Search

Clouds moving in front or away from the sun are the leading cause of irradiance variability. These variations have a repercussion on the electricity production of photovoltaic systems. Predicting such changes is essential for proper control of these systems and for maintaining grid stability. Images from the sky have proven to help with short-term solar irradiance forecasting, especially when combined with artificial intelligence. Nevertheless, these models tend to smooth the irradiance fluctuations. We propose a forecasting model to predict the clear-sky index in a forecast horizon of 20 min with a 1-minute resolution. Our model, based on a classifier to determine the sky conditions and, on an optical flow, applies an artificial intelligence model explicitly trained on each class of sky conditions. This strategy has an equivalent performance to an unclassified model and a forecast skill between 5 and 20% with respect to the smart persistence model for most classes of sky conditions while requiring considerably less training data. Although our model reduces the overall predicting error, it still has difficulties predicting irradiance changes and mainly overcast days. Our classifying strategy can be applied to other models targeting different objectives to predict sudden changes in either irradiance or power related to photovoltaic systems. [Display omitted] • Classification of sky conditions. • Merging different predicted classes of sky conditions to reduce the prediction error. • Inclusion of optical flow to incorporate temporal information. • Classification reduced the amount of data needed to train the models. [ABSTRACT FROM AUTHOR]

Solar resource assessment is fundamental to reduce the risk in selecting the solar power-plants' location; also for designing the appropriate solar-energy conversion technology and operating new sources of solar-power generation. Having a reliable methodology for solar irradiance forecasting allows accurately identifying variations in the plant energy production and, as a consequence, determining improvements in energy supply strategies. A new trend for solar resource assessment is based on the analysis of the sky dynamics by processing a set of images of the sky dome. In this paper, a methodology for processing the sky dome images to obtain the position of the Sun is presented; this parameter is relevant to compute the solar irradiance implemented in solar resource assessment. This methodology is based on the implementation of several techniques in order to achieve a combined, fast, and robust detection system for the Sun position regardless of the conditions of the sky, which is a complex task due to the variability of the sky dynamics. Identifying the correct position of the Sun is a critical parameter to project whether, in the presence of clouds, the occlusion of the Sun is occurring, which is essential in short-term solar resource assessment, the so-called irradiance nowcasting. The experimental results confirm that the proposed methodology performs well in the detection of the position of the Sun not only in a clear-sky day, but also in a cloudy one. The proposed methodology is also a reliable tool to cover the dynamics of the sky. [ABSTRACT FROM AUTHOR]