Systems and apparatuses are disclosed that include a distributed power system configured to provide power to a number of loads. The system includes power converters configured to receive DC power from a common power source, each of the plurality of power converters configured to provide DC power to a corresponding load from. Each of the power converters is positioned proximal to the corresponding load that it powers.

A method includes providing, by processing circuitry, a net resource consumption trajectory including net resource consumption targets for one or more subperiods of a time period. Each net resource consumption target indicates a target difference between resource consumption and resource production or offset for a subperiod of the one or more subperiods. The method includes generating, by the processing circuitry and for a subperiod of the one or more subperiods, a set of actions predicted to achieve the net resource consumption target for the subperiod. The method includes implementing, by the processing circuitry, the set of actions.

A method for controlling a wind farm to damp low-frequency electrical oscillations, in particular subsynchronous resonances, in an electrical supply grid having a grid voltage with a nominal grid frequency is provided. The wind farm comprises at least one wind turbine connected to the electrical supply grid. The method includes sensing at least one low-frequency electrical oscillation of the electrical supply grid; determining an oscillation characteristic of each of the at least one sensed oscillation, the oscillation characteristic describing at least one property of the sensed oscillation; specifying an active-power damping signal and/or a reactive-power damping signal for damping the at least one low-frequency oscillation; feeding in an active power component in accordance with the active-power damping signal or a reactive power component in accordance with the reactive-power damping signal, the active-power damping signal and the reactive-power damping signal being specified in dependence on the determined oscillation characteristic.

Embodiments implement non-intrusive load monitoring using ensemble machine learning techniques. A first trained machine learning model configured to disaggregate target device energy usage from source location energy usage and a second trained machine learning model configured to detect device energy usage from source location energy usage can be stored, where the first trained machine learning model is trained to predict an amount of energy usage for the target device and the second trained machine learning model is trained to predict when a target device has used energy. Source location energy usage over a period of time can be received, where the source location energy usage includes energy consumed by the target device. An amount of disaggregated target device energy usage over the period of time can be predicted, using the first and second trained machine learning models, based on the received source location energy usage.

A method for remote monitoring includes (1) generating first sensor data from a first sensor at a first network node of a communications network and (2) sending the first sensor data from the first sensor to a second network node that is remote from the first network node, via the communications network. The first network node is powered from an electrical power grid that is separate from the communications network. The first sensor data may be raw sensor data and/or lossless sensor data.

Disclosed is a device for the certified measurement of electric parameters and customers' flexibility behaviour, and for communicating with a distribution system operator, comprises a System on Module, or SoM, a Certification Module, a Customer Communication Module and a Communication Module.

Methods and apparatuses for controlling reactive power of a wind turbine, and a wind farm are provided. An exemplary method includes: obtaining operation data of single wind turbines in a wind turbine group at the current time point; determining the total maximum capacitive reactive capacity and total minimum inductive reactive capacity, satisfying a safety constraint condition at the next time point, of the wind turbine group; calculating a deviation value of a wind turbine group reactive instruction at the current time point; and updating the wind turbine group reactive instruction on the basis of the acquired, determined, and calculated data so as to perform reactive power control.

A method for electrical grid monitoring using aggregated smart meter data includes receiving, from an electric grid monitoring device, electrical data aggregated from a plurality of electric meters each connected to a secondary side of at least one electrical transformer within a local geographic region. Each electric meter is configured to generate measurement data based on measurements taken at a respective electrical load. The electrical data indicates one or more characteristics of a secondary electrical distribution system connected to the at least one electrical transformer. The method includes determining, based on the electrical data aggregated from the plurality of electric meters, one or more characteristics of the primary electrical distribution system connected to the electrical transformer.

Disclosed techniques include using machine learning to detect an electrical anomaly in a power distribution system. In an example, a method includes accessing voltage measurements measured at an electric metering device and over a time period. The method further includes calculating, from voltage measurements and for each time window of a set of time windows, a corresponding average voltage and a corresponding minimum voltage. The method further includes applying a machine learning model to the average voltages and the minimum voltages. The machine learning model is trained to identify one or more predetermined electrical anomalies from voltages. The method further includes receiving, from the machine learning model, a classification indicating an identified anomaly. The method further includes based on the classification, sending an alert to a utility operator.

A line module for use in a network device includes a plurality of circuits; and a power module connected to the plurality of circuits, and to a first Power Distribution Unit (PDU) and a second PDU, wherein the first PDU and the second PDU provide power distribution by different feeds, wherein the power module is configured to initiate a shutdown procedure when one or more of i) a current drawn from any feed equals or exceeds a first current threshold, and ii) an aggregate current drawn from all feeds equal or exceeds a second current threshold.