Methods, computer program products, and systems are presented. The methods include, for instance: extracting from historical data and demand response agreements, attributes relevant to responsivities of demand response programs; and training a demand-response (DR) user pooling model as a machine learning model with training datasets including the attributes from the extracting,

This disclosure relates generally to a system and method for transactive energy (TE) market model. Existing TE models either consider market without a network simulation model or both the market model and the network simulation model are considered in a single formulation which makes the computation complex. The disclosed system considers both the power flow simulation of the network and the market model in a sequence. In other words, the disclosed system decouples the market model and network model to reduce the computational complexity at the same time without sacrificing on the technical feasibility of the solution.

In order to suppress frequency fluctuation caused by a load frequency, an AR calculating section calculates an AR using system frequency deviation and tie-line power flow deviation as inputs. An output distribution ratio determining section determines a ratio of output distribution according to merit order based on the AR calculated by the AR calculating section. An output distributing section determines output distribution according to an output change speed based on the output distribution ratio determined by the output distribution ratio determining section according to the output change speed. An output distributing section determines output distribution according to the merit order based on the output distribution ratio determined by the output distribution ratio determining section according to the merit order. An output distribution instruction value determining section determines an output distribution instruction value to each regulated power source using, as inputs, output distribution values determined by the output distributing sections.

Microgrids and methods for controlling a microgrid. In one example, a microgrid includes a microgrid controller, a primary junction, a high-voltage supply line, a high-voltage output line, one or more switchgear connecting the primary junction to at least one other component of the microgrid, a plurality of photovoltaic (PV) panels, a breaker connected to the plurality of PV panel inverters, a first load connected to the breaker, and one or more battery banks. In some instances, the microgrid includes a ground bank transformer configured to provide a ground current path. Each of the plurality of PV panels is connected to one of a plurality of PV panel inverters. Each of the battery banks may include a plurality of battery cells.

[Object] To control the power usage by plural facilities such that information related to the power usage is acquired from equipment devices and the power usage per equipment device is accurately predicted based on the acquired information.

[Solution] A power control system for performing power control such that a total power usage of plural facilities satisfies a predetermined power usage condition, the power control system including an actual result information acquisition unit 360 that acquires information on power usages by equipment devices installed in the facilities; a first prediction unit 320 that predicts power usages of the facilities in which the equipment devices are installed, based on the information on the power usages by the equipment devices; and a control information generation unit 340 that controls the total power usage of the plural facilities, based on the power usages of the facilities predicted by the first prediction unit 320.

The techniques disclosed herein enable systems to optimize generation and dispatch of renewable energies using data-driven models. In many contexts, a renewable energy system is collocated with a local consumer such as a datacenter, a smart building, and so forth. The objective of the renewable energy system is to meet local power needs while participating in various energy markets of differing trading frequencies. To optimally manage the renewable energy system, a data-driven model is configured to analyze current conditions and generate policies to control renewable energy system operations. For instance, the model can retrieve current market prices, generation capacity, costs associated with generating energy, and so forth. Based on the collected information, the model can generate a policy that maximizes revenue obtained by the renewable energy system while meeting local demand. Through many iterations, the model can determine a realistically optimal policy for managing the renewable energy system.

A method of trading electrical energy is provided. The method comprises a smart agent receiving state data affecting electricity usage within an electrical power grid over a specified time period and forecasting, with a supply/demand model, supply and demand for electricity within the power grid according to the state data. The smart agent uses a reinforced learning neural network to calculate a price for electricity according the state data and forecasted supply and demand. The smart agent submits an order to a matching engine to buy or sell electricity on the power grid at the calculated price according to specified market rules. The smart engine receives an acknowledgment from the matching engine if the order is matched to another agent on the power grid or a rejection from the matching engine if the order is not matched to another agent.

A decentralized electrical power allocation system is provided. The system includes a power bus, electric power consumers, and at least two power source assemblies. Each power source assembly includes a power controller and a power source. Each power controller is configured to execute an adaptive droop control scheme so as to cause their respective power sources to output power to meet a power demand on the power bus applied by the power consumers. The power output of a given power source is controlled based at least in part on correlating a power feedback of the given power source with a droop function that represents an efficiency of the given power source to generate electrical power for a given power output. The droop functions are collaboratively defined so that one power source shares more output at lower power levels while another power source shares more output at higher power levels.

There is provided a power adjustment method in a microgrid connected to an external power supply system and having a power storage unit capable of adjusting an amount of stored power by charging and discharging and a power consumption unit capable of adjusting power consumption of the power. The power adjustment method includes adjusting transmission and reception of the power by simultaneously controlling the power consumption in the power consumption unit and charge/discharge power in the power storage unit in order to transmit and receive power based on a planned value determined for each planned section to and from the external power supply system.

This invention provides an energy storage device manager, a system comprising the energy storage device manager, computer-readable media configured for providing the energy storage device manager, and methods of using the energy storage device manager. The energy storage device manager can optionally control charge buses and/or load buses to modulate the state of charge of an energy storage device. The energy storage device manager can optionally be configured with a plurality of modes that target different states of charge. The plurality of modes can optionally comprise a maintain mode which targets a nominal (e.g. 50%) charge state and a high-charge mode that targets a state of charge greater than the maintain mode. The plurality of modes can optionally further include an in-use mode which targets a state of charge greater than the maintain mode, and turns on a load bus that is turned off in the preparation mode. The energy storage device manager can optionally be configured to determine a charge start time to execute the preparation mode. The energy storage device manager can optionally be configured to determine the charge start time based on forecast data (e.g. power prediction forecast determined based on weather forecast).