The invention relates to a disaggregation apparatus (1) for identifying an electrical consumer in an electrical network (2). An electrical signature providing unit (7) provides electrical signatures of the electrical consumers (4, 5, 6), and an electrical parameter determining unit (8) determines an overall electrical parameter of the electrical network (2). An identification unit (9) identifies an electrical consumer depending on the determined overall electrical parameter and a correlation of the electrical signatures. Since the identification unit identifies an electrical consumer depending on the determined overall electrical parameter and a correlation of the electrical signatures, the identification of an electrical consumer does not depend on the detection of an event only. This makes the identification more robust, especially less prone to errors caused by missed events, thereby improving the reliability of identifying an electrical consumer in the electrical network.

Embodiments implement non-intrusive load monitoring using a novel learning scheme. A trained machine learning model configured to disaggregate device energy usage from household energy usage can be stored, where the machine learning model is trained to predict energy usage for a target device from household energy usage. Household energy usage over a period of time can be received, where the household energy usage includes energy consumed by the target device and energy consumed by a plurality of other devices. Using the trained machine learning model, energy usage for the target device over the period of time can be predicted based on the received household energy usage.

In some embodiments, a load power monitoring system includes a distribution board to distribute a electric power applied from a external electric power supply source or a first renewable energy source to an electric device, at least one power metering device to sense electric energy of at least one of the electric power supply source and the first renewable energy source, a second power metering device to sense electric energy distributed to the electric device, a third power metering device to sense electric energy generated from a second renewable energy source, and a monitoring server to collect electric energy data sensed at each of the power metering devices and monitor the load power based on the collected electric energy data.

Activity sensing in the home has a variety of important applications, including healthcare, entertainment, home automation, energy monitoring and post-occupancy research studies. Many existing systems for detecting occupant activity require large numbers of sensors, invasive vision systems, or extensive installation procedures. Disclosed is an approach that uses a single plug-in sensor to detect a variety of electrical events throughout the home. This sensor detects the electrical noise on residential power tines created by the abrupt switching of electrical devices and the noise created by certain devices while in operation. Machine learning techniques are used to recognize electrically noisy events such as turning on or off a particular light switch, a television set, or an electric stove. The system has been tested to evaluate system performance over time and in different types of houses. Results indicate that various electrical events can be learned and classified with accuracies ranging from 85-90%.

When an appliance identification art is provided, the computing speed and the identification accuracy are improved while the required memory amount, etc., is decreased. In a gas meter 100, an ultrasonic flowmeter 104 measures the flow rate of gas flowing into a flow path 102 at a given time interval, and a computation section 108 computes a difference value of the predetermined time period between the measured flow rates. A difference value conversion section 112 converts the computed difference value into a code with reference to a flow rate class table by which classes of difference values corresponding to a size of the difference value and codes representing the classes are associated with each other. Further, a flow rate change history generation section 114 generates a flow rate change history approximately representing flow rate change of gas based on a set of the codes of the predetermined time period.

A method identifies electric load types of a plurality of different electric loads. The method includes providing a support vector machine load feature database of a plurality of different electric load types; sensing a voltage signal and a current signal for each of the different electric loads; determining a load feature vector including at least six steady-state features with a processor from the sensed voltage signal and the sensed current signal; and identifying one of the different electric load types by relating the load feature vector including the at least six steady-state features to the support vector machine load feature database.

Systems and methods are disclosed for monitoring power consumption by electrical devices. In some aspects, a computing device can detect a change in aggregate electricity usage at a monitored environment that includes multiple electrical devices. The computing device can determine that electricity usage by one of the electrical devices has changed. The computing device can determine that the change in electricity usage has occurred based on a change in a monitored operational parameter other than electrical power provided to the electrical device. The value of the monitored operational parameter can change based on an operation performed by the electrical device when using electricity. The computing device can determine how electricity is used by the electrical device by correlating the change in the aggregate electricity usage and the change in the electricity usage by the electrical device.

The present invention is directed to systems and methods of disaggregating and detecting energy usage associated with electric vehicle charging from a whole-house consumption signal. In general, methods of the present invention may include: a method of electronically detecting and disaggregating a consumption signal associated with the charging of an electric vehicle from a whole-house profile, comprising: identifying by an electronic processor potential interval candidates of electric vehicle charging; determining by the electronic processor intervals associated with the charging of an electric vehicle, based at least in part on evaluating each potential interval candidate against factors including amplitude, duration, and time-of-day; and accounting by the electronic processor for feedback of any incorrectly detected signals.

A system disaggregates and estimates power consumption of electric loads powered by a single electrical outlet. The system includes a processor having a routine; a current sensor cooperating with the processor to measure samples for one line cycle of an aggregated current waveform for the electric loads powered by the single electrical outlet; and a voltage sensor cooperating with the processor to measure samples for the one line cycle of a voltage waveform for the electric loads powered by the single electrical outlet. The processor routine transfers the measured samples for the one line cycle of the aggregated current waveform and the voltage waveform into an aggregated voltage-current trajectory for the single electrical outlet, and provides an instantaneous decomposition of power consumption for a plurality of different categories of the electric loads from the aggregated voltage-current trajectory for the one line cycle.

A monitoring system including a plurality of monitoring devices (20) and a server (10) is provided. When new device data including a feature amount of a new electrical device different form existing electrical devices is extracted from measurement data (current consumption or the like), the monitoring device (20) calibrates the feature amount of the new electrical device using calibration data generated based on calibration data of the exiting electrical device, and transmits the new device data to the server (10) in association with identification information of the new electrical device. When the calibrated new device data of the new electrical device is received from the plurality of monitoring devices (20), the server (10) generates and registers training data of the new electrical device based on the plurality of pieces of calibrated new device data.