Short-Term Electrical Load Forecasting Based on VMD and GRU-TCN Hybrid Network
Source abstract
Abstract
With the continuous increase in user-side flexible controllable resources connected into a distribution system, the components of electrical load become too diverse and difficult to be accuracy forecasted. A short-term load forecast method that integrates variational modal decomposition (VMD), gated recurrent unit (GRU) and time convolutional network (TCN) into a hybrid network is proposed in this paper. Firstly, original electrical load sequence data with noise are decomposed into intrinsic IMF components with different frequencies and amplitudes based on the VMD method. Secondly, a combined load forecasting method based on the GRU and TCN network is proposed for the high and low-frequency load subsequent signals, respectively. Finally, the high and low-frequency signals forecasting results of the GRU and TCN network are rebuilt for the final load forecasting. The experiment results based on actual operation data (data set 1) and simulation data (data set 2), which show that the proposed method can reduce the forecasting error by 36.20% and 10.8%, respectively, in comparison with VMD-GRU. The reliability and accuracy of the proposed method is verified through the comparison with other methods such as LSTM, Prophet and XG Boost.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Energy Load and Power Forecasting · Image and Signal Denoising Methods · Traffic Prediction and Management Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Jiangsu Key Laboratory of Power Transmission and Distribution Equipment Technology, Hohai University, Changzhou 213022, China
College of The Internet of Things Engineering, Hohai University, Changzhou 213022, China
State Grid Changzhou Power Supply Company, Changzhou 210024, China
Funding
National Natural Science Foundation of China · The Fundamental Research Funds for the Central Universities · The open funding of Jiangsu Key Laboratory of Power Transmission & Distribution Equipment Technology
References (38)
Show source-provided references
1. Probabilistic electric load forecasting: A tutorial review10.1016/j.ijforecast.2015.11.011 ↗
2. Forecasting uncertainty in electricity smart meter data by boosting additive quantile regression10.1109/TSG.2016.2527820 ↗
3. Short term residential load forecasting based on resident behaviour learning10.1109/TPWRS.2017.2688178 ↗
4. Conditional residual modeling for probabilistic load forecasting10.1109/TPWRS.2018.2868167 ↗
5. Customer short term load forecasting by using ARIMA transfer function model
6. Probabilistic load forecasting via quantile regression averaging on sister forecasts
7. Short term load forecasting in electric power systems: A comparison of ARMA models and extended wiener filtering10.1002/for.3980020107 ↗
8. Comparative study of wavelet-ARIMA and wavelet-ANN models for temperature time series data in Northeastern Bangladesh10.1016/j.jksus.2015.12.002 ↗
9. A novel CNN-GRU-based hybrid approach for short-term residential load forecasting10.1109/ACCESS.2020.3009537 ↗
10. Short-term power load probability density forecasting method using Kernel-based support vector quantile regression and Copula theory10.1016/j.apenergy.2016.10.079 ↗
11. Clothing sale forecasting by a composite GRU–Prophet model with an attention mechanism10.1109/TII.2021.3057922 ↗
12. Grey predictor for wind energy conversion systems output power prediction10.1109/TPWRS.2006.879246 ↗
13. Recurrent neural networks for short-term load forecasting10.1109/59.651623 ↗
14. An ensemble approach for short-term load forecasting by extreme learning machine10.1016/j.apenergy.2016.02.114 ↗
15. Meng, X.Z., Zhou, Q., Hu, J.X., Shu, L.S., and Jiang, P. (2017, January 10–13). A global support vector regression based on sorted k-fold method. Proceedings of the 2017 IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), Singapore.10.1109/IEEM.2017.8290276 ↗
