A method of estimating power flexibility for a climate system includes receiving a component power flexibility measurement from one or more components of the climate system, and aggregating the component power flexibility measurement from each of the one or more components of the climate system to determine a climate system power flexibility. A method of responding to a fast demand request from an electrical power source for a climate system is also disclosed.

Techniques for instantiating energy saving setpoint adjustments are described. In an example, a heating, ventilation, and air conditioning (HVAC) system is controlled via a thermostat during a first time period according to a first temperature setpoint schedule including one or more temperature setpoints and a first usage amount of the HVAC system is monitored during the first time period. After it is determined that the first usage amount of the HVAC system during the first time period has met a first predefined HVAC runtime threshold criterion, a second temperature setpoint schedule is generated with at least one of the one or more temperature setpoints being adjusted to decrease energy usage by the HVAC system compared to the first temperature setpoint schedule. The HVAC system is then controlled via the thermostat during a second time period according to the second temperature setpoint schedule.

A system and method for determining HVAC set points are provided. A present season is determined. An allowable temperature comfort range for each occupant in a room in a space is also determined. For each room, an energy saving set point temperature is calculated for the space based on the allowable temperature comfort range for that room. A set point temperature for the space is determined based on the energy saving set point temperatures for each of the rooms in the space. The set point temperature is provided to a thermostat or HVAC system to regulate temperature in the building.

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 automated range hood includes a controller that selects a fan speed for one or more ventilation assemblies by identifying a minimum number of pixels that satisfy a threshold. The controller automatically turns on one or more light sources to illuminate a surface under the range hood when motion is detected or when the one or more ventilation assemblies are in use.

A monitoring and/or control device for an environmental control unit such as a heat pump determines the performance status and whether maintenance is required of a component of the unit for example a compressor during operation of the component. The device includes sensors configured to be situated relative to the compressor so as to receive and signal data from the compressor during operation of the component. In some embodiments, the device includes a vibration detector and a controller coupled to the vibration detector. The controller is configured to (i) receive electrical signals from the vibration detector, (ii) compare the electrical signals to a reference signal, (iii) determine the performance characteristic of the component based on the results of the comparison, and (iv) output a signal corresponding to the performance characteristic of the component to a user display. The controller may also request maintenance and/or order parts automatically.

A control system for a HVAC system for a structure and including a blower that flows air over an indoor heat exchanger. The control system may include a first input device, a first sensor, and a processor in electronic communication with the first input device, the first sensor, and the blower of the HVAC system. The first input device may be operable to accept a zoning mode selection. The first sensor may be sensor operable to measure a first temperature at a first location within the structure. The processor may be programmed to determine a cooling or heating demand on the HVAC system based on an input temperature and the first measured temperature. The processor may be further programmed to adjust an air flow rate produced by the blower based on the demand on the HVAC system and the zoning mode selection.

A system for controlling heating, ventilation, or air conditioning (HVAC) equipment of a building includes one or more processing circuits configured to generate simulated building data using a simulation model of the building, pre-train a reinforcement learning (RL) model using the simulated building data, operate the HVAC equipment of the building using the RL model, and retrain the RL model using actual building data generated responsive to operating the HVAC equipment using the RL model.

A non-transitory computer-readable storage medium for a heating, ventilation, and/or air conditioning (HVAC) system includes instructions that, when executed by a processor, cause the processor to receive an input indicative of a user location, perform a verification that the user location is within a determined distance from the HVAC system, and control access to system settings of the HVAC system based on the verification.

A method for automatically adapting a predictive model used to control a heating, ventilation, or air conditioning (HVAC) system in a building to compensate for a detected fault in the HVAC system is shown. The method includes obtaining an indication of the detected fault in the HVAC system or a zone in the building. The method further includes determining a predicted impact of the detected fault on an operational performance of the HVAC system. The method further includes adjusting one or more parameters of the predictive model based on the predicted impact of the detected fault to generate a fault-adapted predictive model. The method further includes operating the HVAC system to control an environmental condition of the building using the fault-adapted predictive model.