Multi-temporal Scale Wind Power Forecasting Based on Lasso-CNN-LSTM-LightGBM

Authors

DOI:

https://doi.org/10.4108/ew.5792

Keywords:

wind power prediction, ICEEMDAN, CNN network, LSTM, LightGBM model, multi-time scale

Abstract

Due to the increasingly severe climate problems, wind energy has received widespread attention as the most abundant energy on Earth. However, due to the uncertainty of wind energy, a large amount of wind energy is wasted, so accurate wind power prediction can greatly improve the utilization of wind energy. To increase the forecast for wind energy accuracy across a range of time scales, this paper presents a multi-time scale wind power prediction by constructing an ICEEMDAN-CNN-LSTM-LightGBM model. Initially, feature selection is performed using Lasso regression to identify the most significant variables affecting the forecast for wind energy across distinct time intervals. Subsequently, the ICEEMDAN is utilized to break down the wind power data into various scales to capture its nonlinear and non-stationary characteristics. Following this, a deep learning model based on CNN and LSTM networks is developed, with the CNN responsible for extracting spatial features from the time series data, and the LSTM designed to capture the temporal relationships. Finally, the outputs of the deep learning model are fed into the LightGBM model to leverage its superior learning capabilities for the ultimate prediction of wind power. Simulation experiments demonstrate that the proposed ICEEMDAN-CNN-LSTM-LightGBM model achieves higher accuracy in multi-time scale wind power prediction, providing more reliable decision assistance with the management and operation of wind farms.

Downloads

Download data is not yet available.

References

Yuxin Gong, Bo Wang, Huaizheng Ren, Deyu Li, Dianlong Wang, Huakun Liu and Shixue Dou. Recent Advances in Structural Optimization and Surface Modification on Current Collectors for High-Performance Zinc Anode: Principles, Strategies, and Challenges. Nano-Micro Letters. 2023; 15(11):325-356. DOI: https://doi.org/10.1007/s40820-023-01177-4

Xixian G. Energy Transition:Huge Potential For China-ASEAN Cooperation. China Report ASEAN. 2023;8(Z2):26-29.

Yachen Xie, Xuning Wu, Zhengmeng Hou, Zaoyuan Li, Jiashun Luo, Christian Truitt Lüddeke, Liangchao Huang, Lin Wu and Jianxing Liao. Gleaning insights from German energy transition and large-scale underground energy storage for China's carbon neutrality. International Journal of Mining Science and Technology. 2023; 33(05):529-553. DOI: https://doi.org/10.1016/j.ijmst.2023.04.001

ZHANG, G., LIU, H. and ZHANG, J. Wind power prediction based on variational mode decomposition multi-frequency combinations. J. Mod. Power Syst. Clean Energy. 2019; 7:281–288. DOI: https://doi.org/10.1007/s40565-018-0471-8

Wang, SX., Li, M. and Zhao, L. Short-term wind power prediction based on improved small-world neural network. Neural Comput & Applic. 2019; 31:3173–3185.

Farah S, Atif M and Rizwan K. Short-term wind power prediction based on improved small-world neural network. Neural Comput & Applic. 2019; 31:3173–3185. DOI: https://doi.org/10.1007/s00521-017-3262-7

Ning L, Jie D and Lingyue L. A novel EMD and causal convolutional network integrated with Transformer for ultra short-term wind power forecasting. nternational Journal of Electrical Power and Energy Systems. 2023;154.

Zhu Q, Chen J and Zhu L. Wind speed prediction with spatio–temporal correlation: A deep learning approach. Energies, 2018, 11(4):705. DOI: https://doi.org/10.3390/en11040705

He M, Yang L and Zhang J. Spatio-temporal analysis for smart grids with wind generation integration. 2013 International Conference on Computing, Networking and Communications (ICNC). 2013:1107-1111.

