Meteorological data and Sky Images meets Neural Models for Photovoltaic Power Forecasting

TL;DR

The results demonstrate that the inclusion of meteorological data significantly improves current predictions in both nowcasting and forecasting tasks, especially on cloudy days, and highlights the importance of integrating diverse data sources to improve the reliability and interpretability of solar energy prediction models.

Abstract

Due to the rise in the use of renewable energies as an alternative to traditional ones, and especially solar energy, there is increasing interest in studying how to address photovoltaic forecasting in the face of the challenge of variability in photovoltaic energy production, using different methodologies. This work develops a hybrid approach for short and long-term forecasting based on two studies with the same purpose. A multimodal approach that combines images of the sky and photovoltaic energy history with meteorological data is proposed. The main goal is to improve the accuracy of ramp event prediction, increase the robustness of forecasts in cloudy conditions, and extend capabilities beyond nowcasting, to support more efficient operation of the power grid and better management of solar variability. Deep neural models are used for both nowcasting and forecasting solutions, incorporating individual and multiple meteorological variables, as well as an analytical solar position. The results demonstrate that the inclusion of meteorological data, particularly the surface long-wave, radiation downwards, and the combination of wind and solar position, significantly improves current predictions in both nowcasting and forecasting tasks, especially on cloudy days. This study highlights the importance of integrating diverse data sources to improve the reliability and interpretability of solar energy prediction models.

Figures (4)

• Figure 1: Latitude and longitude of the four ERA5 ERA5 grid points surrounding the camera location in Stanford University. These points, spaced at 0.25° resolution (NW, NE, SW, SE), define the area from which ERA5 ERA5 variables are extracted. The red square indicates the real camera location for image acquisition.
• Figure 2: Analytical sun position estimation. Four sky input images in different conditions where our sun position estimation is displayed by means of a $\times$ red mark. Best viewed in color.
• Figure 3: Architectures of the neural model for both nowcast (left) and forecast (right) tasks. The diagram shows the different blocks, the input variables fed into the model, and the output shapes at each stage.
• Figure 4: Qualitative comparison on nowcast and forecast estimation for sunny and cloudy days. In both cases, we report our estimation MSUNSET + i10fg + wind100 + sun position. Grey area corresponds to the ground truth; blue and red lines represent the result of our model prediction for nowcast and forecast, respectively.