Disclosed is a generating facility management device capable of automatically calculating and determining inspection intervals of generating facilities using a system. In an example embodiment, the generating facility management device calculates inspection intervals of unit devices constituting each of the generating facilities using a time code index, a stressor index and a degradation mechanism index.

According to an example aspect of the present invention, there is provided an apparatus comprising at least one processing core and at least one memory including computer program code, the at least one memory and the computer program code being configured to, with the at least one processing core, cause the apparatus at least to nm a convolutional neural network comprising an input layer arranged to provide signals to a first convolutional layer and a last convolutional layer, run a first intermediate classifier, the first intermediate classifier operating on a set of feature maps of the first convolutional layer, and decide to abort or to continue processing of a signal set based on a decision of the first intermediate classifier.

A system and method for providing risk mitigation and resilience to the electrical grid system by allowing bi-directional electricity usage from a distributed network of energy storage stations to form a large, distributed resource for the grid. A machine learning optimization module ingests various forms of data—from grid telemetry to traffic data to trip-to-trip data and more—in order to make informed spatiotemporal decisions about strategically placing and balancing energy stores across various regions to support optimum energy usage, risk mitigation, and grid fortification. Energy stores are then sent updated parameters as to the amount of energy to hold or release.

A wind farm supervision monitoring system includes: a data collection unit configured to collect data about a status monitoring of each wind turbine from at least one site server; an abnormality status detection unit configured to detect an abnormality status of each wind turbine based on the collected data about the status monitoring and issue an alarm; a wind data management unit configured to early detect a fault of each wind turbine and or monitor performance of each wind turbine based on the data about the status monitoring or the data about the abnormality status; and a supervision unit configured to manage a turbine operation status and operation and maintenance of each wind turbine and provide information for establishing an operation and maintenance plan for the detected abnormality status of the wind turbine.

A wind farm supervision monitoring method includes: displaying, by a user interface (UI) unit, a location of the site server on a map along with a dashboard menu, a navigation menu, and an alarm & event menu; collecting, by a data collection unit, data about status monitoring of each wind turbine from the site server; detecting, by an abnormality status detection unit, an abnormality status of each wind turbine based on the data about the status monitoring of each wind turbine and issuing an alarm based on the detecting the abnormality status; providing, by a supervision unit, a turbine operation status of each wind turbine using the dashboard menu, managing operation and maintenance; and establishing, by the supervision unit, an operation and maintenance plan for the detected abnormality status of the wind turbine.

A method of controlling an energy storage system to reduce a peak energy procurement includes obtaining a load forecast for an energy consumption system, and, at each of a plurality of predetermined time intervals during a predetermined time period, observing a charge state of an energy storage component and a load presented by the energy consumption system, determining an energy action for the energy storage component as a function of the load forecast, observed load and observed charge state, and executing the determined energy action. Determining the energy action can include composing and optimizing a sample average approximation of a cost function for the energy storage component and energy consumption system, where the sample average approximation is composed by generating a predetermined number of random load trajectories for the energy consumption system, and forming the sample average approximation as an average of a maximum energy purchase function for each of the random load trajectories as a function of the energy action.

A time series data adversarial sample generating method and system, an electronic device, and a storage medium, relating to the field of time series data processing. The method comprises: training a time series prediction model using original time series data (101); calculating a maximum value of a loss function in the time series prediction model by means of a stochastic gradient descent optimization strategy (102); determining corresponding noise according to the maximum value of the loss function (103); and superimposing the noise on the original time series data to generate a globally disturbed time series data adversarial sample (104). The method can significantly reduce the model accuracy under the condition of a small amount of data disturbance, has important significance for safe application of an industrial system, and has wide applicability and transferability.

A power distribution management apparatus (10) includes acquiring the amount of demand obtained by forecasting the amount of power to be used by load equipment of a customer, and the amount of power generation obtained by forecasting the amount of power to be generated by power generation equipment of the customer, and setting a plurality of voltage values as a plurality of candidates for a transmission voltage from a substation of a power distribution system, and calculating a voltage at a connection point of the load equipment of the customer and equipment of the power distribution system at each of the plurality of candidates by utilizing a difference between the demand amount and the power generation amount of each customer, and determining the transmission voltage of the substation from the plurality of candidates based on a result of the calculating.

A graphical workflow definition and management tool enables administrators and other authorized users to implement a workflow process that can be used to evaluate project submissions or other applications that require step-by-step process completion. The steps required to navigate through the workflow are first defined. Inputs, outputs, and actions, including conditional criteria, can be specified for the steps. The flow of control between the individual steps in the workflow is mapped out; changes to the status of a project submission can cause a submission to migrate to a succeeding step in the workflow. A “sandbox” testing environment allows changes to any aspect of the workflow to be safely evaluated without affecting live data. Conflicts between production and test workflows are identified and intelligently resolved.

An information processing device includes an acquirer that acquires first date and time information including information relating to a date and time at which a battery detachably installed in a moving body capable of moving by use of electric power is used and second date and time information including position information of a user's portable terminal and information relating to a date and time at which the position information is acquired; and an integrator that generates position history information of the battery on the basis of the first date and time information and the second date and time information acquired by the acquirer.