Abstract: Methods, computer systems, and apparatus, including computer programs encoded on computer storage media, for training a machine-learning model for predicting event tags. The system obtains asset data for an electric power distribution system in a geographic area. The asset data includes: for each of a plurality of electrical assets of the electrical power distribution system, data indicating one or more characteristics of the electrical asset. The system further obtains sensor data for the electric power distribution system. The sensor data includes measurement data from a plurality of electric sensors. The system generates, by processing the asset data and the sensor data, partition data that includes, for each of the plurality of electrical assets, an assignment that assigns the electrical asset to one of a set of feeder networks.

Abstract: A switching state of a switching arrangement of an electrical distribution arrangement is optimized. In each switching state, an outgoing circuit of the distribution arrangement is connected to a supply by the switching arrangement via a component. Each state differs from others in that the outgoing circuit is connected to the supply via another component. The switching arrangement has enough switching states that each outgoing circuit is connectable to a supply via two different components. An outgoing circuit is presented based on: operating parameters of the components, a switching state, outgoing loads; environmental parameters of the electrical components, forecasted environmental parameters, and forecasted outgoing loads. Forecasted operating parameters are simulated to compare future operating parameters with limit values. Based on likely exceeding limit values in the future, an alternative switching state is suggested such that limit values are not exceeded.

Abstract: System for controlling voltage supply to a portion of a distribution grid. The portion of the grid including 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 includes: a data set including a previously measured power consumption associated with previously measured values of a property(ies) being one of voltage, current, frequency or load, or a combination thereof, a measuring device to measure the property(ies) within the portion of the grid, a processing device to determine a most likely effect of altering the value(s) of the property(ies) from a first value to a second value, a storage device for storing one or more rules associating a trigger event with a response action associated with the substation, and a control device to receive a measurement of the property(ies) within the portion of the grid.

Abstract: A preemptive optimization of a power distribution event associated with providing an electrical power from a battery onboard a vehicle to a charging station offboard the vehicle. The preemptive optimization may include preemptively charging the battery in advance of the power distribution event and/or preemptively configuring the vehicle and the battery, such as with establishment of standby session, to provide electrical power from the battery to the charging station without providing the electrical power to the charging station until the charging station thereafter experiences an outage, interrupt, etc.

Abstract: A communications interface between electric vehicle supply equipment and an electric vehicle includes: a first connection for connecting to a controller of the electric vehicle supply equipment; a second connection for connecting to a controller of the electric vehicle; and an Ethernet interface coupling the first and second connections for communication between the controller of the electric vehicle supply equipment and the controller of the electric vehicle.

Abstract: According to an embodiment of the invention, an energy balance adjustment control method is provided and includes a process of receiving an output curtailment instruction for a distributed power source, a process of requesting a load adjustment to a consumer according to the receiving of the output curtailment instruction, a process of receiving a reply to the request from the consumer, and a process based on the reply including notifying the distributed power source of an avoidance of the output curtailment instruction in the case where the load adjustment is possible or notifying the distributed power source of the output curtailment instruction in the case where the load adjustment is impossible. Thus, an energy balance adjustment control method and an adjustment control device are provided in which the occurrence of output curtailment can be suppressed.

Abstract: A method for power management in a microgrid, the microgrid including at least one renewable energy source, at least one non-renewable energy source and at least one grid-forming energy storage source.

Abstract: An integrated circuit includes; a core configured to process an instruction in accordance with a voltage-frequency level, an instruction complexity calculation circuit configured to calculate an instruction complexity for at least one instruction to-be-processed after a reference time in relation to heating information related to the core acquired before the reference time, wherein the instruction complexity calculation circuit is further configured to generate a control signal corresponding to the instruction complexity, and a dynamic voltage and frequency scaling (DVFS) controller configured to adjust the voltage-frequency level after the reference time in response to the control signal.

Abstract: Among other things, a method is disclosed which includes the following: acquiring at least one set of acceleration data indicative of a progression of measured acceleration values; determining status data indicative of a process step within a cleaning program performed by a dishwasher; outputting or causing the output of the determined status data. Further revealed is a device for executing and/or controlling this method, a system with one or more devices for executing and/or controlling this method and a computer program for executing and/or controlling this method by employing a processor.

