Identify the individual consumption of multiple appliances using a single general meter and intelligent software (virtual submetering). The meter reads and sends one sample per second of active power, reactive power and voltage; it results at the end of the day in a plot of 86,000 points that is on which the pattern recognition algorithm is applied. This is launched every night to analyze the previous 24h (deferred disaggregation).
The algorithm looks for steps of power consumed (corresponding to the turning on or off of devices) and other particular signal features of each household appliance. Therefore what is measured is real, it is not estimated nor statistical.
The algorithm automatically detects some appliances, but for others it needs help. One way to help the algorithm to make the detections is the confirmation of several questions that the system launches automatically. Another way to help the algorithm is the ‘manual trainer’: a pattern recorder designed to tell the algorithm what the pattern of consumption of simple devices is like (for ON / OFF devices).
Devices that currently can be detected are the following:
For now, it is beyond the scope of the algorithm: induction hob, inverter-type air conditioning, lighting, televisions, computers and electronic devices in general.