Despite the raising awareness in general public on environmental changes and high energy costs, a significant part of energy consumption is still due to an improper use of electrical appliances. Thus, there is a growing interest in developing systems for profiling the use of electrical appliances and suggesting adequate policies for energy saving. In this context, we propose a novel approach to extract the power consumption of a set of appliances from aggregate measurements collected from a smart meter. Our approach employs finite state machines based on fuzzy transitions (FSMFT) and a novel disaggregation algorithm. The FSMFTs are used to coarsely model how each type of appliance works. The disaggregation algorithm exploits a database of FSMFTs for, at each meaningful variation of real and reactive aggregate powers, hypothesizing possible configurations of active appliances. This set of configurations is concurrently managed by the algorithm which, whenever requested, outputs the configuration with the highest confidence with respect to the sequence of detected events. We have successfully tested our approach in an experimental environment in which five appliances have been monitored for 30 minutes.
An algorithm based on finite state machines with fuzzy transitions for non-intrusive load disaggregation
Ducange P;MARCELLONI, FRANCESCO;
2012-01-01
Abstract
Despite the raising awareness in general public on environmental changes and high energy costs, a significant part of energy consumption is still due to an improper use of electrical appliances. Thus, there is a growing interest in developing systems for profiling the use of electrical appliances and suggesting adequate policies for energy saving. In this context, we propose a novel approach to extract the power consumption of a set of appliances from aggregate measurements collected from a smart meter. Our approach employs finite state machines based on fuzzy transitions (FSMFT) and a novel disaggregation algorithm. The FSMFTs are used to coarsely model how each type of appliance works. The disaggregation algorithm exploits a database of FSMFTs for, at each meaningful variation of real and reactive aggregate powers, hypothesizing possible configurations of active appliances. This set of configurations is concurrently managed by the algorithm which, whenever requested, outputs the configuration with the highest confidence with respect to the sequence of detected events. We have successfully tested our approach in an experimental environment in which five appliances have been monitored for 30 minutes.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
