Short Term Solar Irradiance Forecast based on Image Processing and Cloud Motion Detection

Photovoltaic (PV) grid integration has been the epicenter of research across the globe since their intermittent nature of solar generation can be more predictable. Irradiance forecast using different methods for various time horizons has been the center of attention in the recent literature. In this study, a framework for a very short term irradiance forecast is proposed via combining image processing and machine learning. A series of whole sky images is used for this purpose. Cloud detection and movement tracking are accomplished based on image processing algorithms, future position of the clouds and occlusion to the sun. Then, the irradiance drop is predicted using machine learning algorithms. The effectiveness of the proposed technique is evaluated by the Root Mean Square Error (RMSE) between the actual and forecast values of solar irradiance.

[1]  Gunnar Farnebäck,et al.  Two-Frame Motion Estimation Based on Polynomial Expansion , 2003, SCIA.

[2]  Qilong Min,et al.  Short-Term Solar Irradiance Forecasts Using Sky Images and Radiative Transfer Model , 2018 .

[3]  Mario Paolone,et al.  Cloud Motion Identification Algorithms Based on All-Sky Images to Support Solar Irradiance Forecast , 2017, PVSC 2017.

[4]  Tao Zhang,et al.  Solar Power Prediction in Smart Grid Based on NWP Data and an Improved Boosting Method , 2017, 2017 IEEE International Conference on Energy Internet (ICEI).

[5]  Mohammad Rasouli,et al.  Short Term Solar Irradiance Forecast Using Numerical Weather Prediction (NWP) with Gradient Boost Regression , 2018, 2018 9th IEEE International Symposium on Power Electronics for Distributed Generation Systems (PEDG).

[6]  M. Cervantes,et al.  Utilization of Low Cost, Sky-Imaging Technology for Irradiance Forecasting of Distributed Solar Generation , 2016, 2016 IEEE Green Technologies Conference (GreenTech).

[7]  Hendrik F. Hamann,et al.  Solar radiation forecast with machine learning , 2016, 2016 23rd International Workshop on Active-Matrix Flatpanel Displays and Devices (AM-FPD).

[8]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[9]  Martin Hofmann,et al.  One-Hour Prediction of the Global Solar Irradiance from All-Sky Images Using Artificial Neural Networks , 2018, Energies.

[10]  Trevor Darrell,et al.  Learning Features by Watching Objects Move , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[11]  Yonggang Peng,et al.  A model of very short-term solar irradiance forecasting based on low-cost sky images , 2017 .

[12]  Hadrien Verbois,et al.  Solar irradiance forecasting in the tropics using numerical weather prediction and statistical learning , 2018 .