Multi-source power data fusion method based on deep learning

Wang Wenwen; Liu Kunling; Liu Chang

doi:10.1117/12.3004427

25 September 2023 Multi-source power data fusion method based on deep learning

Wang Wenwen, Liu Kunling, Liu Chang

Proceedings Volume 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023); 127883Q (2023) https://doi.org/10.1117/12.3004427
Event: Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 2023, Kuala Lumpur, Malaysia

Abstract

With the rapid growth of energy big data and types of sensors for energy data monitoring, a series of problems have been encountered in power data quality and data fusion. To solve these problems, we proposed a novel multi-source power data fusion method based on deep learning, in which the training network of energy big data is established. By adopting the idea of incremental learning and offline learning, the MCS-RF framework of energy big data is built in the online training of real-time image data, which can effectively mitigate the sparse problem of big data and encode the discrete data into one tailored for association rules. In this way, the redundant information in energy big data would be eliminated. We compared this new method with the traditional residual-based algorithms based on the power flow data in the SCADA system, and experimental results show that the proposed method can reduce the requirements for identifying energy data with bad noise and achieve higher accuracy.

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

Citation Download Citation

Wang Wenwen, Liu Kunling, and Liu Chang "Multi-source power data fusion method based on deep learning", Proc. SPIE 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 127883Q (25 September 2023); https://doi.org/10.1117/12.3004427

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