Abstract:
A non-transitory computer-readable recording medium stores a machine learning program for causing a computer to execute processing including: acquiring a first parameter that represents an environment and a second parameter that represents a movement attribute of each of a plurality of moving bodies in the environment; classifying the plurality of moving bodies into a plurality of groups on the basis of the second parameter; generating a third parameter that indicates the number of moving bodies classified into each of the plurality of groups; and inputting the first parameter and the third parameter to a machine learning model to generate estimation information regarding movement of the plurality of moving bodies in the environment.
Abstract:
A non-transitory computer-readable storage medium storing a shape data output program that causes at least one computer to execute process, the process includes, normalizing each shape data of a plurality of pieces of shape data for each component in each coordinate axis direction to create unit shape data; classifying the plurality of pieces of shape data based on the created unit shape data of each of the pieces of shape data; specifying, based on dimensions of sites of each shape data in classified group, a dimensional relationship between different sites of the shape data in the group; and outputting information indicating the specified dimensional relationship in association with the unit shape data of the shape data in the group.
Abstract:
The present invention relates to a machine learning program for causing a computer to execute a process. In an example, the process executed by the computer when the program is executed includes: acquiring a current distribution image by an equivalent circuit simulation based on circuit information; acquiring a shape image that indicates a shape of a circuit based on the circuit information; acquiring an EMI value by electromagnetic field analysis based on the circuit information; and generating an EMI prediction model by machine learning based on training data that includes the current distribution image, the shape image, and the EMI value.
Abstract:
A modular data center includes: a rack which houses an electronic device; a blower device capable of switching a flowing direction of air and configured to feed the air into the rack; a space housing a moisture absorbent; an in-rack temperature detector which detects a temperature inside the rack; a dew-point temperature detector which detects a dew-point temperature of outside air; and a controller. The controller receives signals inputted from the in-rack temperature detector and the dew-point temperature detector, and controls shutters and the blower device.
Abstract:
A disclosed air conditioning control system includes: a flow path through which cooling air discharged from an exhaust surface of an electronic apparatus is returned to an intake surface thereof, a damper provided in the flow path, a temperature measuring unit for measuring the real temperature of the cooling air, a humidity measuring unit for measuring the real humidity of the cooling air, a target value changing unit for changing target temperature and humidity in accordance with the real temperature and humidity, and a controlling unit for predicting future predicted values of the real temperature and humidity, and controlling the opening extent of the damper such that the predicted temperature and humidity become close to the target temperature and humidity, respectively. The target value changing unit sets the target temperature and humidity such that the real temperature and humidity are raised and lowered in the opposite directions.
Abstract:
A modular data center includes a fan which creates a cooling wind by taking in outside air, electronic devices which takes in the cooling wind and to discharge an exhaust flow, a flow passage which guides a part of the exhaust flow to upstream of the fan, an opening-closing portion which opens and closes the flow passage, and a control unit which adjusts the cooling wind by controlling the fan, and thereby to cool a temperature of the electronic device to a specified temperature. The control unit closes the opening-closing portion when a first assumed value of power consumed by the fan is smaller than a current value of the power. The control unit opens the opening-closing portion when a second assumed value of the power consumed by the fan is smaller than the current value of the power.
Abstract:
A temperature management system includes: temperature detection units which individually detect temperatures of a plurality of electronic devices each changing an amount of heat generation depending on its operational state; a cooling device which cools the electronic devices; and a control unit which controls the cooling device depending on outputs from the temperature detection units. The control unit includes: an idle state determination unit which determines whether or not the electronic devices are in an idle state; a manipulated variable calculation unit which has an integrator and calculates a manipulated variable by using a difference between a target value and a controlled variable; and an accumulation value correction unit which corrects an accumulation value of the integrator with a predetermined value when the idle state determination unit determines that the electronic devices are in the idle state.
Abstract:
A policy training device that trains, through first reinforcement learning, a first agent configured to output a first action of a control object according to an input of a first state of the control object, includes a memory, and processor circuitry coupled to the memory and configured to change a first parameter regarding a constraint condition in the first reinforcement learning for every predetermined number of times of a training operation in the first reinforcement learning, and train the first agent by using the first parameter as at least a part of the first state and by ensuring that the constraint condition is satisfied.
Abstract:
A recording medium stores a reinforcement learning program for causing a computer to execute a process. The process includes: calculating a second demand amount after a certain period of time and a reliability of the second demand amount based on a current first demand amount for a service provided in a predetermined environment; determining an action to be performed for the environment in accordance with a machine learning model based on input data that includes the second demand amount, the reliability, and a current first state of the environment; executing the determined action for the environment; and updating, based on a second state of the environment after the action is performed and a reward, a parameter of the model by constrained reinforcement learning in which the reward is increased in a range that satisfies a constraint on the state of the environment.
Abstract:
A non-transitory computer-readable recording medium stores a program for causing a computer to execute a process, the process includes obtaining a third matrix by changing at least one of a position of a target object already installed or a scale of the target object in a two-dimensional second matrix, obtaining three-dimensional second data by superimposing a two-dimensional first matrix and the third matrix, the first matrix being provided for each facility already installed and indicating a position and a scale thereof, and predicting a degree of influence of the target object by inputting the second data, a type of day of week, and time to a machine learning model trained with three-dimensional first data, a type of day of week, and time as input, and with a degree of influence of the target object as output, the first data being obtained by superimposing the first matrix and the second matrix.