Abstract: A building system including one or more memory devices configured to store instructions that, when executed on one or more processors, cause the one or more processors to collect building device data of a building device, generate a time correlated data stream for a data point, and generate a time correlated reliability data stream for the data point. The building device data includes a plurality of data samples of the data point. The time correlated data stream includes values of the plurality of data samples of the data point. The time correlated reliability data stream includes a plurality of reliability values time correlated to corresponding values of the plurality of data samples of the data point and indicating reliability of the values of the plurality of data samples of the data point.

Abstract: A method for controlling building equipment includes providing an occupancy prediction for a building using an occupancy prediction model that uses both historical values and forecast values of an environmental condition as inputs. The method also includes controlling the building equipment based on the occupancy prediction.

Abstract: A system located in a building. The system including a processing circuit configured to receive tags describing points of a piece of building equipment, the piece of building equipment connected to the system. The processing circuit configured to map the tags to classes of a schema of a graph data structure. The processing circuit configured to perform clustering to generate clusters of the points. The processing circuit configured to identify, based on the clusters, relationships in the schema of the graph data structure between the tags mapped to the classes of the schema of the graph data structure. The processing circuit configured to communicate data to a second system based at least in part on the tags mapped to the classes and the relationships.

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 receive an indication to execute an artificial intelligence (AI) agent of a digital twin, the digital twin including the AI agent and a graph data structure, the graph data structure including nodes representing entities of a building and edges between the nodes representing relationships between the entities of the building. The instructions cause the one or more processors to execute the AI agent based on data of the building to generate an inference that is a prediction of a future data value of a data point of the building for a future time and store at least one of the inference, or a link to the inference, in the graph data structure.

Abstract: Sensorized commercial buildings are a rich target for building a new class of applications that improve operational and energy efficiency of building operations that take into account human activities. Such applications, however, rarely experience widespread adoption due to the lack of a common descriptive schema that would enable porting these applications and systems to different buildings. Our demo presents Brick [4], a uniform schema for representing metadata in buildings. Our schema defines a concrete ontology for sensors, subsystems and relationships among them, which enables portable applications. Using a web application, we will demonstrate real buildings that have been mapped to the Brick schema, and show application queries that extracts relevant metadata from these buildings. The attendees would be able to create example buildings and write their own queries.

Abstract: A building system including one or more storage devices storing instructions thereon that, when executed cause the one or more processors to store a data structure of a digital twin of an entity of a building, execute a learning algorithm to construct a trigger rule and an action rule as an input to the learning algorithm, store the trigger rule and the action rule in the digital twin, determine that the trigger rule of the digital twin is triggered by comparing at least some of the information of the data structure against one or more conditions of the trigger rule by querying the data structure for data values and comparing the data values against the one or more conditions of the trigger rule, determine an action of the action rule of the digital twin responsive to determining that the trigger rule is triggered by executing the action rule, and cause one or more devices to operate based on the action determined by the action rule.

Abstract: A building system including one or more memory devices configured to store instructions that, when executed on one or more processors, cause the one or more processors to collect building device data of a building device, the building device data comprising a plurality of data samples of a data point and generate a time correlated data stream for the data point, the time correlated data stream comprising values of the plurality of data samples of the data point. The instructions cause the one or more processors to generate a time correlated reliability data stream for the data point, the time correlated reliability data stream comprising a plurality of reliability values indicating reliability of the values of the plurality of data samples of the data point.

Abstract: A heating, ventilation, and air conditioning (HVAC) fault prediction system for a building including a processing circuit including a processor and memory, the memory having instructions stored thereon that, when executed by the processor, cause the processing circuit to receive HVAC data relating to a plurality of HVAC components, the HVAC data indicating performance of the plurality of HVAC components, generate, based on the received HVAC data, a univariate prediction model and a multivariate prediction model, generate, using the received HVAC data, one or more predicted operational parameters for the plurality of HVAC components corresponding to a future time period, and execute at least one of the univariate prediction model or the multivariate prediction model on the one or more predicted operational parameters to predict a HVAC fault associated with at least one of the plurality of HVAC components to occur during the future time period.

Abstract: A method of operating a building management system is disclosed. The method includes determining, by a processing circuit, policy rankings for a plurality of control policies based on building operation data of a first previous time period, selecting, by the processing circuit, a set of control policies from among the plurality of control policies based on the policy rankings of the set of control policies satisfying a ranking threshold, generating, by the processing circuit, a plurality of prediction models for the set of control policies, selecting, by the processing circuit, a first prediction model of the plurality of prediction models based on building operation data of a second previous time period, and responsive to selecting the first prediction model, operating, by the processing circuit, the building management system using the first prediction model.

