为提高非平稳风速短期预测精度,采用滑动窗口构建滚动分解（RD）与预测方法,通过对比多种神经网络模型的预测结果并结合变分模态分解（VMD）方法,提出采用RD-CNN-BiLSTM神经网络组合模型对非平稳风速序列进行预测。进一步地,针对神经网络组合模型的预测精度不足,提出一种融合误差修正和RD-CNN-BiLSTM神经网络组合模型的非平稳风速短期预测方法。结果表明,对实测风速数据设置滑动窗口并进行一次预测延伸,对延伸后的数据进行分解与修剪重构可有效弱化边界效应的影响并可避免信息泄漏问题。CNN-BiLSTM组合模型相比传统单一的神经网络模型,如自回归积分滑动平均（ARIMA）、反向传播（BP）、长短期记忆网络（LSTM）和双向长短期记忆网络（BiLSTM）模型具有更高的预测精度。采用二次抛物线的误差修正方法相比线性误差修正方法更优,尤其在高风速区间,前者对预测精度的提升效果尤为显著。通过其他时段的实测风速数据预测结果,验证了所提出的融合误差修正和RD-CNN-BiLSTM神经网络组合模型在非平稳风速短期预测方面具有较高的预测精度与泛化性。
Abstract
To improve the accuracy of short-term prediction for non-stationary wind speeds, a rolling decomposition （RD） and prediction method was built by using a sliding window. By comparing the predictive results of various neural network models and incorporating the variational mode decomposition（VMD） algorithm, an RD-CNN-BiLSTM neural network combined model was proposed for predicting non-stationary wind speed sequences. Furthermore, addressing the predictive accuracy limitations of the neural network combined model, a short-term predictive approach for non-stationary wind speeds that integrates the error correction and RD-CNN-BiLSTM neural network combined model was proposed. The research results indicate that applying sliding windows to the actual wind speed data and carrying out a single prediction and extension, followed by decomposition, trimming, and reconstruction of the extended data, the impact of boundary effects can be effectively weakened and the information leakage can be prevented. The CNN-BiLSTM combined model outperforms traditional individual neural network models, such as autoregressive integrated moving average（ARIMA）, back propagation（BP）, long short-term memory（LSTM）, and bidirectional long short-term memory （BiLSTM） models, in terms of the predictive accuracy. It was found that the quadratic parabola error correction method is superior to the linear error correction method, particularly in high wind speed ranges, where the predictive accuracy improvement by the former method is especially significant. The predictive results from actual wind speed data at different time intervals further validate that the proposed approach of integrating error correction and RD-CNN-BiLSTM neural network combined model has high predictive accuracy and generalization in short-term prediction of non-stationary wind speeds.
关键词
非平稳风速 /
短期预测 /
卷积神经网络 /
信息泄漏 /
滑动窗口 /
误差修正
Key words
non-stationary wind speed /
short-term prediction /
convolutional neural network /
information leakage /
sliding window /
error correction
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] HONG Y Y, RIOFLORIDO C L P P. A hybrid deep learning-based neural network for 24-h ahead wind power forecasting[J]. Applied energy, 2019, 250: 530-539.
[2] 杨茂, 董昊. 基于数值天气预报风速和蒙特卡洛法的短期风电功率区间预测[J]. 电力系统自动化, 2021, 45(5): 79-85.
YANG M, DONG H.Short-term wind power interval prediction based on wind speed of numerical weather prediction and Monte Carlo method[J]. Automation of electric power systems, 2021, 45(5): 79-85.
[3] ZHANG Y G, ZHAO Y, KONG C H, et al.A new prediction method based on VMD-PRBF-ARMA-E model considering wind speed characteristic[J]. Energy conversion and management, 2020, 203: 112254.
[4] 张宇帆, 艾芊, 林琳, 等. 基于深度长短时记忆网络的区域级超短期负荷预测方法[J]. 电网技术, 2019, 43(6): 1884-1892.
ZHANG Y F, AI Q, LIN L, et al.A very short-term load forecasting method based on deep LSTM RNN at zone level[J]. Power system technology, 2019, 43(6): 1884-1892.
[5] WU C Y, WANG J Z, CHEN X J, et al.A novel hybrid system based on multi-objective optimization for wind speed forecasting[J]. Renewable energy, 2020, 146: 149-165.
[6] 王晓霞, 俞敏, 冀明, 等. 基于气候相似性与SSA-CNN-LSTM的光伏功率组合预测[J]. 太阳能学报, 2023, 44(6): 275-283.
WANG X X, YU M, JI M, et al.Photovoltaic power combination forecasting based on climate similarity and SSA-CNN-LSTM[J]. Acta energiae solaris sinica, 2023, 44(6): 275-283.
