Abstract of Thesis presented at COPPE/UFRJ as a partial fulfillment of the requirements for the degree of Master of Science (M.Sc.)
A Nonintrusive Neural Electric Load Monitoring System for Household Appliances
Alvaro David Orjuela Cañón
October/2009
Advisors: |
José Manoel de Seixas
Luiz Pereira Calôba
|
Department: |
Eletrical Engineering |
A noninvasive electric load monitoring of household appliances is developed for evaluating the residential energy consumption profile. Based on characteristics of transient response, the developed system employs an automatic event detector and a multi neural classifier, which assigns the detected transient to one of the eleven classes considered. With this information, it is possible to compute the amount of the energy consumed by the different types of appliances. For an automatic event detection, the energy reconstruction efficiency was 88 %. The analysed signals represent the most relevant appliances and were acquired separately in laboratory. The achieved classification efficiency was 85 %.