Systems and methods for determining a location of an event in an electric power delivery system using a machine learning engine are provided. The machine learning engine may be trained based on a topology of the electric power delivery system, where the topology may be a layout of line sections and corresponding sensors of the electric power delivery system. Based on the topology, one or more training matrices that indicate possible event locations may be generated. In turn, the machine learning engine may be trained using the training matrices and logistic regression models to determine locations of events that occur during operation of the electric power delivery system.

Disclosed is an electrical power system having a transmission system with a first voltage, a distribution network with a second voltage, and a coupling unit having a coupling ratio, and a distributed generation unit DGU to generate the electric power and be in a communication with the distribution network. The system may also have a control unit to control the coupling unit and the DGU in an emergency operating mode to bring and/or to keep the value of the first voltage between a first threshold and a third threshold, and/or the value of the second voltage between a second threshold and a fourth threshold, the first threshold corresponding to the value of the first voltage at the time of entry into the emergency operating mode and the second threshold corresponding to the value of the second voltage at the time of entry into the emergency operating mode.

A method of testing a distribution center bus system having one or more of the following features: (a) opening a reserve bus breaker between a reserve bus UPS and a reserve bus, (b) initiating a self-test mode at the reserve bus UPS, (c) routing current through the reserve bus UPS, the reserve bus, a reserve bus static bypass circuit back to the reserve bus UPS, (d) testing the reserve bus to detect heat, determine any significant current loss, or identify other attributes suggesting failure, (e) identifying if a primary bus static transfer switch has tripped over to the reserve bus, and (f) terminating the self-test at the reserve bus UPS if the primary bus static transfer switch has tripped.

Systems and methods for managing power on an electric power grid including a server for communicating IP-based messages over a network with distributed power consuming devices and/or power supplying devices, the IP-based messages including information relating to activities by the power consuming devices and/or the power supplying devices; and wherein the information is transformed by the system into settlement grade data corresponding to the activities of the power consuming devices and/or the power supplying devices.

The present application provides a method and a system for controlling continuous high voltage ride-through and low voltage ride-through of a permanent magnet direct-driven wind turbine. The method includes: determining a transient time period during which the wind turbine is transitioned from a high voltage ride-through state to a low voltage ride-through state; controlling the wind turbine to provide, during the transient time period, a gradually increasing active current to the point of common coupling; and controlling the wind turbine to provide, during the transient time period, a reactive current to the point of common coupling according to an operation state of the wind turbine before the high voltage ride-through state.

A system includes a processor operatively coupled to memory. The processor performs operations that include obtaining electrical measurements of a power system. The processor determines a scaled energy value of a first set of the electrical measurements that are scaled with respect to a second set of electrical measurements. The processor determines that a potential ringdown event occurred by comparing the scaled energy value to a threshold energy value. The processor determines that the potential ringdown event is a confirmed ringdown event by comparing a scaled error value to a threshold error value. The processor generates one or more mode estimates from the confirmed ringdown event.

Methods, systems, and computer readable mediums determining a system state of a power system using a convolutional neural network using a convolutional neural network are disclosed. One method includes converting power grid topology data corresponding to a power system into a power system matrix representation input and applying the power system matrix representation input to a plurality of convolutional layers of a deep convolutional neural network (CNN) structure in a sequential manner to generate one or more feature maps. The method further includes applying the one or more feature maps to a fully connected layer (FCL) operation for generating a respective one or more voltage vectors representing a system state of the power system.

A system for transferring energy based on predicted outages is described herein.

A method and an apparatus are presented which enable the identification of a capacitor fault in a given string of a capacitor bank, based on the computation of the string impedance by measuring the string AC current and voltages, where each string includes a plurality of capacitor elements connected in series. The method consists of measuring the string capacitive impedance and comparing this value with a previously measured capacitive impedance of the same string. If a difference between these two values is obtained, which exceeds a given threshold for a certain duration, a fault is recorded.

A power plant-connected energy storage system maintains frequency quality of power generated and supplied by a power plant. The system includes an electric energy storage unit that includes two or more batteries of different types and is configured to be charged or discharged to improve frequency quality of power output from the power plant; and a power conditioner configured to control of the power output from the power plant and to control charge and discharge at least one of the two or more batteries in accordance with the control of the power output from the power plant. The two or more batteries include a short cycle battery having a relatively short charge/discharge cycle and a long cycle battery having a relatively long charge/discharge cycle.