Research on photovoltaic system faults detection strategy based on memory network

Mingjun Li; Xinrui Wang; Qihong Sun

doi:10.1117/12.3004451

25 September 2023 Research on photovoltaic system faults detection strategy based on memory network

Mingjun Li, Xinrui Wang, Qihong Sun

Author Affiliations +

Proceedings Volume 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023); 127880T (2023) https://doi.org/10.1117/12.3004451
Event: Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 2023, Kuala Lumpur, Malaysia

Abstract

Recently, solar energy has been developed and widely utilized in photovoltaic system networks and provided a significant clean energy supply for the world. Additionally, the photovoltaic system is an essential module to generate the electrical power in energy supplement systems. However, existing photovoltaic systems are vulnerable to the affection of climate environment and may cause uncountable economic loss and decrease the power generation for power supply system. Therefore, the development for faults recovery strategies are necessary in photovoltaic system. Existing methods are concentrated on utilizing the units control detection method to identify the faults points and cause numerous identification costs. In this paper, we utilize the long short-term memory network (LSTM) to achieve photovoltaic system faults detection task, which can enhance the detection accuracy and reduce the computation cost for identifying procedure. From our extensive experiment results, we can conclude that our proposed method achieves more than 90% detection accuracy with reasonable detection costs through comparing with existing detection methods.

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

Citation Download Citation

Mingjun Li, Xinrui Wang, and Qihong Sun "Research on photovoltaic system faults detection strategy based on memory network", Proc. SPIE 12788, Second International Conference on Energy, Power, and Electrical Technology (ICEPET 2023), 127880T (25 September 2023); https://doi.org/10.1117/12.3004451

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