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 at each of a plurality of time steps during a frequency response period, and a frequency response controller. The frequency response controller is configured to receive a regulation signal from an incentive provider, determine statistics of the regulation signal, use the statistics of the regulation signal to generate an optimal frequency response midpoint that achieves a desired change in a state-of-charge (SOC) of the battery while participating in a frequency response program, and use the midpoints 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: 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, a high level controller, and a low level controller. The high level controller is 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 an optimal frequency response midpoint. The optimal midpoint achieves a desired change in the state-of-charge of the battery while participating in a frequency response program. The low level controller is configured to use the midpoints to determine optimal battery power setpoints for the power inverter. The power inverter is configured to use the optimal battery power setpoints to control an amount of the electric power stored or discharged from the battery.

Abstract: A cascaded model predictive control system includes an inner controller and an outer controller. The outer controller determines an amount of power to defer from a predicted power usage to optimize a total cost of power usage. A power setpoint is calculated based on a difference between the predicted power usage and the amount of power to defer. The inner controller determines an operating setpoint for building equipment in order to achieve the power setpoint.

Abstract: A model predictive control system is used to optimize energy cost in a variable refrigerant flow (VRF) system. The VRF system includes an outdoor subsystem and a plurality of indoor subsystems. The model predictive control system includes a high-level model predictive controller (MPC) and a plurality of low-level indoor MPCs. The high-level MPC performs a high-level optimization to generate an optimal indoor subsystem load profile for each of the plurality of indoor subsystems. The optimal indoor subsystem load profiles optimize energy cost. Each of the low-level indoor MPCs performs a low-level optimization to generate optimal indoor setpoints for one or more indoor VRF units of the corresponding indoor subsystem. The indoor setpoints can include temperature setpoints and/or refrigerant flow setpoints for the indoor VRF units.

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 heating, ventilation, or air conditioning (HVAC) system for a building includes a plurality of indoor subsystems, a high-level controller, and a plurality of low-level controllers. Each indoor subsystem includes one or more indoor units configured to provide heating or cooling to one or more building spaces. The high-level controller is configured to generate a plurality of indoor subsystem energy targets, each indoor subsystem energy target corresponding to one of the plurality of indoor subsystems and generated based on a thermal capacitance of one or more building spaces to which heating or cooling is provided by the corresponding indoor subsystem.

Abstract: A controller for central plant equipment obtains a model of one or more sources configured to supply input resources, one or more subplants configured to convert the input resources to output resources, and one or more sinks configured to consume the output resources. The controller generates a resource balance constraint that requires balance between a first amount of each resource and a second amount of each resource. The first amount of each resource includes a sum of an amount of the resource supplied by the sources and an amount of the resource produced by the subplants. The second amount of each resource includes a sum of an amount of the resource consumed by the subplants and an amount of the resource consumed by the sinks. The controller performs an optimization of an objective function subject to the resource balance constraint to determine target amounts of each resource to be produced or consumed by the central plant equipment at a plurality of times within an optimization period.

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 building management system includes building equipment operable to affect a variable state or condition of a building and a control system configured to receive a user input indicating a model form. The model form includes a plurality of matrices having a plurality of elements defined in terms of a plurality of parameters. The control system is configured to parse the model form to generate a sequence of machine-executable steps for determining a value of each of the plurality of elements based on a set of potential parameter values, identify a system model by executing the sequence of machine-executable steps to generate a set of parameter values for the plurality of parameters, generate a graphical user interface that illustrates a fit between predictions of the identified system model and behavior of the variable state or condition of the building, and control the building equipment using the identified system model.

Abstract: An optimization system for a central plant includes a processing circuit configured to receive load prediction data indicating building energy loads and utility rate data indicating a price of one or more resources consumed by equipment of the central plant to serve the building energy loads. The optimization system includes a high level optimization module configured to generate an objective function that expresses a total monetary cost of operating the central plant over an optimization period as a function of the utility rate data and an amount of the one or more resources consumed by the central plant equipment. The optimization system includes a demand charge module configured to modify the objective function to account for a demand charge indicating a cost associated with maximum power consumption during a demand charge period. The high level optimization module is configured to optimize the objective function over the demand charge period.

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 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 (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 building management system includes a controller configured to control building equipment by providing a control input to the building equipment for each of the plurality of time steps and generate a set of training data for a system model for the building. The training data includes input training data and output training data for each of the plurality of time steps. The controller is further configured to perform a system identification process to identify parameters of the system model. The system identification process includes predicting, for each time step, a predicted value for one or more of the output variables for each of a plurality of subsequent time steps, generating a prediction error function by comparing the output training data to the predicted values, and optimizing the prediction error function to determine values for the parameters of the system model that minimize the prediction error 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.