基于ICA优化SVR的风电场短期风速预测  

Short-Term Wind Speed Prediction of Wind Farm Based on ICA Optimization of SVR

作　　者：尤亚锋 周武能[1] YOU Yafeng;ZHOU Wuneng(School of Information Science and Technology,Donghua University,Shanghai 201600)

机构地区：[1]东华大学信息科学与技术学院,上海201600

出　　处：《计算机与数字工程》2020年第7期1547-1551,共5页Computer & Digital Engineering

基　　金：国家自然科学基金项目(编号:61573095)资助。

摘　　要：提出了一种新的预测风速的优化组合算法,利用帝国竞争算法实现参数寻优,优化支持向量机回归的关键参数,建立精准的回归预测模型用来预测风速。通过实例证明,优化后的算法与传统人工神经网络相比较,在预测精度上有一定的提升,从而证实了算法的有效性。A new optimal combination algorithm for predicting wind speed is proposed.The imperial competition algorithm is used to optimize the parameters,the key parameters of support vector machine regression are optimized,and a precise regression prediction model is established to predict the wind speed.The example proves that compared with the traditional artificial neural net⁃work,the optimized algorithm has a certain improvement in prediction accuracy,which confirms the effectiveness of the algorithm.

关 键 词：帝国竞争算法 参数寻优 支持向量机回归 风速预测 人工神经网络 

分 类 号：TM614[电气工程—电力系统及自动化]