Improved convolutional neural network-based quantile regression for regional photovoltaic generation probabilistic forecast

作     者：Yu, Yixiao Wang, Mengxia Yan, Fangqing Yang, Ming Yang, Jiajun 

作者机构：Shandong Univ Key Lab Power Syst Intelligent Dispatch & Control Jinan 250061 Peoples R China State Grid Shandong Elect Power Co Laiwu Elect Power Supply Co Laiwu 271100 Peoples R China State Grid Shaanxi Elect Power Res Inst Xian 710054 Peoples R China 

出 版 物：《IET RENEWABLE POWER GENERATION》 (IET. Renew. Power Gener.)

年 卷 期：2020年第14卷第14期

页      面：2712-2719页

核心收录：

学科分类：0820[工学-石油与天然气工程] 0808[工学-电气工程] 08[工学] 

基　　金：National Key R&D Program of China [2018YFB0904200] eponymous Complement S&T Program of State Grid Corporation of China [SGLNDKOOKJJS1800266] 

主　　题：neural nets regression analysis photovoltaic power systems power grids load forecasting convolutional neural network-based quantile regression regional photovoltaic generation probabilistic forecast photovoltaic plants regional power grid regional PV power generation regional power system operation probabilistic forecast method regional PV generation nonlinear quantile regression nonlinear features nonlinear QR function improved CNN high-dimensional input data complex input data nonlinear QR model quantile forecast information clustered PV plants 

摘      要：Nowadays, an increasing number of photovoltaic (PV) plants are becoming integrated into one regional power grid. Under this circumstance, the probabilistic forecast of regional PV power generation is of significance for the regional power system operation and control. This study presents a novel probabilistic forecast method for regional PV generation that integrates the convolutional neural network (CNN) with non-linear quantile regression (QR). In this method, the CNN structure is enhanced to extract the non-linear features of the input data and generate the non-linear QR function. As a result, the improved CNN can effectively process high-dimensional and complex input data and the non-linear QR model can provide quantile forecast information of regional PV power. The validity of the proposed method is verified by using it to forecast the regional PV generation from the clustered PV plants in the Weifang region of China.