CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 13513 > Article
Open Access Paper
15 January 2025 A fusion model for predicting distributed photovoltaic power
Rui Li, Hui Hui, Ming Wang, Yang Zhao, Miao Zhao, Qianfan Zhou
Author Affiliations +
Proceedings Volume 13513, The International Conference Optoelectronic Information and Optical Engineering (OIOE2024); 135133Z (2025) https://doi.org/10.1117/12.3056624
Event: The International Conference Optoelectronic Information and Optical Engineering (OIOE2024), 2024, Wuhan, China
Abstract
In this paper a predictive method using a fused model for separately processing data is proposed to address the strong stochasticity and variability in distributed photovoltaic (PV) power plants which cannot be adequately accommodated by traditional approaches. The data from the distributed PV plant are processed to meet the precision requirements of prediction. Firstly the isolation forest (iForest) algorithm is employed for data cleaning followed by data reconstruction through cubic spline interpolation for the cleaned data with missing values. Finally prediction is carried out using a stacking fused model with the input data having undergone feature engineering through correlation analysis. The effectiveness of the proposed method is confirmed through validation using real-world data.
(2025) Published by SPIE. Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Rui Li, Hui Hui, Ming Wang, Yang Zhao, Miao Zhao, and Qianfan Zhou "A fusion model for predicting distributed photovoltaic power", Proc. SPIE 13513, The International Conference Optoelectronic Information and Optical Engineering (OIOE2024), 135133Z (15 January 2025); https://doi.org/10.1117/12.3056624
PROCEEDINGS
 6 PAGES
DOWNLOAD PAPER SAVE TO MY LIBRARY
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Photovoltaics
Data modeling
Solar radiation models
Interpolation
Machine learning
Data analysis
Meteorology
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top