|
|
基于VMD-SE-CEEMDAN-PSO-SVR短期风速预测
|
Abstract:
风能具有随机性和间歇性，准确可靠的风速预测对于风电场规划和电网运营规划至关重要？本文提出VMD (variational mode decomposition, VMD)-SE (sample entropy, SE)-CEEMDAN (complete ensemble empirical mode decomposition with adaptive noise, CEEMDAN)-PSO (particle swarm optimization, PSO)-SVR (support vector regression, SVR)的组合分解短期风速预测？首先是对VMD分解的子序列(intrinsic mode function, IMF)用样本熵(SE)判别方法对复杂度较高的子序列用自适应噪声的完备经验模态分解(CEEMDAN)进行二次分解，然后将两者分解后得到的序列用支持向量机(SVR)进行预测？此外，为了找到更优的SVR参数，文中引入粒子群优化算法进行改进，并基于粒子群算法对SVR参数寻优，进而对某风电场进行短期风速预测，实验结果证明，VMD-SE-CEEMDAN-PSO-SVR模型的预测精度相对于其他模型更高？
Wind energy is random and intermittent, and accurate and reliable wind speed predictions are essential for wind farm planning and grid operation planning. This article presents: VMD (variational mode decomposition, VMD)-SE (sample entropy, SE)-CEEMDAN (complete ensemble empirical mode decomposition with adaptive noise, CEEMDAN)-PSO (particle swarm optimization, PSO)-SVR (support vector regression, SVR) is a combination of decomposition short-term wind speed prediction. Firstly, the intrinsic mode function (IMF) of VMD decomposition is decomposed by sample entropy (SE) discrimination method, and the subsequence with high complexity is decomposed by CEEMDAN, and then the sequence obtained by decomposition is predicted by support vector machine (SVR).In addition, in order to find better SVR parameters, the particle swarm optimization algorithm is introduced to improve it, and the SVR parameters are optimized based on the particle swarm optimization algorithm, and then the short-term wind speed prediction of a wind farm is carried out, and the experimental results show that the prediction accuracy of the VMD-SE-CEEMDAN-PSO-SVR model is higher than that other models.
| [1] | Pujari, K.N., Miriyala, S.S., Mittal, P., et al. (2023) Better Wind Forecasting Using Evolutionary Neural Architecture Search Driven Green Deep Learning. Expert Systems with Applications, 214, Article ID: 119063. https://doi.org/10.1016/j.eswa.2022.119063 |
| [2] | Hao, Y., Yang, W. and Yin, K. (2023) Novel Wind Speed Forecasting Model Based on a Deep Learning Combined Strategy in Urban Energy Systems. Expert Systems with Applications, 219, Article ID: 119636. https://doi.org/10.1016/j.eswa.2023.119636 |
| [3] | Karimi-Arpanahi, S., Pourmousavi, S.A. and Mahdavi, N. (2023) Quantifying the Predictability of Renewable Energy Data for Improving Power Systems Decision-Making. Patterns, 4, Article ID: 100708. https://doi.org/10.1016/j.patter.2023.100708 |
| [4] | 杨正瓴, 赵强, 吴炳卫, 等. 采用K近邻进行空间相关性超短期风速预测[J]. 电力自动化设备, 2019, 39(3): 175-181. |
| [5] | Yang, W., Tian, Z. and Hao, Y. (2022) A Novel Ensemble Model Based on Artificial Intelligence and Mixed-Frequency Techniques for Wind Speed Forecasting. Energy Conversion and Management, 252, Article ID: 115086. https://doi.org/10.1016/j.enconman.2021.115086 |
| [6] | Ding, Q., Yan, F., Xia, W., et al. (2022) Multi-Source Data Fusion Based on Wavelet Decomposition and LSTM for Distributed Photovoltaic Power Prediction. 2022 IEEE 8th International Conference on Computer and Communications (ICCC), Chengdu, 9-12 December 2022, 2246-2250. https://doi.org/10.1109/ICCC56324.2022.10065771 |
