论文部分内容阅读
为提高短期风速预测精度,研究了考虑气象特征提取的短期风速预测方法。针对输入气象特征较多且难以提取,提出一种简易气象特征提取方法,通过极限学习机和改进珊瑚礁算法,从较多气象特征中提取最优气象特征。以最优气象特征为预测模型输入,能够有效增强模型泛化能力。对墨西哥某风电场风速预测结果表明,改进珊瑚礁算法结合极限学习机的方法能够有效提取气象特征,提高预测精度,具有一定的实用价值。
In order to improve the prediction accuracy of short-term wind speed, the short-term wind speed prediction method considering meteorological feature extraction is studied. Aiming at the problems that the input meteorological features are more and difficult to extract, a simple meteorological feature extraction method is proposed. The optimal meteorological features are extracted from more meteorological features by using extreme learning machine and improved coral reef algorithm. Taking the best meteorological characteristics as the input of prediction model, the model generalization ability can be effectively enhanced. The wind speed prediction results of a wind farm in Mexico show that the improved coral reef algorithm combined with extreme learning machine can effectively extract the meteorological features and improve the prediction accuracy, and has certain practical value.