Journal of Electrical Engineering and Automation
IRO Journals
Volume 5 — Issue 2 — June 2023

Electricity Demand Forecasting using LSTMs

https://doi.org/10.36548/jeea.2023.2.006
A. Jeffee Jenson
Dept of EEE, Government College of Technology, Coimbatore, Tamilnadu, India
S. Sowkarthika
Assistant Professor, Department of EEE, Government College of Technology, Coimbatore, India
PDF
PDF

How to Cite

Jenson, A. Jeffee, and S. Sowkarthika. 2023. “Electricity Demand Forecasting Using LSTMs”. Journal of Electrical Engineering and Automation 5 (2): 228-37. https://doi.org/10.36548/jeea.2023.2.006.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

— Demand forecasting
— LSTMs
— Deep Learning
— Root Mean Square Error
Published: 06-06-2023

Abstract

Electricity demand forecasting is an essential task in the energy industry, enabling utilities and energy suppliers to optimize the generation, transmission, and distribution of electricity. In recent years, deep learning techniques such as Long Short -Term Memory (LSTM) neural networks have shown great potential in improving the accuracy and efficiency of time-series forecasting tasks, including electricity demand forecasting. This research proposes an LSTM-based neural network architecture for short-term electricity demand forecasting. The proposed model is evaluated on real-world electricity demand data, and the results demonstrate its effectiveness in predicting future demand patterns. The model's performance is evaluated using the Mean Squared Error loss function and the Root Mean Squared Error metric. The proposed model shows promising results compared to traditional time-series forecasting models. The results suggest that LSTM-based neural networks can be a powerful tool for electricity demand forecasting, providing more accurate and efficient forecasting models that can help improve energy system planning and decision making.

References

  1. Amjady, N., Keynia, F., & Ardakanian, R. (2018). Short-term electricity demand forecasting using LSTM networks: Iranian power grid case study. Energy, 150, 35-44.
  2. Zhang, Z., Zheng, L., Wang, Y., & Yao, W. (2018). Electricity demand forecasting using long short-term memory neural network with data augmentation. Energy, 160, 497-510.
  3. Elgendy, M. A., & Youssef, M. A. (2020). Short-term load forecasting using LSTM-based neural networks. Electric Power Systems Research, 182, 106231.
  4. Wang, S., Wang, J., Wu, Y., & Tian, H. (2019). Short-term load forecasting using long short-term memory neural network with data augmentation. Energies, 12(5), 924.
  5. Hu, J., Zheng, Y., Li, L., & Li, X. (2020). Long Short-Term Memory for Electricity Demand Forecasting: A Review. Energies, 13(5), 1225.
  6. Aung, Z. H., Khalid, N. A. M., & Salam, Z. (2019). Electricity Load Forecasting Using Long Short-Term Memory Recurrent Neural Network. International Journal of Electrical and Computer Engineering (IJECE), 9(2), 1284-1293.
  7. Choudhary, P., Gupta, P., & Kumbhare, A. (2019). Long Short-Term Memory based Load Forecasting for Electricity Distribution System. International Journal of Engineering and Advanced Technology (IJEAT), 9(2), 3026-3031.
  8. Shi, J., & Hong, T. (2019). Day-Ahead Electricity Load Forecasting Using Long Short-Term Memory Neural Network. Energies, 12(15), 2962.
  9. Jiang, Y., He, Y., & Xiong, J. (2019). Hourly Electricity Load Forecasting Using LSTM Recurrent Neural Networks. Journal of Electrical Engineering & Technology, 14(5), 2112-2122.
  10. Ghofrani, M., Shahsavari, M., Al-Abdeli, Y., & Hill, D. (2020). Hourly Peak Electricity Demand Forecasting Using Deep Learning Techniques. Energies, 13(17), 4569.