Clustering Methods for Power Quality Measurements in Virtual Power Plant

In this article, a case study is presented on applying cluster analysis techniques to evaluate the level of power quality (PQ) parameters virtual plant. The conducted research concerns application K-means algorithm in comparison with agglomerative for PQ data, which have different sizes features. object deals standardized datasets containing classical from two sub-studies. Moreover, optimal number clusters both algorithms discussed using elbow method and dendrogram. experimental results show that dendrogram requires long processing time but gives consistent result when there are additional parameters. comparison, easy compute inconsistent results. According Calinski–Harabasz index silhouette coefficient, performs better than clustering data points no features data. Finally, based standard EN 50160, shows all each objects still below limit work under normal operating conditions.