Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a thermostat-based demand response event. In one aspect, a method includes accessing, for sites, historical readings of HVAC activity, indoor temperature, and outdoor temperature and building a model for each of the sites using the historical readings of HVAC activity, indoor temperature, and outdoor temperature. The method also includes using a simulation engine to achieve a target load shed and load reduction shape for a thermostat-based demand response event, and performing the thermostat-based demand response event based on results of the simulation engine.

Abstract: A power controller for a data storage system automatically selects different power modes based on changing forecasts of availability of renewable energy. The power modes indicate settings for each of a plurality of hardware resources, such as processors, fans, memory, and drives. At times when the storage system can operate at less than the maximum level of performance in terms of IO latency or IOPS, power consumption of one or more of the hardware resources is reduced to a degree corresponding to availability of renewable energy. For example, the hardware resources may be operated in a relatively higher power mode when renewable energy is available than when renewable energy is unavailable. The storage system may be configured to automatically implement a low power mode when power from all sources is in limited supply, e.g., during a brownout.

Abstract: Reliable, automated or semi-automated systems/methods that address technical problems involved in electrical power grid design, planning, and operation/control are disclosed. Applications include the technical problem of optimizing adjustments of, and/or infrastructure additions to, large electrical power grids in response to changed operating conditions or planned facility additions that may impact their reliability. An automated or semi-automated system for identifying appropriate adjustments to the electrical power grid and/or addition of new facilities, and the methods and executable computer instructions that enable them, are disclosed.

Abstract: A method and a system for automatic machine learning-based prediction of new energy power with cloud-edge collaboration are disclosed. The method includes: obtaining, in response to a power prediction demand for a target new energy station, future numerical weather prediction data of the target new energy station in a future period and historical output power of a historical period corresponding to the future period; selecting, based on missing of the future numerical weather prediction data and a data amount of the historical output power, a target power prediction model corresponding to the target new energy station; and adjusting the target power prediction model according to the target working mode, and predicting, by the adjusted target power prediction model, a target output power of the target new energy station in the future period, based on the future numerical weather prediction data and the historical output power.

Abstract: A method includes accessing historic five-minute electricity data for a predetermined number of previous days, determining, using the historic five-minute electricity data for the predetermined number of previous days, a maximum charge price for the predetermined number of previous days, and determining, using the historic five-minute electricity data for the predetermined number of previous days, a minimum discharge price for the predetermined number of previous days. The method further includes determining a current amount of charge of a battery, accessing live five-minute electricity data for a current day, and communicating one or more instructions to discharge a battery when a next live five-minute electricity price is greater than the determined minimum discharge price and the current amount of charge of the battery is greater than zero.

Abstract: Systems, methods, techniques and apparatuses of nested microgrids are disclosed. One exemplary embodiment is a method for removing false data in a nested microgrid system, the method comprising: calculating a first local state estimation using a first plurality of local measurements and a second local state estimation using a second plurality of local measurements; calculating, with a central control system, a plurality of global state estimations including a first global state estimation a second global state estimation; performing a first false data detection test using the first local state estimation and one global state estimation of the plurality of global state estimations; performing a second false data detection test using the first global state estimation and the second global state estimation; detecting false data; and updating the first global state estimation, the second global state estimation, or the first local state estimation in response to detecting the false data.

Abstract: A design support device including: a unit configured to acquire configuration information indicating a configuration of the power distribution supply path; a unit configured to acquire, for each of the plurality of load devices, operation pattern information representing an operation pattern of the load device; a unit configured to calculate, for each power cable, a maximum current value, which is a maximum value of a current flowing through the power cable, based on the configuration information and the operation pattern information of each load device; and a unit configured to output, for each power cable, at least one of the maximum current value for the power cable and recommended cable information representing a cable recommended for use as the power cable based on the calculated maximum current value for each power cable. With this configuration, the design of the power supply system is supported.

Abstract: An example method comprises receiving an initial topology of an electrical, receiving a selection of a region of interest, determining one or more external equivalents of the electrical network that are external to the region of interest, determining one or more internal equivalents of the region of interest, calculating a sensitivity matrix based on electrical impedances of at least one of the one or more internal equivalents and based on an amount of power exchanged when in operation, determining a subset of the sensitivity matrix as indicating highly sensitive buses, receiving historical data regarding power flows, predicting power flow for each highly sensitive buses, comparing the predicted power flow to at least one predetermined threshold to determine possible network congestion, and generating a report regarding network congestion and locations of possible network congestion in the region of interest based on the comparison.

