Abstract: A predictive building control system includes equipment operable to provide heating or cooling to a building and a predictive controller. The predictive controller includes one or more optimization controllers configured to perform an optimization to generate setpoints for the equipment at each time step of an optimization period subject to one or more constraints, a constraint generator configured to use a neural network model to generate the one or more constraints, and an equipment controller configured to operate the equipment to achieve the setpoints generated by the one or more optimization controllers at each time step of the optimization period.

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 the optimization period as a function of the utility rate data and an amount of the one or more resources consumed by multiple groups of the central plant equipment. The optimization system includes a load change penalty module configured to modify the objective function to account for a load change penalty resulting from a change in an amount of the building energy loads assigned to one or more of the groups of central plant equipment.

Abstract: Systems and methods for low level central plant optimization are provided. A controller for the central plant uses binary optimization to determine one or more feasible on/off configurations for equipment of the central plant that satisfy operating constraints and meet a thermal energy load setpoint. The controller determines optimum operating setpoints for each feasible on/off configuration and generates operating parameters including at least one of the feasible on/off configurations and the optimum operating setpoints. The operating parameters optimize an amount of energy consumed by the central plant equipment. The controller outputs the generated operating parameters via a communications interface for use in controlling the central plant equipment.

Abstract: A controller for a building system receives training data that includes input data and output data. The output data measures a state of the building system affected by both the input data and an extraneous disturbance. The controller performs a two-stage optimization process to identify system parameters and Kalman gain parameters of a dynamic model for the building system. During the first stage, the controller filters the training data to remove an effect of the extraneous disturbance from the output data and uses the filtered training data to identify the system parameters. During the second stage, the controller uses the non-filtered training data to identify the Kalman gain parameters. The controller uses the dynamic model with the identified system parameters and Kalman gain parameters to generate a setpoint for the building system. The building system uses the setpoint to affect the state measured by the output data.

Abstract: A building control system includes a wireless measurement device and a controller. The wireless measurement device measures a plurality of values of an environmental variable and uses the plurality of measured values to predict one or more future values of the environmental variable. The wireless device periodically transmits, at a transmission interval, a message that includes a current value of the environmental variable and the one or more predicted values of the environmental variable. The controller receives the message from the wireless device and parses the message to extract the current value and the one or more predicted future values of the environmental variable. The controller periodically and sequentially applies, at a controller update interval shorter than the transmission interval, each of the extracted values as an input to a control algorithm that operates to control the environmental variable.

Abstract: An energy plant includes a plurality of subplants, a high level optimizer, a low level optimizer, and a controller. The plurality of subplants include a cogeneration subplant configured to generate steam and electricity and a chiller subplant electrically coupled to the cogeneration subplant and configured to consume the electricity generated by the cogeneration subplant. The high level optimizer is configured to determine recommended subplant loads for each of the plurality of subplants. The recommended subplant loads include a rate of steam production and a rate of electricity production of the cogeneration subplant and a rate of electricity consumption of the chiller subplant. The low level optimizer is configured to determine recommended equipment setpoints for equipment of the plurality of subplants based on the recommended subplant loads. The controller is configured to operate the equipment of the plurality of subplants based on the recommended equipment setpoints.

Abstract: An energy storage system includes a battery and an energy storage controller. The battery is configured to store electrical energy purchased from a utility and to discharge the stored electrical energy for use in satisfying a building energy load. The energy storage controller is configured to generate a cost function including multiple demand charges. Each of the demand charges corresponds to a demand charge period and defines a cost based on a maximum amount of the electrical energy purchased from the utility during any time step within the corresponding demand charge period. The controller is configured to modify the cost function by applying a demand charge mask to each of the multiple demand charges. The demand charge masks cause the controller to disregard the electrical energy purchased from the utility during any time steps that occur outside the corresponding demand charge period when calculating a value for the demand charge.

Abstract: A controller is configured to use an energy cost function to predict a total cost of energy purchased from an energy provider as a function of one or more setpoints provided by the controller. The energy cost function includes a demand charge term defining a cost per unit of power corresponding to a maximum power usage of the building system. The controller is configured to linearize the demand charge term by imposing demand charge constraints and to mask each of the demand charge constraints that applies to an inactive pricing period. The controller is configured to determine optimal values of the one or more setpoints by performing an optimization procedure that minimizes the total cost of energy subject to the demand charge constraints and to provide the optimal values of the one or more setpoints to equipment of the building system that operate to affect the maximum power usage.

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 HVAC system includes an airside system having a plurality of airside subsystems, a waterside system, a high-level model predictive controller (MPC), and a plurality of low-level airside MPCs. Each airside subsystem includes airside HVAC equipment configured to provide heating or cooling to the airside subsystem. The waterside system includes waterside HVAC equipment configured to produce thermal energy used by the airside system to provide the heating or cooling. The high-level MPC is configured to perform a high-level optimization to generate an optimal airside subsystem load profile for each of the plurality of airside subsystems. The optimal airside subsystem load profiles optimize a total cost of energy consumed by the airside system and the waterside system Each of the low-level airside MPCs is configured to operate the airside HVAC equipment of an airside subsystem according to the load profile for the airside subsystem.

