An Ultra-Short-Term Wind Power Prediction Model Based on Crested Porcupine Optimizer and Cross-Domain Attention Mechanism
Keywords:
Wind Power Prediction, Crested Porcupine Optimizer, Variational Mode Decomposition, Wavelet Transform Convolution, CrossformerAbstract
Wind power prediction is one of the critical tasks for ensuring power grid stability. Traditional forecasting methods often encounter challenges due to the non-stationarity and complexity of wind power data. To address these issues, this paper proposes a CPO-VMD-WTC-Crossformer model that integrates Crested Porcupine Optimizer (CPO)-optimized Variational Mode Decomposition (VMD) with Wavelet Transform Convolution (WTC) to enhance the accuracy and robustness of wind power forecasting. The CPO algorithm is first applied to optimize VMD's mode number and penalty factor, thereby improving its decomposition performance for wind power signals and providing high-quality input for the forecasting model. WTC utilizes its distinctive multiresolution analysis capability to precisely capture local key features such as subtle wind speed variations, compensating for Crossformer's limitations in local feature processing. Crossformer employs innovative cross-attention and cross-domain feature fusion mechanisms to efficiently analyze the spatiotemporal coupling characteristics of wind power data with low computational cost, enabling accurate forecasting. Experimental results demonstrate that compared to conventional forecasting models, the proposed model achieves significant improvements in forecasting accuracy, contributing to more scientific and stable power system dispatching.
References
Algarni S, Tirth V, Alqahtani T, et al. Contribution of renewable energy sources to the environmental impacts and economic benefits for sustainable development[J]. Sustainable energy technologies and assessments, 2023, 56: 103098.
Wang J, Zhu H, Zhang Y, et al. A novel prediction model for wind power based on improved long short-term memory neural network[J]. Energy, 2023, 265: 126283.
Wei J, Wu X, Yang T, et al. Ultra-short-term forecasting of wind power based on multi-task learning and LSTM[J]. International Journal of Electrical Power & Energy Systems, 2023, 149: 109073.
Wei H, Wang W, Kao X. A novel approach to ultra-short-term wind power prediction based on feature engineering and informer[J]. Energy Reports, 2023, 9: 1236-1250.
Markovics D, Mayer M J. Comparison of machine learning methods for photovoltaic power forecasting based on numerical weather prediction[J]. Renewable and Sustainable Energy Reviews, 2022, 161: 112364
Hu S, Xiang Y, Zhang H, et al. Hybrid forecasting method for wind power integrating spatial correlation and corrected numerical weather prediction[J]. Applied Energy, 2021, 293: 116951
Chen W, Zhou H, Cheng L, et al. Prediction of regional wind power generation using a multi-objective optimized deep learning model with temporal pattern attention[J]. Energy, 2023, 278: 127942.
Tian Z. A state-of-the-art review on wind power deterministic prediction[J]. Wind Engineering, 2021, 45(5): 1374-1392.
Wang Y, Pei L, Li W, et al. Short-term wind power prediction method based on multivariate signal decomposition and RIME optimization algorithm[J]. Expert Systems with Applications, 2025, 259: 125376.
Guo N Z, Shi K Z, Li B, et al. A physics-inspired neural network model for short-term wind power prediction considering wake effects[J]. Energy, 2022, 261: 125208.
Dosdoğru A T, İpek A Ä B. Hybrid boosting algorithms and artificial neural network for wind speed prediction[J]. International Journal of Hydrogen Energy, 2022, 47(3): 1449-1460.
Peng X, Li C, Jia S, et al. A short‐term wind power prediction method based on deep learning and multistage ensemble algorithm[J]. Wind energy, 2022, 25(9): 1610-1625.
Alkesaiberi A, Harrou F, Sun Y. Efficient wind power prediction using machine learning methods: A comparative study[J]. Energies, 2022, 15(7): 2327
Lei L, Shao S, Liang L. An evolutionary deep learning model based on EWKM, random forest algorithm, SSA and BiLSTM for building energy consumption prediction[J]. Energy, 2024, 288: 129795.
Guan S, Wang Y, Liu L, et al. Ultra-short-term wind power prediction method combining financial technology feature engineering and XGBoost algorithm[J]. Heliyon, 2023, 9(6)
Garg S, Krishnamurthi R. A CNN encoder decoder LSTM model for sustainable wind power predictive analytics[J]. Sustainable Computing: Informatics and Systems, 2023, 38: 100869.
Farah S, Humaira N, Aneela Z, et al. Short-term multi-hour ahead country-wide wind power prediction for Germany using gated recurrent unit deep learning[J]. Renewable and Sustainable Energy Reviews, 2022, 167: 112700.
Chen H, Wu H, Kan T, et al. Low-carbon economic dispatch of integrated energy system containing electric hydrogen production based on VMD-GRU short-term wind power prediction[J]. International Journal of Electrical Power & Energy Systems, 2023, 154: 109420
Huang L, Li L, Wei X, et al. Short-term prediction of wind power based on BiLSTM–CNN–WGAN-GP[J]. Soft Computing, 2022, 26(20): 10607-10621.
Liu R, Song Y, Yuan C, et al. Gan-based abrupt weather data augmentation for wind turbine power day-ahead predictions[J]. Energies, 2023, 16(21): 7250.
Xiong J, Peng T, Tao Z, et al. A dual-scale deep learning model based on ELM-BiLSTM and improved reptile search algorithm for wind power prediction[J]. Energy, 2023, 266: 126419.
Wang S, Shi J, Yang W, et al. High and low frequency wind power prediction based on Transformer and BiGRU-Attention[J]. Energy, 2024, 288: 129753.
Qu K, Si G, Shan Z, et al. Short-term forecasting for multiple wind farms based on transformer model[J]. Energy Reports, 2022, 8: 483-490.
Wang W, Feng B, Huang G, et al. Conformal asymmetric multi-quantile generative transformer for day-ahead wind power interval prediction[J]. Applied Energy, 2023, 333: 120634
Zhang Y, Yan J. Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting[C]//The eleventh international conference on learning representations. 2023.
Finder S E, Amoyal R, Treister E, et al. Wavelet convolutions for large receptive fields[C]//European Conference on Computer Vision. Cham: Springer Nature Switzerland, 2024: 363-380.
Jiajun H, Chuanjin Y, Yongle L, et al. Ultra-short term wind prediction with wavelet transform, deep belief network and ensemble learning[J]. Energy Conversion and Management, 2020, 205: 112418.
Gao X, Li X, Zhao B, et al. Short-term electricity load forecasting model based on EMD-GRU with feature selection[J]. Energies, 2019, 12(6): 1140.
Ding Y, Chen Z, Zhang H, et al. A short-term wind power prediction model based on CEEMD and WOA-KELM[J]. Renewable Energy, 2022, 189: 188-198.
Abdel-Basset M, Mohamed R, Abouhawwash M. Crested Porcupine Optimizer: A new nature-inspired metaheuristic[J]. Knowledge-Based Systems, 2024, 284: 111257
