K-means cluster analysis of hourly measured power demand in the district heating system in Kaposvár : Putting theoretical figures into practical use

Within this paper the actual cluster analysis is performed in order to identify clusters within Kaposvár district heating. The data was measured not directly at households but heat transfer stations. smart meters were installed stations for several reasons, measure and control needed supply temperature also leakages quicker easier. method used k-means which end did determine four different clusters: high demand low operating hours, long hours as well hours. details determined values can be further research already first steps towards identifying new sources.