Abstract: The present disclosure provides a method for planning a distribution network with reliability constraints based on a feeder corridor, including determining installation states of respective elements in the distribution network; determining an objective function, the objective function being an objective function of minimizing a total investment cost of the distribution network; obtaining fault-isolation-and-load-transfer time and fault recovery time in a case where the feeder segment of each feeder line that is contained in each feeder corridor fails; determining constraint conditions including reliability constraints; building a distribution network planning model according to the objective function and the constraints; and solving the distribution network planning model built to obtain optimal solutions as planning states and reliability indexes to plan the distribution network.

Abstract: A hierarchical health index evaluation method for an intelligent substation includes: obtaining a basic health index of a device based on static information and dynamic information of the device; obtaining a device correlation based on a communication connection relationship between the device and another device, and correcting the basic health index of the device based on the device correlation to obtain a health index of the device; obtaining a layer-based health index of a layer based on a device health index and a device importance weight of the layer; obtaining a whole-station health index of an intelligent substation based on a layer-based health index of each layer and a sum of device importance weights of each layer; and regulating the intelligent substation based on a health index of each device in the intelligent substation, the layer-based health index of each layer, and the whole-station health index.

Abstract: Technologies for solar power system performance model tuning are disclosed. In at least one illustrative embodiment, a method of tuning a system performance model for a power plant may comprise estimating an expected output of an inverter of the power plant using the system performance model, obtaining a measured output of the inverter, determining whether a difference between the expected and measured inverter outputs is within a predefined range, and tuning the system performance model using the difference in response to determining that the difference is within the predefined range. The power plant may further comprise at least one solar panel array, and the inverter may be electrically coupled to the at least one solar panel array.

Abstract: Systems and methods for demonstrating power control system (PCS) operating sequences provide a model builder and a sequence builder. The PCS model builder allows a user to build a graphical model of a PCS using drag-and-drop objects representing PCS components, such as generators, circuit breakers, transfer switches, and the like. The PCS sequence builder allows the user to enter plain language commands that represent operations performed by the model objects. The model builder then graphically animates the model according to the plain language commands. Animation may include changing an image color, shape, configuration, position, orientation, or size for the model objects. This allows any user to graphically demonstrate how a PCS would work before resources are invested toward developing the PCS.

Abstract: A building system including one or more storage devices storing instructions thereon that, when executed by one or more processors, cause the one or more processors to receive an indication to execute an artificial intelligence (AI) agent of a digital twin, the digital twin including the AI agent and a graph data structure, the graph data structure including nodes representing entities of a building and edges between the nodes representing relationships between the entities of the building. The instructions cause the one or more processors to execute the AI agent based on data of the building to generate an inference that is a prediction of a future data value of a data point of the building for a future time and store at least one of the inference, or a link to the inference, in the graph data structure.

Abstract: A cloud-based modeler component that generates interactive models of an industrial automation system(s) (IAS(s)) is presented. An interactive model facilitates remote viewing of, interaction with, troubleshooting of problems with, or optimization of industrial assets of an IAS. The modeler component polls industrial assets via cloud gateways to obtain information relating to the industrial assets to identify industrial assets of the IAS and relationships with other industrial assets or can receive information from a communication device that obtains information relating to legacy industrial assets to identify those legacy assets and their relationships. The modeler component generates an interactive model of the industrial assets of the IAS based on the information.

Abstract: Implementations are directed to achieving a real-time and distributed control solution that can at least selectively achieve a deterministic flow of power at a virtual point of interconnection (vPOI) of a virtual microgrid, where there is limited or no power measurement data available at the vPOI. Some of those implementations are directed to automatically generating virtual microgrids for a power network, optionally including generating additional and/or alternative virtual microgrids in response to transient and/or persistent changes to the power network. Some of those implementations are additionally or alternatively directed to dynamic control of a virtual microgrid to achieve the deterministic flow of power at the vPOI thereof.

Abstract: Distributed energy resources are validated by dispatching a distributed energy resources individually in known ambient conditions and monitoring the particular effect of dispatch to then establish a database of performance for multiple different distributed energy resources. The distributed energy resources can be permanently monitored to further build up this database and to verify that the distributed energy resource 1s performing consistent with its validation or other expected performance. Distributed energy resources of a slow responding variety and a fast responding variety can be paired together and dispatched together, so that the paired fast responding and slow responding distributed energy resources mimic a large fast responding distributed energy resource. The benefits of a high capacity fast responding distributed energy resource is thus provided, such as for the load shedding and grid support benefits thereof.

