Segmentation Algorithms for Ground-Based Infrared Cloud Images

TL;DR

This paper compares machine learning algorithms for real-time segmentation of clouds in ground-based infrared images to improve solar irradiance forecasting and optimize energy dispatch in smart grids.

Contribution

It introduces a comparison of machine learning methods that do not require labeled data for effective real-time cloud segmentation in infrared images.

Findings

Machine learning algorithms can effectively segment clouds without labeled training data.

Real-time segmentation enables better cloud feature extraction for solar forecasting.

Improved cloud detection can enhance energy management in smart grids.

Abstract

The increasing number of Photovoltaic (PV) systems connected to the power grid are vulnerable to the projection of shadows from moving clouds. Global Solar Irradiance (GSI) forecasting allows smart grids to optimize the energy dispatch, preventing energy shortages caused by occlusion of the sun. This investigation compares the performances of machine learning algorithms (not requiring labelled images for training) for real-time segmentation of clouds in images acquired using a ground-based infrared sky imager. Real-time segmentation is utilized to extract cloud features using only the pixels in which clouds are detected.