Short-term photovoltaic power prediction model based on quadratic frequency domain decomposition algorithm for neural networks

Shihan Li; Chun Yang; Yuan Gao

doi:10.1117/12.3004418

25 September 2023 Short-term photovoltaic power prediction model based on quadratic frequency domain decomposition algorithm for neural networks

Shihan Li, Chun Yang, Yuan Gao

Author Affiliations +

Proceedings Volume 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023); 1278811 (2023) https://doi.org/10.1117/12.3004418
Event: Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 2023, Kuala Lumpur, Malaysia

Abstract

This paper decomposes the normalised and pre-processed raw PV data into different components by the quadratic frequency domain decomposition method, and then uses the random forest algorithm and the GRU prediction neural network optimised by the genetic algorithm to process the different components, and then reconstructs the results of the different prediction methods to obtain a short-term PV forecasting model. The improved quadratic frequency domain decomposition forecasting model is applied to the forecasting problem and compared with the traditional forecasting method, and the improved quadratic frequency domain decomposition forecasting model is proved to obtain more accurate forecasting results.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Shihan Li, Chun Yang, and Yuan Gao "Short-term photovoltaic power prediction model based on quadratic frequency domain decomposition algorithm for neural networks", Proc. SPIE 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 1278811 (25 September 2023); https://doi.org/10.1117/12.3004418

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