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.

A method for recording power consumption data of a residential unit, the residential unit having a distributor (4) with at least one load circuit (7), wherein at least one load (9) is arranged in each load circuit (7), at least one load (9) can be individually actuated and at least one load circuit (7) has mechanism (6) for measuring the power consumed in the load circuit (7). The residential unit has a control unit (10), which actuates the load or loads (9) on the basis of predetermined or predeterminable scenes. The power consumption of the load circuits (7) is measured individually and recorded by the control unit (10) and the control unit (10) assigns the power consumption to the set scenes.

Systems and techniques are provided for power delivery to vehicles on a roadway. A vehicle can be detected traveling on a roadway having a plurality of power distribution units for providing electrical power. The vehicle is authenticated to receive electrical power from one or more power distribution units based on identifying information associated with the vehicle. Based on successful authentication of the vehicle, a selected one or more power distribution units can be energized, the selected one or more power distribution units selected from the plurality of power distribution units as being nearest to the authenticated vehicle. Electrical power can be provided from at least one of the energized power distribution units to the authenticated vehicle while the authenticated vehicle travels along the roadway. The selected one or more power distribution units can be de-energized based on detecting that a load associated with the authenticated vehicle is no longer present.

A system for managing devices supplied through a power grid is proposed. Each device is configured to consume over time electric power according to at least one respective power profile when operating. The system comprises at least one unit interfaced with the devices for exchanging data. The at least one unit collects power profile data indicative of the power profiles of the devices, and generates a time schedule of the device operations by distributing over time start times of the power profiles in such a way that at any time the total power consumption of the devices is kept under a maximum power threshold of the power grid.

The present disclosure provides a portable standby starting device for a vehicle. The portable standby starting device includes a battery circuit, a load access detecting circuit, and a vehicle starting circuit, wherein the battery circuit is coupled to the load access detecting circuit and the vehicle starting circuit, and is configured to supply power to the load access detecting circuit and the vehicle starting circuit; the load access detecting circuit is coupled to the vehicle starting circuit, and is configured to detect whether the vehicle starting circuit is connected to a vehicle load; the vehicle starting circuit is configured to, when the load access detecting circuit detects the connection of the vehicle load, output a vehicle starting current for controlling an ignition operation performed for the vehicle.

Devices, systems and methods are provided that introduce electrical components to alter the electrical characteristics of power delivery systems in residential and commercial power circuits to: prevent the disaggregation of electrical utility consumption data by alteration of the composite load profiles. The device and method prevent accurate identification of powered devices, their presence, their operating characteristics, their consumption data, and any inferences of power device user's behaviors and activities by the analysis of disaggregated data. The operation of the device may include any of a range of steps, actions and instructions to introduce altering impedance elements and filtration circuits in coordinated fashion with the operation of the targeted devices to be masked.

A system for monitoring electric energy amount according to one embodiment of the present disclosure includes an electric energy system including one or more loads receiving electric energy through an external electric energy source and a renewable energy generator, a home server for receiving information of a first electric energy amount that is an electric energy amount consumed by the one or more loads, a second electric energy amount that is supplied from the external electric energy source to the electric energy system, and a third electric energy amount that is supplied from the renewable energy generator to the electric energy system, and an electric energy amount monitoring server calculating the second electric energy amount or the third electric energy amount from electric energy consumption of the electric energy system, which is received from the home server, and supply electric energy amount information supplied to the electric energy system.

Disclosed embodiments relate to a power monitoring system. In some embodiments, the power monitoring system includes: a sampling device configured to measure patterns of energy consumed by loads included in the power system; an electric meter configured to measure an amount of second energy supplied from a system to the power system; a power supply configured to supply power stored therein or generate power to supply the power system and measure an amount of third energy supplied; and an external server configured to receive at least one of the patterns, the amount of the second energy and the amount of the third energy and analyze the patterns to acquire an amount of first energy for each of the loads. In some embodiments, the external server calculates at least one of the amount of the first, second and third energy.

Disclosed embodiments relate to a power monitoring system. In some embodiments, the power monitoring system includes: a sampling device configured to measure patterns of how loads included in the power system consume energy; an electric meter configured to measure a first amount of energy supplied from a transmission system to the power system; a power supply configured to supply power stored therein or generate power to supply it to the power system, and measure a second amount of energy supplied to the power system; an external server configured to receive measurements of the patterns from the sampling device, and obtain a third amount of energy consumed by the loads based on the measurements; and a home server configured to receive the first amount of energy and/or second amount of energy and transmit/receive data to/from the external server.

The present invention is generally directed to methods of disaggregating low resolution whole-house energy consumption data. In accordance with some embodiments of the present invention, methods may include steps of: receiving at a processor the low resolution whole house profile; selectively communicating with a first database including non-electrical information; selectively communicating with a second database including training data; and determining by the processor based on the low resolution whole house profile, the non-electrical information and the training data, individual appliance load profiles for one or more appliances.