A method and apparatus for predicting power consumption, a device, and a readable storage medium. The method includes: acquiring a reference variable generated in a history time period; and acquiring predicted power consumption in a target time period by inputting a variable characteristic into a power consumption prediction model, the target time period and the history time period having a corresponding relationship, and the power consumption prediction model being obtained by training a sample reference variable marked with sample power consumption. In the method, the reference variable including a discrete reference variable and a continuous reference variable in the history time period is acquired, and a characteristic of the acquired reference variable is acquired; and an extracted variable characteristic is input into a variable prediction model to output the predicted power consumption in the target time period.

A power management system including a management apparatus configured to assign divided computation processing constituting at least a part of predetermined computation processing to a distributed computing device placed in a facility, wherein the management apparatus includes a receiver configured to receive a message including an information element indicating executability of computation processing by the distributed computing device, and a controller configured to perform assignment processing configured to assign the divided computation processing to the distributed computing device based on the executability of the computation processing.

Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for training a machine-learning model for predicting event tags. The system obtains asset data for an electric power distribution system in a geographic area. The asset data includes: for each of a plurality of electrical assets of the electrical power distribution system, data indicating one or more characteristics of the electrical asset. The system further obtains sensor data for the electric power distribution system. The sensor data includes measurement data from a plurality of electric sensors. The system generates, by processing the asset data and the sensor data, partition data that includes, for each of the plurality of electrical assets, an assignment that assigns the electrical asset to one of a set of feeder networks.

Examples relate to adjusting load power consumption based on a power option agreement. A computing system may receive power option data that is based on a power option agreement and specify minimum power thresholds associated with time intervals. The computing system may determine a performance strategy for a load (e.g., set of computing systems) based on a combination of the power option data and one or more monitored conditions. The performance strategy may specify a power consumption target for the load for each time interval such that each power consumption target is equal to or greater than the minimum power threshold associated with each time interval. The computing system may provide instructions the set of computing systems to perform one or more computational operations based on the performance strategy.

Methods and apparatus for grid connectivity control are provided herein. For example, a method can include receiving status information of a microgrid configured to connect to a grid, transmitting a live status update screen of the microgrid to a user, the live status update screen comprising a grid connectivity button configured to receive a user input and based on a received user input, transmitting a control signal to a microgrid interconnect device connected between the microgrid and the grid for coordinating one of connection or disconnection microgrid connected to the grid.

A rapidly deployable modular microgrid including a plurality of renewable and other energy generation technologies, energy storage technologies, energy distribution networks, and intelligent control systems capable of managing the flow of electrical energy between one or more locations of energy generation, storage, and consumption are disclosed. The aforementioned microgrid may be delivered and rapidly deployed to provide primary or secondary electricity for a variety of purposes; including but not limited to household electrification, commercial or industrial productivity, grid resiliency, water pumping, telecommunication systems, medical facilities, and disaster relief efforts.

Provided is a building equipment energy control system, the system including: a library configured to receive information on an equipment unit from a DDC device controlling a plurality of equipment units installed in a building, and store the received information; a modeling module configured to retrieve information on the equipment unit from the library and perform simulation modeling for the equipment unit to calculate energy usage; a control module configured to generate a control command for the equipment unit based on the energy usage calculated by the modeling module and provide the control command to the DDC device; and a correction module configured to calculate an error rate between actual energy usage of the equipment unit and the calculated energy usage and correct information on the equipment unit. Therefore, it is possible to derive an optimized control set value for each equipment unit by performing simulation modeling for various equipment units, so that energy saving performance and operating efficiency of the equipment units can be increased. In addition, by providing equipment performance information and equipment operation information for each equipment unit to a library in a modeling process, it is possible to optimize a control according to product specifications and operating characteristics of each equipment unit.

The present disclosure provides a grid forming vector current control system configured to emulate a virtual synchronous machine (VSM). The disclosed system comprises a droop control unit, a current control unit, a virtual admittance unit and a phase locked loop (PLL) unit. The virtual admittance unit and the PLL unit are configured to emulate an inertia of the VSM. A virtual current source is connected in parallel to the VSM.

The present invention relates to a method for power balancing a power grid (10) having multiple phases (12:1,2 3) and a common ground (0). The power grid (10) is connected to at least one load (13, 17) causing a non-uniform power consumption between the multiple phases (12: 1, 2, 3) of the power grid (10). The method comprises: monitoring power provided to the power grid (10) in controller (18), storing available energy in the power grid (10) in an energy storage (16) using multiple inverters (I1, I2, I3), each inverter (I1, I2, I3) is connected between the energy storage (16) and each phase (12: 1, 2, 3) of the power grid (10), and redistributing power between phases (12: 1, 2, 3) based on power available in the energy storage (16) by controlling power flow through the inverters (I1, I2, I3) by the controller (18) based on the non-uniform power consumption.

A solar energy system includes a photovoltaic (PV) assembly and a drive system. The PV assembly comprises a support subassembly and an array of PV panels pivotable therewith about a longitudinal axis of the PV assembly. The drive system comprises a motor assembly comprising an electric motor and a gearing arrangement, and a pivot wheel comprising a hoop-portion and joined to the PV assembly. The hoop portion includes an outer circumferential channel, and two opposing catches defining a maximum pivot range. A chain resides partly within the circumferential channel, is engaged with the two opposing catches, and is also in geared communication with the motor assembly such that the motor is operable to rotate the pivot wheel. In some embodiments, the opposing catches define a maximum pivot range through an arc of more than π radians and less than 2π radians.