Abstract
As a kind of energy from the sun, solar energy is recognized as one of the most competitive renewable energy sources due to its inexhaustible and pollution-free nature. IN recent years, photovoltaic grid capacity is gradually increasing. However, the output of photovoltaic power station is affected by various meteorological factors to different degrees, which makes the output of photovoltaic power station show obvious periodicity and uncertainty. Therefore, photovoltaic power prediction is of great significance for the safety and economic operation of photovoltaic power stations. In order to improve the accuracy of the prediction, a climate impact model suitable for the power prediction of photovoltaic power stations was established for short-term power prediction objects. In this paper, strong meteorological factors are selected as input factors of fuzzy c-means clustering (FCM) algorithm. The original photovoltaic output data were clustered according to the weather type, and they were grouped into three differed ° not weather categories: sunny day, cloudy day and rainy day. The influence of different weather conditions on photovoltaic prediction was analyzed based on the algorithm of convolutional neural network to study the effects of different climates on predictions. It provides the data basis for the establishment of short-term prediction model of photovoltaic output.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call