Electric bus charging load forecasting method-based on improved spectral clustering and IPSO-LSTM

Jiangzhe Huang; Yiqiong Liu; Bin Zhou

doi:10.1117/12.3004949

25 September 2023 Electric bus charging load forecasting method-based on improved spectral clustering and IPSO-LSTM

Jiangzhe Huang, Yiqiong Liu, Bin Zhou

Proceedings Volume 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023); 127881P (2023) https://doi.org/10.1117/12.3004949
Event: Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 2023, Kuala Lumpur, Malaysia

Abstract

The accurate prediction of the charging load of electric buses is helpful to the rational dispatching of the power grid. Therefore, this paper proposes a daily load curve forecasting method for electric bus clusters. First, a two-scale similarity measurement method for load curve is proposed, and the improved spectral clustering algorithm is used to cluster the daily load curve. Secondly, considering the influence factors such as temperature and season of each type of load, the improved Long Short-Term Memory (LSTM) is used to predict the charging load of each type of bus, and the total charging load on the day to be predicted is obtained by summing the prediction results of each type. Finally, a case study is carried out with the actual data of a city in East China. Compared with other prediction methods, the proposed method shows higher accuracy.

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

Citation Download Citation

Jiangzhe Huang, Yiqiong Liu, and Bin Zhou "Electric bus charging load forecasting method-based on improved spectral clustering and IPSO-LSTM", Proc. SPIE 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 127881P (25 September 2023); https://doi.org/10.1117/12.3004949

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