[7] 张家安, 刘东, 刘辉, 等. 基于风速波动特征提取的超短期风速预测[J]. 太阳能学报, 2022, 43(9): 308-313.
ZHANG J A, LIU D, LIU H, et al.Ultra short term wind speed prediction based on wind speed fluctuation feature extraction[J]. Acta energiae solaris sinica, 2022, 43(9): 308-313.
[8] 王俊, 李霞, 周昔东, 等. 基于VMD和LSTM的超短期风速预测[J]. 电力系统保护与控制, 2020, 48(11): 45-52.
WANG J, LI X, ZHOU X D, et al.Ultra-short-term wind speed prediction based on VMD-LSTM[J]. Power system protection and control, 2020, 48(11): 45-52.
[9] DE SOUZA U B, ESCOLA J P L, DA CUNHA BRITO L. A survey on Hilbert-Huang transform: evolution, challenges and solutions[J]. Digital signal processing, 2022, 120: 103292.
[10] WANG Y M, WU L.On practical challenges of decomposition-based hybrid forecasting algorithms for wind speed and solar irradiation[J]. Energy, 2016, 112: 208-220.
[11] LI K, SHEN R F, WANG Z G, et al.An efficient wind speed prediction method based on a deep neural network without future information leakage[J]. Energy, 2023, 267: 126589.
[12] SHANG Z H, HE Z S, CHEN Y, et al.Short-term wind speed forecasting system based on multivariate time series and multi-objective optimization[J]. Energy, 2022, 238: 122024.
[13] 叶瑞丽, 郭志忠, 刘瑞叶, 等. 基于小波包分解和改进Elman神经网络的风电场风速和风电功率预测[J]. 电工技术学报, 2017, 32(21): 34-42.
YE R L, GUO Z Z, LIU R Y, et al.Wind speed and wind power forecasting method based on wavelet packet decomposition and improved Elman neural network[J]. Transactions of China Electrotechnical Society, 2017, 32(21): 34-42.
[14] YANG J Z, PANG F, XIANG H W, et al.A novel hybrid deep learning model for forecasting ultra-short-term time series wind speeds for wind turbines[J]. Processes, 2023, 11(11): 3247.
[15] 陈蕻峰, 王贺, 李岩, 等. 组合两步分解和ARIMA-LSTM的短期风速预测研究[J]. 太阳能学报, 2024, 45(2): 164-171.
CHEN H F, WANG H, LI Y, et al.Short-term wind speed prediction by combining two-step decomposition and ARIMA-LSTM[J]. Acta energiae solaris sinica, 2024, 45(2): 164-171.
[16] ZHANG L, WANG F L, SUN T, et al.A constrained optimization method based on BP neural network[J]. Neural computing and applications, 2018, 29(2): 413-421.
[17] HOCHREITER S, SCHMIDHUBER J.Long short-term memory[J]. Neural computation, 1997, 9(8): 1735-1780.
[18] 唐清苇, 向月, 代佳琨, 等. 基于CNN-LSTM的风电场发电功率迁移预测方法[J]. 工程科学与技术, 2024, 56(2): 91-99.
TANG Q W, XIANG Y, DAI J K, et al.Wind farm power transfer forecasting method based on CNN-LSTM[J]. Advanced engineering sciences, 2024, 56(2): 91-99.
[19] CHEN H M, MENG W, LI Y J, et al.An anti-noise fault diagnosis approach for rolling bearings based on multiscale CNN-LSTM and a deep residual learning model[J]. Measurement science and technology, 2023, 34(4): 045013.
[20] ZHOU P H, SHEN L, HAN Y, et al.A short-term wind speed prediction method utilizing rolling decomposition and time-series extension to avoid information leakage[J]. Energy sources, part A: recovery, utilization, and environmental effects, 2024, 46(1): 3338-3362.
[21] XUE J K, SHEN B.A novel swarm intelligence optimization approach: sparrow search algorithm[J]. Systems science & control engineering, 2020, 8(1): 22-34.
[22] NIE Z H, SHEN F, XU D J, et al.An EMD-SVR model for short-term prediction of ship motion using mirror symmetry and SVR algorithms to eliminate EMD boundary effect[J]. Ocean engineering, 2020, 217: 107927.
[23] JABER A M, ISMAIL M T, ALTAHER A M.Empirical mode decomposition combined with local linear quantile regression for automatic boundary correction[J]. Abstract and applied analysis, 2014, 2014(1): 731827.
基金
国家自然科学基金（52478495; 52178451）; 湖南省自然科学基金（2024JJ2002）; 长沙理工大学研究生科研创新项目（CSLGCX23038）
PDF(1463 KB)