Abstract: A building HVAC system includes an airside system having a plurality of airside subsystems, a high-level model predictive controller (MPC), and a plurality of low-level airside MPCs. Each airside subsystem includes airside HVAC equipment configured to provide heating or cooling to the airside subsystem. The high-level MPC is configured to perform a high-level optimization to generate an optimal airside subsystem load profile for each airside subsystem. The optimal airside subsystem load profiles optimize energy cost. Each of the low-level airside MPCs corresponds to one of the airside subsystems and is configured to perform a low-level optimization to generate optimal airside temperature setpoints for the corresponding airside subsystem using the optimal airside subsystem load profile for the corresponding airside subsystem.

Abstract: Methods and systems to minimize energy cost in response to time-varying energy prices are presented for a variety of different pricing scenarios. A cascaded model predictive control system is disclosed comprising an inner controller and an outer controller. The inner controller controls power use using a derivative of a temperature setpoint and the outer controller controls temperature via a power setpoint or power deferral. An optimization procedure is used to minimize a cost function within a time horizon subject to temperature constraints, equality constraints, and demand charge constraints. Equality constraints are formulated using system model information and system state information whereas demand charge constraints are formulated using system state information and pricing information. A masking procedure is used to invalidate demand charge constraints for inactive pricing periods including peak, partial-peak, off-peak, critical-peak, and real-time.

Abstract: A building control system includes a wireless measurement device and a controller. The wireless measurement device measures a plurality of values of an environmental variable and uses the plurality of measured values to predict one or more future values of the environmental variable. The wireless device periodically transmits, at a transmission interval, a message that includes a current value of the environmental variable and the one or more predicted values of the environmental variable. The controller receives the message from the wireless device and parses the message to extract the current value and the one or more predicted future values of the environmental variable. The controller periodically and sequentially applies, at a controller update interval shorter than the transmission interval, each of the extracted values as an input to a control algorithm that operates to control the environmental variable.

Abstract: A central plant that generates and provides resources to a building. The central plant includes an electrical energy storage subplant configured to store electrical energy purchased from a utility and to discharge the stored electrical energy. The central plant includes a plurality of generator subplants that consume one or more input resources. The central plant includes a controller configured to determine, for each time step within a time horizon, an optimal allocation of the input resources and the output resources for each of the subplants in order to optimize a total monetary value of operating the central plant over the time horizon. The total monetary value includes revenue from participating in incentive-based demand response programs as well as costs associated with resource consumption, equipment degradation, and losses in battery capacity.

Abstract: A building management system includes building equipment configured to consume electrical energy and generate thermal energy, thermal energy storage configured to store at least a portion of the thermal energy generated by the building equipment and to discharge the stored thermal energy, electrical energy storage configured to store electrical energy purchased from a utility and to discharge the stored electrical energy, and a controller. The controller is configured to determine, for each time step within a time horizon, an optimal amount of electrical energy stored or discharged by the electrical energy storage by optimizing a value function.

Abstract: A method for detecting and responding to disturbances in a HVAC system using a noisy measurement signal and a signal filter is provided. The method includes detecting a deviation in the noisy measurement signal, resetting the filter in response to a detected deviation exceeding a noise threshold, filtering the noisy measurement signal using the signal filter to determine an estimated state value, and determining that a disturbance has occurred in response to the estimated state value crossing a disturbance threshold. In some embodiments, the method further includes performing one or more control actions in response to the detection of a disturbance.

Abstract: A system for visualizing equipment utilization in a central plant includes a subplant monitor, a subplant utilization database, and a dispatch graphical user interface (GUI) generator. The subplant monitor receives subplant utilization data including an indication of a thermal energy load served by each of a plurality of subplants of the central plant. The subplant utilization database stores the subplant utilization data for each of a plurality of time steps. The dispatch GUI generator generates a dispatch GUI using the subplant utilization data. The dispatch GUI includes an indication of the thermal energy load served by each of the plurality of subplants for each of the plurality of time steps. The dispatch GUI may include a set of stacked bars for each of the time steps. Each of the stacked bars may represent the thermal energy load served by one of the subplants during a corresponding time step.

Abstract: A central plant includes an electrical energy storage subplant configured to store electrical energy, a plurality of generator subplants configured to consume one or more input resources, including discharged electrical energy, and a controller. The controller is configured to determine, for each time step within a time horizon, an optimal allocation of the input resources. The controller is configured to determine optimal allocation of the output resources for each of the subplants in order to optimize a total monetary value of operating the central plant over the time horizon.

Abstract: A building HVAC system includes a waterside system and an airside system. The waterside system consumes one or more resources from utility providers to generate a heated and/or chilled fluid. The airside system uses the heated and/or chilled fluid to heat and/or cool a supply airflow provided to the building. A HVAC controller performs an integrated airside/waterside optimization process to simultaneously determine control outputs for both the waterside system and the airside system. The optimization process includes optimizing a predictive cost model that predicts the cost of the resources consumed by the HVAC system, subject to a set of optimization constraints including temperature constraints for the building. The HVAC controller uses the determined control outputs to control the HVAC equipment of the waterside system and the airside system.