Abstract: Systems and methods are disclosed relating to user interface generation using machine learning models. A system can include one or more processors configured to receive, from a device associated with a user identifier, a prompt for generating data regarding a building management system. The one or more processors can generate, using at least one machine learning model, a completion to the prompt based at least on the prompt and the user identifier, the completion indicating one or more actions corresponding to a performance target for the building management system. The one or more processors can present the completion using at least one of a display device or an audio output device.

Abstract: A controller for chillers that operate to serve a cooling load of a building or facility obtains a first balance constraint that requires balance between chilled water production and consumption and obtains a second balance constraint that requires balance between water, electricity, or steam consumption and production. The controller solves a control problem using the first balance constraint and the second balance constraint to determine an amount of the chilled water to be produced by the chillers and an amount of the water, electricity, or steam to be consumed by the chillers or other equipment. The controller operates the chillers in accordance with a setpoint to consume the amount of the water, electricity, or steam or produce the amount of the chilled water determined by solving the control problem. The amount of chilled water is delivered for use in serving the cooling load of the building or facility.

Abstract: Systems and methods are disclosed relating to building management systems with sustainability improvement for a building. For example, a system can include at least one machine learning model configured using training data that includes at least one of unstructured data or structured data regarding sustainability of buildings. The system can provide inputs, such as prompts, to the at least one machine learning model regarding a sustainability performance of the building, and generate, according to the inputs, responses regarding the sustainability performance of the building, such as responses for detecting factors and/or sources contributing to the sustainability performance of the building.

Abstract: A method includes receiving, by one or more processors, user input describing characteristics of a central utility plant for a building, the user input comprising textual or audible input, identifying, by the one or more processors, a plurality of pieces of building equipment satisfying the characteristics of the user input using an AI model based on the user input, and generating, by the one or more processors using the AI model, a central utility plant model for the central utility plant based on the textual or audible input. The central utility plant model satisfies the characteristics and includes the identified pieces of building equipment.

Abstract: A controller for operating building equipment of a building including processors and non-transitory computer-readable media storing instructions that, when executed by the processors, cause the processors to perform operations including obtaining a first setpoint trajectory from a cloud computation system. The first setpoint trajectory includes setpoints for the building equipment or for a space of the building. The setpoints correspond to time steps of an optimization period. The operations include determining whether a connection between the controller and the cloud computation system is active or inactive at a time step of the optimization period and determining an active setpoint for the time step of the optimization period using either the first or second setpoint trajectory based on whether the connection between the controller and the cloud computation system is active or inactive at the time step. The operations include operating the building equipment based on the active setpoint.

Abstract: A building system operates to receive building data from one or more building data sources associated with the building, wherein at least a portion of the building data is associated with control of the one or more environmental conditions of the building and generate, based on the building data, one or more data quality indicators for the building data received from the one or more building data sources, the one or more data quality indicators indicating quality levels of the building data. The building system operates to generate user interface data configured to cause a user device to display a user interface providing indications of the one or more data quality indicators.

Abstract: A controller is provided for building equipment including a plurality of devices that operate in parallel to affect an environmental condition of a building. The controller includes one or more processing circuits including one or more processors and memory. The memory store instructions that, when executed by the one or more processors, cause the one or more processors to perform operations. The operations include lowering an upper bound or raising a lower bound of one or more constraints based on a minimum off schedule or a minimum on schedule for the building equipment, performing an optimization of an objective function subject to the one or more constraints to generate control decisions for the building equipment, and operating the building equipment in accordance with the control decisions to affect the environmental condition of the building.

Abstract: One implementation of the present disclosure is a controller for a variable refrigerant flow system. The controller includes processors and memory storing instructions that, when executed by the processors, cause the processors to perform operations including identifying zones within a structure, generating zone groupings defining zone groups and specifying which of the zones are grouped together to form each of the zone groups, generating metric of success values corresponding to the zone groupings and indicating a control feasibility of a corresponding zone grouping, selecting a zone grouping based on the metric of success values, and using the selected zone grouping to operate equipment of the variable refrigerant flow system to provide heating or cooling to the zones.

Abstract: A controller for equipment that operate to store, discharge, generate, or consume one or more resources is configured to provide an objective function indicating a total value of obtaining a resource from a utility provider over a plurality of time steps subject to a load-following-block rate structure. The objective function includes a first term representing a load-following-block of the resource as being sourced from the utility provider at a fixed rate and a second term representing a remainder of the resource as being sourced from the utility provider at a variable rate. The controller is configured to use the objective function to generate values for decision variables and control the equipment to store, discharge, generate, or consume amounts of the resources indicated by the values of the decision variables at the plurality of time steps.

Abstract: A method includes finding, in subplant performance data points defined by values of an independent variable and values of a dependent variable, a first point for which a convexity metric of the dependent variable with respect to the independent variable exceeds a threshold, creating a subplant curve by providing a first convex region on a first side of the first point and a second convex region on a second side of the first point, and controlling the campus subplant based on the subplant curve.

