This paper presents the development of a series of Key Performance Indicators (KPIs) for the electrical system of the campus of the National University of Colombia based on the deployed smart metering infrastructure (AMI). To develop the proposed indicators, it was necessary to use different sources of information to complement the data provided by the AMI system. In the document, the formulation of the main indicators is presented alongside an analysis of the behavior obtained for each one. It was possible to observe how, based on the results obtained from the different indicators periods of inefficiency in electricity consumption. Finally, the main conclusion corresponds to the challenge of applying these KPIs to different conditions.
<span lang="EN-US">The development of dynamic energy distribution grids to optimize energy resources has become very important at the international level in recent years. A very important step in this development is to be able to characterize the population based on their consumption behaviour. However, traditional consumption meters that report information at a monthly rate provide little information for in-depth analysis. In Colombia, this has changed in recent years due to the implementation and integration of advanced metering infrastructure (AMI). This infrastructure allows to record consumption values in small time intervals, and the available data then allows for the execution of many analysis mechanisms. In this paper we present an analysis of the electricity demand profile from a new dataset of energy consumption in Colombia. A characterization of the users demand profiles is presented using a k-means clustering procedure. Whit this customer segmentation technique we show that is possible identify customer consumption patterns and to identify anomalies in the system. In addition, this type of analysis also allows to assess changes in the consumption pattern of users due to social measures such as those resulting from the coronavirus disease (COVID-19) pandemic.</span>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.