结合HS算法与ESN算法的光伏发电短期出力预测  

Short-term Power Forecasting for Photovoltaic Generation Based on HS-ESN

作　　者：温润[1] 谭丽[1] 

机构地区：[1]兰州交通大学自动化与电气工程学院,兰州730070

出　　处：《计算机科学》2017年第6期226-231,265,共7页Computer Science

摘　　要：为提高光伏发电系统短期出力预测的精度,提出了一种和声搜索(Harmony Search,HS)算法与回声状态网络(Echo State Network,ESN)算法相结合的预测模型。该模型以光伏电站的历史发电量数据和气象数据为基础。首先通过相似日选择算法挑选出预测日的相似日,将相似日的气象特征向量和预测日的气象特征向量的差值作为预测模型的输入变量;然后选择训练样本,并用和声搜索算法优化后的回声状态网络模型(HS-ESN)对样本进行训练和预测;最后以甘肃某光伏电站为例进行实例验证。实证分析表明,利用和声搜索算法优化回声状态网络预测模型的储备池参数可有效提高回声状态网络的预测精度,因此该模型具有较好的实用价值。To improve the accuracy of short-term power prediction for photovoltaic generation,the forecasting model of combination of harmony search（HS）algorithm and echo state network（ESN）algorithm was proposed.The model is based on historical power and weather data provided by aphotovoltaic plant.Firstly,it selects the similar day of the forecasting day by the algorithm of similar day,and treats the difference of meteorological feature between the similar day and the forecasting day as the input variable of the model.Secondly,it chooses the training sample to train and forecast with the ESN model based on optimization of HS algorithm.Finally,it takes the photovoltaic plant in Gansu province as an example to test HS-ESN prediction model.Case analysis shows that the parameters of the reservoir of ESN prediction model optimized by HS algorithm can improve the prediction accuracy effectively,so it has better utility value.

关 键 词：光伏发电系统 短期出力预测 和声搜索算法 回声状态网络算法 相似日选择算法 HS-ESN预测模型 

分 类 号：TM615[电气工程—电力系统及自动化]