为提高风速序列预测精度,提出一种基于两步分解的短期风速组合预测模型,首先使用鲁棒经验模态分解（REMD）将风速数据分解为不同频率的子序列,然后将REMD分解得到的高频模态分量使用小波包分解（WPD）进行第二步分解,降低风速序列不稳定性,提高其可预测性。其次对分解得到的高频子序列建立长短期记忆神经网络（LSTM）预测模型,低频子序列建立差分自回归移动平均模型（ARIMA）预测模型。最后叠加子序列预测结果得到风速预测结果。通过两组不同风速数据集的实验对该模型的性能进行科学评估,模型预测结果的平均绝对误差分别为0.3026、0.1255;均方根误差分别为0.498、0.1607。与其他几种对比预测模型相比,验证该模型具有一定的优越性。
Abstract
To improve the accuracy of wind speed series prediction, a combined short-term wind speed prediction model based on two-step decomposition is proposed. The wind speed data are first decomposed into subseries of different frequencies using robust empirical modal decomposition （REMD）, and then the high-frequency modal components obtain from REMD decomposition are decomposed in a second step using wavelet packet decomposition （WPD） to reduce the wind speed series instability and improve its predictability. Next, a long short-term memory neural network （LSTM） prediction model is built for the decomposed high-frequency subsequences, and a differential autoregressive moving average model （ARIMA） prediction model is built for the low-frequency subsequences. Finally, the wind speed prediction results are obtained by superimposing the subseries prediction results. The performance of the model is scientifically evaluated through experiments with two different wind speed datasets, and the mean absolute errors of the model predictions are 0.3026 and 0.1255. The root mean square errors are 0.498 and 0.1607, respectively. Compared with other comparative prediction models, it is proved that this model has certain advantages.
关键词
风速 /
神经网络 /
统计方法 /
两步分解 /
鲁棒经验模态分解 /
组合预测
Key words
wind speed /
neural network /
statistical method /
two-step decomposition /
REMD /
combination prediction
{{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] DONG Y X, WANG J, XIAO L, et al.Short-term wind speed time series forecasting based on a hybrid method with multiple objective optimization for non-convex target[J]. Energy, 2021, 215: 119180.
[3] 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.
[4] ZHANG Y G, ZHAO Y P, SHEN X Y, et al.A comprehensive wind speed prediction system based on Monte Carlo and artificial intelligence algorithms[J]. Applied energy, 2022, 305: 117815.
[5] 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.
[6] YUNUS K, THIRINGER T, CHEN P Y.ARIMA-based frequency-decomposed modeling of wind speed time series[J]. IEEE transactions on power systems, 2016, 31(4): 2546-2556.
[7] 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.
[8] WANG S, WANG J Z, LU H Y, et al.A novel combined model for wind speed prediction-combination of linear model, shallow neural networks, and deep learning approaches[J]. Energy, 2021, 234: 121275.
[9] 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.
[10] CHEN G G, TANG B R, ZENG X J, et al.Short-term wind speed forecasting based on long short-term memory and improved BP neural network[J]. International journal of electrical power & energy systems, 2022, 134: 107365.
[11] 赵泽妮, 云斯宁, 贾凌云, 等. 基于统计模型的短期风能预测方法研究进展[J]. 太阳能学报, 2022, 43(11): 224-234.
ZHAO Z N, YUN S N, JIA L Y, et al.Recent progress in short-term forecasting of wind energy based on statistical models[J]. Acta energiae solaris sinica, 2022, 43(11): 224-234.
[12] AHMED A, KHALID M.A review on the selected applications of forecasting models in renewable power systems[J]. Renewable and sustainable energy reviews, 2019, 100: 9-21.
[13] MI X W, ZHAO S.Wind speed prediction based on singular spectrum analysis and neural network structural learning[J]. Energy conversion and management, 2020, 216: 112956.
[14] MI X W, LIU H, LI Y F.Wind speed prediction model using singular spectrum analysis, empirical mode decomposition and convolutional support vector machine[J]. Energy conversion and management, 2019, 180: 196-205.
[15] 贺坤, 李星野. 基于经验模态分解和遗传算法改进的神经网络模型的风速时间序列预测[J]. 电子测量技术, 2018, 41(8): 146-149.
HE K, LI X Y.Wind speed forcasting based on EEMD-GA-BP[J]. Electronic measurement technology, 2018, 41(8): 146-149.
[16] 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.
[17] 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.
[18] 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): 103-111.
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): 103-111.
[19] LIU Z L, PENG D D, ZUO M J, et al.Improved Hilbert-Huang transform with soft sifting stopping criterion and its application to fault diagnosis of wheelset bearings[J]. ISA transactions, 2022, 125: 426-444.
[20] 向玲, 刘佳宁, 苏浩, 等. 基于CEEMDAN二次分解和LSTM的风速多步预测研究[J]. 太阳能学报, 2022, 43(8): 334-339.
XIANG L, LIU J N, SU H, et al.Research on multi-step wind speed forecast based on CEEMDAN secondary decomposition and LSTM[J]. Acta energiae solaris sinica, 2022, 43(8): 334-339.
[21] 赵征, 汪向硕. 基于CEEMD和改进时间序列模型的超短期风功率多步预测[J]. 太阳能学报, 2020, 41(7): 352-358.
ZHAO Z, WANG X S.Ultra-short-term multi-step wind power prediction based on ceemd and improved time series model[J]. Acta energiae solaris sinica, 2020, 41(7): 352-358.
PDF(2213 KB)
