摘要
风向预测是提高风能转化率、保障偏航系统运行安全的基础。为了建立高精度风向预测算法,提出一种基于自校正小波长短时记忆网络(self-tuning wavelet long-short term memory neural network,SWLSTM)算法。首先,利用互信息法选取时间序列特征的长度;然后,经过小波分解进一步提取风向序列的时域信息和频域信息;在此基础上,选择长短时记忆递归神经网络(long-short term memory neural network,LSTM)进行建模;最后,设计误差自校正策略,进一步提升预测精度。为了验证该文算法的适应性与预测精度,选择风电场实际风向数据分别进行实验。实验结果表明,SWLSTM算法优于常见数据建模方法,风向预测误差小于1.73%,满足风电场的生产要求。
The wind direction forecasting is the basis of raising the wind energy conversion rate and the yaw control system security. To construct an accurate wind direction prediction model, a self-tuning wavelet long-short term memory neural network(SWLSTM) algorithm was presented. First, the feature length was selected via the mutual information method.Then, the time and frequency domain information of time series were extracted by the wavelet decomposition. Consequently, the wind direction forecasting model was established with the long-short term memory neural network(LSTM). Additionally, a self-tuning strategy was proposed to improve prediction accuracy.To testify the robustness and the accuracy of the SWLSTM algorithm, the actual wind farm data based experiments were carried out. The experiment results indicate that the SWLSTM algorithm is superior to the other common-used algorithms. The prediction errors are less than 1.73%, which can meet the requirements of wind farm.
引文
[1]张东东,崔新维.BP神经网络在风力发电机风向预测中的应用[J].太阳能,2015(3):47-49.Zhang Dongdong,Cui Xinwei.Application of BP neural network in wind direction forecast of wind turbine[J].Solar Energy,2015(3):47-49(in Chinese).
[2]李莉,刘永前,杨勇平,等.基于CFD流场预计算的短期风速预测方法[J].中国电机工程学报,2013,33(7):27-32.Li Li,Liu Yongqian,Yang Yongping,et al.Short-term wind speed forecasting based on CFD pre-calculated flow fields[J].Proceedings of the CSEE,2013,33(7):27-32(in Chinese).
[3]Cheng W Y Y,Liu Yubao,Bourgeois A J,et al.Short-term wind forecast of a data assimilation/weather forecasting system with wind turbine anemometer measurement assimilation[J].Renewable Energy,2017,107:340-351.
[4]Erdem E,Shi Jing.ARMA based approaches for forecasting the tuple of wind speed and direction[J].Applied Energy,2011,88(4):1405-1414.
[5]Kavasseri R G,Seetharaman K.Day-ahead wind speed forecasting using f-ARIMA models[J].Renewable Energy,2009,34(5):1388-1393.
[6]Liu Heping,Shi Jing,Erdem E.Prediction of wind speed time series using modified Taylor Kriging method[J].Energy,2010,35(12):4870-4879.
[7]Masseran N,Razali A M,Ibrahim K,et al.Fitting a mixture of von Mises distributions in order to model data on wind direction in Peninsular Malaysia[J].Energy Conversion and Management,2013,72:94-102.
[8]Wang Shouxiang,Zhang Na,Wu Lei,et al.Wind speed forecasting based on the hybrid ensemble empirical mode decomposition and GA-BP neural network[J].Renewable Energy,2016,94:629-636.
[9]孙驷洲,付敬奇,朱峰.CGAQPSO优化LSSVM短期风电预测[J].电子测量与仪器学报,2016,30(11):1718-1725.Sun Sizhou,Fu Jingqi,Zhu Feng.Short-term wind power prediction based on LSSVM optimized by chaos Gauss attractor quantum-behaved particle swarm optimization[J].Journal of Electronic Measurement and Instrumentation,2016,30(11):1718-1725(in Chinese).
[10]杨锡运,孙宝君,张新房,等.基于相似数据的支持向量机短期风速预测仿真研究[J].中国电机工程学报,2012,32(4):35-41,S5.Yang Xiyun,Sun Baojun,Zhang Xinfang,et al.Short-term wind speed forecasting based on support vector machine with similar data[J].Proceedings of the CSEE,2012,32(4):35-41,S5(in Chinese).
[11]Cadenas E,Rivera W.Short term wind speed forecasting in La Venta,Oaxaca,México,using artificial neural networks[J].Renewable Energy,2009,34(1):274-278.
[12]Mohandes M A,Halawani T O,Rehman S,et al.Support vector machines for wind speed prediction[J].Renewable Energy,2004,29(6):939-947.
[13]Zhou Junyi,Shi Jing,Li Gong.Fine tuning support vector machines for short-term wind speed forecasting[J].Energy Conversion and Management,2011,52(4):1990-1998.
[14]Rahman A,Srikumar V,Smith A D.Predicting electricity consumption for commercial and residential buildings using deep recurrent neural networks[J].Applied Energy,2018,212:372-385.
[15]Lago J,De Ridder F,De Schutter B.Forecasting spot electricity prices:Deep learning approaches and empirical comparison of traditional algorithms[J].Applied Energy,2018,221:386-405.
[16]Qiu Xueheng,Ren Ye,Suganthan P N,et al.Empirical mode decomposition based ensemble deep learning for load demand time series forecasting[J].Applied Soft Computing,2017,54:246-255.
[17]Liu Hui,Mi Xiwei,Li Yanfei.Smart multi-step deep learning model for wind speed forecasting based on variational mode decomposition,singular spectrum analysis,LSTM Network and ELM[J].Energy Conversion and Management,2018,159:54-64.
[18]Liu Hui,Mi Xiwei,Li Yanfei.Wind speed forecasting method based on deep learning strategy using empirical wavelet transform,long short term memory neural network and Elman neural network[J].Energy Conversion and Management,2018,156:498-514.
[19]Osório G J,Matias J C O,Catal?o J P S.Short-term wind power forecasting using adaptive neuro-fuzzy inference system combined with evolutionary particle swarm optimization,wavelet transform and mutual information[J].Renewable Energy,2015,75:301-307.
[20]Yu Chuanjin,Li Yongle,Zhang Mingjin.An improved wavelet transform using singular spectrum analysis for wind speed forecasting based on Elman neural network[J].Energy Conversion and Management,2017,148:895-904.
[21]Singh K J,De T.MLP-GA based algorithm to detect application layer DDoS attack[J].Journal of Information Security and Applications,2017,36:145-153.
[22]Guo Zhenhai,Wu Jie,Lu Haiyan,et al.A case study on a hybrid wind speed forecasting method using BP neural network[J].Knowledge-Based Systems,2011,24(7):1048-1056.
[23]王孔森,盛戈皞,孙旭日,等.基于径向基神经网络的输电线路动态容量在线预测[J].电网技术,2013,37(6):1719-1725.Wang Kongsen,Sheng Gehao,Sun Xuri,et al.Online prediction of transmission dynamic line rating based on radial basis function neural network[J].Power System Technology,2013,37(6):1719-1725(in Chinese).
[24]Tang Zhenhao,Zhang Haiyang,Che Ping,et al.Data analytics based dual-optimized adaptive model predictive control for the power plant boiler[J].Mathematical Problems in Engineering,2017,2017:8048962.
