南京信息工程大学学报2023，Vol.15Issue(6)：684-691,8.DOI:10.13878/j.cnki.jnuist.20230210001
基于改进Stacking与误差修正的短期太阳辐照度预测
Short-term solar irradiance prediction based on improved Stacking and error correction
摘要
Abstract
To improve the accuracy and reliability of solar irradiance prediction for photovoltaic power system,we propose a model to forecast short-term solar irradiance based on improved Stacking ensemble learning and error cor-rection.First,the Gradient Boosting Decision Tree(GBDT)is used to perform feature selection and remove redun-dant characteristics of original data set,thus increase prediction accuracy and computing efficiency.Then,an im-proved Stacking irradiance prediction model is established.In accordance with the difference in prediction accuracy of prediction models in the primary layer under K-fold cross-validation,the prediction results are weighted,and the Box-Cox is employed to transform and process the training set data input from the first layer to the second layer of Stacking,so as to increase the normality and homoscedasticity of prediction.Finally,the historical prediction error data are extracted,and Random Forest is applied to construct an error model to further improve the prediction accu-racy.The experimental results show that,compared with traditional models and classic Stacking models,the proposed method significantly improves the prediction performance on solar irradiance.关键词
太阳辐照度/光伏发电/Stacking算法/回归预测算法/交叉验证Key words
solar radiation/photovoltaic power generation/Stacking/regression prediction algorithm/cross-validation分类
信息技术与安全科学引用本文复制引用
王珊珊,吴霓,何嘉文,朱威..基于改进Stacking与误差修正的短期太阳辐照度预测[J].南京信息工程大学学报,2023,15(6):684-691,8.基金项目
国家重点研发计划(2018YFC0116100) （2018YFC0116100）
湖北省重点研发计划(2020BAB114) （2020BAB114）
湖北省教育厅科学研究计划重点项目(D20211402) （D20211402）
