Abstract: A building control system uses an empirical technique to determine the uncertainty in parameters of an energy use model. The energy use model is used to predict energy consumption of a building site as a function of the model parameters and one or more predictor variables. The empirical technique includes obtaining a set of data points, each of the data points including a value for the one or more predictor variables and an associated energy consumption value for the building site. Multiple samples are generated from the set of data points, each of the multiple samples including a plurality of data points selected from the set of data points. For each of the multiple samples, the model parameters are estimated using the plurality of data points included in the sample. The uncertainty in the model parameters is determined using the multiple estimates of the model parameters.

Abstract: 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.

Abstract: A system includes a plurality of thermostats corresponding to a plurality of HVAC systems that serve a plurality of spaces and a computing system communicable with the plurality of thermostats via a network. The computing system is configured to, for each space of the plurality of spaces, obtain a set of training data relating to thermal behavior of the space, identify a model of thermal behavior of the space based on the set of training data, perform a model predictive control process using the model of thermal behavior of the space to obtain a temperature setpoint for the space, and provide the temperature setpoint to the thermostat corresponding to the HVAC system serving the space. The plurality of thermostats are configured to control the plurality of HVAC systems in accordance with the temperature setpoints.

Abstract: 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.

Abstract: A model predictive maintenance system for building equipment. The system includes one or more processing circuits including one or more processors and memory storing instructions that, when executed by the one or more processors, cause the one or more processors to perform operations. The operations include performing an optimization of an objective function that defines a present value of a total cost of operating the building equipment and performing maintenance on the building equipment as a function of operating decisions and maintenance decisions for the building equipment for time steps within a time period. The total cost includes one or more costs incurred during one or more future time steps of the time period. The operations include operating the building equipment and performing maintenance on the building equipment in accordance with decisions defined by the result of the optimization.

Abstract: A controller is configured to obtain a cost function defining a cost of operating building equipment over a time period. The cost function includes a revenue term defining revenue to be obtained by operating the equipment to participate in an incentive program over the time period. The controller is configured to modify the cost function to account for an initial purchase cost of a new asset to be added to the equipment and an effect of the new asset on the cost of operating the equipment. The initial purchase cost of the new asset and the effect of the new asset on the cost of operating the equipment are functions of asset size variables. The controller is also configured to perform an optimization of the modified cost function to determine values for energy load setpoints, the asset size variables, and participation in the incentive program over the time period.

Abstract: A controller for maintaining occupant comfort in a space of a building. The controller includes processors and non-transitory computer-readable media storing instructions that, when executed by the processors, cause the processors to perform operations. The operations include obtaining building data and obtaining occupant comfort data. The operations include generating an occupant comfort model relating the building data to a level of occupant comfort within the space based on the building data and the occupant comfort data. The operations include generating time-varying comfort constraint for an environmental condition of the space using the occupant comfort model and include performing a cost optimization of a cost function of operating building equipment over a time duration to determine a setpoint for the building equipment. The operations include operating the building equipment based on the setpoint to affect the variable state or condition of the space.

Abstract: A model predictive maintenance (MPM) system for building equipment. The MPM system includes an equipment controller configured to operate the building equipment to affect a variable state or condition in a building. The MPM system includes an operational cost predictor configured to predict a cost of operating the building equipment over a duration of an optimization period. The MPM system includes a budget manager configured to generate one or more budget constraints. The MPM system includes an objective function optimizer configured to optimize an objective function subject to the one or more budget constraints to determine a maintenance and replacement schedule for the building equipment. The objective function includes maintenance and replacement costs of the building equipment and the predicted cost of operating the building equipment.

Abstract: A central plant includes storage devices configured to store resources purchased from a utility or generated by the central plant and to discharge the one or more resources. The central plant includes a controller configured to obtain a cost function comprising a peak load contribution (PLC) term representing a cost based on an amount of the one or more resources purchased during coincidental peak (CP) subperiods. The controller is configured to modify the cost function by applying a peak subperiods mask to the PLC term, wherein, for each subperiod, the peak subperiods mask modifies a portion of the PLC term corresponding to the subperiod based on a probability that the subperiod will be one of the CP subperiods. The controller is also configured to perform an optimization of the modified cost function.

Abstract: A model predictive maintenance system for building equipment including an equipment controller to operate the building equipment to affect a variable state or condition in a building. The system includes an operational cost predictor to predict a cost of operating the building equipment over a duration of an optimization period, a maintenance cost predictor to predict a cost of performing maintenance on the building equipment, and a cost incentive manager to determine whether any cost incentives are available and, in response to a determination that cost incentives are available, identify the cost incentives. The system includes an objective function optimizer to optimize an objective function to predict a total cost associated with the building equipment over the duration of the optimization period. The objective function includes the predicted cost of operating the building equipment, the predicted cost of performing maintenance on the building equipment, and, if available, the cost incentives.

Abstract: A method for generating an optimal nominated capacity value for participation in a capacity market program (CMP) includes generating, by a processing circuit, an objective function comprising a nominated capacity term, wherein the nominated capacity term indicates a nominated capacity value, wherein the nominated capacity value is a curtailment value that a facility is on standby to reduce its load by in response to receiving a dispatch from a utility. The method includes optimizing, by the processing circuit, the objective function to determine the optimal nominated capacity value for a program operating period and transmitting, by the processing circuit, the optimal nominated capacity value to one or more systems associated with the CMP to participate in the CMP.

