Search

In this work, a day-ahead to week-ahead solar irradiance prediction mechanism based on convolutional Long Short-Term Memory (LSTM) model is proposed. The system takes hourly irradiance data from several days previous to the prediction day as the input. Then, features are extracted from the input data using one dimensional convolutional filters. The extracted features from different days are concatenated and serve as the input of the LSTM network. The output of the LSTM is further concatenated with selected original data to emphasize its importance and enhance the prediction results. Afterwards, a fully connected layer is used to produce the final prediction output. The proposed framework can be trained using a relatively small amount of training data within the duration of only two months. Therefore, it has the advantage of being applicable in the initial deployment phase when the amount of training data is limited. The proposed system has been validated using a highly challenging dataset collected in Taiwan with tropical and subtropical marine island climate. [Display omitted] • A convolutional long short-term memory framework is designed for solar irradiance prediction. • Weather observation and forecast information are used in the training and prediction process. • The proposed framework can be trained with relatively small amount of data. • The proposed convolutional LSTM framework outperforms related works. [ABSTRACT FROM AUTHOR]

This paper proposes a framework to automatically conduct cloud classification on all-sky images and perform short-term solar irradiance prediction according to the classification results. The all-sky images are divided into blocks to deal with the mixed cloud type conditions. Local texture patterns and statistical texture features are extracted from the image blocks for cloud classification. Different cloud types with various heights, thickness, and opacity have different impact on the variation of solar irradiance. Therefore, several regression models are trained to capture the characteristics of irradiance changes under different cloud types. The current classified cloud type is used to select a corresponding prediction model. Such design substantially increases the prediction accuracy. The experimental results verify the effectiveness of the proposed framework. Both the proposed cloud classification method and irradiance prediction mechanism outperform existing works. Adding local texture patterns in the feature vector enhance the classification performance. Compared with non-block based methods, the proposed block-based method could increase the classification rate by 5%–10%. Utilizing multiple prediction models according cloud types could lower both the mean absolute error and the root mean squared error on short-term irradiance prediction. [ABSTRACT FROM AUTHOR]

Abstract: This paper proposes an accurate short-term solar irradiance prediction scheme via support vector regression. Utilizing clearness index conversion and appropriate features, the support vector regression models are able to output satisfying prediction results. The prediction results are further improved by the proposed ramp-down event forecasting and solar irradiance refinement procedures. With the help of all-sky image analysis, two separated regression models are constructed based on the cloud obstruction conditions near the solar disk. With bi-model prediction, the behavior of the changing irradiance can be captured more accurately. Moreover, if a ramp-down event is forecasted, the predicted irradiance is corrected based on the cloud cover ratio in the area near the sun. The experiments have shown that the proposed method can effectively improve the prediction accuracy on a highly challenging dataset. [Copyright &y& Elsevier]