Typologization of medium voltage distribution networks using data mining techniques: A case study

Abstract

Nowadays photovoltaic systems can be considered to play the key role in increasing decentralized power generation. These power generation systems are typically connected to distribution networks and affecting their operation. The spread of high output power connection demands the development of the infrastructure. Examination of development opportunities is done with software simulation, so the creation network models are required. To achieve a large-scale simulation, the generation of reference networks which describe real networks well is essential. In order for the reference networks to be created, clustering of real networks may be a solution. When the clusters and their parameters are defined well the software implementable of networks can be created. In this work, the clustering process of Hungarian distribution networks, the determination of the optimal cluster number, and the established network clusters are also presented.