Short-Term Load Forecasting using Residual Bi-directional Gated Recurrent Unit with Self-Attention in Smart Grids
Keywords:
North South Wales, Short-Term Load Forecasting, Smart GridsAbstract
Short-Term Load Forecasting (STLF) plays a significant role in electrical management systems which provides accurate predictions of electricity demand over short-time demands and makes effective resource allocation. STLF makes distribution system operators implement effective energy management by engaging energy consumers over the demand-response program in Smart Grids (SG). However, STLF is challenging due to load exhibits highly nonlinear patterns which result from different factors like sudden changes in consumer behavior, and complex interactions. These nonlinearities make inaccurate forecasting. To address this issue, the Residual Bi-directional Gated Recurrent Unit with Self-Attention (Rbi-GRU-SA) is proposed to accurately forecast short-term load in SG which produces enhanced forecasting performance and reliability. Initially, the data is acquired from the electric load dataset to access the proposed approach. The z-score normalization is employed to normalize the dataset’s features in the pre-processing phase which maximizes stability and convergence rate. Then, the Rbi-GRU-SA is performed to forecast the electric load in SG which provides more accurate forecasting. When compared to existing approaches like Feature Engineering-Wavelet Neural Networks and Self-Adaptive Momentum Factor (FE-WNN-SAMF), FE-Adaptive Grasshopper Optimization-based Locally Weighted Support Vector Regression (FE-AGO-LWSVR), and Gaussian Process Regression (GPR), the Rbi-GRU-SA achieves better MAPE of 0.0978 and 0.1054 for North South Wales (NSW) and Victoria (VIC) respectively.
Downloads
References
S. U. R. Khan, I. A. Hayder, M. A. Habib, M. Ahmad, S. M. Mohsin, F. A. Khan, and K. Mustafa, “Enhanced machine-learning techniques for medium-term and short-term electric-load forecasting in smart grids,” Energies, vol. 16, no. 1, p. 276, Dec. 2022, https://doi.org/10.3390/en16010276.
L. Sun, H. Qin, K. Przystupa, M. Majka, and O. Kochan, “Individualized short-term electric load forecasting using data-driven meta-heuristic method based on LSTM network,” Sensors, vol. 22, no. 20, p. 7900, Oct. 2022, https://doi.org/10.3390/s22207900.
A. Motwakel, E. Alabdulkreem, A. Gaddah, R. Marzouk, N. M. Salem, A. S. Zamani, A. A. Abdelmageed, and M. I. Eldesouki, “Wild horse optimization with deep learning-driven short-term load forecasting scheme for smart grids,” Sustainability, vol. 15, no. 2, p. 1524, Jan. 2023, https://doi.org/10.3390/su15021524.
Y. Liu, Z. Dong, B. Liu, Y. Xu, and Z. Ding, “FedForecast: A federated learning framework for short-term probabilistic individual load forecasting in smart grid,” Int. J. Electr. Power Energy Syst., vol. 152, p. 109172, Oct. 2023, https://doi.org/10.1016/j.ijepes.2023.109172.
A. Inteha, F. Hussain, and I. A. Khan, “A data driven approach for day ahead short term load forecasting,” IEEE Access, vol. 10, pp. 84227-84243, Aug. 2022, https://doi.org/10.1109/ACCESS.2022.3197609.
N. Alemazkoor, M. Tootkaboni, R. Nateghi, and A. Louhghalam, “Smart-meter big data for load forecasting: An alternative approach to clustering,” IEEE Access, vol. 10, pp. 8377-8387, Jan. 2022, https://doi.org/10.1109/ACCESS.2022.3142680.
M. Madhukumar, A. Sebastian, X. Liang, M. Jamil, and M. N. S. K. Shabbir, “Regression model-based short-term load forecasting for university campus load,” IEEE Access, vol. 10, pp. 8891-8905, Jan. 2022, https://doi.org/10.1109/ACCESS.2022.3144206.
T. Zhang, X. Zhang, T. K. Chau, Y. Chow, T. Fernando, and H. H. C. Iu, “Highly accurate peak and valley prediction short-term net load forecasting approach based on decomposition for power systems with high PV penetration,” Appl. Energy, vol. 333, p. 120641, Mar. 2023, https://doi.org/10.1016/j.apenergy.2023.120641.
X. Chen, W. Chen, V. Dinavahi, Y. Liu, and J. Feng, “Short-term load forecasting and associated weather variables prediction using ResNet-LSTM based deep learning,” IEEE Access, vol. 11, pp. 5393-5405, Jan. 2023, https://doi.org/10.1109/ACCESS.2023.3236663.
L. Xiao, M. Li, and S. Zhang, “Short-term power load interval forecasting based on nonparametric Bootstrap errors sampling,” Energy Rep., vol. 8, pp. 6672-6686, Nov. 2022, https://doi.org/10.1016/j.egyr.2022.05.016.
