Ensemble load pattern clustering method based on deep representation features

Yue Zhai; Jian Sun; Guangchao Qian; Yabin Ma; Wei Li; Minghao Fan

doi:10.1117/12.2667633

6 March 2023 Ensemble load pattern clustering method based on deep representation features

Yue Zhai, Jian Sun, Guangchao Qian, Yabin Ma, Wei Li, Minghao Fan

Proceedings Volume 12553, Fourth International Conference on Optoelectronic Science and Materials (ICOSM 2022); 125530X (2023) https://doi.org/10.1117/12.2667633
Event: 2022 4th International Conference on Optoelectronic Science and Materials (ICOSM2022), 2022, Henfei, China

Abstract

With the development of smart meters, a large number of high-dimensional load data become available, which also brings great challenges to load pattern clustering (LPC). Although current studies have been devoted to extracting features from high-dimensional load data to achieve dimensionality reduction, they focus on the manually extracted features, which may not be able to effectively model the nonlinearity of load data. In this paper, a fused load pattern recognition method based on deep representation feature extraction is proposed to solve this problem. Specifically, two unsupervised deep representation feature extraction models are conducted to extract the characteristics of customers' electricity consumption behaviour from different views, which are convolutional neural network based autoencoder (CNN-AE) and long short-term memory based autoencoder (LSTM-AE) respectively. Then, the fusion feature selection (FFS) method is proposed to construct a set of effective feature subspaces. Finally, the ensemble clustering based on co-association (CA) is carried out to obtain the clustering results. Experimental results show that the proposed method can effectively improve the clustering performance of load profiling.

Citation Download Citation

Yue Zhai, Jian Sun, Guangchao Qian, Yabin Ma, Wei Li, and Minghao Fan "Ensemble load pattern clustering method based on deep representation features", Proc. SPIE 12553, Fourth International Conference on Optoelectronic Science and Materials (ICOSM 2022), 125530X (6 March 2023); https://doi.org/10.1117/12.2667633

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Feature extraction

Data modeling

Feature selection

Neural networks

Pattern recognition

Design and modelling

Deep learning

Keywords/Phrases

Search In:

Publication Years