Electric load monitoring of residential buildings using goodness of fit and multi-layer perceptron neural networks

Nonintrusive appliance load Non-intrusive load monitoring is an emerging signal processing and analysis technology that aims to identify individual appliance in residential or commercial buildings or to diagnose shipboard electro-mechanical systems through continuous monitoring of the change of On and Off status of various loads. The goal of the NIALM system is to identify and track instances when appliance in a building is turned on and off. This is achieved by collecting electric power data measure live from the service entry point of a building; disaggregate it and extracting unique features of the signal that can be used to identify appliances in the building. The NIALM provides a relatively cheap and efficient way to monitor appliances without invading the home or disrupting the normal configuration of the household appliances. To better plan for our current and future energy needs, it is important for us to know how each of our electrical appliance is been utilized. This information would help facility managers to better manage and distribute power; appliance producer to design and produce more energy efficient appliances; and also home owners/building managers understand each appliance, utilization and energy consumption which would help in decision making.