The high accuracy of short-term power load forecasting has a pivotal role in helping power companies to construct reasonable production scheduling plans and avoid resource waste. In this paper, a multi-model short-term power load prediction method based on Variational mode decomposition (VMD)-improved whale optimization algorithm (IWOA)-wavelet temporal convolutional network (WTCN)-bidirectional gated recurrent unit (BiGRU)-attention and CatBoost model fusion is proposed. First, VMD was employed to decompose the load data into different intrinsic mode functions. Second, a WTCN was utilized to extract the load data features, and multi-dimensional feature factors were integrated into the BiGRU network for model training. Moreover, an attention mechanism was added to enhance the influence degree of important information. The WTCN-BiGRU-attention model is improved by the WOA algorithm to optimize the hyperparameters of the network. Finally, the model was fused with the predicted data of the CatBoost network by the mean absolute percentage error-reciprocal weight (MAPE-RW) algorithm to construct the best fusion model. Compared with other forecasting models, the proposed multi-model fusion method has higher accuracy in short-term power load forecasting using the public data set for an Australian region.
Citation: Xiaotong Ji, Dan Liu, Ping Xiong. Multi-model fusion short-term power load forecasting based on improved WOA optimization[J]. Mathematical Biosciences and Engineering, 2022, 19(12): 13399-13420. doi: 10.3934/mbe.2022627
The high accuracy of short-term power load forecasting has a pivotal role in helping power companies to construct reasonable production scheduling plans and avoid resource waste. In this paper, a multi-model short-term power load prediction method based on Variational mode decomposition (VMD)-improved whale optimization algorithm (IWOA)-wavelet temporal convolutional network (WTCN)-bidirectional gated recurrent unit (BiGRU)-attention and CatBoost model fusion is proposed. First, VMD was employed to decompose the load data into different intrinsic mode functions. Second, a WTCN was utilized to extract the load data features, and multi-dimensional feature factors were integrated into the BiGRU network for model training. Moreover, an attention mechanism was added to enhance the influence degree of important information. The WTCN-BiGRU-attention model is improved by the WOA algorithm to optimize the hyperparameters of the network. Finally, the model was fused with the predicted data of the CatBoost network by the mean absolute percentage error-reciprocal weight (MAPE-RW) algorithm to construct the best fusion model. Compared with other forecasting models, the proposed multi-model fusion method has higher accuracy in short-term power load forecasting using the public data set for an Australian region.
| [1] | X. Shan, X. Lu, M. Y. Zhai, Z. Gao, C. Xu, X. Teng, et al., Analysis of key technologies for artificial intelligence applied to power grid dispatch and control, Autom. Electr. Power Syst., 43 (2019), 49–57. |
| [2] | S. Fan, L. Li, S. Wang, X. Liu, Y. Yu, B. Hao, Application analysis and exploration of artificial intelligence technology in power grid dispatch and control, Power Syst. Technol., 44 (2020), 401–411. |
| [3] |
C. Bian, S. Liu, H. Xing, Y. Jia, Research on fault-tolerant operation strategy of rectifier of square wave motor in wind power system, CES Trans. Electr. Mach. Syst., 5 (2021), 62–69. https://doi.org/10.30941/cestems.2021.00008 doi: 10.30941/cestems.2021.00008
|
| [4] | F. L. Tan, J. Zhang, H. Z. Ma, Combined forecasting method of power load based on trend change division, J. North China Electr. Power Univ., 47 (2020), 17–24. |
| [5] | P. Y. Chen, Y. J. Fang, Short-term load forecasting of power system for holiday point-by-point growth rate based on Kalman filtering, Eng. J. Wuhan Univ., 53 (2020), 139–144. |
| [6] | B. Li, F. Qin, Y. Wu, J. Huang, Short-Term daily load curve forecasting based on fuzzy information granulation and multi-strategy sensitivity, Trans. China Electrotech. Soc., 32 (2017), 149–159. |
| [7] |
D. X. Niu, S. Y. Dai, A short-term load forecasting model with a modified particle swarm optimization algorithm and least squares support vector machine based on the denoising method of empirical mode decomposition and grey relational analysis, Energies, 10 (2017), 408–428. https://doi.org/10.3390/en10030408 doi: 10.3390/en10030408
|
| [8] | Q. Liu, Z. Z. Huang, S. Li, Research on power load forecasting based on support vector machine, J. Balkan Tribol. Assoc., 22 (2016), 151–159. |
| [9] |
C. B. Li, S. K. Li, Y. Q. Liu, A least squares support vector machine model optimized by moth-flame optimization algorithm for annual power load forecasting, Appl. Intell., 45 (2016), 1166–1178. https://doi.org/10.1007/s10489-016-0810-2 doi: 10.1007/s10489-016-0810-2
|
| [10] | J. J. Sun, S. Z. Zhang, M. D. Zeng, Multi-objective optimal control for flexible load in active distribution network considering time-of-use tariff, Trans. China Electrotech. Soc., 33 (2018), 401–412. |
