A power grid reactive voltage control model training method. The method comprises: establishing a power grid simulation model; establishing a reactive voltage optimization model, according to a power grid reactive voltage control target; building interactive training environment based on Adversarial Markov Decision Process, in combination with the power grid simulation model and the reactive voltage optimization model; training the power grid reactive voltage control model through a joint adversarial training algorithm; and transferring the trained power grid reactive voltage control model to an online system. The power grid reactive voltage control model trained by using the method according to the present disclosure has transferability as compared with the traditional method, and may be directly used for online power grid reactive voltage control.

Systems and methods for battery management are disclosed. A system may include an internal control network including multiple node controllers powered by a unique cell or combination of cells of a battery. The node controllers may communicate with each other via a node communication system. Each node controller may be responsible for managing a charge level associated with one or more cells. The one or more devices of the internal control network may enable measurement of environmental factors such as a temperature and a current and voltage applied at the battery. Based on the measured environmental factors, the internal control network may perform an ongoing assessment of the one or more cells of the battery and of an overall battery condition. The internal control network may initiate turning on or off a battery output to prevent over discharge and possible damage to the battery or devices connected to the battery.

A cloud control power socket device includes a housing, a power plug, a first switch device, a second switch device, a socket and a cloud control circuit. The power plug has first and second conductive wires. The first switch device is arranged on the housing. The second switch device is arranged in the housing and has a first end, a second end, and a control end. The socket is connected to the second end of the second switch device and the second conductive wire. The cloud control circuit is connected to the control end of second switch device. The first switch device includes an AC switch; a first indicator having two ends connected to the AC switch and the second conductive wire; and a second indicator having two ends connected to the second conductive wire and the second switch device.

A computer-implemented method for aggregating electric vehicle loads for demand response events includes receiving a demand response (DR) event request from a utility system indicative of a DR event for an area. The DR event request includes at least one event parameter for participation in the DR event. The method includes determining a first original equipment manufacturer (OEM) DR event load for the area based on the DR event request and charging data received from electric vehicles associated with a first OEM. Upon determining the first original OEM DR event load does not meet the at least one event parameter, the method includes aggregating charging data from electric vehicles associated with a second OEM with the first OEM DR event load to determine an aggregated DR load for the area.

Methods, systems, and apparatus, including computer programs encoded on a storage device, for electric grid asset detection are enclosed. An electric grid asset detection method includes: obtaining overhead imagery of a geographic region that includes electric grid wires; identifying the electric grid wires within the overhead imagery; and generating a polyline graph of the identified electric grid wires. The method includes replacing curves in polylines within the polyline graph with a series of fixed lines and endpoints; identifying, based on characteristics of the fixed lines and endpoints, a location of a utility pole that supports the electric grid wires; detecting an electric grid asset from street level imagery at the location of the utility pole; and generating a representation of the electric grid asset for use in a model of the electric grid.

A method analyzes a fault of an ungrounded power distribution system. The method determines a type of a fault in a line segment of the ungrounded power distribution system, and modifies a nodal admittance matrix of the line segment determined before the fault using a transformation matrix corresponding to the type of the fault to produce a faulty nodal admittance matrix of the line segment after the fault. The ungrounded power distribution system is analyzed using the faulty nodal admittance matrix and nodal admittance matrices of functional branches or line segments of the power distribution system.

Methods for implementing power delivery transactions between a buyer and a seller of electrical energy supplied to an electrical grid by an integrated renewable energy source (RES) and energy storage system (ESS) of a RES-ESS facility are provided. Estimated total potential output of the RES is compared to a point of grid interconnect (POGI) limit to identify potential RES overgeneration, and the buyer is charged if potential RES overgeneration is less than potential overgeneration during one or more retrospective time windows. The method provides a basis for the RES-ESS facility owner to be paid for an estimated amount of energy that did not get stored as a result of a grid operator not fully discharging an ESS prior to the start of a new day.

A battery management system including a battery center and a controller. The battery center includes one or more battery receptacle. The battery center is configured to: receive one or more batteries, identify one or more batteries, and charge one or more batteries. The controller includes a memory and an electronic processor. The controller is configured to: receive, from the battery center, a status of one or more batteries, receive, from a user, an unlock request, and output, to the battery center, an unlock command. Wherein, the battery center unlocks one or more batteries from the one or more battery receptacle upon receiving the unlock command.

A method and a device are provided for monitoring an electrical power supply network. A temporal frequency change value is determined for at least two sections or for at least two points of the power supply network. The frequency change value indicates the respective temporal frequency change of the network frequency. A conclusion is drawn regarding a possible islanding within the power supply network, and a warning signal which indicates the possible islanding within the power supply network is generated when the difference between the frequency change values, exceeds a predetermined frequency change threshold value.

A power generation planning apparatus that calculates a generation plan which is a plan of starting and stopping and output power of electric generators. The apparatus includes an information calculation unit that calculates demand and supply of electric power, a plan calculation unit that calculates the generation plan of the starting and stopping and the output power of the electric generators by using, as an input, the generation information calculated by the information calculation unit, and an adjustment unit that calculates a generation plan with a time interval shorter than the generation plan by adjusting a starting initiation time and/or a stopping initiation time of the electric generator in the generation plan such that total power generation cost is reduced by using, as inputs, the generation plan calculated by the plan calculation unit and generation information with a time interval shorter than the generation plan.