Wind speed forecasting in three different regions of Mexico, using a hybrid ARIMA-ANN model
Wind speed forecasting in three different regions of Mexico, using a hybrid ARIMA-ANN model
复制标题
DOI：
10.1016/j.renene.2010.04.022
复制
发表时间：
2010-12-01
期刊：
影响因子：
8.7
通讯作者：
Rivera, Wilfrido
中科院分区：
文献类型：
--
作者：
Cadenas, Erasmo;Rivera, Wilfrido
本文介绍了下加利福尼亚州塞德罗斯岛、萨卡特卡斯州处女山和金塔纳罗奥州霍尔博克斯的风速预报。使用的时间序列是在大约一个月的时间里，从不同地点的测量直接获得的平均每小时风速数据。为了进行风速预报，建立了由自回归综合移动平均（ARIMA）模型和人工神经网络（ANN）模型组成的混合模型。首先利用ARIMA模型对时间序列进行风速预测，然后利用得到的误差，考虑ARIMA技术无法识别的非线性趋势，建立人工神经网络，从而减小最终误差。混合模型建立后，每个站点的48个样本数据被用于风速预测，并将结果与ARIMA和ANN模型分别进行比较。计算平均误差（ME）、均方误差（MSE）和平均绝对误差（MAE）等统计误差度量来比较三种方法。结果表明，Hybrid模式对3个站点的风速预测精度高于ARIMA和ANN模式。(C) 2010 Elsevier Ltd.版权所有。
In this paper the wind speed forecasting in the Isla de Cedros in Baja California, in the Cerro de la Virgen in Zacatecas and in Holbox in Quintana Roo is presented. The time series utilized are average hourly wind speed data obtained directly from the measurements realized in the different sites during about one month. In order to do wind speed forecasting Hybrid models consisting of Autoregressive Integrated Moving Average (ARIMA) models and Artificial Neural Network (ANN) models were developed. The ARIMA models were first used to do the wind speed forecasting of the time series and then with the obtained errors ANN were built taking into account the nonlinear tendencies that the ARIMA technique could not identify, reducing with this the final errors. Once the Hybrid models were developed 48 data out of sample for each one of the sites were used to do the wind speed forecasting and the results were compared with the ARIMA and the ANN models working separately. Statistical error measures such as the mean error (ME), the mean square error (MSE) and the mean absolute error (MAE) were calculated to compare the three methods. The results showed that the Hybrid models predict the wind velocities with a higher accuracy than the ARIMA and ANN models in the three examined sites. (C) 2010 Elsevier Ltd. All rights reserved.