K-Means Clustering for Identification of Household Energy Utilization and Production

This paper presents an analysis of household different energy situations using the k-means clustering algorithm, based on real-world data collected in Dingle, Ireland. The study begins with an overview of the growing importance of photovoltaic (PV) installations in the residential energy balance. The core of the work focuses on a single household equipped with a PV system and an energy storage unit, monitored throughout the entire year of 2020. The collected time-series data undergo preprocessing to ensure quality and consistency. Subsequently, the k-means clustering method is applied to identify typical patterns and distinct situations of household energy usage. The resulting clusters are visualized and interpreted to gain insights into the household's operational behaviour under different energy scenarios. This type of research is crucial to support the integration of single households into efficient energy communities.