Statistical characterization of electricity use profile: Leveraging data analytics for stochastic simulation in a smart campus

Abstract

On the path to energy transition, advanced metering infrastructures have been installed in distribution systems to support sustainability goals, generating a substantial volume of electricity consumption data that are essential for planning and management studies. Additionally, given the stochastic nature of electricity consumption, understanding and quantifying statistical properties such as data distribution, normality, stationarity, and autocorrelation are crucial for the development of more sustainable systems and the enhancement of building performance. In this context, this paper presents a statistical methodology for assessing key aspects of electricity consumption in buildings on a smart campus, which is an initiative originated on university campuses that integrates sustainable energy systems, efficient electrical infrastructure, and data-driven technologies to establish a sustainable learning environment. Using 28 months of electricity consumption data from a Brazilian smart campus, Electricity Use Profile models are developed and several hypothesis tests and probability distribution fittings are conducted to extract statistical features from the models of 128 buildings. The results indicate that each building exhibits unique statistical properties that cannot be generalized, emphasizing the need for data analysis for each building before using the data in decision-making processes.