| [11] | S. Zhang, J. X. Yang, J. C. Liu, J. Y. Liu, Power load recovery based on multi-scale time-series modeling and estimation, Trans. China Electrotech. Soc., 35 (2020), 2736–2746. |
| [12] |
M. Tan, S. P. Yuan, S. H. Li, Y. Su, H. Li, F. He, Ultra-short-term industrial power demand forecasting using LSTM based hybrid ensemble learning, IEEE Trans. Power Syst., 35 (2020), 2937–2948. https://doi.org/10.1109/TPWRS.2019.2963109 doi: 10.1109/TPWRS.2019.2963109
|
| [13] |
J. F. Rendon-Sanchez, L. M. de Menezes, Structural combination of seasonal exponential smoothing forecasts applied to load forecasting, Eur. J. Oper. Res., 27 (2019), 916–924. https://doi.org/10.1016/j.ejor.2018.12.013 doi: 10.1016/j.ejor.2018.12.013
|
| [14] | J. Lu, Q. Zhang, Z. Yang, M. Tu, J. Lu, H. Peng, Short-term load forcasting method based on CNN-LSTM hybrid neural network model, Autom. Electr. Power Syst., 43 (2019), 131–137. |
| [15] | B. Zhao, Z. Wang, W. Ji, X. Gao, X. Li, A short-term power load forecasting method based on attention mechanism of CNN-GRU, Power Syst. Tech., 43 (2019), 4370–4376. |
| [16] | L. J. Zhu, Z. Xun, Y. X. Wang, Short-term power load forecasting based on CNN-BiLSTM, Power Syst. Tech., 45 (2021), 4532–4539. |
| [17] | Y. Zhao, H. Wang, L. Kang, Z. Zhang, Temporal convolution network-based short-term electrical load forecasting, Trans. China Electrotech. Soc., 5 (2022), 1243–1251. |
| [18] |
Z. D. Tian, H. Chen, A novel decomposition-ensemble prediction model for ultra-short-term wind speed, Energy Convers. Manage., 248 (2021), 1–18. https://doi.org/10.1016/j.enconman.2021.114775 doi: 10.1016/j.enconman.2021.114775
|
| [19] |
Z. D. Tian, Short-term wind speed prediction based on LMD and improved FA optimized combined kernel function LSSVM, Eng. Appl. Artif. Intell., 91 (2020), 1–24. https://doi.org/10.1016/j.engappai.2020.103573 doi: 10.1016/j.engappai.2020.103573
|
| [20] |
C. Tong, L. Zhang, H. Li, Y. Ding, Temporal inception convolutional network based on multi-head attention for ultra-short-term load forecasting, IET Gener. Transm. Distrib, 16 (2021), 1680–1696. https://doi.org/10.1049/gtd2.12394 doi: 10.1049/gtd2.12394
|
| [21] |
Z. D. Tian, Approach for short-Term traffic flow prediction based on empirical mode decomposition and combination model fusion, IEEE Trans. Intell. Transp. Syst., 22 (2021), 5566–5576. https://doi.org/10.1109/TITS.2020.2987909 doi: 10.1109/TITS.2020.2987909
|
| [22] |
Z. D. Tian, S. J. Li, Y. H. Wang, A prediction approach using ensemble empirical mode decomposition-permutation entropy and regularized extreme learning machine for short-term wind speed, Wind Energy, 23 (2020), 177–206. https://doi.org/10.1002/we.2422 doi: 10.1002/we.2422
|
| [23] | S. E. Haupt, S. Dettling, J. K. Williams, J. Pearson, T. Jensen, T. Brummet, et al., Blending distributed photovoltaic and demand load forecasts and deep bidirectional long short-term memory and multiple linear regression, Sol. Energy, 157 (2017), 542–551. |
| [24] |
K. Dragomiretskiy, D. Zosso, Variational mode decomposition, IEEE Trans. Signal Process., 62 (2014), 531–544. https://doi.org/10.1109/TSP.2013.2288675 doi: 10.1109/TSP.2013.2288675
|
| [25] | S. J. Bai, J. Z. Kolter, V. Koltun, An empirical evaluation of generic convolutional and recurrent networks for sequence modeling, preprint, arXiv: 1803.01271. |
| [26] |
S. H. Rafi, N. AI Masood, S. R. Deeba, S. R. Deeba, E. Hossain, A short-term load forecasting method using integrated CNN and LSTM network, IEEE Access, 9 (2021), 32436–32448. https://doi.org/10.1109/ACCESS.2021.3060654 doi: 10.1109/ACCESS.2021.3060654
|
| [27] |
X. B. Jin, W. Z. Zheng, J. L. Kong, X. Y. Wang, Y. T. Bai, T. L. Su, et al., Deep-learning forecasting method for electric power load via attention-based encoder-decoder with Bayesian optimization, Energies, 14 (2021), 1406–1596. https://doi.org/10.3390/en14061596 doi: 10.3390/en14061596
|
| [28] |
Y. Y. Wang, J. Chen, X. Q. Chen, X. Zeng, Y. Kong, S. Sun, et al., Short-term load forecasting for industrial customers based on TCN-LightGBM, IEEE Trans. Power Syst., 36 (2021), 1984–1997. https://doi.org/10.1109/TPWRS.2020.3028133 doi: 10.1109/TPWRS.2020.3028133
|
| [29] |
M. Lysaker, A. Lundervold, X. C. Tai, Noise removal using fourth-order partial differential equation with applications to medical magnetic resonance images in space and time, IEEE Trans. Image Process., 12 (2003), 1579–1590. https://doi.org/10.1109/TIP.2003.819229 doi: 10.1109/TIP.2003.819229
|
| [30] | Y. Zhang, Q. Ai, L. Lin, S. Yuan, Z. Y. Li, A very short-term load forecasting method based on deep LSTM RNN at zone level, Power Syst. Tech., 43 (2019), 1884–1892. |
Figures(12) / Tables(10)
Xiaotong Ji, Dan Liu, Ping Xiong. Multi-model fusion short-term power load forecasting based on improved WOA optimization[J]. Mathematical Biosciences and Engineering, 2022, 19(12): 13399-13420. doi: 10.3934/mbe.2022627
DownLoad: