|
|
基于灰狼优化算法的LSTM风速预测方法研究
|
Abstract:
风力发电的主要决定因素是风速，而风速具有不稳定性特征，准确预测风速对调度风力发电系统，提高风能转换效率等具有非常重要的意义。针对目前风速预测中，智能模型参数设置难的问题，本文提出了一种基于灰狼优化算法(GWO)对长短期记忆模型(LSTM)超参数进行寻优的GWO-LSTM模型，并利用Halifax风速数据集进行风速的预测。实验结果表明，GWO-LSTM在预测风速上能获得更高的精度，在均方根误差(RMSE)、平均绝对误差(MAE)及相关系数R2上，比传统的LSTM、GRU、Simple RNN效果更优，这充分说明了本研究提出的GWO-LSTM算法在风速预测上有较好的应用前景。
The primary factor of wind energy production is wind speed, which is unstable. For scheduling wind power-producing systems and increasing wind energy conversion efficiency, accurate wind speed forecasting is crucial. This paper proposes a GWO-LSTM model based on the gray wolf optimization algorithm (GWO) to find the optimization of the hyperparameters of the long and short-term memory model (LSTM), and uses the Halifax wind speed dataset for wind speed prediction in order to address the issue that it is difficult to set the parameters of intelligent models in wind speed prediction. The experimental results demonstrate that the GWO-LSTM algorithm proposed in this study has better application prospects in wind speed prediction because it can predict wind speed with a higher degree of accuracy and performs better than the traditional LSTM, GRU, and Simple RNN in terms of root mean square error (RMSE), mean absolute error (MAE), and correlation coefficient (R2).
| [1] | Yatiyana, E., Rajakaruna, S. and Ghosh, A. (2017) Wind Speed and Direction Forecasting for Wind Power Generation Using ARIMA Model. 2017 Australasian Universities Power Engineering Conference, Melbourne, 19-22 November 2017, 1-6. https://doi.org/10.1109/AUPEC.2017.8282494 |
| [2] | Grigonytė, E. and Butkevičiūtė, E. (2016) Short-Term Wind Speed Forecasting Using ARIMA Model. Energetika, 62, 45-55. https://doi.org/10.6001/energetika.v62i1-2.3313 |
| [3] | Rajeevan, A.K., Shouri, P.V. and Nair, U. (2014) ARIMA Modeling of Wind Speed for Wind Farm Reliability Analysis. 2014 Annual International Conference on Emerging Research Areas: Magnetics, Machines and Drives, Kottayam, 24-26 July 2014, 1-5. https://doi.org/10.1109/AICERA.2014.6908190 |
| [4] | Haddad, M., Nicod, J., Mainassara, Y.B., et al. (2019) Wind and Solar Forecasting for Renewable Energy System Using Sarima-Based Model. 2019 International Conference on Time Series and Forecasting, Granada, 25-27 September 2019. |
| [5] | Tyass, I., Bellat, A., Raihani, A., et al. (2022) Wind Speed Prediction Based on Seasonal ARIMA Model. E3S Web of Conferences, 336, Article No. 00034. https://doi.org/10.1051/e3sconf/202233600034 |
| [6] | Filik, Ü.B. and Filik, T. (2017) Wind Speed Prediction Using Artificial Neural Networks Based on Multiple Local Measurements in Eskisehir. Energy Procedia, 107, 264-269. https://doi.org/10.1016/j.egypro.2016.12.147 |
| [7] | Li, Z.H,, Sun, W., Xiang, Y., et al. (2022) A Transfer Strategy for Power Output Estimation of Wind Farm at Planning Stage Based on SVR Model. CSEE Journal of Power and Energy Systems, 9, 1460-1471. |
| [8] | de Freitas, N.C., Silva, M.P.S. and Sakamoto, M.S. (2018) Wind Speed Forecasting: A Review. International Journal of engineering Research and Applications, 8, 4-9. |
| [9] | Hochreiter, S. and Schmidhuber, J. (1997) Long Short-Term Memory. Neural Computation, 9, 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735 |
| [10] | 程冬梅. LSTM研究现状综述[J]. 信息系统工程, 2022, 337(1): 149-152. |
| [11] | 李亚蒙, 孙宝楠, 丁军航, 官晟. 基于LSTM的海洋表面短期风速预测研究[J]. 海洋科学, 2022, 46(11): 55-66. |
| [12] | 熊龙祥, 涂佳黄, 廖惠惠. 基于LSTM循环神经网络的风力预测研究[J]. 湘潭大学学报(自然科学版), 2023, 45(4): 118-128. |
| [13] | Shao, B., Song, D., Bian, G., et al. (2021) Wind Speed Forecast Based on the LSTM Neural Network Optimized by the Firework Algorithm. Advances in Materials Science and Engineering, 2021, 1-13. https://doi.org/10.1155/2021/4874757 |
| [14] | Mirjalili, S., Mirjalili, S.M. and Lewis, A. (2014) Grey Wolf Optimizer. Advances in Engineering Software, 69, 46-61. https://doi.org/10.1016/j.advengsoft.2013.12.007 |
| [15] | Faris, H., Aljarah, I., Al-Betar, M.A., et al. (2018) Grey Wolf Optimizer: A Review of Recent Variants and Applications. Neural Computing and Applications, 30, 413-435. https://doi.org/10.1007/s00521-017-3272-5 |
| [16] | Aufa, B.Z., Suyanto, S. and Arifianto, A. (2020) Hyperparameter Setting of LSTM-Based Language Model Using Grey Wolf Optimizer. 2020 International Conference on Data Science and Its Applications, Bandung, 5-6 August 2020, 1-5. https://doi.org/10.1109/ICoDSA50139.2020.9213031 |
| [17] | 王立辉, 杨辉斌, 王银堂等. 基于GWO-LSTM的丹江口水库入库径流预测[J]. 水利水运工程学报, 2021(6): 51-59. |
| [18] | Li, B.J., Sun, G.L., Liu, Y., et al. (2022) Monthly Runoff Forecasting Using Variational Mode Decomposition Coupled with Gray Wolf Optimizer-Based Long Short-Term Memory Neural Networks. Water Resources Management, 36, 2095-2115. https://doi.org/10.1007/s11269-022-03133-0 |
| [19] | Hossain, M.A., Gray, E.M.A., Islam, M.R., et al. (2021) Forecasting Very Short-Term Wind Power Generation Using Deep Learning, Optimization and Data Decomposition Techniques. 24th International Conference on Electrical Machines and Systems, Gyeongju, 31 October 2021-03 November 2021, 323-327. https://doi.org/10.23919/ICEMS52562.2021.9634361 |
| [20] | Zaman, U., Teimourzadeh, H., Sangani, E.H., et al. (2021) Wind Speed Forecasting Using ARMA and Neural Network Models. 2021 IEEE Electrical Power and Energy Conference, Toronto, 22-31 October 2021, 243-248. https://doi.org/10.1109/EPEC52095.2021.9621650 |
| [21] | Elsaraiti, M. and Merabet, A. (2021) A Comparative Analysis of the Arima and Lstm Predictive Models and Their Effectiveness for Predicting Wind Speed. Energies, 14, Article 6782. https://doi.org/10.3390/en14206782 |
