A short-term prediction model for photovoltaic power forecasting based on CEEMDAN-CS-LSTM

Weijin Mao; Wenzhen Wu

doi:10.1117/12.3024734

13 May 2024 A short-term prediction model for photovoltaic power forecasting based on CEEMDAN-CS-LSTM

Weijin Mao, Wenzhen Wu

Proceedings Volume 13159, Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023); 131590D (2024) https://doi.org/10.1117/12.3024734
Event: Eighth International Conference on Energy System, Electricity and Power (ESEP 2023), 2023, Wuhan, China

Abstract

Accurate prediction of PV power is essential to maximize solar energy utilization, enhance the performance of PV power generation systems, and ensure the dependability of power infrastructures. In this paper, an approach based on CS-LSTM neural network is proposed for short term power forecasting. The proposed approach involves processing the data using CEEMDAN, followed by the application of the CS algorithm to determine the optimal LSTM hyperparameters. To evaluate the accuracy and dependability of the model, CEEMDAN-CS-LSTM is compared to other models. Experiments show that CEEMDAN-CS-LSTM outperforms the other models in terms of prediction accuracy and stability.

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

Citation Download Citation

Weijin Mao and Wenzhen Wu "A short-term prediction model for photovoltaic power forecasting based on CEEMDAN-CS-LSTM", Proc. SPIE 13159, Eighth International Conference on Energy System, Electricity, and Power (ESEP 2023), 131590D (13 May 2024); https://doi.org/10.1117/12.3024734

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