Abstract: A machine learning system for maintaining distributed computer control systems for a train may include a data acquisition hub communicatively connected to a plurality of sensors configured to acquire real-time configuration data from one or more of the computer control systems. The machine learning system may also include an analytics server communicatively connected to the data acquisition hub. The analytics server may include a virtual system modeling engine configured to model an actual train control system comprising the distributed computer control systems, a virtual system model database configured to store one or more virtual system models of the distributed computer control systems, wherein each of the one or more virtual system models includes preset configuration settings for the distributed computer control systems, and a machine learning engine configured to monitor the real-time configuration data and the preset configuration settings.

Abstract: The disclosed invention provides system and method for providing autonomous actions that are consistently applied to evolving missions in physical and virtual domains. The system includes a autonomy engine that is implanted in computing devices. The autonomy engine includes a sense component including one or more sensor drivers that are coupled to the one or more sensors, a model component including a world model, a decide component reacting to changes in the world model and generating a task based on the changes in the world model, and an act component receiving the task from the decide component and invoking actions based on the task. The sense component acquires data from the sensors and extracts knowledge from the acquired data. The model component receives the knowledge from the sense component, and creates or updates the world model based on the knowledge received from the sense component.

Abstract: The present disclosure describes transaction-enabling systems and methods. A system can include a controller and a fleet of machines, each having at least one of a compute task requirement, a networking task requirement, and an energy consumption task requirement. The controller may include a resource requirement circuit to determine an amount of a resource for each of the machines to service the task requirement for each machine, a forward resource market circuit to access a forward resource market, and a resource distribution circuit to execute an aggregated transaction of the resource on the forward resource market.

Abstract: A method is provided for an engine. During this method, a database is provided for a parameter of the engine. The database includes a plurality of values for the parameter determined over a period of time. Confidence bands are established using a probability density function on the database. An action is performed in response to a comparison of a first updated value for the parameter to the confidence bands. The engine may be configured as a gas turbine engine or another type of heat engine.

Abstract: An apparatus monitoring system stability of a DC power system includes a switching power converter with a control loop. The converter is connected to a DC bus of the system. A monitoring loop injected into the control loop includes a sensor circuit monitoring voltage and current of the DC bus and a small signal injector producing a periodic signal with variable amplitude and frequency and injects the periodic signal on a reference signal of the control loop. The monitoring loop includes a stability measurement circuit that varies a frequency input to the small signal injector until the periodic signal has a frequency equal to a system minor loop gain crossover frequency of an impedance ratio of a converter closed loop output impedance and an impedance of the DC power system. The monitoring loop includes a measurement output circuit that outputs a DC power system stability margin at the crossover frequency.

Abstract: A system and method are provided for controlling a wind turbine of a wind farm. Accordingly, a controller implements a first model to determine a modeled performance parameter for the first wind turbine. The modeled performance parameter is based, at least in part, on an operation of a designated grouping of wind turbines of the plurality of wind turbines, which is exclusive of the first wind turbine. The controller then determines a performance parameter differential for the first wind turbine at multiple sampling intervals. The performance parameter differential is indicative of a difference between the modeled performance parameter and a monitored performance parameter for the first wind turbine. A second model is implemented to determine a predicted performance parameter of the first wind turbine at each of a plurality of setpoint combinations based, at least in part, on the performance parameter differential the first wind turbine.

Abstract: A condition monitoring system which collects operation data from a machine and monitors a condition of the machine includes: a storage unit that stores information indicating components of a first machine for which a model for a sensor data analysis has been created and components of a second machine for which the model is newly created, information indicating a correspondence relationship between the components of the first machine and the components of the second machine, and information relating to the model; a model creation unit that creates model candidates of the second machine from the model similar to the second machine by using the information stored in the storage unit, and creating information relating to a model candidate selected via an input unit out of the model candidates as the model of the second machine; and a display unit that displays the model candidates.

Abstract: A method and apparatus for automatically generating periodic boiler combustion models and aperiodic boiler combustion models through automatic learning are provided. The method of automatically generating a boiler combustion model may include determining whether a specific event has occurred in association with a boiler, changing a training condition according to a result of the determining, generating a boiler combustion model trained on operation data measured in the boiler and stored in a database according to the training condition, and determining a precision of the generated boiler combustion model.

