A Novel Short-Term Power-Load Forecasting Method Based on High-Dimensional Meteorological Data Dimensionality Reduction and Hybrid Deep Neural Network
Publication: Journal of Energy Engineering
Volume 149, Issue 6
Abstract
Accurate power load forecasting could provide a scientific basis for the rapid response and stable operation of a modern power system. To take advantage of the meteorological big data to improve short-term forecasting accuracy, while considering the nonlinear and spatiotemporal correlation characteristics of the power load data, this paper proposes a short-term power load forecasting method based on meteorological data dimensionality reduction and a hybrid deep neural network. First, the elastic network is used to reduce the dimensions of high-dimensional meteorological big data, eliminate irrelevant meteorological factors, and improve the quality of input data. Then, taking the dimension-reduced meteorological data and historical load data as input, a load forecasting model based on a novel deep neural network is established. This model uses a convolution neural network (CNN) and a bi-directional long short-term memory (BiLSTM) neural network to extract the spatial and temporal correlation features of power load related data, and combines the attention mechanism to enhance the learning weight of the load series in important periods, and adopts residual connection (RC) to optimize the network training speed and alleviate the overfitting problem. Finally, taking the open data set of the New York Independent System Operating Agency (NYISO) as an example, single-step and multi-step advance prediction experiments are carried out to verify the advantages of the proposed method.
Get full access to this article
View all available purchase options and get full access to this article.
Data Availability Statement
Publicly available datasets were analyzed in this study, which can be found at https://www.nyiso.com/. The remaining data, models, and codes that support the findings of this study are available from the corresponding author upon reasonable request.
Acknowledgments
This research was supported by the 2022 Comprehensive Energy Demonstration Project of State Grid East Inner Mongolia Power Supply Service Supervision Center (Grant No. 64664K220004).
References
Aasim, S. N. Singh, and A. Mohapatra. 2021. “Data driven day-ahead electrical load forecasting through repeated wavelet transform assisted SVM model.” Appl. Soft Comput. 111 (Nov): 107730. https://doi.org/10.1016/j.asoc.2021.107730.
Alhussein, M., K. Aurangzeb, and S. I. Haider. 2020. “Hybrid CNN-LSTM model for short-term individual household load forecasting.” IEEE Access 8 (Oct): 180544–180557. https://doi.org/10.1109/ACCESS.2020.3028281.
Amini, F., and G. Hu. 2021. “A two-layer feature selection method using Genetic Algorithm and Elastic Net.” Expert Syst. Appl. 166 (Mar): 114072. https://doi.org/10.1016/j.eswa.2020.114072.
Chen, G., Y. Wu, L. Yang, K. Xu, G. Lin, Y. Zhang, and Y. Zhang. 2022. “Ultra-short-term load dynamic forecasting method considering abnormal data reconstruction based on model incremental training.” Energies 15 (19): 7353. https://doi.org/10.3390/en15197353.
Chodakowska, E., J. Nazarko, and U. Nazarko. 2021. “ARIMA models in electrical load forecasting and their robustness to noise.” Energies 14 (23): 7952. https://doi.org/10.3390/en14237952.
Dong, H., Y. Gao, Y. Fang, M. Liu, and Y. Kong. 2021. “The short-term load forecasting for special days based on bagged regression trees in Qingdao, China.” Comput. Intell. Neurosci. 2021 (Sep): 1–16. https://doi.org/10.1155/2021/3693294.
Fallah, S. N., M. Ganjkhani, S. Shamshirband, and K.-W. Chau. 2019. “Computational intelligence on short-term load forecasting: A methodological overview.” Energies 12 (3): 393. https://doi.org/10.3390/en12030393.
Feng, C., K. Xu, and H. Ma. 2022. “Research on impulse power load forecasting based on improved recurrent neural networks.” Comput. Intell. Neurosci. 2022 (Apr): 2784563. https://doi.org/10.1155/2022/2784563.
