Systems and methods for providing visualization of health risks within a building. Health risk levels for building spaces are determined using occupancy data and health risk data relating to a risk of contracting or spreading an infectious disease. A visualization of the health risk levels is generated and presented on a user interface.

An estimation unit estimates a thermal sensation representing how hot or cold a user feels based on an image of the user taken by a camera. A control unit controls an air-conditioning operation of an air conditioner based on an estimation result of the estimation unit so that the thermal sensation falls within a target range, the air conditioner targeting a room in which the user is present. The image shows a motion and/or state of the user representing a hot or cold sensation of the user, and the estimation unit extracts the motion and/or state of the user from the image to estimate the thermal sensation.

A thermostat is disclosed. The thermostat can include one or more temperature sensors configured to measure one or more temperature values. The thermostat can include a processing circuit. The processing circuit can receive the one or more temperature values from the one or more temperature sensors. The processing circuit can receive one or more central processing unit (CPU) usage values, wherein the one or more CPU usage values indicate computing usage of the processing circuit. The processing circuit can determine, based on an empirical model comprising one or more gain values and one or more filters and based on one or more signals, a temperature of the building. The one or more signals comprise the one or more temperature values and the one or more CPU usage values. The empirical model accounts for dynamics of heat generated by the processing circuit and airflow acting on the thermostat.

HVAC control system's supervisory control is crucial for energy-efficient thermal comfort in buildings. The control logic is usually specified as ‘if-then-that-else’ rules that capture the domain expertise of HVAC operators, but they often have conflict that may lead to sub-optimal HVAC performance. Embodiments of the present disclosure provide a method and system for optimized Heating, ventilation, and air-conditioning (HVAC) control using domain knowledge combined with Deep Reinforcement Learning (DRL). The system disclosed utilizes Deep Reinforcement Learning (DRL) for conflict resolution in a HVAC control in combination with domain knowledge in form of control logic. The domain knowledge is predefined in an Expressive Decision Tables (EDT) engine via a formal requirement specifier consumable by the EDT engine to capture domain knowledge of a building for the HVAC control.

A camera (26) takes an image of at least one user (U1, U2, U3). A room environment information sensor (13) senses room environment information relating to an environment of a room (r1) in which the at least one user (U1, U2, U3) is present. The estimator (66) estimates a drowsiness condition of the at least one user (U1, U2, U3) based on the image of the at least one user (U1, U2, U3) taken by the camera (26) and the room environment information sensed by the room environment information sensor (13).

In a commercial building, individual occupant thermal comfort is achieved with optimal cost and energy efficiency through the integration of a variety of local thermal comfort components into a communication network that employs emerging optimization principles to meet individual preferences for the thermal environment on a workstation basis while reducing building energy use and operating in accordance with any constraints on the energy grids that serve the buildings. These multiple objectives are met in part through a robust communication network that employs distributing processing to achieve preferred thermal conditions with optimal control of all components at subzone, zone, system, central plant, and energy grid levels.

A comfort-analyzing device includes a display unit, a first control unit, an input unit, and a cognitive-structure constructing unit. The display unit is configured to present a questionnaire for extracting both a comfort level of a user in an environment and at least one environmental factor to determine the comfort level. The first control unit is configured to cause the display unit to present the questionnaire twice or more during a survey period. The input unit is configured to accept, from the user, input of each reply to the questionnaire presented twice or more. The cognitive-structure constructing unit is configured to construct a cognitive-structure model representing a cognitive structure of the user regarding comfort by extracting both the comfort level and the at least one environmental factor in chronological order based on each reply to the questionnaire presented twice or more.

An HVAC system for enhanced source-to-load matching without sacrificing airflow delivery in low load structures. Embodiments of the present disclosure provide for an HVAC system for enhanced source-to-load matching in a low load environment, i.e. dwellings with a BTU/hour capacity of less than 18,000. Prior art HVAC equipment is oversized for dwellings with a BTU/hour capacity of less than 18,000 that are insulated to minimum code requirements. Embodiments of the present disclosure provide for an HVAC system that separates the delivery of airflow (CFM) output from that of the BTU capacity output, thereby enabling a distributed delivery system for optimal source-to-load matching without sacrificing airflow delivery in low load environments. The source-to-load matching enabled by the present disclosure ensures optimal indoor air quality, enhanced comfort for occupants of the dwelling, and approximately a 60% reduction in heating and cooling costs when compared to prior art HVAC systems.

According to one embodiment, an air-conditioning control device includes model storage and a processor. The model storage is configured to store a discomfort probability model which estimates a value of discomfort of an occupant by a pair of time elapsed after an energy-saving operation of an air conditioner is turned on and before the energy-saving operation is turned off by the occupant, and an air-conditioning state at the time when the energy-saving operation is turned off. The processor is configured to acquire a current air-conditioning state during the energy-saving operation of the air conditioner, and turn off the energy-saving operation, based on occupant's discomfort estimated from the discomfort probability model.

One embodiment of the present disclosure is a system for predicting performance of building equipment. The system comprises one or more sensors in communication with the building equipment, and the sensors are operable to detect characteristics from the building equipment. The system further comprises a computing device in communication with the sensors and in the same geographic location as the sensors. The computing device comprises one or more memory devices configured to store instructions that, when executed on one or more processors, cause the one or more processors to receive data from the sensors, the data based on the detected characteristics. The one or more processors also generate, based on a machine learning model and the data, a predicted performance of the building equipment when the machine learning model comprises a prior data substantially similar to the data.