Abstract: A method for optimizing the energy expenditure and the comfort of a building, including comfort systems provided with an online consumption sensor, local environment data sensors associated with an identifier of a zone of the building, and at least one server for collecting and recording the timestamped data remotely includes the following steps: —constructing and saving a simplified digital model of the thermal behavior of the building; —a step of calibrating the simplified digital model calculated during the preceding step; —a step of validating the calibrated digital model calculated during the preceding step by comparing the digital variables obtained by predictive processing of the calibrated model and the digital variables stored by the server over a period of a few days; —a step of calculating digital parameters for resource allocation by applying a Pareto optimum calculation applied to the validated calibrated digital model.

Abstract: A storage device includes a non-volatile memory including a plurality of non-volatile memory cells, a buffer memory configured to temporarily store write data to be written to the non-volatile memory or read data read from the non-volatile memory, and a controller configured to receive a sleep mode signal from an external host. When the sleep mode signal is received by the controller, the controller is configured to block a first power supplied to the non-volatile memory and set the buffer memory to one of a first mode in which a second power is blocked from being supplied to the buffer memory and a second mode in which the buffer memory operates with low power. The write data stored in the buffer memory is written to the non-volatile memory when the buffer memory is set to the first mode.

Abstract: Methods and systems are disclosed to identify network nodes/cells with performance seasonality based on time series of performance data and external reference data. A plurality of time series of data values is obtained, each time series comprising a series of data values corresponding to a performance indicator of one network node in a periodicity. A plurality of series of external reference data values in the first periodicity is also obtained. For a time series of data values, the method identifies a network node providing the time series of data values as having performance seasonality regarding the performance indicator of the network, when similarity between the time series of data values and a corresponding series of external reference data values meets a criterion based on dynamic time warping distance calculation and pair-wise distance calculation using the time series of data values and the series of external reference data values.

Abstract: Computer-implemented methods and computer systems are disclosed herein as implemented by a controller operatively coupled to a network of electric vehicles. The methods and systems include the controller (i) receiving a notification that an electric vehicle is stranded without sufficient power to operate; (ii) receiving information regarding the stranded electric vehicle; (iii) detecting one or more other electric vehicles in a vicinity of the stranded electric vehicle; (iv) receiving information regarding the detected one or more other electric vehicles; and/or (v) determining, based upon the received information, which of the detected one or more other electric vehicles to send a power source request. Alternatively, the notification may indicate that an electric vehicle has a low state of charge (SOC), or is otherwise has a battery in need of being recharged to facilitate the electric vehicle traveling to a destination.

Abstract: An optimal energy management method and a system that implements the method for a nearly zero energy building (nZEB) based on the genetic algorithm technique that can provide an optimal balance between the objectives of energy saving, comfort of the building residents and maximum exploitation of the generated electric energy by the renewable energy sources through the proper utilization of a battery storage system, is developed in this invention. The above can be attained by minimizing a cost function that considers the real-time electricity price, the generated/consumed electric energy by each device, the user preferences, the state-of-charge and the energy price of the battery storage system (BSS), and the weather forecast. the system that implements the optimal energy management method comprises energy and temperature sensors, controllable power switches, a battery storage system and a controller with human machine interface.

Abstract: Embodiments relate to a method for predicting power generation and remaining useful life to predict operational soundness of a power plant and a system for performing the same, the method including acquiring sensing data from each of a plurality of sensors included in a plurality of systems in the power plant, outputting each of a predicted power generation and a predicted remaining useful life from a measurement value in sensing data of an input sensor through a pre-trained prediction model, assessing the operational soundness in aspect of the power generation and the remaining useful life using a prediction result and a current result in each aspect, and determining the operational soundness of the system based on prediction uncertainty and an assessment result in aspect of the power generation and the remaining useful life.