Abstract: The present disclosure describes systems and techniques that enhance effectiveness and efficiency of a contingency analysis tool that is used for studying the magnitude and likelihood of extreme contingencies and potential cascading events across a power system. The described systems and techniques include deploying the contingency analysis tool in a high-performance computing (HPC) environment and incorporating visual situational awareness approaches to allow power system engineers to quickly and efficiently evaluate multiple power system simulation models. Furthermore, the described systems and techniques include the power system contingency-analysis tool calculating and coordinating protection element settings, as well as assessing controls of the power system using small-signal nomograms, allowing power system engineers to more effectively comprehend, evaluate, and analyze causes and effects of cascading events against a topology of a power system.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a storage device, for electric grid asset detection are enclosed. An electric grid asset detection method includes: obtaining overhead imagery of a geographic region that includes electric grid wires; identifying the electric grid wires within the overhead imagery; and generating a polyline graph of the identified electric grid wires. The method includes replacing curves in polylines within the polyline graph with a series of fixed lines and endpoints; identifying, based on characteristics of the fixed lines and endpoints, a location of a utility pole that supports the electric grid wires; detecting an electric grid asset from street level imagery at the location of the utility pole; and generating a representation of the electric grid asset for use in a model of the electric grid.

Abstract: The present application provides a method and apparatus for evaluating the health state of a distribution transformer, and a medium and a program. In an embodiment, the method for evaluating the health state of a distribution transformer includes: extracting features from electric power parameters of a plurality of distribution transformers; clustering the plurality of distribution transformers into M subsets based on the extracted features, M being a natural number greater than 1 and less than a number of the distribution transformers; and respectively executing processing for each of the M subsets. In an embodiment, the processing includes determining a cluster center of the subset as a reference transformer for the subset; calculating the similarity between each of the distribution transformers in the subset and the reference transformer therein; and sorting the distribution transformers in the subset according to the calculated similarity.

Abstract: Systems, methods, and non-transitory computer-readable storage media for a fast power network simulator. A system configured per this disclosure can use identify a power network, the power network comprising generators, transmission lines, and loads, and receive a model of the power network. The model of the power network can include: models of the generators modeled as differential equations, and models of the transmission lines and the loads modeled as algebraic equations. The system can convert, via a processor, the algebraic equations of the models of the transmission lines and the loads to additional differential equations, then combine, via the processor, the differential equations and the additional differential equations, to yield combined differential equations. The system can then iteratively solve linear equations, via the processor, associated with the combined differential equations, to yield solutions, and output the solutions as part of a power simulation of the power network.

Abstract: In a power control system a server maintains asset models that represent asset behaviour, each asset model being in real-time communication with its asset to dynamically inform the model of the status of the asset. A test is performed at the server by issuing a command to an asset requesting the asset to perform a function. Sensors at the asset measure physical parameters at the asset and report these to the server. The server determines whether the asset responded to the command and, if the asset responded, how it responded over time. The server establishes a model for the asset in terms of an energy capacitance and a time constant based on the measured response. An optimizer determines which assets are to participate in which service models. The server sends instructions to the selected assets to attempt to fulfill the services.

Abstract: A system for enhanced sequential power system model calibration is provided. The system is programmed to store a model of a device. The model includes a plurality of parameters. The system is also programmed to receive a plurality of events associated with the device, receive a first set of calibration values for the plurality of parameters, generate a plurality of sets of calibration values for the plurality of parameters, for each of the plurality of sets of calibration values, analyze a first event of the plurality of events using a corresponding set of calibration values to generate a plurality of updated sets of calibration values, analyze the plurality of updated sets of calibration values to determine a current updated set of calibration values, and update the model to include the current updated set of calibration values.

Abstract: An energy offloading system is in direct electric communication with an energy generating system and dynamically receives energy from the energy generating system. The energy offloading system uses energy for high-load computations. The energy offloading system includes computers performing the high-load computations as well as servers, cooling units, and communication devices. When the energy from the energy generating system is terminated, the energy offloading system may power down these and other devices, or may switch these devices to an alternative power source. The energy offloading system may be portable.

Abstract: The energy management system is an energy management system for a microgrid including at least either one of an electrical load and a renewable energy power-generation system, and an energy storage device, the energy management system including: a prediction unit that predicts, at a fixed time interval, at least either one of an electricity demand and an amount of electricity generated from renewable energy, and an electricity fee, within a predetermined period; and an optimization unit that performs optimization for an optimum charging/discharging plan for the energy storage device by using a prediction result from the prediction unit and in consideration of uncertainty in prediction.

