An extreme random tree model combining EDA and PCA for predicting PV module temperature method

Li Peng; Li Liao; Gang Lai; Meiru Li; Liang Zhang

doi:10.1117/12.3016364

1 February 2024 An extreme random tree model combining EDA and PCA for predicting PV module temperature method

Li Peng, Li Liao, Gang Lai, Meiru Li, Liang Zhang

Proceedings Volume 13068, Fifth International Conference on Optoelectronic Science and Materials (ICOSM 2023); 130681I (2024) https://doi.org/10.1117/12.3016364
Event: Fifth International Conference on Optoelectronic Science and Materials (ICOSM 2023), 2023, Hefei, China

Abstract

The variation in temperature of PV modules can affect the efficiency of power generation. Therefore, many studies have been conducted to predict the temperature of PV modules. In this paper, the extreme random tree algorithm is utilized with EDA and PCA analysis to accurately predict the temperature of PV modules in the next hour by filtering and structuring available features. EDA and PCA analysis enhance the model's understanding of the degree of addition, subtraction, and similarity between different features. They also help filter out and construct new key features. Compared to the random forest commonly used in previous studies, the extreme random tree algorithm is more random in the choice of bifurcation in tree building, enabling it to jump out of the vicious circle of local optima and learn the data adequately. After training, the model is tested using actual operating wind turbine data for validation, and the results indicate that the method is highly accurate, noise-resistant, targeted, and practical.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Li Peng, Li Liao, Gang Lai, Meiru Li, and Liang Zhang "An extreme random tree model combining EDA and PCA for predicting PV module temperature method", Proc. SPIE 13068, Fifth International Conference on Optoelectronic Science and Materials (ICOSM 2023), 130681I (1 February 2024); https://doi.org/10.1117/12.3016364

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available