A Novel Maximum Power Point Inference Method for Distributed Marine Photovoltaic Monitoring DOI Creative Commons
Yujie Chen, Jianan Wang, Lele Peng

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(11), P. 2760 - 2760

Published: May 26, 2025

In actual operation, the output power of distributed marine photovoltaic monitoring faces challenges from wind, waves, and other dynamic motion factors. To address these challenges, this paper proposes a novel maximum point inference method for monitoring. First, digital fusion model has been constructed to obtain comprehensive dataset system. Second, Multilayer Convolutional Neural Networks (CNN) are extract local high-frequency characteristics, Squeeze Excitation Attention (SE-Attention) is employed capture global low-frequency Long Short-Term Memory (LSTM) utilized perform temporal modeling characteristics. Subsequently, Crested Porcupine Optimizer (CPO) algorithm used achieve high-precision recognition in Finally, effectiveness verified through experiments simulations. The results indicate that exhibits multi-spectral with highest frequency at 335.2 Hz lowest 12.9 Hz. proposed enables efficient under conditions, an accuracy 98.63%.

Language: Английский

A Novel Maximum Power Point Inference Method for Distributed Marine Photovoltaic Monitoring DOI Creative Commons
Yujie Chen, Jianan Wang, Lele Peng

et al.

Energies, Journal Year: 2025, Volume and Issue: 18(11), P. 2760 - 2760

Published: May 26, 2025

In actual operation, the output power of distributed marine photovoltaic monitoring faces challenges from wind, waves, and other dynamic motion factors. To address these challenges, this paper proposes a novel maximum point inference method for monitoring. First, digital fusion model has been constructed to obtain comprehensive dataset system. Second, Multilayer Convolutional Neural Networks (CNN) are extract local high-frequency characteristics, Squeeze Excitation Attention (SE-Attention) is employed capture global low-frequency Long Short-Term Memory (LSTM) utilized perform temporal modeling characteristics. Subsequently, Crested Porcupine Optimizer (CPO) algorithm used achieve high-precision recognition in Finally, effectiveness verified through experiments simulations. The results indicate that exhibits multi-spectral with highest frequency at 335.2 Hz lowest 12.9 Hz. proposed enables efficient under conditions, an accuracy 98.63%.

Language: Английский

Citations

0