K-Mean Algorithm to Support Energy Future Decision for Household with PV and EV

This paper explores the application of the K-means clustering algorithm to analyze household energy data, focusing on electricity demand, photovoltaic (PV) generation, and electric vehicle (EV) charging. The objective is to identify distinct patterns of energy usage and generation, which can inform better energy management and decision-making strategies. Using data from a London household, we apply K-means clustering to segment the energy usage into meaningful clusters. The analysis reveals distinct profiles corresponding to different times of day and types of energy consumption and generation. Key findings suggest that clustering can effectively differentiate between high and low usage periods, the impact of PV generation on household energy dynamics, and the charging patterns of EVs. The results of this study provide valuable insights into how households can optimize energy consumption and leverage their PV and EV systems more effectively. Additionally, the paper discusses the implications of these findings for future energy policy and smart grid development. Recommendations are offered for integrating advanced data analytics into residential energy management systems to enhance sustainability and efficiency.