Abstract: A method for providing filtered air to a zone of a building includes operating an air handler to pass unfiltered air through a filter and output filtered air to the zone of the building. The method includes determining an amount of filtered air provided to the zone of the building by the air handler. The method includes determining if additional air filtration is required to satisfy at least one of a desired amount of clean airflow or a desired reduction of a risk of infection. The method includes activating an in-zone filtration device and operating the in-zone filtration device to draw air from the zone into an inner volume, filter the air, and recirculate the filtered air to the zone of the building in response to determining additional air filtration is required.

Abstract: A system for rejecting heat generated within a data center with a hybrid cooling system using liquid cooling and/or air-based cooling of the computers. The system allocates an amount of heat generated by the one or more computers of the rack group into (i) a first amount of heat to be rejected from the rack group into a first coolant provided by a first cooling system and (ii) a second amount of heat to be rejected from the rack group into a second coolant provided by a second cooling system. The system can allocate heat rejection capacity from the first cooling system and second cooling system differentially to CPUs and GPUs. The system may generate constraints to ensure that the CPUs and GPUs receive heat rejection capacity from an appropriate system and at an appropriate temperature. Compute tasks are allocated to advantageously generate heat that can be efficiently rejected.

Abstract: A system for rejecting heat generated within a data center with a hybrid cooling system using both liquid cooling and air-based cooling of the computers. The system allocates an amount of heat generated by the one or more computers of the rack group into (i) a first amount of heat to be rejected from the rack group into cool air provided by an air cooling system and (ii) a second amount of heat to be rejected from the rack group into chilled water provided by a water cooling system. The air cooling system and the water cooling system operate in parallel to provide both the cool air and the chilled water to the rack group. The system operates the air cooling system in accordance with the allocation to reject the first amount of heat from the rack group into the cool air and operates the water cooling system accordance with the allocation to reject the second amount of heat from the rack group into the chilled water.

Abstract: A heating, ventilating, or air conditioning (HVAC) system that operates equipment to affect a physical property of an environment. The HVAC system obtains schedules including two time periods during which a criterion for the physical property of a environment is to be satisfied (for example, occupied time periods) and a third time period occurring between the two time periods during which the criterion need not be satisfied (for example, unoccupied time periods). The HVAC system performs one prediction of the physical property forward from the end of the middle time period and one prediction backward from the last of the three time periods to determine a transition period during the second time period within which to operate the equipment by finding an intersection of the predictions. The HVAC system controls the equipment during the transition time period to satisfy the criterion at the beginning of the last time period.

Abstract: Systems and methods for executing an IAQ analysis of a building. One system includes a controller including memory and one or more processors configured to obtain IAQ data from one or more sensors within the building, wherein the IAQ data is associated with at least one of a plurality of environment species, obtain BAS data, identify one or more unknown parameters from the IAQ data and BAS data of two or more of the plurality of environment species, estimate the one or more unknown parameters based on inputting the IAQ data and the BAS data into an optimization model, and wherein the optimization model analyzes predicted concentrations of the plurality of environment species subject to the two or more of the plurality of environment species evolving according to a single-species concentration model, and provide the estimated one or more unknown parameters to one or more predictive models.

Abstract: A method for providing filtered air to a zone of a building includes operating an air handler to pass unfiltered air through a filter and output filtered air to the zone of the building. The method includes determining an amount of filtered air provided to the zone of the building by the air handler. The method includes determining if additional air filtration is required to satisfy at least one of a desired amount of clean airflow or a desired reduction of a risk of infection. The method includes activating an in-zone filtration device and operating the in-zone filtration device to draw air from the zone into an inner volume, filter the air, and recirculate the filtered air to the zone of the building in response to determining additional air filtration is required.

Abstract: A building system can operate to receive a requirement to implement an artificial intelligence (AI) service. The requirement can include an indication of a type of an entity, wherein the AI service is configured to generate an analytic for the entity of the type of the entity or a control setting for the entity of the type of the entity. The requirement can include a data element that the AI service is configured to operate on to generate the analytic or the control setting. The building system can operate to determine that the building system meets the requirement to implement the AI service responsive to a determination that a digital twin of the building system includes the entity of the entity type and the data element and implement the AI service responsive to a determination that the building system meets the requirement.

Abstract: Systems and methods for controlling building equipment based on an indoor air quality (IAQ) ventilation analysis of a building. One system includes a controller including memory and one or more processors configured to continuously collect IAQ data from one or more sensors within the building, estimate a plurality of outdoor airflow rates for an area of the building during a plurality of transient periods using the IAQ data as input, generate a time series outdoor airflow rate includes the plurality of estimated outdoor airflow rates, and modify a control strategy for the area of the building based on the time series outdoor airflow rate and a ventilation schedule for the area of the building.

Abstract: Systems and methods for executing an IAQ analysis of a building. One system includes a controller including memory and one or more processors configured to obtain IAQ data from one or more sensors within the building, wherein the IAQ data is associated with at least one of a plurality of environment species, obtain BAS data, identify one or more unknown parameters from the IAQ data and BAS data of two or more of the plurality of environment species, estimate the one or more unknown parameters based on inputting the IAQ data and the BAS data into an optimization model, and wherein the optimization model analyzes predicted concentrations of the plurality of environment species subject to the two or more of the plurality of environment species evolving according to a single-species concentration model, and provide the estimated one or more unknown parameters to one or more predictive models.

