Research on power load pattern recognition based on clustering algorithm

Ke Zheng; Fei Wei; Baoyue Xing; Xu Wang; Furongzi Chen

doi:10.1117/12.3005155

25 September 2023 Research on power load pattern recognition based on clustering algorithm

Ke Zheng, Fei Wei, Baoyue Xing, Xu Wang, Furongzi Chen

Proceedings Volume 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023); 127884A (2023) https://doi.org/10.1117/12.3005155
Event: Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 2023, Kuala Lumpur, Malaysia

Abstract

With the deepening of the construction of electricity information collection for power grid enterprises, the scale of power load data continues to increase. It is of great significance to carry out power load data mining and analysis for the production and operation of power grid enterprises. In this paper, the shortcomings of traditional load classification methods are studied. Firstly, the power load characteristics and related indicators are compared, and the load curve is selected to carry out K-means clustering algorithm to realize the power load pattern recognition. According to the clustering algorithm process, the power load clustering data of 1000 households were selected to carry out data normalization and data dimension reduction. After comparison, the elbow method was used to select K value, and the simulation test was carried out. It has been proved that the K-means clustering algorithm can realize accurate identification and classification of user load, and the effect is obvious.

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

Citation Download Citation

Ke Zheng, Fei Wei, Baoyue Xing, Xu Wang, and Furongzi Chen "Research on power load pattern recognition based on clustering algorithm", Proc. SPIE 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 127884A (25 September 2023); https://doi.org/10.1117/12.3005155

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