In an example method, first electrical power is generated using one or more solar panels. Saline water is desalinated using a desalination facility powered, at least in part, by the first electrical power. The desalinated water is stored in a reservoir located at a first elevation. A usage of an electrical grid is monitored, and a determination is made that one or more criteria are satisfied at a first time. In response, the desalinated water is directed from the reservoir to a turbine generator located at a second elevation, second electrical power is generated using the turbine generator, the desalinated water is directed from the turbine generator into an aquifer located at a third elevation, and at least a portion of the second electrical power is provided to the electrical grid.

Cooperation in supply and demand balance of renewable energy in a region is implemented by operation of infrastructures of an infrastructure service such as water supply.

In an energy management system including: a processor; and a storage device, the processor predicts an electric power supply amount utilizing renewable energy in a predetermined region, predicts an electric power demand amount in the region, predicts a demand amount of an infrastructure service different from an electric power service in the region, predicts an electric power demand amount corresponding to the infrastructure service on the basis of the predicted demand amount of the infrastructure service in the region, and determines use time of electric power corresponding to the infrastructure service such that the electric power demand amount in the region approaches the electric power supply amount.

A power management apparatus and a housing complex combination method for trading surplus power for a housing are provided. Influencing factors in analyzing a consumption pattern of an individual housing and various correlations between the influencing factors are analyzed, and an optimal sustainable housing complex through supply of new renewable energy is formed.

Systems and methods are described herein for novel uses and/or improvements to artificial intelligence applications in an environment with limited or no available data. In particular, systems and methods are described herein for providing network arrangement recommendations based on power consumption predictions for selected applications within network arrangements featuring devices with non-homogenous or unknown specifications.

In a method and system, voltage and/or current signals on an electrical/power system is monitored. A power event is identified from the monitored voltage and/or current signals. In response to event identification, waveforms of the monitored voltage and/or current signals are captured. Energy-related signals are calculated and extracted from pre-event measurements, event measurements and post-event measurements using the captured waveforms. Additional information associated with the event is identified and calculated by comparing (a) the calculated and used energy-related signals from pre-event measurements, with (b) the calculated and used energy-related signals from post-event measurements.

A power usage prediction system and method determines whether or not a predicted power usage exceeds a limit value using modeling data for power usage. The system includes a power measurement unit for measuring power usage at a certain time interval; a modeling unit for generating a plurality of data sets by grouping a certain number of a plurality of measurement data indicating the measured power usage in time series, storing the last measurement data of the data set as a modeling output, and storing measurement data other than the modeling output of the data set as a modeling input; and a prediction unit for inputting real-time data measured in real time in the power measurement unit into the modeling unit in time series, and predicting the power usage after the real-time data by corresponding the real-time data with the plurality of data sets.

A power calculation apparatus calculating an amount of power suppliable to a power system by an energy source connectable, at a connection point, to the power system and capable of power generation and power storing, the power calculation apparatus includes: a microprocessor and a memory connected to the microprocessor, wherein the microprocessor is configured to perform: specifying a position of the connection point of the energy source in connection with the power system; acquiring a capacity information indicating a power generation capacity or a remaining storage capacity of the energy source; and calculating an amount of power suppliable by the energy source to the power system in an area within a predetermined range including the connection point, based on the capacity information and the position of the connection point.

Systems include one or more critical datacenter connected to behind-the-meter flexible datacenters. The critical datacenter is powered by grid power and not necessarily collocated with the flexboxes, which are powered “behind the meter.” When a computational operation to be performed at the critical datacenter is identified and determined that it can be performed at a lower cost at a flexible datacenter, the computational operation is instead routed to the flexible datacenters for performance. The critical datacenter and flexible datacenters preferably shared a dedicated communication pathway to enable high-bandwidth, low-latency, secure data transmissions.

A method, system and apparatus are provided for optimized load shaping for optimizing production and consumption of energy. Information signals indicative of a first load shape signal are obtained corresponding to a total load, a renewable energy load of one or more renewable energy sources and a non-renewable energy load of one or more non-renewable energy sources. The first load shape signal corresponding to renewable energy load is removed from a non-renewable energy load to obtain a resulting load shape signal. The resulting load shape is flattened signal by apportioning the resulting load shape signal across time intervals to obtain a flattened load shape signal. At least a portion of the first component corresponding to the renewable energy load is added to the flattened load shape signal to create an optimized load shape signal. The optimized load shape signal is provided to modulate electric loads of energy-consuming devices.

An electronic device includes an AI power controller that predicts future load transients within a system and that dynamically alters power settings in anticipation of the predicted future load transients. To predict a future load transients, the AI power controller receives as an input application signature data from an application executing on the device. The application signature data includes at least media frame data generated by the application during a time interval. The AI power controller executes logic to compare the received application signature data to historical application signature data, where the historical application signature data includes media frame data generated by the application during one or more past execution instances of the application. Based on the comparison, the AI power controller predicts a load transient of the application at a future point in time and dynamically adjusts a power control setting of the device in anticipation of the predicted load transient.