Abstract: An infection control tool for a building HVAC system includes processing circuitry configured to receive one or more inputs defining a HVAC system configuration for each of a baseline scenario and one or more other scenarios. The processing circuitry is also configured to estimate infection risk and at least one of energy consumption or operating cost for each of the one or more other scenarios relative to the baseline scenario. The processing circuitry is also configured to operate a display to provide the infection risk and at least one of the energy consumption or operating cost to a user.

Abstract: A predictive modeling and control system for building equipment assesses whether a data set from a first device of building equipment is sufficient to train a prediction model for the first device. In response to a determination that the data set from the first device is insufficient to train the prediction model for the first device, the system generates a ranking of a plurality of additional devices of building equipment based on similarities between the first device and the plurality of additional devices, augments the data set with supplemental data from one or more of the plurality of additional devices in an order based on the ranking until the augmented data set is sufficient to train the prediction model, and trains the prediction model for the first device using the augmented data set. The system influences operations of the first device using the prediction model.

Abstract: A system includes a plurality of devices of building equipment, an additional device of building equipment, and a computing system. The computing system is configured to process data from the plurality of devices to extract common features of the plurality of devices, train a global model based on the common features, obtain additional data from the additional device, adapt the global model for the additional device based on the additional data to obtain an adapted model for the additional device, predict a status of the additional device using the adapted model, and affect an operation of the additional device based on the status.

Abstract: Systems and methods for controlling building equipment include simulating operation of the building equipment at a plurality of initial points to generate corresponding values of a first control objective and a second control objective that competes with the first control objective, automatically generating a new point at which to run a new simulation based on the plurality of initial points and the corresponding values of the control objectives, running the new simulation at the new point to generate corresponding values of the control objectives, classifying a subset of the plurality of initial points and the new point as Pareto-optimal points based on the corresponding values of the control objectives, and operating the building equipment at a Pareto-optimal point selected from the subset of the plurality of initial points and the new point classified as Pareto-optimal points.

Abstract: A controller for heating, ventilation, or air conditioning (HVAC) equipment operable to affect an environmental condition of a building is configured to obtain predictive models that predict values of an energy control objective and an air quality control objective as a function of control decision variables for the HVAC equipment. The controller executes a multi-objective optimization process using the predictive models to produce multiple sets of optimization results corresponding to different values of the control decision variables, the energy control objective, and the air quality control objective. The controller selects one or more of the sets of optimization results based on the values of the energy control objective and the air quality control objective. The controller operates the HVAC equipment to affect the environmental condition of the building in accordance with the values of the control decision variables corresponding to a selected set of the optimization results.

Abstract: A method includes providing, by processing circuitry, a net resource consumption trajectory including net resource consumption targets for one or more subperiods of a time period. Each net resource consumption target indicates a target difference between resource consumption and resource production or offset for a subperiod of the one or more subperiods. The method includes generating, by the processing circuitry and for a subperiod of the one or more subperiods, a set of actions predicted to achieve the net resource consumption target for the subperiod. The method includes implementing, by the processing circuitry, the set of actions.

Abstract: A method includes automatically selecting a prediction horizon used by the predictive model by performing evaluations of model performance at successively narrower ranges of possible prediction horizons until the prediction horizon is determined based on results of the evaluations. The method may also include using the predictive model with the prediction horizon to perform an automated control action, which may include at least one of controlling or monitoring the building equipment.

Abstract: A method for controlling building equipment includes generating synthetic building data including synthetic operating parameters for building equipment that operate to affect one or more conditions of a building space using a generative artificial intelligence model, determining whether the synthetic building data comply with one or more regulations or certification standards by comparing the synthetic operating parameters or a value derived from the synthetic operating parameters against a threshold set by the one or more regulations or certifications standards, and operating the building equipment to affect the one or more conditions of the building space using the synthetic operating parameters in response to determining that the synthetic building data comply with the one or more regulations or certification standards.

Abstract: A method includes obtaining a fault prediction model for building equipment, predicting, with the fault prediction model, both (i) whether a fault will occur during a first prediction bin and (ii) whether a fault will occur during a second prediction bin, performing a first mitigating action for the building equipment if the fault is predicted to occur during the first prediction bin, and performing a second mitigating action for the building equipment if the fault is predicted to occur during the second prediction bin.

Abstract: A method includes providing a net consumption trajectory comprising net consumption targets for one or more subperiods of a time period. Each net consumption target indicates a target difference from a beginning of a time period to an end of the subperiod between total consumption and total production or offset. The method also includes generating, for a subperiod of the plurality of subperiods, a set of curtailment actions predicted to achieve the net consumption target for the subperiod and implementing the set of curtailment actions.

Abstract: A method for operating a temperature control system having a cooling system and ventilation system to vent outside air within a structure is disclosed.