Abstract: A fuel sub-metering mechanism for appliances that consume fuel. Each appliance may have a firing rate indicator. An individual fuel line may be connected to each appliance. A main fuel line may be connected to individual fuel lines. A meter may be connected to the main fuel line. A processor may be connected to the firing rate indicators and to the meter. The meter may measure total fuel consumption by the appliances. The processor may provide a sub-meter estimate of fuel consumed by each appliance. The sub-meter estimate may be based at least in part on a firing rate of the respective appliance and the total fuel consumption as indicated by the meter.

Abstract: Identifying models of dynamic systems is described herein. One method for identifying a model of a dynamic system includes estimating a number of parameters for each of a number of models of the dynamic system, predicting an output using the estimated number of parameters for each of the number of models, calculating a rate of error of the predicted output for each of the number of models compared to an observed output, and identifying a best model among the number of models of the dynamic system based on the calculated rate of errors.

Abstract: Various embodiments herein include at least one of systems, devices, methods, and methods for distributed HVAC system cost optimization. Such embodiments are generally implemented within a controller of HVAC system component, such as within boiler, cooler, air handling unit, and rooftop unit controllers. In some embodiments, multiple controllers exchange data to control various components of an HVAC system. One of the controllers, such as a primary plant of the system for heating or cooling, is designated as a master controller and the other component controllers are designated as slave controllers. Each controller, both master and slave controllers, includes at least one model that models variable settings of the component or components for which the respective controller is responsible. The model is utilized by the respective controller to both adjust the modeled variable component settings and to determine a cost-variable of operation.

Abstract: A system incorporating a camera sensor situated in a room having walls with windows and sun blinds. The sun blinds may control outdoor light to the room. Indoor light sources may provide artificial light in the room. A controller may receive signals from the camera sensor. The controller may estimate a presence of occupants and provide control signals to the sun blinds and light sources. A room temperature sensor and an HVAC system may be connected to the controller. A preset temperature, which may depend on occupancy, in the room or zone may be achieved with various kinds of heating or cooling. At the same time, outdoor light and indoor artificial light may be controlled to obtain a preset intensity of lighting in the room, which may depend on occupancy, in a manner to achieve a minimum cost of energy used by the HVAC and the light sources.

Abstract: Tuning model structures of dynamic systems are described herein. One method for tuning model structures of a dynamic system includes predicting a variable for each of a number of models associated with a number of model structures of a dynamic system, calculating a rate of error of the predicted variable for each of the number of models compared to an observed variable, determining a best model structure among the number of model structures based on the calculated rate of error, and creating a revised model structure using the best model structure to tune the number of model structures of the dynamic system.

Abstract: A method includes aggregating multiple zones of an indoor structure, each zone having associated comfort limits, formulating an aggregated single zone model predictive control (MPC) problem representative of the multiple zones for a heating ventilation and air conditioning (HVAC) system, determining optimal aggregated actions as a function of the aggregated single zone model predictive control problem, simulating an optimal trajectory of indoor qualities, and determining zone temperature setpoints to comply with the comfort limits for each zone and pre-cool the indoor structure.

Abstract: Tuning model structures of dynamic systems are described herein. One method for tuning model structures of a dynamic system includes predicting a variable for each of a number of models associated with a number of model structures of a dynamic system, calculating a rate of error of the predicted variable for each of the number of models compared to an observed variable, determining a best model structure among the number of model structures based on the calculated rate of error, and creating a revised model structure using the best model structure to tune the number of model structures of the dynamic system.

Abstract: A method includes aggregating multiple zones of an indoor structure, each zone having associated comfort limits, formulating an aggregated single zone model predictive control (MPC) problem representative of the multiple zones for a heating ventilation and air conditioning (HVAC) system, determining optimal aggregated actions as a function of the aggregated single zone model predictive control problem, simulating an optimal trajectory of indoor qualities, and determining zone temperature setpoints to comply with the comfort limits for each zone and pre-cool the indoor structure.

Abstract: A thermal control system for a building is disclosed, which includes a regression model: Given a forecast temperature outside the building, the regression model predicts how much an HVAC system will cost to run during a day, for a given set of time-varying target temperatures for all the thermostats in the thermal control system. The thermal control system may also include an optimizer, which invokes multiple applications of the regression model. Given a forecast temperature outside the building, the optimizer predicts an optimal set of time-varying target temperatures for all the thermostats in the thermal control system. Running the HVAC system with the optimal set of time-varying target temperatures should have a reduced or a minimized cost, or a reduced or minimized total energy usage. The optimizer works by running the regression model repeatedly, while adjusting the time-varying target temperature for each thermostat between runs of the model.

Abstract: Devices, methods, and systems for determining a heating, ventilation, and air conditioning (HVAC) model for a building are described herein. One method includes receiving a description of the building, receiving an HVAC meta-model, wherein the HVAC meta-model is independent of the building, and determining an HVAC model for the building based on the description of the building and the HVAC meta-model.

