Abstract: Tools and techniques are described to modify a defined space state depending on number of users in the space and/or preferences of users in the space. In some embodiments, users entering or leaving a space are noticed by network systems. A controller then modifies resources in the space to account for the greater or lesser load. In other cases, the network system notices that a specific user has entered a building. This user may have preferences stored in the system which the building control system then responds to by changing state of a device that controls physical state within the space.

Abstract: Apparatuses, systems, methods, and computer program products are disclosed for organizing automatic control in automation systems from a system description, using deconstruction of complex equipment graphs. A system control scheme is automatically generated from a deconstruction of an equipment graph into controllable sets of prioritized sub-systems. An equipment graph comprises one or more subsystems of equipment. Prioritized sub-systems comprise a unique routing path through an equipment graph. Prioritized sub-systems comprise the ability to be actuated and are divided into groups of sub-system sets. Groups of sub-system sets comprise synchronous and asynchronous sets and are created for conjoined routing paths of parallel sub-systems.

Abstract: Apparatuses, systems, and methods of physical-model based building automation using in-situ regression to optimize control systems are presented. A simulation engine is configured to simulate a behavior or a controlled system using a physical model for the controlled system. A data stream comprises data from a controlled system. A training loop is configured to compare an output of a simulation engine to a data stream using a heuristic so that a physical model is regressed in a manner that the output of the simulation engine approaches the data stream.

Abstract: Tools and techniques are described to attach a device to a controller, whereby the controller analyzes the device inputs, looks up information about the device in a database, and then determines which inputs on the device match the defined device inputs. It then may translate information received from the device into an intermediate language. It may also use the information received from the device, the location of the device, and information about the device to create a digital twin of the device.

Abstract: Apparatuses, systems, methods, and computer program products are disclosed for organizing automatic control in automation systems from a system description, using deconstruction of complex equipment graphs. A system control scheme is automatically generated from a deconstruction of an equipment graph into controllable sets of prioritized sub-systems. An equipment graph comprises one or more subsystems of equipment. Prioritized sub-systems comprise a unique routing path through an equipment graph. Prioritized sub-systems comprise the ability to be actuated and are divided into groups of sub-system sets. Groups of sub-system sets comprise synchronous and asynchronous sets and are created for conjoined routing paths of parallel sub-systems.

Abstract: Apparatuses, systems, and methods of physical-model based building automation using in-situ regression to optimize control systems are presented. A simulation engine is configured to simulate a behavior or a controlled system using a physical model for the controlled system. A data stream comprises data from a controlled system. A training loop is configured to compare an output of a simulation engine to a data stream using a heuristic so that a physical model is regressed in a manner that the output of the simulation engine approaches the data stream.

Abstract: Tools and techniques are described to attach a device to a controller, whereby the controller analyzes the device inputs, looks up information about the device in a database, and then determines which inputs on the device match the defined device inputs. It then may translate information received from the device into an intermediate language. It may also use the information received from the device, the location of the device, and information about the device to create a digital twin of the device.

Abstract: A machine learning optimizer that runs a simulator uses time-state waves as input to determine initial node values for the simulator in an official simulation run, producing time state waves as a result. A learning model uses the input and output as a training example by reversing the time-state waves, using the output from the simulator as input, obtains output, reversed the output, and then uses the reversed output as ground truth to compare to desired output of the simulation.