| [7] | Zhang, Y., Zhao, Y., Kong, C., et al. (2020) A New Prediction Method Based on VMD-PRBF-ARMA-E Model Considering Wind Speed Characteristic. Energy Conversion and Management, 203, Article ID: 112254. https://doi.org/10.1016/j.enconman.2019.112254 |
| [8] | Zhou, Z., Dai, Y., Xiao, J., et al. (2022) Research on Short-Time Wind Speed Prediction in Mountainous Areas Based on Improved ARIMA Model. Sustainability, 14, Article No. 15301. https://doi.org/10.3390/su142215301 |
| [9] | Barjasteh, A., Ghafouri, S.H. and Hashemi, M. (2024) A Hybrid Model Based on Discrete Wavelet Transform (DWT) and Bidirectional Recurrent Neural Networks for Wind Speed Prediction. Engineering Applications of Artificial Intelligence, 127, Article ID: 107340. https://doi.org/10.1016/j.engappai.2023.107340 |
| [10] | Abbasipour, M., Lgder, M.A. and Liang, X. (2021) A Novel Hybrid Neural Network-Based Day-Ahead Wind Speed Forecasting Technique. IEEE Access, 9, 151142-151154. https://doi.org/10.1109/ACCESS.2021.3126747 |
| [11] | Wang, J., Zhang, W., Liu, X., et al. (2012) Modifying Wind Speed Data Observed from Manual Observation System to Automatic Observation System Using Wavelet Neural Network. Physics Procedia, 25, 1980-1987. https://doi.org/10.1016/j.phpro.2012.03.338 |
| [12] | Singh, D.S. and Zhao, Q. (2016) Pseudo-Fault Signal Assisted EMD for Fault Detection and Isolation in Rotating Machines. Mechanical Systems and Signal Processing, 81, 202-218. https://doi.org/10.1016/j.ymssp.2016.03.007 |
| [13] | Qin, Q., Lai, X. and Zou, J. (2019) Direct Multistep Wind Speed Forecasting Using LSTM Neural Network Combining EEMD and Fuzzy Entropy. Applied Sciences, 9, 126. https://doi.org/10.3390/app9010126 |
| [14] | Li, Z., Luo, X., Liu, M., et al. (2022) Wind Power Prediction Based on EEMD-Tent-SSA-LS-SVM. Energy Reports, 8, 3234-3243. https://doi.org/10.1016/j.egyr.2022.02.150 |
| [15] | Chen, Y., Dong, Z., Wang, Y., et al. (2021) Short-Term Wind Speed Predicting Framework Based on EEMD-GA-LSTM Method under Large Scaled Wind History. Energy Conversion and Management, 227, Article ID: 113559. https://doi.org/10.1016/j.enconman.2020.113559 |
| [16] | 魏炘, 石强, 符文熹, 等. 考虑CEEMDAN样本熵和SVR的短期风速预测[J]. 水电能源科学, 2020, 38(11): 207-210. |
| [17] | Gao, X., Qi, C., Xue, G., et al. (2020) Forecasting the Heat Load of Residential Buildings with Heat Metering Based on CEEMDAN-SVR. Energies, 13, Article No. 6079. https://doi.org/10.3390/en13226079 |
| [18] | 方娜, 陈浩, 邓心, 等. 基于VMD-ARIMA-DBN的短期电力负荷预测[J]. 电力系统及其自动化学报, 2023, 35(6): 59-65. |
| [19] | 王亚娟, 李怀良, 庹先国, 等. 一种集成经验模态分解的样本熵阈值微地震信号降噪方法[J]. 物探与化探, 2019, 43(5): 1083-1089. |
| [20] | Torre, M.E., Colominas, M.A., Schlotthauer, G., et al. (2011) A Complete Ensemble Empirical Mode Decomposition with Adaptive Noise. International Conference on Acoustics, Speech, and Signal Processing, Prague, 22-27 May 2011, 4144-4147. https://doi.org/10.1109/ICASSP.2011.5947265 |
| [21] | Xiao, Y., Kang, N., Hong, Y., et al. (2017) Misalignment Fault Diagnosis of DFWT Based on IEMD Energy Entropy and PSO-SVM. Entropy (Basel, Switzerland), 19, Article No. 6. https://doi.org/10.3390/e19010006 |
| [22] | 石柱, 虞莉娟, 郑拓, 等. 基于VMD-PSO-SVR模型的短期负荷预测[J]. 武汉理工大学学报, 2023, 45(6): 139-145. |
