Abstract
Energy consumption forecasting has known a big interest in the last few years due to its important role in the smart grid domain. It helps to manage and dispatch the smart grid energy sources. Furthermore, load consumption predictions and scheduling of the generation resources to satisfy the demand side enable minimizing the energy generation cost. This paper represents multi-horizons electrical energy forecasting models developed using LSTM, BI-LSTM, unidimensional convolution neural network (1DCNN) and an individual household energy consumption dataset. In addition, a comparative study is exhibited between three forecasting horizons: two hours, four hours, and eight hours. The results show that LTSM and bi-LSTM-based prediction models’ mean squared error (MSE) increases by increasing the prediction horizon. In contrast, 1DCNN based prediction model's MSE decreases by increasing the forecasting horizon.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Liu, T., Chengliang, X., Chen, H., Li, Z.: Study on deep reinforcement learning techniques for building energy consumption forecasting. Energy Build. (2019). https://doi.org/10.1016/j.enbuild.2019.109675
Syed, D., Abu-Rub, H., Ghrayeb, A., Refaat, S.S.: Household-level energy forecasting in smart buildings using a novel hybrid deep learning model. IEEE Access 9, 33498–33511 (2021). https://doi.org/10.1109/ACCESS.2021.3061370
Jrhilifa, I., Ouadi, H., Jilbab, A.: Smart home's wireless sensor networks lifetime optimizing using Q-learning. In: IECON 2021 – 47th Annual Conference of the IEEE Industrial Electronics Society, pp. 1–6 (2021). https://doi.org/10.1109/IECON48115.2021.9589460
Hadri, S., Naitmalek, Y., Najib, M., Bakhouya, M., Fakhri, Y., Elaroussi, M.: A comparative study of predictive approaches for load forecasting in smart buildings. Procedia Comput. Sci., 160, 173–180 (2019). ISSN 1877–0509. https://doi.org/10.1016/j.procs.2019.09.458
Yazici, I., Faruk Beyca, O., Delen, D.: Deep-learning-based short-term electricity load forecasting: a real case application. Eng. Appl. Artif. Intell. 109 (2022). https://doi.org/10.1016/j.engappai.2021.104645
Ahajjam, M.A., Licea, D.B., Ghogho, M., Kobbane, A.: Short-term multi-horizon residential electric load forecasting using deep learning and signal decomposition methods. ArXiv, abs/2202.03264 (2022)
Zhang, F., Deb, C., Lee, S.E., Yang, J., Shah, K.W.: Time series forecasting for building energy consumption using weighted Support Vector Regression with differential evolution optimization technique. Energy Build. 126, 94–103 (2016). ISSN 0378-7788. https://doi.org/10.1016/j.enbuild.2016.05.028
Kong, W., Dong, Z.Y., Hill, D.J., Luo, F., Xu, Y.: Short-term residential load forecasting based on resident behaviour learning. IEEE Trans. Power Syst. 33(1), 10871088 (2018). https://doi.org/10.1109/TPWRS.2017.2688178
Candanedo, L.M., Feldheim, V., Deramaix, D.: Data driven prediction models of energy use of appliances in a low-energy house. Energy Build. 140, 8197 (2017). https://doi.org/10.1016/j.enbuild.2017.01.083
Liu, T., Liu, K., Fang, P., Zhao, J.: A hybrid model of AR and PNN method for building thermal load forecasting. In: Zhang, L., Song, X., Wu, Y. (eds.) AsiaSim/SCS AutumnSim -2016. CCIS, vol. 643, pp. 146–155. Springer, Singapore (2016). https://doi.org/10.1007/978-981-10-2663-8_16
Zainab, A., Syed, D.: Deployment of deep learning models on resource decent devices for object detection. In: Proceedings of IEEE International Conference on Informatics IoT, Enabling Technologies (ICIoT), pp. 73‒78, February 2020. https://doi.org/10.1109/ICIoT48696.2020.9089651
Fukuoka, R., et al.: Wind speed prediction model using LSTM and 1D-CNN. J. Sig. Process. 22(4), 207‒210 (2018). Released on J-STAGE, 25 July 2018. Online ISSN 1880-1013, Print ISSN 1342-6230. https://doi.org/10.2299/jsp.22.207
UCI Machine Learning Repository: Individual Household Electric Power Consumption Data Set. Accessed 22 Jan. 2021. archive.ics.uci.edu/ml/datasets/Individual +household+electric+power+consumption
Sessa, J., Syed, D.: Techniques to deal with missing data. In: Proceedings of 5th International Conference on Electronic Devices Systems and Applications, Sarawak, Malaysia, pp. 1‒4, December 2016. https://doi.org/10.1109/ICEDSA.2016.7818486
Acknowledgment
This work was supported by the Ministry of Higher Education, Scientific Research and Innovation, the Digital Development Agency (DDA), and the CNRST of Morocco (Alkhawarizmi/2020/39).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Jrhilifa, I., Ouadi, H., Jilbab, A. (2023). Multi-horizon Short-Term Load Consumption Forecasting Using Deep Learning Models. In: Kacprzyk, J., Ezziyyani, M., Balas, V.E. (eds) International Conference on Advanced Intelligent Systems for Sustainable Development. AI2SD 2022. Lecture Notes in Networks and Systems, vol 714. Springer, Cham. https://doi.org/10.1007/978-3-031-35245-4_26
Download citation
DOI: https://doi.org/10.1007/978-3-031-35245-4_26
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-35244-7
Online ISBN: 978-3-031-35245-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)