一种改进概率权的短时风电功率组合预测方法  

A short-term wind power predication method based on improved probability weights theory

作　　者：王林泓[1] 杨余鸿 

机构地区：[1]重庆电子工程职业学院应用电子学院,重庆401331 [2]重庆大学输配电装备及系统安全与新技术国家重点实验室,重庆400044

出　　处：《电测与仪表》2015年第8期45-49,共5页Electrical Measurement & Instrumentation

摘　　要：针对风电功率预测组合模型中各模型的权重系数确定的问题,提出一种基于概率权和优化相融合的组合模型权重系数的确定方法。首先利用概率和权数的同质性,对多种单个模型进行优化组合,然后确定单个模型的最优权重系数,最后将组合预测模型改进为动态组合预测模型以提高预测精度。实验测试表明:提出的基于概率权的风电功率组合模型能有效提高短期风电功率预测结果的准确性,而动态权重系数的自适应变化可以进一步增强该方法在风功率预测中的普遍适用性。According to the problem of weight determination of every model in combined wind power prediction, a probability-based weight and optimization combined method is proposed. Firstly, different prediction models are opti- mized and combined based on the feature of homogeneity between weights and probability. Then the optimal weight under different wind fields for every model is determined. At last, the combined model is improved to dynamical pre- diction model for higher prediction accuracy. Experimental results indicate that the proposed method based on proba- bility can effectively improve the accuracy of short-term wind power prediction. The combined prediction model has certain reference value for wind power prediction.

关 键 词：风电功率预测 组合模型 概率权 动态预测 

分 类 号：TM614[电气工程—电力系统及自动化]