Abstract: Predicting power usage of a chip may include receiving placement data describing a placement, within the chip, of a plurality of logical components of the chip; providing the placement data as an input to a neural network; and determining, by the neural network, based on the placement data, a predicted power usage of the chip.

Abstract: A method of generating a customized secondary power distribution assembly (SPDA) includes generating one or more customizable SPDAs. Each of the one or more customizable SPDAs is a construct corresponding with a microprocessor configured to control a set of customizable channels in each of a set of virtual line replaceable modules (vLRMs). The method also includes creating a mapping between one of the one or more customizable SPDAs and the customized SPDA, the mapping indicating line replaceable modules (LRMs) of the customized SPDA and defining each channel of each LRM, and deploying the customized SPDA in an application. The microprocessor is initiated to control the customized SPDA according to the mapping at startup.

Abstract: A computer system is configured to group solar power systems that provide electric power to an electricity distribution system into clusters. The computer system identifies a solar source meter in each of the clusters that is representative of the respective one of the clusters as a bellwether meter. Each of the bellwether meters monitors a power output of one of the solar power systems in one of the clusters. The computer system receives solar power generation data from the bellwether meters. The computer system generates a solar power generation forecast for each of the clusters of the solar power systems using the solar power generation data from the bellwether meters in respective ones of the clusters.

Abstract: A method and a device for monitoring a power supply apparatus of a traffic system. A computer-based model of the power supply apparatus is created inter alia with the aid of predetermined parameters which are relevant for the power supply apparatus. The invention aims to meet changed requirements of modern power supply devices. Current characteristic quantities are determined during the operation of the traffic system and the operation of the power supply device is simulated at least with the aid of the model and the characteristic quantities.

Abstract: A versatile intelligent fault diagnosis (IFD) method for a distribution grid integrating renewable energy resources is described. Advanced signal processing techniques extract useful features from recorded three-phase current signals, which are input to a multilayer perceptron neural networks (MLP-NN) to diagnose i.e., to detect, classify, identify the feeder branch, and locate the faults. Once a fault is detected, classified and located, a grid operator may adjust grid parameters or dispatch a technician to correct the fault. The IFD method is independent of load demand, renewable energy generation, and fault information (resistance and inception angle) uncertainties, as well as measurement noise.

Abstract: System for controlling voltage supply to a portion of a distribution grid. The portion of the grid includes a substation providing one or more transformers operable to increase or decrease the voltage supplied to consumers within the portion of the grid. The voltage control system providing a data set can include a previously measured power consumption associated with previously measured values of (a) property(ies) for a portion of the grid, the property(ies) being one of voltage, current, frequency or load, or a combination thereof. The voltage control system can provide a measurement device to measure the property(ies) supplied within the portion of the grid. The voltage control system can provide a processing device to determine from the previously measured values of the property(ies) in the data set a most likely effect of altering the value of the property(ies) from a first value to a second value, on the power consumption.

Abstract: A system and method for detecting the operational status of a brake system on a railcar. The system receives from a sensor an indication of the magnitude of a braking force applied by the braking system in response to an instruction to increase or decrease the braking force. It compares the response to possible responses of the braking system in view of the instruction provided. Based on the comparison, the system generates at least one of a message and/or an alert indicating the status of the brake system. Additional sensors, including a pressure sensor on a brake pipe of the railcar, can be added for additional functionality.

Abstract: A method and system for estimating open circuit voltage of lithium ion batteries with temperature input, that has the following steps: step 1 the undetermined equation for estimating open circuit voltage with temperature input is derived according to the gas-liquid dynamic model; step 2: the estimation equation parameters are identified according to the experimental data and put into the undetermined equation for estimating open circuit voltage in the step 1 to obtain a complete equation for estimating open circuit voltage; step 3: the method for estimating open circuit voltage with temperature input is designed according to the complete equation for estimating open circuit voltage.

Abstract: An example method for detecting and mitigating attacks on electric power substations comprises detecting a command to open or close a circuit breaker in the electric power substation. A modified extended substation model for the electric power substation is generated, based on the detected command and based on measurements in substation, where the modified extended substation model is a power flow model for the substation and for one or more directly connected neighboring substations. A power flow analysis is performed, using the modified extended substation model, to generate a predicted voltage for each of a plurality of nodes in the substation and in the one or more directly connected neighboring substations. Each predicted voltage is compared to a corresponding allowable voltage range, and execution of the command is blocked in response to determining that one or more of the voltages is outside the corresponding allowable voltage range.