16. Nie, Y., Santis, L.D., Carratu, M., Nils, M.O., Sommella, P., and Lundgren, J. (July, January 1). Deep Melanoma classification with K-Fold Cross-Validation for Process optimization. Proceedings of the 2020 IEEE International Symposium on Medical Measurements and Applications (MeMeA), Bari, Italy.10.1109/MeMeA49120.2020.9137222 ↗
17. Cai, C.C., Tao, Y., Zhu, T.Q., and Deng, Z.X. (2021). Short-Term load forecasting based on deep learning bidirectional LSTM neural network. Appl. Sci., 11.10.3390/app11178129 ↗
18. A hybrid short-term load forecasting with a new input selection framework10.1016/j.energy.2015.01.028 ↗
19. A new hybrid model for short-term electricity load forecasting10.1109/ACCESS.2019.2937222 ↗
20. Short-term load forecasting of regional distribution network based on generalized regression neural network optimized by grey wolf optimization algorithm
21. Forecasting of electricity price through a functional prediction of sale and purchase curves10.1002/for.2624 ↗
22. Wang, S.Y., Ji, T.Y., and Li, M.S. (2020, January 23–25). Power load forecasting of LSSVM based on real time price and chaotic characteristic of loads. Proceedings of the 2020 IEEE Sustainable Power and Energy Conference (iSPEC), Chengdu, China.10.1109/iSPEC50848.2020.9351228 ↗
23. Short term forecasting of price-responsive loads using inverse optimization10.1109/TSG.2017.2671743 ↗
24. A hybrid FCW-EMD and KF-BA-SVM based model for short-term load forecasting10.17775/CSEEJPES.2016.00080 ↗
25. Short-term wind-speed forecasting based on multiscale mathematical morphological decomposition, K-Means clustering, and stacked denoising autoencoders10.1109/ACCESS.2020.3015336 ↗
26. Modeling and forecasting short-term power load with copula model and deep belief network10.1109/TETCI.2018.2880511 ↗
27. Yu, Y., Ji, T.Y., Li, M.S., and Wu, Q.H. (2018, January 5–10). Short-term load forecasting using deep belief network with empirical mode decomposition and local predictor. Proceedings of the 2018 IEEE Power & Energy Society General Meeting (PESGM), Portland, OR, USA.10.1109/PESGM.2018.8586129 ↗
28. Song, L.Q., Xie, Q.Y., He, Y.K., and Dang, P.J. (2020, January 12–14). Ultra-short-term wind power combination forecasting model based on MEEMD-SAE-Elman. Proceedings of the 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), Chongqing, China.10.1109/ITNEC48623.2020.9084768 ↗
29. Yang, J.Z., Zhou, C.J., and Li, X.F. (2022). Research on fault feature extraction method based on parameter optimized variational mode decomposition and robust independent component analysis. Coatings, 12.10.3390/coatings12030419 ↗
30. Fault severity classification of ball bearing using SinGAN and deep convolutional neural network10.1177/09544062211043132 ↗
31. Faster R-CNN: Towards real-time object detection with region proposal networks
32. Temporal convolutional networks for multiperson activity recognition using a 2-D LIDAR10.1109/JIOT.2020.2984544 ↗
33. Short-term load forecasting for industrial customers based on TCN-LightGBM
34. Deep-Based conditional probability density function forecasting of residential loads10.1109/TSG.2020.2972513 ↗
35. A Stacked GRU-RNN-Based approach for predicting renewable energy and electricity load for smart grid operation10.1109/TII.2021.3056867 ↗
36. Guest Editorial: Special section on analytics for energy forecasting with applications to smart grid10.1109/TSG.2013.2295522 ↗
37. Zhao, J.T., and Huang, J.C. (2020, January 14–16). Application and research of short-term power load forecasting based on LSTM. Proceedings of the 2020 International Conference on Information Science, Parallel and Distributed Systems (ISPDS), Xi’an, China.10.1109/ISPDS51347.2020.00050 ↗
38. Gupta, R., Yadav, A.K., Jha, S.K., and Pathak, P.K. (2022, January 11–13). Time Series Forecasting of Solar Power Generation Using Facebook Prophet and XG Boost. Proceedings of the 2022 IEEE Delhi Section Conference (DELCON), New Delhi, India.10.1109/DELCON54057.2022.9752916 ↗