Short-term wind power prediction based on optimized BP neural network with improved ant lion optimization algorithm

Yiwei Xian; Yingbo Tao; Jianguo Li

doi:10.1117/12.3004438

25 September 2023 Short-term wind power prediction based on optimized BP neural network with improved ant lion optimization algorithm

Yiwei Xian, Yingbo Tao, Jianguo Li

Author Affiliations +

Proceedings Volume 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023); 127884L (2023) https://doi.org/10.1117/12.3004438
Event: Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 2023, Kuala Lumpur, Malaysia

Abstract

Accurate short-term wind power forecasting can enhance the safety and reliability of the power system and effectively address the impact of wind power uncertainty on the grid. However, traditional Back Propagation (BP) neural networks for wind power forecasting have issues such as slow convergence, easily getting trapped in local minima, and significantly reducing the accuracy of the prediction model. In order to improve the accuracy of short-term wind power forecasting, an Ant Lion Optimization (ALO) algorithm is employed to optimize the BP neural network (ALO-BP), and a Cauchy Gaussian mutation operator is introduced to optimize the Ant Lion Optimization (CALO) algorithm, which can greatly improve the algorithm's global exploration ability. In this paper, a short-term wind power forecasting model based on the CALO-BP neural network is constructed. The actual historical data from a wind farm in Shanghai is used for simulation testing, and the simulation results are compared with other combination models. The results indicate that the CALO-BP neural network model yields higher prediction accuracy.

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

Citation Download Citation

Yiwei Xian, Yingbo Tao, and Jianguo Li "Short-term wind power prediction based on optimized BP neural network with improved ant lion optimization algorithm", Proc. SPIE 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 127884L (25 September 2023); https://doi.org/10.1117/12.3004438

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