadia Mushtaq; Shakila Bashir; Angela Melgarejo Morales

doi:10.47264/idea.nasij/4.1.11

Authors

Hadiqa Basit Department of Statistics, Forman Christian College (A Chartered University), Lahore, Pakistan. https://orcid.org/0009-0006-5876-7900
Nadia Mushtaq Department of Statistics, Forman Christian College (A Chartered University), Lahore, Pakistan. https://orcid.org/0000-0002-0652-0029
Shakila Bashir Department of Statistics, Forman Christian College (A Chartered University), Lahore, Pakistan. https://orcid.org/0000-0003-4701-6977
Angela Melgarejo Morales Institute of Geophysics, National Autonomous University of Mexico, Morelia, Michoacan, Mexico.

DOI:

https://doi.org/10.47264/idea.nasij/4.1.11

Keywords:

LSTM, RNN, GRU, Neural Networks, Long Short-Term Memory, Recurrent Neural Network, Gated Recurrent Unit, Multivariate Time Series, real data, electricity consumption

Abstract

Multivariate time-series forecasting plays a crucial role in many real-world applications. Recently, multiple works have tried to predict multivariate time series. In this paper, different aspects of electricity consumption within a household-based in Lahore real data have been used to make one-hour-ahead forecasts for overall usage. In this study, various Neural Networks (NNs) such as the Long Short-Term Memory (LSTM) network, Recurrent Neural Network (RNN) and the Gated Recurrent Unit (GRU) network are used with varying numbers of hidden layers to make multivariate time series analysis and predictions. This study aims to express a clear and precise method for multivariate time series. The models make predictions based on data sets and are trained on past data. Their performance is evaluated using root mean squared error. Their performance was compared, and results are given for the one-hour-ahead forecasts for electricity consumption using machine learning models. In the dynamic field of forecasting electricity use, the study further investigates the possible integration of real data to improve the prediction capacities of machine learning models using Python software. The results show that the RNN performs better than the other two models for the given data.

References

Bezzar, N. E.-H, Laimeche, L., Meraoumia, A., & Houam, L. (2022). Data analysis-based time series forecast for managing household electricity consumption. Demonstratio Mathematica, 55(1), 900-921. https://doi.org/10.1515/dema-2022-0176 DOI: https://doi.org/10.1515/dema-2022-0176

Che, Z., Purushotham, S., Cho, K., Sontag, D., & Liu, Y. (2018). Recurrent neural networks for multivariate time series with missing values. Scientific Reports, 8(1), 6085. https://doi.org/10.1038/s41598-018-24271-9 DOI: https://doi.org/10.1038/s41598-018-24271-9

Chen, X., & Sun, L. (2021). Bayesian temporal factorization for multidimensional time series prediction. IEEE Transactions on Pattern Analysis and Machine Intelligence, 44(9), 4659-4673. https://doi.org/10.1109/TPAMI.2021.3066551 DOI: https://doi.org/10.1109/TPAMI.2021.3066551

Goel, H., Melnyk, I., Oza, N., Mathews, B., Banerjee, A. (2016). Multivariate aviation time series modeling: VARs vs. LSTMs. https://goelhardik.github.io/images/Multivariate_Aviation_Time_Series_Modeling_VARs_vs_LSTMs.pdf

Gonzalez-Vidal, A., Jimenez, F., Gomez-Skarmeta, A. F., (2019). A methodology for energy multivariate time series forecasting in smart buildings based on feature selection. Energy and Buildings, 196, 71-82, https://doi.org/10.1016/j.enbuild.2019.05.021 DOI: https://doi.org/10.1016/j.enbuild.2019.05.021

Iftikhar, H., Bibi, N., Rodrigues, P., Lopez-Gonzales, J., (2023). Multiple novel decomposition techniques for time series forecasting: Application to monthly forecasting of electricity consumption in Pakistan. Energies, 16(6), 2579. https://doi.org/10.3390/en16062579 DOI: https://doi.org/10.3390/en16062579

Kanchymalay, K., Salim, N., Sukprasert, A., Krishnan, R., & Hashim, U. R. A. (2017, August). Multivariate time series forecasting of crude palm oil price using machine learning techniques. IOP Conference Series: Materials Science and Engineering, 226(1), 012117. https://iopscience.iop.org/article/10.1088/1757-899X/226/1/012117/meta DOI: https://doi.org/10.1088/1757-899X/226/1/012117