Jiaqi Liang, Chaoye Wang, Di Zhang, Yubin Xie, Yanru Zeng, Tianqin Li, Zhixiang Zuo, Jian Ren and Qi Zhao. VSOLassoBag:a variable-selection oriented LASSO bagging algorithm for biomarker discovery in omic-based translational research. Journal of Genetics and Genomics. 2023; 50(03):151-162. DOI: https://doi.org/10.1016/j.jgg.2022.12.005

Meihong S and Wenjian W . A network Lasso model for regression. Communications in Statistics-Theory and Methods. 2023; 52(6):1702-1727. DOI: https://doi.org/10.1080/03610926.2021.1938125

Saibabu B B, Kiran T and Vishalteja K . Hybrid wind speed forecasting using ICEEMDAN and transformer model with novel loss function. Energy. 2023; 265 DOI: https://doi.org/10.1016/j.energy.2022.126383

Ning Li, Jie Dong, Lingyue Liu, He Li and Jie Yan. A novel EMD and causal convolutional network integrated with Transformer for ultra short-term wind power forecasting. International Journal of Electrical Power & Energy Systems, 2023; 154:109470. DOI: https://doi.org/10.1016/j.ijepes.2023.109470

Chenjia Hu, Yan Zhao, He Jiang, Mingkun Jiang, Fucai You, Qian Liu. Prediction of ultra-short-term wind power based on CEEMDAN-LSTM-TCN. Energy Reports. 2022; 8:483-492. DOI: https://doi.org/10.1016/j.egyr.2022.09.171

Matin S M, Rikhtehgar A G and Aminzadeh A G. Predicting wind power generation using machine learning and CNN-LSTM approaches. Wind Engineering. 2022; 46(6):1853-1869. DOI: https://doi.org/10.1177/0309524X221113013

Anggraini Puspita Sari, Hiroshi Suzuki, Takahiro Kitajima, Takashi Yasuno, Dwi Arman Prasetya and Rahman Arifuddin. Short‐Term Wind Speed and Direction Forecasting by 3DCNN and Deep Convolutional LSTM. IEEJ Transactions on Electrical and Electronic Engineering. 2022; 17(11):1620-1628. DOI: https://doi.org/10.1002/tee.23669

Ahmed A. Ewees, Mohammed A.A. Al-qaness, Laith Abualigah and Mohamed Abd Elaziz. HBO-LSTM: Optimized long short term memory with heap-based optimizer for wind power forecasting. Energy Conversion and Management. 2022; 268 DOI: https://doi.org/10.1016/j.enconman.2022.116022

Indolia S, Goswami A K and Mishra S P. Conceptual understanding of convolutional neural network-a deep learning approach. Procedia computer science. 2018; 132:679-688. DOI: https://doi.org/10.1016/j.procs.2018.05.069

Shijie G, Yongsheng W and Limin L.Ultra-short-term wind power prediction method combining financial technology feature engineering and XGBoost algorithm. Heliyon. 2023; 9(6):e16938-e16938. DOI: https://doi.org/10.1016/j.heliyon.2023.e16938

Ju Y, Sun G and Chen Q. A Model Combining Convolutional Neural Network and LightGBM Algorithm for Ultra-Short-Term Wind Power Forecasting. IEEE Access. 2019; 728309-28318. DOI: https://doi.org/10.1109/ACCESS.2019.2901920

Shengli L, Xudong T and Benxi L. Short-Term Wind Power Prediction Based on LightGBM and Meteorological Reanalysis. Energies. 2022; 15(17):6287-6287. DOI: https://doi.org/10.3390/en15176287

Downloads

Published

15-04-2024

How to Cite

1.
Gao Q. Multi-temporal Scale Wind Power Forecasting Based on Lasso-CNN-LSTM-LightGBM. EAI Endorsed Trans Energy Web [Internet]. 2024 Apr. 15 [cited 2024 May 20];11. Available from: https://publications.eai.eu/index.php/ew/article/view/5792