Abstract: A method for controlling power consumption includes receiving a flexibility request from an electrical utility and discovering energy relevant devices in a building. The energy relevant devices include electrical loads and alternative energy sources. Power requirements are predicted from an electrical utility for the loads, the prediction takes into account available power from the alternative power sources. Power set points are determined for the energy relevant devices based on the prediction. The power set points meet the flexibility request. The energy relevant devices are directed to operate at the power set points. A building energy management system is also disclosed.

Abstract: A method for handling surplus or deficit of energy in local energy systems (30) is presented. The method comprising; determining an accumulator status based on data pertaining to an accumulator (20) of a moveable device (10); determining energy status of each of a plurality of local energy systems (30) based on data pertaining to the respective local energy system 30; scoring, based on the determined accumulator status and the determined energy statuses, each of the local energy systems (30); determining, based on the respective scores of each of the plurality of local energy systems (30), a local energy system (30), among the plurality of local energy systems (30), to which the moveable device (10) is to be directed. Also a server (40) configured to handling surplus or deficit of energy in local energy systems is presented.

Abstract: An embodiment establishes a knowledge base based at least in part on sensor data received from a network. The embodiment generates a predicted performance parameter for a designated entity of the network using a first machine learning algorithm. The embodiment compares the predicted performance parameter to an actual performance parameter and determines whether the actual performance parameter exceeds a threshold difference from the predicted performance parameter. The embodiment generates, responsive to determining that the threshold difference is exceeded, incentive data using a second machine learning algorithm, where the incentive data is representative of an action selected by the second machine learning algorithm using an iterative optimization process, and where the iterative optimization process comprises performing the action and determining that the actual performance parameter approaches the threshold value in response to the action.

Abstract: The actual performance information classify part derives a classification result of an actual performance information on electric power demand, by a classification setting information, from an environment information and a date attribute information which is correlated with each of the electric power demands which is included in an actual performance information on electric power demand. The prediction information calculate part derives a classification result of a prediction target day, using the date attribute information of the prediction target day, which is a day to conduct a prediction, and the environment information which is measured before a start of the prediction of a prediction target day, and in addition, predicts an electric power demand of a prediction target day, based on the electric power demand of the actual performance information on electric power demand, which corresponds to the classification result of the prediction target day.

Abstract: Systems and methods may coordinate and provide bidirectional energy transfer events between electrified vehicles and households or other structures, such as for supporting transient loads associated with the households/structures, for example. Vehicle information, driving habit information, and household information may be leveraged for providing enhanced transient load capability controls that permit increased appliance usage without increasing energy costs. The proposed systems/methods may particularly allow for bidirectional energy transfer support of high load appliances for increasing a user's comfort, pleasure, and convenience.

Abstract: The disclosure provides a distributed dispatch method for ubiquitous power Internet of Things based on a transition matrix. The ubiquitous power Internet of Things includes generators. The method includes: S1, setting a marginal cost function of each of the generators, and extracting key cost parameters in the marginal cost function; S2, establishing an optimization model based on the key cost parameters of each of the generators and a communication topology of the ubiquitous power Internet of Things, and solving the optimization model to obtain an optimized transition matrix; and S3, generating a plan of a power output of each of the generators based on the optimized transition matrix and a distributed dispatch protocol to perform a distributed dispatch.

Abstract: Provided is a power supply system configured to supply AC power to a building. The power supply system includes a discharge assembly which is connectable to a discharge port provided in a vehicle. The discharge assembly includes a first end which receives electric power from the discharge port connected thereto, and a second end which outputs AC power. The second end of the discharge assembly is connected to the building by a single-phase three-line wiring.

Abstract: Disclosed is a centralized cloud energy storage system for massive and distributed users and a transaction settlement method thereof, a storage medium, and a terminal. The system includes: a centralized energy storage facility invested and operated by a cloud energy storage service provider; the massive and distributed users; and a power network and a user energy management system connecting the centralized energy storage facility with the massive and distributed users. A user sends a charging and discharging request to the cloud energy storage service provider through the user energy management system, and the cloud energy storage service provider issues a charging and discharging instruction to the centralized cloud energy storage system.

