Clustering Techniques Performance Analysis for a Solar Thermal Collector Hybrid Model Implementation

This work addresses the performance comparison of clustering techniques in order to achieve robust hybrid models. With this goal, three different clustering techniques have been tested. The experimental environment designed for this purpose is based on a real case study, a thermal solar generation system installed in a bio-climate house located in Sotavento Experimental Wind Farm, in Xermade (Lugo) in Galicia (Spain). In this way, clustering methods have been applied over the real dataset extracted from the thermal solar generation installation. For comparing the quality of each clustering technique, two approaches have been used. The first one is oriented to a set of three unsupervised learning metrics (Silhouette, Calinski-Harabasz, and Davies-Bouldin), while the second one is based on error measurements associated with a regression method such as Multi-Layer Perceptron.