Performance analysis of the DAMICORE algorithm in the Identification of residential loads

• Grant number: 17/07885-9
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: August 01, 2017
• End date: July 31, 2018
• Field of knowledge: Engineering - Electrical Engineering - Electrical, Magnetic and Electronic Measurements, Instrumentation
• Principal Investigator: Ricardo Augusto Souza Fernandes
• Grantee: Raphael Zanandréa Moda
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

This research project has as main objective the use of the clustering algorithm named DAMICORE. For this purpose, the clustering algorithm will be employed based on Noninvasive Load Monitoring techniques to identify residential loads. Therefore, we intend to use only the instantaneous measurements of voltage and current, which are also necessary to calculate the energy consumption. Highlighting that the smart meter was already developed by the Research Group and the challenges of the present project are to ensure that DAMICORE can separate groups of loads in clusters that help in the identification of such loads. It should be noted that this is a machine learning algorithm considered unsupervised. A step of signal pre-processing is important in order to guarantee the efficiency of the algorithm. At last, it is important to mention that this type of algorithm allows the application of Demand Response methods, because the identification of loads guarantees the definition of rules for energy usage. In this way, the monthly energy price could be minimized (AU)