Abstract: Systems, methods, and related technologies for self-training classification are described. In certain aspects, a plurality of device classification methods with associated models are accessed. Each of the classification methods have an associated reliability level. The models of classification methods with a higher reliability level than other classifications methods are used to train the models associated with lower reliability level. The trained models and associated classification methods are thus improved.

Abstract: A system and method for managing and distributing an electrical power system is provided. In one embodiment, the system and method comprise at least one powered device that receives electrical power from an electrical power system utilizing multiple energy sources. Structure and devices are provided within the system to command, regulate, monitor, and transmit power to a device or devices in an efficient, reliable manner based on resource availability, energy cost, and environmental factors. The system selects and manages the resources to optimize the energy output to the device(s) to achieve the specific requirements in resiliency, cost, and the environmental impact of the application.

Abstract: Provided are a method and apparatus for evaluating a degree of frequency regulation urgency of a generator set, a power system and a storage medium.

Abstract: A method for tracking non-homogeneous products on a shelf comprises monitoring weight measurement data points corresponding to the weight of the shelf and the products arranged thereupon, determining a set of weight-event parameters of a weight event, such as product identification and an action taken with respect to the product, and at least one of recording information about the results and displaying information about the results. A system for tracking non-homogeneous products on a shelf comprises processors for carrying out stored program instructions for carrying out the steps of the method.

Abstract: The disclosed method reconstructs a topology of an electrical distribution network. An ohmic matrix model is generated as a function of consumption measurements provided by smart meters in the network. A tree table of nodes to which the smart meters are connected is defined. A branch in exploration is defined in the table and the nodes of the branch meeting preestablished relations are entered in the table as a function of connection values derived from resistive quantities in the matrix model. One of the relations determines a junction of the branch in exploration with a branch already explored connectable to a root to which a distribution transformer of the distribution network is connected. The topology is reconstructed by iteratively proceeding with sequences of decreasing values derived from the resistive quantities.

Abstract: A liquefaction apparatus that automatically adjusts the load on the liquefaction apparatus correspondingly with an upper limit value of contracted power in different time slots, and which is capable of maximizing the amount of liquefied product produced and of achieving optimum operating efficiency is provided.

Abstract: Provided are an apparatus and a method for generating an alternative routine, the method comprising monitoring a first routine comprising at least one activity representing at least one interaction of a user with one or more IoT devices, determining semantic information associated with the at least one activity, and generating at least one second routine comprising one or more activities corresponding to the at least one activity based on the semantic information associated with the at least one activity.

Abstract: A power grid control device of the present invention may comprise: a grid input interface for receiving an input of information on an operation state of a power grid; a grid output interface for outputting a signal for operating the power grid; a communication interface for performing data communication with a remote device; a component unit in which a plurality of software components for performing individual functions required for operating the power grid are stored; and a processing module for executing the components to process a work required for the operation of the power grid.

Abstract: This disclosure describes techniques that enable a supplemental voltage to be delivered to a Remote Radio Unit (RRU) to compensate for a voltage loss that occurs between a primary Direct Current (DC) power source and the RRU. A supplemental voltage controller is described that captures current environmental metadata associated with an operation of the RRU and calculates an RRU voltage at the RRU. In doing so, the supplemental voltage controller may generate a supplemental voltage control signal that supplements the RRU with a supplemental DC voltage.

Abstract: A power calculation apparatus calculates an amount of power suppliable and demandable between a battery and a power grid. The power calculation apparatus includes a microprocessor and a memory connected to the microprocessor. The microprocessor is configured to perform: predicting the amount of power suppliable and demandable between the battery and the power grid at a predetermined point in time to calculate a prediction value of the amount of power suppliable and demandable; and switching a calculation logic to be applied to a calculation of the prediction value, based on a length of duration from a present point in time to the predetermined point in time.

