A supply and demand adjustment monitoring device of a power grid includes an output actual power value database that stores an output actual power value of at least one generator, an output power command value database that stores an output power command value issued to the generator, a planned adjustment capacity value database that stores a planned adjustment capacity value for the generator, and an adjustment capacity evaluation unit that evaluates an adjustment capacity based on the output actual power value, the output power command value, and the planned adjustment capacity value.

Disclosed herein are AI-based platforms for enabling intelligent orchestration and management of power and energy. In various embodiments, a set of edge devices includes a set of artificial intelligence systems that are configured to process data handled by the edge devices and determine, based on the data, a mix of energy generation, storage, delivery and/or consumption characteristics for a set of systems that are in local communication with the edge devices and to output a data set that represents the constituent proportions of the mix. In some embodiments, the output data set indicates a fraction of energy generated by an energy grid and a fraction of energy generated by a set of distributed energy resources that operate independently of the energy grid. In some embodiments, the output data set indicates a fraction of energy generated by renewable energy resources and a fraction of energy generated by nonrenewable resources.

Provided is a system and method for determining the state estimate of a power grid by dividing the power grid into smaller sub-sections, generating state estimates for each sub-section, and then generating a consensus among the sub-sections. In one example, the method may include partitioning a section of the power distribution grid into a plurality of sub-sections based on loads distributed within the section of the power distribution grid, generating a plurality of state estimates for the plurality of sub-sections based on load distribution within the plurality of sub-sections and a Kalman Filter model, generating an aggregate state estimate for the section of the power distribution grid based on an aggregate of the plurality of state estimates and a boundary consensus between the plurality of sub-sections from a previous state estimation, and displaying data about the aggregate state estimate via a user interface.

A system for controlling power distribution between a renewable energy source (RES) that generates electrical power, a power grid, an energy storage system (ESS) coupled to and configured to store electrical power from the RES and the power grid, and a behind-the-meter (BTM) load coupled to and configured to receive electrical power from the RES, the ESS, and the power grid includes a controller. The controller includes a processor and a non-transitory computer readable storage medium comprising instructions stored thereon that, upon execution by the processor, cause the controller to determine a prioritization mode and control the flow of electrical power in the system based on the prioritization mode.

A long-term predictor circuit predicts a long-term predicted power indicating temporal variations in consumed power of a customer, using a long-term prediction model indicating the variations for each moment of clock times. A short-term predictor circuit predicts a short-term predicted power using a short-term prediction model indicating the variations over a time interval before and after a change in a consumed power of each load apparatus, based on the variations over a time interval immediately before a current time, the short-term predicted power indicating the variations over a time interval immediately after the current time. A controller circuit controls charging and discharging of a battery apparatus by setting a charging power or a discharging power based on the long-term predicted power, and controls discharging of the battery apparatus by setting a discharging power based on the short-term predicted power.

An improved system and method for managing and distributing electrical power is provided. In various embodiments, systems and methods comprise at least one powered device that receives electrical power from at least one source. Structure and devices are provided within the system to monitor, regulate, and transmit power from a source to a powered or driven device in an efficient and reliable manner based on availability, cost, and environmental factors.

A building energy system includes an energy storage system (ESS) configured to store energy received from an energy source and provide the stored energy to one or more pieces of building equipment. The system includes a local building system configured to collect building data and communicate the building data to a cloud platform and the cloud platform configured to receive the building data from the local building system via the network, determine whether to retrain a trained load prediction model based on at least some of the building data, retrain the trained load prediction model based on at least some of the building data in response to a determination to retrain the trained load prediction model, determine a load prediction for the building based on the retrained load prediction model, and cause the local building system to operate.

A simulator models an energy and power system. The simulator allows a user to manipulate digital representations of nodes, which represent one or more components of power and energy assets. The simulator also allows a user to manipulate digital representations of edges, which connect the nodes, to form a power and energy network. A plurality of object classes correspond to the nodes and edges. The object classes comprise class inheritance structures so that constraints of a parent class are retained by one or more child classes. The interface on the simulator allows a user to model a power and energy system by allowing the user to connect the nodes with edges to construct a power and energy system, wherein the object classes for the nodes, when executed by the simulator, implement one or more dynamical models to model the power and energy assets.

A micro utility system. The micro utility system may include a portable container configured to house an energy storage system (ESS) and solar panel storage structures; a portable solar panel structure having two or more solar panels coupled to each other at one end, wherein the two or more solar panels are coupled to at least two wheels at a distal end of the portable solar panel structure; and circuitry configured to receive electrical power from the portable solar panel structure, wherein the circuitry includes a processor configured by machine-readable instructions to direct electrical energy from the portable solar panel structure or the ESS to a load.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for shaping compute load using virtual capacity. In one aspect, a method includes obtaining a load forecast that indicates forecasted future compute load for a cell, obtaining a power model that models a relationship between power usage and computational usage for the cell, obtaining a carbon intensity forecast that indicates a forecast of carbon intensity for a geographic area where the cell is located, determining a virtual capacity for the cell based on the load forecast, the power model, and the carbon intensity forecast, and providing the virtual capacity for the cell to the cell.