Abstract: A building system operates to receive building data for a building describing one or more conditions of the building and perform a first optimization with a multi-tiered model that predicts a first condition of the building based on a first control setting, the first optimization determining one or more first values of the first control setting. The building system operates to perform a second optimization with the multi-tiered model that predicts a second condition of the building based on a second control setting and the one or more first values of the first control setting, the second optimization determining one or more second values of the second control setting and operate building equipment based on the one or more first values of the first control setting and the one or more second values of the second control setting.

Abstract: A heating, ventilation, and air conditioning (HVAC) fault prediction system for a building including a processing circuit including a processor and memory, the memory having instructions stored thereon that, when executed by the processor, cause the processing circuit to receive HVAC data relating to a plurality of HVAC components, the HVAC data indicating performance of the plurality of HVAC components, generate, based on the received HVAC data, a univariate prediction model and a multivariate prediction model, generate, using the received HVAC data, one or more predicted operational parameters for the plurality of HVAC components corresponding to a future time period, and execute at least one of the univariate prediction model or the multivariate prediction model on the one or more predicted operational parameters to predict a HVAC fault associated with at least one of the plurality of HVAC components to occur during the future time period.

Abstract: Systems and methods for training a reinforcement learning (RL) model for HVAC control are disclosed herein. Simulated experience data for the HVAC system is generated or received. The simulated experience data is used to initially train the RL model for HVAC control. The HVAC system operates within a building using the RL model and generates real experience data. A determination may be made to retrain the RL model. The real experience data is used to retrain the RL model. In some embodiments, both the simulated and real experience data are used to retrain the RL model. Experience data may be sampled according to various sampling functions. The RL model may be retrained multiple times over time. The RL model may be retrained less frequently over time as more real experience data is used to train the RL model.

Abstract: A method for affecting operation of building equipment includes providing a plurality of reliability models that model failure probabilities of components of the building equipment as functions of equipment runtime, providing associations of the components with a plurality of subsystems of the building equipment, calculating, for the plurality of subsystems of the building equipment, probabilities of subsystem failure based on the reliability models for the components and the associations, and initiating an automated action to affect operation of the building equipment based on the probabilities of subsystem failure.

Abstract: A building system including one or more memory devices configured to store instructions that, when executed by one or more processors, cause the one or more processors to receive training data including acronym strings and tag strings, train a sequence to sequence neural network based on the training data, receive an acronym string for labeling, the acronym string comprising a particular plurality of acronyms, and generate a tag string for the acronym string with the sequence to sequence neural network, wherein the sequence to sequence neural network outputs a tag of the tag string for one acronym of the particular plurality of acronyms based on the one acronym and contextual information of the acronym string, wherein the contextual information includes other acronyms of the particular plurality of acronyms.

Abstract: A model management system for building equipment includes one or more memory devices configured to store instructions that, when executed on one or more processors, cause the one or more processors to determine whether fault data exists in equipment data used to generate a plurality of shutdown prediction models for the building equipment, generate a first performance evaluation value for each of the plurality of shutdown prediction models using a first evaluation technique in response to a determination that the fault data exists in the equipment data, generate a second performance evaluation value for each of the plurality of shutdown prediction models using a second evaluation technique in response to a determination that the fault data does not exist in the equipment data, and select one of the plurality of shutdown prediction models based on the first performance evaluation value and the second performance evaluation value.

Abstract: A building system for training a prediction model with augmented training data. The building system comprising one or more memory devices configured to store instructions thereon that, when executed by one or more processors, cause the one or more processors to obtain a first training data set comprising data values associated with a data point of the building system and with a plurality of time-steps and energy values associated with consumption of the building system at each of the plurality of time-steps; generate an augmented training data set comprising a second training data set, the second training data set comprising the energy values and the data values of the first training data set but with a data value replaced with a predetermined value at a time-step of the plurality of time-steps; and generate a prediction model by training 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: 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 includes training a conditional generator by operating a generative adversarial network that includes the conditional generator, generating, by the conditional generator, synthetic timeseries data corresponding to a plurality of fault types, wherein labels for the plurality of fault types are used as inputs to the conditional generator, training a fault prediction model using the synthetic timeseries data, and predicting a fault for building equipment by applying the fault prediction model to real timeseries data relating to the building equipment.

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.