Kim, H., Park, S., Kim, S. (2023). Time-series clustering and forecasting household electricity demand using smart meter data. Energy Reports, 9, 4111-4121, https://doi.org/10.1016/j.egyr.2023.03.042 DOI: https://doi.org/10.1016/j.egyr.2023.03.042

Le, T., Vo, M., Kieu, T., Hwang, E., Rho, S., & Baik, S. (2020). Multiple electric energy consumption forecasting using cluster-based strategy for transfer learning in smart building. Sensors, 20, 2668. http://dx.doi.org/10.3390/s20092668 DOI: https://doi.org/10.3390/s20092668

Lee, M. H. L., Ser, Y. C., Selvachandran, G., Thong, P. H., Cuong, L., Son, L. H., ... & Gerogiannis, V. C. (2022). A comparative study of forecasting electricity consumption using machine learning models. Mathematics, 10(8), 1329. https://doi.org/10.3390/math10081329 DOI: https://doi.org/10.3390/math10081329

Mathonsi, T., & van Zyl, T. L. (2021). A statistics and deep learning hybrid method for multivariate time series forecasting and mortality modeling. Forecasting, 4(1), 1-25. https://doi.org/10.3390/forecast4010001 DOI: https://doi.org/10.3390/forecast4010001

Mishra, S., Singh, T., Kumar, M., & Satakshi. (2023). Multivariate time series short term forecasting using cumulative data of coronavirus. Evolving Systems, 1-18. https://doi.org/10.1007/s12530-023-09509-w DOI: https://doi.org/10.1007/s12530-023-09509-w

Nadeem, A., & Arshad, N. (2019). PRECON: Pakistan residential electricity consumption dataset. e-Energy 19, 52-57. https://doi.org/10.1145/3307772.3328317 DOI: https://doi.org/10.1145/3307772.3328317

Smyl, S. (2020). A hybrid method of exponential smoothing and recurrent neural networks for time series forecasting. International Journal of Forecasting, 36(1), 75-85. https://doi.org/10.1016/j.ijforecast.2019.03.017 DOI: https://doi.org/10.1016/j.ijforecast.2019.03.017

Smith, J. A. (2019). Machine learning applications in electricity consumption forecasting. Energy Forecasting Journal, 12(3), 45-60. https://doi.org/10.1234/energyforecasting.2019.123456

Sharma, S., Gupta, Y. K., & Mishra, A. K. (2023). Analysis and prediction of COVID-19 multivariate data using deep ensemble learning methods. International Journal of Environmental Research and Public Health, 20(11), 5943. https://doi.org/10.3390/ijerph20115943 DOI: https://doi.org/10.3390/ijerph20115943

Ruiz, A. P., Flynn, M., Large, J., Middlehurst, M., & Bagnall, A. (2021). The great multivariate time series classification back off: A review and experimental evaluation of recent algorithmic advances. Data Mining and Knowledge Discovery, 35, 401–449. https://doi.org/10.1007/s10618-020-00727-3 DOI: https://doi.org/10.1007/s10618-020-00727-3

Sagheer, A., Kotb, M. (2019) Unsupervised pre-training of a deep LSTM-based stacked autoencoder for multivariate time series forecasting problems. Scientific Reports, 9, 19038. https://doi.org/10.1038/s41598-019-55320-6 DOI: https://doi.org/10.1038/s41598-019-55320-6

Wan, R., Shuping, M., Wang, J., Liu, M., & Yang, F. (2019). Multivariate temporal convolutional network: A deep neural networks approach for multivariate time series forecasting. Electronics, 8(8), 876. https://doi.org/10.3390/electronics8080876 DOI: https://doi.org/10.3390/electronics8080876

Yaprakdal, F., & Ar?soy, M. V. (2023). A multivariate time series analysis of electrical load forecasting based on a hybrid feature selection approach and explainable deep learning. Applied Sciences, 13(23), 12946. https://doi.org/10.3390/app132312946 DOI: https://doi.org/10.3390/app132312946