Implementations of the present specification provide a model-based prediction method and apparatus. The method includes: a model running environment receives an input tensor of a machine learning model; the model running environment sends a table query request to an embedding running environment, the table query request including the input tensor, to request low-dimensional conversion of the input tensor; the model running environment receives a table query result returned by the embedding running environment, the table query result being obtained by the embedding running environment by performing embedding query and processing based on the input tensor; and the model running environment inputs the table query result into the machine learning model, and runs the machine learning model to complete model-based prediction.

The present invention discloses a networked control system (NCS) time-delay compensation method based on predictive control. The method comprises the following steps: (1) acquiring random time-delay data in an NCS, and preprocessing the data; (2) predicting the current time-delay by using a fuzzy neural network (FNN) optimized by a particle swarm optimization (PSO) algorithm; (3) compensating the predicted time-delay by using an implicit proportional-integral-based generalized predictive control (PIGPC) algorithm; (4) determining whether a preset work end time is up according to a clock in the NCS; if yes, ending the process; if no, returning to step (2). The method disclosed by the present invention can accurately predict and effectively compensate the NCS time-delay and has excellent development prospect.

Systems and method are disclosed for monitor long-term voltage stability in a power system by estimating post-contingency operating point(s) considering PV-PQ transitions based on the current operating point; predicting a sensitivity based Thevenin index (STI) for each contingency using the estimated operating condition; and determining a voltage stability assessment (VSA) considering N−1 contingency.

Provided in embodiments of the present invention are a micro-grid reconstruction method and device, a micro-grid protection and control center and a storage medium. The method includes: monitoring and acquiring current operating data of a micro-grid in real-time; storing the acquired current operating data and corresponding time stamp information in a database; analyzing an operating state of the micro-grid based on the operating data and the corresponding time stamp information that are stored in the database; and determining a current control scheme for the micro-grid according to a current analysis result, and reconstructing the micro-grid according to the current control scheme. The technical solution mentioned above realizes flexible protection and control of the micro-grid and improves the operating automation and intelligence of a system.

A method for controlling an operating condition of an electric power grid having an intermittent power supply coupled thereto, comprising: using an energy variability controller, controlling variability of a delivered power output of the intermittent power supply to the grid by: monitoring an actual environmental value for a location proximate the intermittent power supply, an available power output of the intermittent power supply being dependent on the actual environmental value; when the actual environmental value is increasing and hence the available power output is increasing, increasing the delivered power output according to a predetermined rate of increase; monitoring a forecast environmental value for the location; when the forecast environmental value is decreasing, decreasing the delivered power output according to a predetermined rate of decrease; and, limiting the delivered power output to below a predetermined threshold. The electric power grid may be or may include an electric power microgrid.

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.

A system for intelligent monitoring and management of an electrical system is disclosed. The system includes a data acquisition component, a power analytics server and a client terminal. The data acquisition component acquires real-time data output from the electrical system. The power analytics server is comprised of a real-time energy pricing engine, virtual system modeling engine, an analytics engine, a machine learning engine and a schematic user interface creator engine. The real-time energy pricing engine generates real-time utility power pricing data. The virtual system modeling engine generates predicted data output for the electrical system. The analytics engine monitors real-time data output and predicted data output of the electrical system. The machine learning engine stores and processes patterns observed from the real-time data output and the predicted data output to forecast an aspect of the electrical system.

A control circuitry includes a first filter configured to filter a gravity compensated longitudinal acceleration of an aircraft to generate a filtered gravity compensated longitudinal acceleration. The propulsor trim control circuitry also includes a second filter configured to generate a filtered speed of the aircraft based on a speed of the aircraft. The propulsor trim control circuitry includes intermediary circuitry configured to generate a filtered longitudinal control effector error based on the filtered gravity compensated longitudinal acceleration and the speed. The propulsor trim control circuitry also includes a third filter configured to generate a filtered longitudinal thrust effector command value based on a longitudinal thrust effector command value. The propulsor trim control circuitry further includes output circuitry configured to generate a predicted longitudinal thrust effector trim value for a target horizontal state based on the filtered longitudinal control effector error and the filtered longitudinal thrust effector command value.

Methods and systems are provided for cruise control velocity tracking. In one example, the method or system may generate a torque command output via a velocity controller that allows for an error within bounds to reduce a fuel consumption amount, the torque command output selected from outcomes of a leader and follower game.

A controller for a building including one or more processors and one or more non-transitory computer-readable media storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations. The operations include parsing a computer-aided design (CAD) file or a building information model (BIM) file for the building to identify building equipment that operates to affect a variable state or condition of a zone of the building. The operations include generating one or more zone models describing one or more control relationships between the building equipment and the variable state or condition of the zone based on the CAD file or the BIM file. The operations include using the one or more zone models to perform a model-based operation for the building equipment.