Abstract: The embodiments of the present disclosure provide methods and systems for natural gas data computation outside a gas IoT based on energy measuring, including establishing the gas IoT. The object platform obtains consumed gas volume data and location data of the smart gas meter as first data and second data, and sending them to the management platform through the sensor network platform. The management platform generates consumed gas preprocessing data based on the first data and the second data, and generates energy measurement data after performing the computation outside the gas IoT on the consumed gas preprocessing data by the cloud platform outside the gas IoT. The management platform sends the energy measurement data to the user platform configured in a regional pipeline network center through the service platform. The user platform performs gas energy measurement of the smart gas meter based on the energy measurement data.

Abstract: AI-assisted Connected Home systems for improving power efficiency at homes and offices are described. The system may perform operations including: receiving, from each of a plurality of power receptacles, power usage information of an electrical device attached to the power receptacle; determining, for each of the plurality of power receptacles, a plurality of power usage metrics of the power receptacle based on the power usage information; feeding the plurality of power usage metrics into a machine learning model to obtain a priority of the electrical device attached to the power receptacle, wherein the priority is one of a plurality of pre-configured priorities; obtaining a power management signal; and transmitting a plurality of control signals to the plurality of power receptacles based on the power management signal and respective priorities of the plurality of electrical devices attached to the plurality of power receptacles.

Abstract: Embodiments generate machine learning predictions to discover target device energy usage. One or more trained machine learning models configured to discover target device energy usage from source location energy usage can be stored. Multiple instances of source location energy usage over a period of time can be received for a given source location. Using the trained machine learning model, multiple discovery predictions for the received instances of source location energy usage can be generated, the discovery predictions comprising a prediction about a presence of target device energy usage within the instances of source location energy usage. And based on the multiple discovery predictions, an overall prediction about a presence of target device energy usage within the given source location's energy usage over the period of time can be generated.

Abstract: Techniques are described for implementing an automated control system to control operations of a target physical system, such as production of electrical power in an electrical grid. The techniques may include determining how much electrical power for each of multiple producers to supply for each of a series of time periods, such as to satisfy projected demand for that time period while maximizing one or more indicated goals, and initiating corresponding control actions. The techniques may further include repeatedly performing automated modifications to the control system's ongoing operations to improve the target system's functionality, by using reinforcement learning to iteratively optimize particles generated for a time period that represent different state information within the target system, to learn one or more possible solutions for satisfying projected electrical power load during that time period while best meeting the one or more defined goals.

Abstract: The present disclosure provides methods, systems, and devices for controlling electric vehicle charging across multiple customers and multiple fleets of electric vehicles. These methods, systems, and devices may implement machine learning to determine distinct charging strategies for a plurality of charging depots. Scheduling methods systems, and devices disclosed herein do not require fixed electric vehicle arrival times but may instead update charging strategies in real time based on changes in a state of a system.

Abstract: A total energy management system for high energy efficiency of a logistics center includes: an energy management system (EMS) server for collecting real-time data associated with the logistics center, wherein the EMS server processes the real-time data and generates at least one of real-time temperature data, real-time humidity data, renewable energy data, and electric power data of the logistics center; and an artificial intelligence (AI) server for outputting at least one of temperature mapping data, defrosting time determination data, and an energy operation guide in the logistics center based on at least one of the real-time temperature data, the real-time humidity data, the renewable energy data, and the electric power data received from the EMS server, wherein the EMS server switches between a plurality of management modes having different operating conditions for the logistics center based on at least one of the temperature mapping data, the defrosting time determination data, and the energy operation

Abstract: Disclosed is a service operation method for managing energy data for each tenant. More particularly, the service operation method monitors energy consumption consumed in a specific space that a tenant manager desires to manage using an individualized energy management service user interface (UI) according to a service development/production environment set by a manager terminal and visualizes a status of use of energy for each specific space from a monitoring result.

Abstract: Architectures, apparatuses, methods, systems, and techniques for controlling electrical power distribution network are disclosed. Embodiment distributed, hierarchical controls including layered locational energy service control variables may be utilized to determine and control the provision of energy services, including real power, reactive power (VAR), and capacity reserves, by DERs in a distribution network. In a first ex-ante iteration a simulation may be performed to calculate a set of subnetwork-specific control variables based on subnetwork locational energy service prices and a plurality of sets of DER-specific control variables based on DER locational energy service prices. A second ex-ante iteration calculates a set of actual subnetwork-specific control variables based on subnetwork locational energy service prices and a plurality of sets of actual DER specific control variables based on DER locational energy service prices.