Gasparin, A., S. Lukovic, and C. Alippi. 2022. “Deep learning for time series forecasting: The electric load case.” CAAI Trans. Intell. Technol. 7 (1): 1–25. https://doi.org/10.1049/cit2.12060.
Haben, S., S. Arora, G. Giasemidis, M. Voss, and D. V. Greetham. 2021. “Review of low voltage load forecasting: Methods, applications, and recommendations.” Appl. Energy 304 (Dec): 117798. https://doi.org/10.1016/j.apenergy.2021.117798.
Hao, Y., and C. Tian. 2019. “A novel two-stage forecasting model based on error factor and ensemble method for multi-step wind power forecasting.” Appl. Energy 238 (Mar): 368–383. https://doi.org/10.1016/j.apenergy.2019.01.063.
Hernandez, L., C. Baladron, J. M. Aguiar, B. Carro, A. J. Sanchez-Esguevillas, J. Lloret, and J. Massana. 2014. “A survey on electric power demand forecasting: Future trends in smart grids, microgrids and smart buildings.” IEEE Commun. Surv. Tutorials 16 (3): 1460–1495. https://doi.org/10.1109/SURV.2014.032014.00094.
Huang, S. J., and K. R. Shih. 2003. “Short-term load forecasting via ARMA model identification including non-Gaussian process considerations.” IEEE Trans. Power Syst. 18 (2): 673–679. https://doi.org/10.1109/TPWRS.2003.811010.
Imani, M. 2021. “Electrical load-temperature CNN for residential load forecasting.” Energy 227 (Jul): 120480. https://doi.org/10.1016/j.energy.2021.120480.
Jahangir, H., H. Tayarani, S. Baghali, A. Ahmadian, A. Elkamel, M. A. Golkar, and M. Castilla. 2019. “A novel electricity price forecasting approach based on dimension reduction strategy and rough artificial neural networks.” IEEE Trans. Ind. Inf. 16 (4): 2369–2381. https://doi.org/10.1109/TII.2019.2933009.
Khwaja, A. S., A. Anpalagan, M. Naeem, and B. Venkatesh. 2020. “Joint bagged-boosted artificial neural networks: Using ensemble machine learning to improve short-term electricity load forecasting.” Electr. Power Syst. Res. 179 (Feb): 106080. https://doi.org/10.1016/j.epsr.2019.106080.
Li, C. 2021. “A fuzzy theory-based machine learning method for workdays and weekends short-term load forecasting.” Energy Build. 245 (Aug): 111072. https://doi.org/10.1016/j.enbuild.2021.111072.
Li, J., S. Wei, and W. Dai. 2021. “Combination of manifold learning and deep learning algorithms for mid-term electrical load forecasting.” IEEE Trans. Neural Networks Learn. Syst. 34 (5): 2584–2593. https://doi.org/10.1109/TNNLS.2021.3106968.
Li, J., S. Zhang, and Z. Yang. 2022. “A wind power forecasting method based on optimized decomposition prediction and error correction.” Electr. Power Syst. Res. 208 (Jul): 107886. https://doi.org/10.1016/j.epsr.2022.107886.
Li, X., J. Li, C. Zhao, Y. Qu, and D. He. 2020. “Gear pitting fault diagnosis with mixed operating conditions based on adaptive 1D separable convolution with residual connection.” Mech. Syst. Signal Process. 142 (Aug): 106740. https://doi.org/10.1016/j.ymssp.2020.106740.
Lv, L., Z. Wu, J. Zhang, L. Zhang, Z. Tan, and Z. Tian. 2021. “A VMD and LSTM based hybrid model of load forecasting for power grid security.” IEEE Trans. Ind. Inf. 18 (9): 6474–6482. https://doi.org/10.1109/TII.2021.3130237.
Phyo, P. P., and C. Jeenanunta. 2021. “Daily load forecasting based on a combination of classification and regression tree and deep belief network.” IEEE Access 9 (Nov): 152226–152242. https://doi.org/10.1109/ACCESS.2021.3127211.
