A prediction model of dust accumulation on photovoltaic modules considering rainfall washing

Abstract

AbstractThe power generation of the photovoltaic plant is related to the cleanliness of the photovoltaic modules. The accumulation of natural dust is the main source of pollution, which is affected by human activities and meteorological factors such as temperature, humidity, wind speed, and rainfall concentration in the current region. On the basis of particle swarm optimization (PSO) and the least‐squares support vector machine (LSSVM), the density of dust on photovoltaic modules was estimated. The authors proposed that the inertia weight decreased as a concave function to improve the efficiency of optimization and let the two positive constants change dynamically to improve convergence performance. The dust accumulation prediction model was established considering natural rainfall and the authors obtained the attenuation rate of the photovoltaic power output. Finally, the experiments in Hangzhou showed that the model can predict the density of accumulated dust quickly, which provides a theory for predicting PV power generation and managing the cleaning frequency.