Abstract: Disclosed are systems and methods for utilizing a unique elastic command and control architecture to incorporate certain resiliency qualities in power grid management and outage mitigation.

Abstract: Provided are techniques for predictively generating demand response (DR) events based on grid operations and faults, based on optimization and self-learning routines. The techniques include obtaining grid status information, and determining a fault condition based at least in part on the grid status information. The techniques also include generating a DR event based at least in part on the fault condition, and responsive to generating the DR event, transmitting a notification of the DR event.

Abstract: A system for completing a well, including a generator, and a plurality of electric load components, each electric load component powered by the generator. The system further includes a load shedding control panel that monitors the generator and, if the generator loses functionality, is capable of deactivating one or more of the plurality of electric load components to reduce the electric load.

Abstract: The present disclosure provides an adaptive energy storage operating system that is programmed or otherwise configured to operate and optimize various types of energy storage devices.

Abstract: In some embodiments, devices, systems, and methods herein may be used to operate an environmental control system in order to improve environmental satisfaction and/or cognitive function for one or more occupants or groups of occupants of an indoor environment. By some approaches, the devices, systems, and methods described herein may be employed by occupants, managers or owners of indoor environments to improve satisfaction with lighting and/or improve the performance of various executive functions for one or more occupants of an indoor environment. In some embodiments, the devices, systems, and methods described herein may be used to adjust various lighting parameters in an indoor environment, for example, lighting parameters that are indicative of access to natural light in the indoor environment.

Abstract: An EMS includes a control unit that controls a power generation facility and a power adjustment unit that adjusts an amount of supply of supply power. The control unit includes: a reverse power flow suppression process determination unit; a priority decision unit that decides a priority for adjusting an amount of power generated for the two power generation devices of the power generation facility on the basis of a predicted degree of fluctuation in load power; and a device control unit that controls the power generation facility such that the amount of power generated is adjusted in descending order of the priority decided by the priority decision unit when the reverse power flow suppression process determination unit determines to reduce the amount of power generated by the power generation facility.

Abstract: Techniques are described for classifying seasonal patterns in a time series. In an embodiment, a set of time series data is decomposed to generate a noise signal and a dense signal, where the noise signal includes a plurality of sparse features from the set of time series data and the dense signal includes a plurality of dense features from the set of time series data. A set of one or more sparse features from the noise signal is selected for retention. After selecting the sparse features, a modified set of time series data is generated by combining the set of one or more sparse features with a set of one or more dense features from the plurality of dense features. At least one seasonal pattern is identified from the modified set of time series data. A summary for the seasonal pattern may then be generated and stored.

Abstract: The present disclosure relates to an apparatus for diagnosing a state of a photovoltaic device, a building Integrated Photovoltaics (BIPV) device, etc., and more particularly to an apparatus for diagnosing photovoltaic power generation, which diagnoses a state of the specific photovoltaic device by comparing the difference in power generation between grouped photovoltaic devices through analysis of power generation for the same period in the past through machine learning, etc., wherein the apparatus processes power generation information, which is collected from the photovoltaic devices, based on failure history and maintenance and repair information of each photovoltaic device and performs precise grouping by minimizing error information regarding a power generation trend based on information such as regional weather information and environment information for a region where each photovoltaic device is located, so that a power generation trend can be analyzed with improved accuracy of analysis of state.

Abstract: A system for controlling air flow in an air handling unit having an air mover is provided. The system includes a first and a second sensing device, each receiving a first input indicative of electric power and a second input indicative of properties of air, respectively. The system further includes a processing unit to determine heat generated from a motor of the air mover based on the first input, determine density of air based on the heat generated from the motor based on the second input, and determine an actual air flow rate based on the density of the air, a speed of the motor, and dimensional characteristics of the air handling unit. Further, the speed of the motor is controlled when the actual air flow rate is different from a target air flow rate.