A deep learning short-term load forecasting method for extreme scenarios

Wuneng Ling; Yan Sun; Qiuwen Li; Jie Lin; Jiaqiu Hu; Zhencheng Liang; Li Xiong

doi:10.1117/12.2689861

7 September 2023 A deep learning short-term load forecasting method for extreme scenarios

Wuneng Ling, Yan Sun, Qiuwen Li, Jie Lin, Jiaqiu Hu, Zhencheng Liang, Li Xiong

Proceedings Volume 12790, Eighth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023); 127901D (2023) https://doi.org/10.1117/12.2689861
Event: 8th International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023), 2023, Hangzhou, China

Abstract

Short-term load forecasting is a crucial for improving the level of power grid dispatching and operation. In recent years, extreme weather occurs frequently, and deep learning is a method that depends on data volume, which leads to low accuracy of load forecasting in extreme scenarios. In this paper, the regularization technique is used to avoid the overfitting of deep learning in extreme scenes, by adding the regularization term to the objective function of the neural network, and improving the back propagation algorithm. Finally, this paper proves that regularization can effectively improve the load forecasting accuracy in extremely small sample scenarios through the comparison of actual examples.

Citation Download Citation

Wuneng Ling, Yan Sun, Qiuwen Li, Jie Lin, Jiaqiu Hu, Zhencheng Liang, and Li Xiong "A deep learning short-term load forecasting method for extreme scenarios", Proc. SPIE 12790, Eighth International Conference on Electromechanical Control Technology and Transportation (ICECTT 2023), 127901D (7 September 2023); https://doi.org/10.1117/12.2689861

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