Qian, K., X. Wang, and Y. Yuan. 2021. “Research on regional short-term power load forecasting model and case analysis.” Processes 9 (9): 1617. https://doi.org/10.3390/pr9091617.
Raza, M. Q., and A. Khosravi. 2015. “A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings.” Renewable Sustainable Energy Rev. 50 (Oct): 1352–1372. https://doi.org/10.1016/j.rser.2015.04.065.
Sjöstrand, K., L. H. Clemmensen, R. Larsen, G. Einarsson, and B. Ersbøll. 2018. “SpaSM: A MATLAB toolbox for sparse statistical modeling.” J. Stat. Software 84 (10): 1–37. https://doi.org/10.18637/jss.v084.i10.
Wang, D., C. Yue, and A. ElAmraoui. 2021. “Multi-step-ahead electricity load forecasting using a novel hybrid architecture with decomposition-based error correction strategy.” Chaos Solitons Fractals 152 (Nov): 111453. https://doi.org/10.1016/j.chaos.2021.111453.
Wang, S., X. Wang, S. Wang, and D. Wang. 2019. “Bi-directional long short-term memory method based on attention mechanism and rolling update for short-term load forecasting.” Int. J. Electr. Power Energy Syst. 109 (Jul): 470–479. https://doi.org/10.1016/j.ijepes.2019.02.022.
Yildiz, B., J. I. Bilbao, and A. B. Sproul. 2017. “A review and analysis of regression and machine learning models on commercial building electricity load forecasting.” Renewable Sustainable Energy Rev. 73 (Jun): 1104–1122. https://doi.org/10.1016/j.rser.2017.02.023.
Zeng, N., H. Zhang, W. Liu, J. Liang, and F. E. Alsaadi. 2017. “A switching delayed PSO optimized extreme learning machine for short-term load forecasting.” Neurocomputing 240 (May): 175–182. https://doi.org/10.1016/j.neucom.2017.01.090.
Zhang, L., J. Wen, Y. Li, J. Chen, Y. Ye, Y. Fu, and W. Livingood. 2021. “A review of machine learning in building load prediction.” Appl. Energy 285 (Mar): 116452. https://doi.org/10.1016/j.apenergy.2021.116452.
Zhang, S., S. Ren, and R. Chen. 2018. “Short term power load forecasting based on big data reduction and PCA improved RBF network.” Acta Metrol. 39 (3): 392–396. https://doi.org/10.3969/j.issn.1000-1158.2018.03.21.
Zhao, B., Z. Wang, W. Ji, X. Gao, and X. Li. 2019. “A short-term power load forecasting method based on attention mechanism of CNN-GRU.” Power Syst. Technol. 43 (12): 4370–4376. https://doi.org/10.13335/j.1000-3673.pst.2019.1524.
Zou, H., and T. Hastie. 2005. “Regularization and variable selection via the elastic net.” J. R. Stat. Soc. B 67 (2): 301–320. https://doi.org/10.1111/j.1467-9868.2005.00503.x.
Information & Authors
Information
Published In
Journal of Energy Engineering
Volume 149 • Issue 6 • December 2023
Copyright
© 2023 American Society of Civil Engineers.
History
Received: Feb 27, 2023
Accepted: Jul 12, 2023
Published online: Oct 5, 2023
Published in print: Dec 1, 2023
Discussion open until: Mar 5, 2024
ASCE Technical Topics:
- Artificial intelligence and machine learning
- Big data
- Climates
- Computer programming
- Computing in civil engineering
- Correlation
- Design (by type)
- Engineering fundamentals
- Environmental engineering
- Forecasting
- Hybrid methods
- Load factors
- Mathematics
- Meteorology
- Methodology (by type)
- Neural networks
- Research methods (by type)
- Statistics
- Structural design
- Weather forecasting
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.