A wireless sensor network at a monitored location can be configured to generate sensor channel(s) of data to assess operational conditions at the monitored location. Inputs based on the sensor channel(s) of data are provided to a host system for analysis of a demand to one or more resources at the monitored location. Response messages can be generated based on the demand analysis and transmitted to actuator(s) at the monitored location to effect an adjustment to the operational conditions.

A thermostat for a building zone includes at least one of a model predictive controller and an equipment controller. The model predictive controller is configured to obtain a cost function that accounts for a cost of operating HVAC equipment during each of a plurality of time steps, use a predictive model to predict a temperature of the building zone during each of the plurality of time steps, and generate temperature setpoints for the building zone for each of the plurality of time steps by optimizing the cost function subject to a constraint on the predicted temperature. The equipment controller is configured to receive the temperature setpoints generated by the model predictive controller and drive the temperature of the building zone toward the temperature setpoints during each of the plurality of time steps by operating the HVAC equipment to provide heating or cooling to the building zone.

A thermostat for a building zone includes at least one of a model predictive controller and an equipment controller. The model predictive controller is configured to obtain a cost function that accounts for a cost of operating HVAC equipment during each of a plurality of time steps, use a predictive model to predict a temperature of the building zone during each of the plurality of time steps, and generate temperature setpoints for the building zone for each of the plurality of time steps by optimizing the cost function subject to a constraint on the predicted temperature. The equipment controller is configured to receive the temperature setpoints generated by the model predictive controller and drive the temperature of the building zone toward the temperature setpoints during each of the plurality of time steps by operating the HVAC equipment to provide heating or cooling to the building zone.

Provided is a home appliance of determining an operation command corresponding to an occupant through learning based on setting information of the home appliance according to the occupant to provide an operation satisfying all occupants. An air conditioner according to an embodiment of the disclosure includes: an outdoor unit; and an indoor unit including a heat exchanger, wherein the indoor unit includes: a communicator configured to communicate with an access point (AP); and a controller configured to receive information about a terminal connected to the access point through the communicator, and change at least one of operation temperature or an operation mode when a new terminal is connected to the access point or a terminal connected to the access point is disconnected from the access point.

An apparatus in one embodiment comprises at least one processing device. The processing device comprises a processor coupled to a memory, and is configured to obtain information characterizing operation of a heat pump at a particular energy usage location, and to process the obtained information in a reinforcement learning agent to generate at least one control signal for controlling the heat pump, wherein the reinforcement learning agent is implemented at least in part utilizing behavioral cloning of a model predictive control process. In some embodiments, the behavioral cloning of the model predictive control process comprises a constraint-informed parameter grouping (CIPG) phase, a training data generation phase and a model training phase. The apparatus can be implemented, for example, at least in part in a cloud-based processing platform, and/or at least in part in one or more of a smart meter, a smart thermostat, a smart-home controller or other smart-home device.

An apparatus in one embodiment comprises at least one processing device. The processing device comprises a processor coupled to a memory, and is configured to obtain information characterizing operation of a heat pump at a particular energy usage location, and to process the obtained information in a reinforcement learning agent to generate at least one control signal for controlling the heat pump, wherein the reinforcement learning agent is implemented at least in part utilizing behavioral cloning of a model predictive control process. In some embodiments, the behavioral cloning of the model predictive control process comprises a constraint-informed parameter grouping (CIPG) phase, a training data generation phase and a model training phase. The apparatus can be implemented, for example, at least in part in a cloud-based processing platform, and/or at least in part in one or more of a smart meter, a smart thermostat, a smart-home controller or other smart-home device.

A machine learning method executed by a computer, the method includes distributing a first learning model learned on the basis of a plurality of logs collected from a plurality of electronic devices to each of the plurality of electronic devices, the first learning model outputting operation content for operating an electronic device; when an operation different from an output result of the first learning model is performed by a user relative to a first electronic device among the plurality of electronic devices, estimating a similar log corresponding to a state of the learning model in which the different operation is performed from the plurality of logs; generating a second learning model on the basis of a log obtained by excluding a log of a second electronic device associated with the similar log from among the plurality of logs; and distributing the second learning model to the first electronic device.

An apparatus and method to selectively create a heat transfer effect and sensation of cooling within bedding on a mattress. A programmable application is accessible on a wireless network and is programmed to provide appropriate settings to attain changes over time of a space within bedding that pertain to at least one of heating the space and realizing a cooling sensation within the space. A wireless receiver is configured to receive commands in a wireless manner that are indicative of the appropriate settings provided by the programmable application to effect changes over time of the space within the bedding attributed to heat transfer with respect to the at least one of heating the space and realizing a cooling sensation within the space. The heat transfer occurs as a result of fluid flow either within a mattress or within space in bedding over the mattress.

A ventilation system includes a first ventilation device, a second ventilation device, a sensor, and an electronic controller. The first ventilation device includes a first fan. The second ventilation device includes a second fan. The sensor is attached to the first ventilation device. The sensor is configured to detect a state of air and to transmit a detection signal indicative of the detected state of air. The electronic controller is configured to receive the detection signal of the sensor and to control the first ventilation device and the second ventilation device based on the detection signal.