Predictions of cloud movements and the sun cover duration

Abstract

In order to optimally control the energy flow in the microgrid, consist of several renewable energy sources, including solar photo electric system and storage system, it is essential to know availability of the specific energy source. So, it is necessary to determine the exact moment of the Sun shading the by clouds as well as shadow duration. These parameters could be obtained by cloud movement tracking system. The cloud movement tracking system is based on the detection of cloud edges and determining angular velocity vector which describes the speed and direction of cloud movements. As clouds change their shapes, directions and speeds, the position of every cloud is determined according to his centroid. This paper deals with cloud recognition and movements analysis based on video stream obtained by camera with resolution 1920×1080 pixels and refresh rate of 25 frames per second. The clouds detection is based on the HSV (Hue-Saturation-Value) color model in combination with mathematical morphological operations of erosion and dilation. Video and image processing was performed by application developed in Java programming language using the JavaCV library that offers the functionalities of computer vision.