Abstract: An energy optimization system for participating in a capacity market program (CMP) includes one or more memory devices storing instructions, that, when executed on one or more processors, cause the one or more processors to receive a nominated capacity value, generate an objective function and one or more CMP constraints, wherein the one or more CMP constraints cause an optimization of the objective function with the CMP constraints to generate a resource allocation that reduces the load of the facility by the nominated capacity value in response to receiving the dispatch from the utility, receive the dispatch from the utility, optimize the objective function based on the nominated capacity value, the dispatch, and the one or more CMP constraints to determine the resource allocation, and control one or more pieces of building equipment based on the determined resource allocation.

Abstract: An automatic parts resupply system for building equipment including a model predictive maintenance system configured to determine a service time at which to perform service on the building equipment by performing a predictive optimization of a total cost of operating and servicing the building equipment over a time period. The service time is a decision variable in the predictive optimization. The automatic parts resupply system includes a resupply manager. The resupply manager is configured to generate a parts resupply order for the building equipment based on a result of the predictive optimization. The resupply manager is configured to determine a transmission time at which to transmit the parts resupply order to a parts supplier. The resupply manager is configured to transmit the parts resupply order to the parts supplier at the transmission time.

Abstract: An energy storage system for a building includes a battery asset configured to store electricity and discharge the stored electricity for use in satisfying a building electric load. The system includes a planning tool configured to identify one or more selected functionalities of the energy storage system and generate a cost function defining a cost of operating the energy storage system over an optimization period. The cost function includes a term for each of the selected functionalities. The planning tool is configured to generate optimization constraints based on the selected functionalities, attributes of the battery asset, and the electric energy load to be satisfied. The planning tool is configured to optimize the cost function to determine optimal power setpoints for the battery asset at each of a plurality of time steps of the optimization period.

Abstract: A frequency response controller includes a high level controller configured to receive a regulation signal from an incentive provider, determine statistics of the regulation signal, and use the statistics of the regulation signal to generate a frequency response midpoint. The controller further includes a low level controller configured to use the frequency response midpoint to determine optimal battery power setpoints and use the optimal battery power setpoints to control an amount of electric power stored or discharged from a battery during a frequency response period.

Abstract: A frequency response optimization system includes a battery configured to store and discharge electric power, a power inverter configured to control an amount of the electric power stored or discharged from the battery, and a frequency response controller. The frequency response controller includes receiving a regulation signal from an incentive provider, determining statistics of the regulation signal, using the statistics of the regulation signal to generate a frequency response midpoint, and using the frequency response midpoint to determine optimal battery power setpoints for the power inverter. The power inverter is configured to use the optimal battery power setpoints to control the amount of the electric power stored or discharged from the battery.

Abstract: An automatic work order generation system for model predictive maintenance (MPM) of building equipment including an MPM system including an equipment controller to operate the building equipment to affect an environmental condition of a building. The MPM system can perform a predictive optimization to determine a service time at which to service the building equipment. The automatic work order generation system includes an equipment service scheduler that can determine whether any service providers are available to perform equipment service within a predetermined time range of the service time. In response to determining that service providers are available to perform the equipment service, the equipment service scheduler can select a service provider and an appointment time based on one or more service provider attributes. The equipment service scheduler can generate a service work order and transmit the service work order to the service provider to schedule a service appointment.

Abstract: A fault parameter of an energy consumption model is modulated. The energy consumption model is used to estimate an amount of energy consumption at various values of the fault parameter. A first set of variables is generated including differences between a target value of the fault parameter and the various values of the fault parameter. A second set of variables is generated including differences between an estimated amount of energy consumption with the fault parameter at the target value and the estimated amounts of energy consumption with the fault parameter at the various values. The first set of variables and second set of variables are used to develop a regression model for the fault parameter. The regression model estimates a change in energy consumption based on a change in the fault parameter. Regression models are developed for multiple fault parameters and used to prioritize faults.

Abstract: An energy storage system for a building includes a battery and an energy storage controller. The battery is configured to store electrical energy purchased from a utility and to discharge stored electrical energy for use in satisfying a building energy load. The energy storage controller is configured to generate a cost function including a peak load contribution (PLC) term. The PLC term represents a cost based on electrical energy purchased from the utility during coincidental peak hours in an optimization period. The controller is configured to modify the cost function by applying a peak hours mask to the PLC term. The peak hours mask identifies one or more hours in the optimization period as projected peak hours and causes the energy storage controller to disregard the electrical energy purchased from the utility during any hours not identified as projected peak hours when calculating a value for the PLC term.

Abstract: An energy cost optimization system for a building includes HVAC equipment and a controller. The controller is configured to generate a cost function defining a cost of operating the HVAC equipment as a function of one or more energy load setpoints. The controller is configured to modify the cost function to account for both an initial purchase cost of a new asset to be added to the HVAC equipment and an effect of the new asset on the cost of operating the HVAC equipment. Both the initial purchase cost of the new asset and the effect of the new asset on the cost of operating the HVAC equipment are functions of one or more asset size variables. The controller is configured to perform an optimization using the modified cost function to determine optimal values for decision variables including the energy load setpoints and the asset size variables.