Paper
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.
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
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Photovoltaics

Solar energy

Solar cells

Data centers

Machine learning

Systems modeling

Industry

Back to Top