Abstract: An energy optimization system includes an asset sizing system to determine an asset size and to cause a new asset to be purchased or installed. The energy optimization system uses a cost function dependent on a cost of operating a building system and on an initial purchase price of the new asset. The new asset may be a heat recover chiller, a solar energy system, a hydroelectric system, or an energy storage system. The optimization may be performed subject to a constraint related to the use of a resource supplied to the building system by one or more utilities. The optimization may include minimizing a simple pay back period or to maximizing a rate of return on the purchase of the new asset.

Abstract: A method includes operating equipment in accordance with a setpoint to affect a measurement for a space during a training period, performing a plurality of assessments of different characteristics of data for a segment of the training period, and training a system model using a set of training data. The data for the segment is included in the set of training data in response to passing the plurality of assessments or excluded from the set of training data in response to failing one or more of the plurality of assessments. The method also includes controlling the equipment using the system model.

Abstract: A system includes a processing circuit configured to provide an energy use setpoint based on energy data including an energy characteristic and subject to a constraint based on a variable condition of a building. The processing circuit is configured to estimate a value for the energy use setpoint that will result in the variable condition of the building satisfying the constraint and provide a control signal for equipment based on a difference between the energy use setpoint and a measured energy use.

Abstract: A predictive controller for building equipment associated with a building includes one or more processing circuits configured to control electric energy used by the building equipment. The building equipment includes an electric energy using component. The one or more processing circuits are configured to utilize a predictive cost function to determine a first amount of the electric energy supplied from an energy grid source and a second amount of the electric energy supplied from a second energy source to the electric energy using component.

Abstract: A controller for a system of equipment that operate to produce or consume one or more resources includes one or more processing circuits configured to generate a resource balance constraint using a balance between a first amount of each resource and a second amount of each resource. The first amount of each resource includes at least an amount of the resource produced by the equipment. The second amount of each resource includes at least an amount of the resource consumed by the equipment. The one or more processing circuits are configured to perform a control process using the resource balance constraint to determine amounts of each resource to be produced or consumed by the equipment and operate the equipment to produce or consume the amounts of each resource determined by the control process.

Abstract: A control system for cost optimal operation of an energy facility including equipment includes a controller configured to provide a cost function comprising a cost term defining a cost as a function of a rate variable and an equipment usage variable, simulate the cost of operating the energy facility over an optimization period at each of a plurality of different values of the rate variable which define a plurality of different costs per unit of the equipment usage variable, select a value of the rate variable that results in a lowest cost of operating the energy facility over the optimization period, perform an online optimization of the cost function with the rate variable set to the selected value to generate one or more setpoints for the equipment, and operate the equipment during the optimization period in accordance with the generated setpoints.

Abstract: A thermal energy production and control system includes a heat recovery chiller, thermal energy storage, and a controller. The controller uses thermal energy load targets to generate control decisions for the heat recovery chiller and the thermal energy storage for a plurality of time steps of a time period. The control decisions include a first amount of hot thermal energy or cold thermal energy to be generated by the heat recovery chiller at a first time step of the time period and stored in the thermal energy storage and a second amount of the hot thermal energy or the cold thermal energy to be discharged from the thermal energy storage and used to satisfy one or more of the thermal energy load targets for a second time step of the time period. The controller operates the heat recovery chiller and the thermal energy storage in accordance with the control decisions.

Abstract: A building system including one or more storage devices storing instructions thereon that, when executed by one or more processors, cause the one or more processors to ingest information comprising at least one of occupancy information or energy usage information associated with a building. The instructions further cause the one or more processors to generate a space usage recommendation based on the information. The instructions further cause the one or more processors to cause a graphical model of the building to include a representation of the information and the space usage recommendation. The instructions further cause the one or more processors to cause a display device of a user device to display the graphical model within a user interface.

Abstract: An control method includes obtaining measurements of a carbon dioxide (CO2) level of a zone and a temperature of the zone. The method includes determining, based on the CO2 level of the zone and the temperature of the zone, a combination if (i) control decisions for an air handling unit (AHU) and (ii) control decisions for a damper of a variable air volume (VAV) unit to satisfy both a ventilation control objective and a temperature control objective. The control decisions for the AHU include adjustments to a fresh air intake fraction of the AHU between multiple values over time, and the control decisions for the VAV unit include adjustments to a position of a damper of the VAV unit over time. The method includes operating the AHU according to the control decisions for the AHU and operate the VAV unit according to the control decisions for the VAV unit.

Abstract: Disclosed herein are related to a system, a method, and a non-transitory computer readable medium for operating an energy plant. In one aspect, the system generates a regression model of a produced thermal energy load produced by a supply device of the plurality of devices. The system predicts the produced thermal energy load produced by the supply device for a first time period based on the regression model. The system determines a heat capacity of gas or liquid in the loop based on the predicted produced thermal energy load. The system generates a model of mass storage based on the heat capacity. The system predicts an induced thermal energy load during a second time period at a consuming device of the plurality of devices based on the model of the mass storage. The system operates the energy plant according to the predicted induced thermal energy load.