复杂时空失配场景下分布式光伏功率鲁棒预测

打开文本图片集

关键词：分布式光伏功率预测；时空失配校正；鲁棒滚动预测；多模型集成；iTransformer模型中图分类号：TM615；TP181 文献标志码：A 文章编号： 1000-5013（2026）01-0028-1：

Robust Forecasting of Distributed Photovoltaic Power Under Complex Spatiotemporal Mismatch Conditions

HAN Qiang1，GUO Yuxiang1，ZHANG Siwei¹， SONG Tairan²，FU Huichu²，LI Tan 2 ， AN Shumo，QIAO Yan1

（1.Institute of Systems Engineering and Joint Laboratory of Intelligent Science and Systems， Macau University of Science and Technology，Macao 999o78，China; 2.IKAS Holdings （Beijing）Limited Company，Beijing l026oo，China; 3.Shenzhen Futian District Foreign Language School，Shenzhen 518ooo，China）

Abstract：To address the mismatch problem in sampling intervals and spatiallocations between meteorological stations and photovoltaic panel monitoring，a robust forecasting framework for distributed photovoltaic power under complex spatiotemporal mismatch conditions is proposed.First，a mechanism-constrained spatiotemporal corection process is constructed to tackle the spatiotemporal mismatch between meteorological stations and photovoltaic panels.Through preprocessing and data calibration，a relative consistent mapping of meteorological observations to iradiance and temperature on photovoltaic panels is achieved，forming high-quality，temporally coherent multi-source inputs. Secondly，a variational mode decomposition （VMD） module is employed to perform multi-scale dcomposition of key meteorological and electrical variables.This is folowed by a kernel principal component analysis （KPCA） module for nonlinear dimensionality reduction and redundancy suppression，thereby enhancing feature representation and noise resistance.Finally，an iTransformer model is introduced as the temporal predictor to model the selected feature sequences，while the sparrow search algorithm （SSA） model is used to globall optimize critical hyperparameters，resulting in the VMD-KPCA-SSA-iTransformer prediction model. The results show that under typical conditions such as sunny，cloudy，and rainy weather，the proposed model consistently outperforms comparison models in terms of key metrics such as the coefficient of determination （R2 ），root mean squared error（RMSE），and mean absolute error （MAE）.

Keywords：forecasting of distributed photovoltaic power; spatiotemporal mismatch correction； robust rolling forecasting；ensemble modeling；iTransformer model

近年来，在碳中和与能源结构转型双重驱动下，光伏装机高速增长，已成为新增可再生能源主体[1-2]。（剩余19506字）