Abstract: A system calculates a first ratio of a prediction error variance of a model of a controller error, and the lesser of a variance of a prediction error of a naïve predictor model and a variance of a controller error. The system rates a process controller as a function of the first ratio. The system also calculates a second ratio of a variance of the controller error and a variance of the prediction error of the naïve predictor model. The system rates the process controller a function of the second ratio. The system uses the first ratio, second ratio, other ratios, and discrete indicators in determining an embedded fusion for loop performance monitoring in the process controller and for displaying a value as a measure of the loop performance.

Abstract: Devices, methods, and systems for data-driven acceleration of deployed services are described herein. One system includes a database configured to store a plurality of case pairs that correspond to previously calculated models, wherein the previously calculated models are based on a number of features, and wherein each of the plurality of case pairs comprise a first value representative of the number of features and a second value representative of deployed heating, ventilation, and air conditioning (HVAC) resources, a ranking engine configured to rank each of the plurality of case pairs based on a performance of the deployed services, and a deployment engine configured to: receive actual feature values, and deploy HVAC resources based on a comparison between the actual feature values and the plurality of ranked case pairs.

Abstract: A system and method obtain a database stored on a storage device containing information on multiple assets, the information including measurements taken from devices monitoring each asset, and context information corresponding to the environment the items are subjected to. The system and method groups assets via a computer system into a homogenous group as a function of selected context information and performs analytics via the computer system on the grouped assets to manage the assets.

Abstract: Various embodiments herein include at least one of systems, devices, methods, and methods for distributed HVAC system cost optimization. Such embodiments are generally implemented within a controller of HVAC system component, such as within boiler, cooler, air handling unit, and rooftop unit controllers. In some embodiments, multiple controllers exchange data to control various components of an HVAC system. One of the controllers, such as a primary plant of the system for heating or cooling, is designated as a master controller and the other component controllers are designated as slave controllers. Each controller, both master and slave controllers, includes at least one model that models variable settings of the component or components for which the respective controller is responsible. The model is utilized by the respective controller to both adjust the modeled variable component settings and to determine a cost-variable of operation.

Abstract: A method includes aggregating multiple zones of an indoor structure, each zone having associated comfort limits, formulating an aggregated single zone model predictive control (MPC) problem representative of the multiple zones for a heating ventilation and air conditioning (HVAC) system, determining optimal aggregated actions as a function of the aggregated single zone model predictive control problem, simulating an optimal trajectory of indoor qualities, and determining zone temperature setpoints to comply with the comfort limits for each zone and pre-cool the indoor structure.

Abstract: A method includes pairing manipulated variables and controlled variables in an HVAC system, perturbing a variable, controlling the HVAC system to maintain controlled variables in a comfort range, determining a state of the system, and deriving a model from the state of the system.

Abstract: Systems, methods, and devices for operation of a thermal comfort system are described herein. For example, one or more embodiments include receiving data, including a target temperature for a zone, an actual temperature of the zone, and an ambient temperature of air being supplied to a thermal comfort system, and determining, through a regression model, from the received data, a calculated time when the zone will reach the target temperature upon operation of the thermal comfort system.

Abstract: A method includes receiving energy-related information associated with multiple elements in a hierarchically-arranged domain. The method also includes determining a value of an energy-related metric for each of the elements using the energy-related information. The method further includes generating a graphical user interface using the metric values and presenting the graphical user interface to a user. The graphical user interface includes a treemap having multiple sections, each associated with one of the elements. The graphical user interface also includes a graph displaying energy-related information associated with a selected element. A size of each section in the treemap could be based on a size, importance, energy usage, and/or carbon emission of the associated element. A color and a color intensity of each section in the treemap could be based on the metric value of the associated element and/or a comparison of the absolute energy usage to a baseline.

Abstract: A system calculates a first ratio of a prediction error variance of a model of a controller error, and the lesser of a variance of a prediction error of a naïve predictor model and a variance of a controller error. The system rates a process controller as a function of the first ratio. The system also calculates a second ratio of a variance of the controller error and a variance of the prediction error of the naïve predictor model. The system rates the process controller a function of the second ratio. The system uses the first ratio, second ratio, other ratios, and discrete indicators in determining an embedded fusion for loop performance monitoring in the process controller and for displaying a value as a measure of the loop performance.

Abstract: A supervisory controller for heating, ventilation, and air conditioning (HVAC) systems is described herein. One device includes a data management module configured to receive a zone demand signal from a local controller of a zone of an HVAC system and receive a number of additional signals from a number of sensors, and a parameter identification module configured to determine, based on the zone demand signal, whether the zone is in a comfort state by loading a best model structure from a number of models and identifying parameters of the best model structure based on data received from the data management module.