The phenomenon of foreign body occlusion often occurs in photovoltaic modules during long-term outdoor operation
which affects photovoltaic power generation. Studying the prediction of power generation efficiency loss under occlusion conditions is very useful for monitoring the severity of photovoltaic module occlusion defects and guiding module cleaning scientifically. In this paper
a forecast model of PV module output power loss under partial occlusion based on Tent-SSA-BP is proposed. Firstly
the output characteristics of PV modules under partial occlusion are analyzed through simulation experiments. On the basis of a large number of simulation data
the Tent-SSA-BP prediction model is established. Because BP neural network model is easy to fall into local optimal solution and the prediction accuracy is not high
the Tent-SSA-BP prediction model established in this paper solves the local optimal problem easily caused by the original network
improves the global search ability
and quickly finds a better parameter combination. Through comparative analysis of experiments
the determination coefficient of Tent-SSA-BP prediction model is improved by 0.04 compared with the original network
which has a better degree of model fitting and improves the prediction accuracy of the model.