M. Abdel-Basset, H. Hawash, K. Sallam, S. S. Askar, and M. Abouhawwash, “STLF-Net: Two-stream deep network for short-term load forecasting in residential buildings,” Journal of King Saud University-Computer and Information Sciences, vol. 34, no. 7, pp. 4296-4311, Jul. 2022, https://doi.org/10.1016/j.jksuci.2022.04.016.
R. Gonzalez, S. Ahmed, and M. Alamaniotis, “Implementing very-short-term forecasting of residential load demand using a deep neural network architecture,” Energies, vol. 16, no. 9, p. 3636, Apr. 2023, https://doi.org/10.3390/en16093636.
N. A. Mohammed and A. Al-Bazi, “An adaptive backpropagation algorithm for long-term electricity load forecasting,” Neural Comput. Appl., vol. 34, no. 1, pp. 477-491, Jan. 2022, https://doi.org/10.1007/s00521-021-06384-x.
W. Chen, G. Han, H. Zhu, and L. Liao, “Short-Term Load Forecasting with an Ensemble Model Using Densely Residual Block and Bi-LSTM Based on the Attention Mechanism,” Sustainability, vol. 14, no. 24, p. 16433, Dec. 2022, https://doi.org/10.3390/su142416433.
F. M. Butt, L. Hussain, S. H. M. Jafri, H. M. Alshahrani, F. N. Al-Wesabi, K. J. Lone, E. M. T. E. Din, and M. A. Duhayyim, “Intelligence based accurate medium and long term load forecasting system,” Applied Artificial Intelligence, vol. 36, no. 1, p. 2088452, Jun. 2022, https://doi.org/10.1080/08839514.2022.2088452.
M. ZulfiqAr, M. Kamran, M. B. Rasheed, T. Alquthami, and A. H. Milyani, “A short-term load forecasting model based on self-adaptive momentum factor and wavelet neural network in smart grid,” IEEE Access, vol. 10, pp. 77587-77602, Jul. 2022, https://doi.org/10.1109/ACCESS.2022.3192433.
M. Zulfiqar, M. Kamran, M. B. Rasheed, T. Alquthami, and A. H. Milyani, “A hybrid framework for short term load forecasting with a navel feature engineering and adaptive grasshopper optimization in smart grid,” Appl. Energy, vol. 338, p. 120829, May 2023, https://doi.org/10.1016/j.apenergy.2023.120829.
A. Yadav, R. Bareth, M. Kochar, M. Pazoki, and R. A. E. Sehiemy, “Gaussian process regression‐based load forecasting model,” IET Generation, Transmission & Distribution, vol. 18, no. 5, pp. 899-910, Mar. 2024, https://doi.org/10.1049/gtd2.12926.
S. M. Shin, A. Rasheed, P. Kil-Heum, and K. C. Veluvolu, “Fast and Accurate Short-Term Load Forecasting with a Hybrid Model,” Electronics, vol. 13, no. 6, p. 1079, Mar. 2024, https://doi.org/10.3390/electronics13061079.
A. K. Srivastava, A. S. Pandey, M. A. Houran, V. Kumar, D. Kumar, S. M. Tripathi, S. Gangatharan, and R. M. Elavarasan, “A day-ahead short-term load forecasting using M5P machine learning algorithm along with elitist genetic algorithm (EGA) and random forest-based hybrid feature selection,” Energies, vol. 16, no. 2, p. 867, Jan. 2023, https://doi.org/10.3390/en16020867.
Link for NSW: https://www.kaggle.com/datasets/joebeachcapital/nsw-australia-electricity-demand-2018-2023
Link for VIC: https://www.kaggle.com/datasets/joebeachcapital/electricity-demand-vic-australia-2018-2023
M. Nie, P. Chen, L. Wen, J. Fan, Q. Zhang, K. Yin, and G. Dou, “Wearable Recognition System for Complex Motions Based on Hybrid Deep‐Learning‐Enhanced Strain Sensors,” Adv. Intell. Syst., vol. 5, no. 11, p. 2300222, Aug. 2023, https://doi.org/10.1002/aisy.202300222.
K. N. Ravikumar, C. K. Madhusudana, H. Kumar, and K. V. Gangadharan, “Classification of gear faults in internal combustion (IC) engine gearbox using discrete wavelet transform features and K star algorithm,” Eng. Sci. Technol. Int. J., vol. 30, p. 101048, Jun. 2022, https://doi.org/10.1016/j.jestch.2021.08.005.
M. S. Başarslan and F. Kayaalp, “MBi-GRUMCONV: A novel Multi Bi-GRU and Multi CNN-Based deep learning model for social media sentiment analysis,” J. Cloud Comput., vol. 12, no. 1, p. 5, Jan. 2023, https://doi.org/10.1186/s13677-022-00386-3.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
