Neural network-based dust deposition prediction method for photovoltaic panels based on ship rolling characteristics

Abstract

This invention discloses a neural network-based photovoltaic (PV) dust accumulation prediction method based on ship sway characteristics. Building upon traditional neural network PV dust accumulation prediction, it incorporates ship sway characteristics to adapt to the dynamically changing conditions of the ocean. In this method, in addition to the traditional use of open-circuit voltage, short-circuit current, maximum power point voltage, and maximum power point current, a new feature, ship sway, is introduced. A CNN-LSTM-Attention hybrid neural network is used to input these features for PV dust accumulation prediction, improving upon the slow convergence speed, long search time, and poor generalization ability issues caused by the unpredictable swaying of ships at sea. A simulation model is established by analyzing the characteristics of ship sway, sample data is obtained, and the neural network algorithm is used to train the input and output data to achieve the prediction of dust accumulation in the ship's PV system.

Images