Abstract: A multi-dimensional holomorphic embedding method for voltage control of an AC power system includes embedding multiple independent symbolic variables representing multiple control elements of the AC power system into AC power flow equations that describe the AC power system, analytically solving voltages for targeted buses of the AC power system in a form of multivariate power series or multivariable Padé approximants about the multiple independent symbolic variables such that coefficients of the multivariate power series or multivariable Padé approximants are obtained non-iteratively, and jointly adjusting the multiple control elements according to the multivariate power series or multivariable Padé approximants to control voltages of the targeted buses.

Abstract: A method for calculating control parameters of a heating supply power of a heating network, pertaining to the technical field of operation and control of a power system containing multiple types of energy. The method: establishing a heating network simulation model that simulates a thermal dynamic process of the heating network; starting an upward simulation based on the heating network simulation model to obtain first control parameters from a set of up adjustment amounts; starting a downward simulation based on the heating network simulation model, to obtain second control parameters from a set of down adjustment amounts.

Abstract: Embodiments of the present disclosure include a system, method, and apparatus comprising a large scale direct steam generator operating on an oxidant of air or enriched air configured to generate steam and combustion exhaust constituents. An exhaust constituent separation system and an energy recovery system to reclaim energy and improve the efficiency of the thermodynamic cycle. An optional CO2 separation system and Non Condensable Gas injection system may be included.

Abstract: An energy audit tool for a wind turbine power system includes a data collector module configured for temporary connection to an existing turbine controller of the existing wind turbine power system. The data collector module is configured to collect operating data of the existing wind turbine power system. The energy audit tool also includes a model simulator module configured for analyzing the collected operating data, generating a model of the existing wind turbine power system based on the collected operating data, and determining an energy loss of the existing wind turbine power system from the model of the existing wind turbine power system.

Abstract: A method determines measurement locations in an energy grid. In the energy grid, use is made of a controllable device for wide-range voltage control. A model of the energy grid is provided which specifies a voltage distribution within the energy grid by a system of equations and/or a system of inequalities depending on the control position of the controllable device. A simulation for minimizing the number of measurement locations is carried out on the basis of the model, and in that as a result of the simulation a minimum number and the respective position of measurement locations and also the control position of the controllable device are specified in order that the energy grid complies with a predefined voltage band during operation.

Abstract: A crash test simulator device for re-creating a software crash scenario within a virtual environment using artificial intelligence processes to consider a large group of variables that may be relevant to the crash incident. The crash test simulator device includes a production environment monitoring engine configured to monitor a user's interaction with an application implemented within a production environment, and generate information used to re-create a crash incident within a virtual environment.

Abstract: The present disclosure discloses an automated integrated test system and method thereof. A virtual mobile device is generated by a host at the test end at an initial time, which executes a preset script file to call the basic functions and the control functions after detecting the abnormal signals of production equipments, so as to simulate the processing flow of abnormal signals and to remotely adjust the equipment parameters. Then, a log file is generated according to the execution result of the script file, and the corresponding report files are generated according to different time ranges in the log file for transmission or display, so as to achieve the technical effect of improving the convenience of system testing in the complex environment.

Abstract: A method for optimizing total load distribution of a power system includes the following steps: determining system initial data, and describing the power system in forms of nodes, branches, and parameters; determining an optimization objective and a constraint condition according to a problem, to construct a real-time economic dispatch model; setting a topology structure between the nodes; constructing a neural network for each node, and setting a parameter; setting an initial variable of the neural network; performing optimization by means of the neural network; determining whether a termination condition is satisfied, and outputting a result when the termination condition is satisfied, or repeating the neural network optimization when the termination condition is not satisfied.

Abstract: In certain aspects of the disclosure, a system includes an isolation device coupled between a first circuit in a first power domain and a second circuit in a second power domain. The system also includes a second power source coupled to a power distribution network, wherein the power distribution network is configured to distribute power from a first power source to the second power domain. The system further includes a failure detector having an input coupled to a node on the power distribution network located upstream of the second power source, and an output coupled to the isolation device, wherein the failure detector is configured to sense a voltage at the node, to detect a power loss of the first power source based on the sensed voltage, and to enable the isolation device in response to detection of the power loss.