Abstract: Tools and techniques are described to automate line testing when wiring devices (such as equipment and sensors) to controllers. Controllers have access to databases of the devices that are controlled by them, including wiring diagrams and protocols, such that the controller can automatically check that each wire responds correctly to stimulus from the controller. After testing, a reporting device rapidly shows the results of the line testing.

Abstract: A simulator is run using a learning model to generate starting values for the nodes in the simulator. After the simulation has run, a cost is determined for the run. When the cost is within a threshold, the learning model results are used as starting values for an optimizer that will be used to generate starting values for the nodes in the simulator. Then, the optimizer is iteratively run such that for each iteration, results of running the optimizer are used as training input into the learning model.

Abstract: Various embodiments relate to a method, controller, and machine-readable storage medium for verifying controlled devices attached to the controller including one or more of the following: selecting, using a system model that models a system of devices comprising the controlled devices attached to the controller, a grouping of the system of devices to be tested; conducting a test of the grouping to produce a test result for the grouping, wherein conducting the test comprises transmitting a communication to at least one device associated with the grouping; choosing a graphical representation of a portion of the system model from a plurality of graphical representations based on the graphical representation including a representation of the grouping; and displaying, on a user interface, the graphical representation and an indication of the test result.

Abstract: Tools and techniques are described to automate line testing when wiring devices (such as equipment and sensors) to controllers. Controllers have access to databases of the devices that are controlled by them, including wiring diagrams and protocols, such that the controller can automatically check that each wire responds correctly to stimulus from the controller. After testing, a reporting device rapidly shows the results of the line testing.

Abstract: Tools and techniques are described to automate commissioning of physical spaces. Controllers have access to databases of the devices that are controlled by them, including wiring diagrams and protocols, such that the controller can automatically check that each wire responds correctly to stimulus from the controller. Controllers also have access to databases of the physical space such that they can check that sensors in the space record the correct information for device activity, and sensors can cross-check each other for consistency. Once a physical space is commissioned, incentives can be sought based on commissioning results.

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: 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: Various embodiments disclosed herein relate to a building automation controller and related method and storage medium including a processor configured, through at least execution of a distributed computer program, to: receive sensor data generated by a sensor, wherein the sensor data is indicative of a state of a defined space, identify an action to be performed by a device to affect the state in accordance with an operating characteristic for the defined space, determine that the device is attached to a second controller of a plurality of additional controllers, and transmit to the second controller, an indication that the action is to be performed by the device, wherein: the distributed computer program is configured to be distributed among the processor and the plurality of additional controllers and, the processor is further configured to apportion work to be performed by the computer program between at least the additional controllers.

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: Controllers that control a building's state functions can be controlled by a master controller that the controllers choose themselves. The master controller communicates with the controllers and sensors to determine when a building state should change. When the building state should change, the master controller or another controller determines the device or devices that need to modify state values of the building, and send messages to the devices so that they can change building state. If the master controller has a fault, the working controllers can choose another master controller. When a sensor indicates that a building state needs to be changed the master controller determines which device should change state, then tells the controller that is attached to the device.

Abstract: Tools and techniques are described to create a controller wiring board. A user, using a user interface associated with a controller, can determine which devices will be attached to a controller. The features of the devices may be already known by the controller. The controller can change wiring terminal types depending on the requirements of the devices wired to the controllers. In some embodiments, a device is wired to a module associated with the controller. The controller can signal to the module to modify its wiring terminal to match the needs of the device to be wired to that location.

Abstract: Tools and techniques are described to create a controller wiring board. A user, using a user interface associated with a controller, can determine which devices will be attached to a controller. The features of the devices may be already known by the controller. The controller can change wiring terminal types depending on the requirements of the devices wired to the controllers. In some embodiments, a device is wired to a module associated with the controller. The controller can signal to the module to modify its wiring terminal to match the needs of the device to be wired to that location.

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: Heterogenous neural networks are disclosed that have neurons that represent objects in the real world or linked functions. The neurons have input and output that represent the movement of variables between the functions; their locations in the neural net represents actual object location or function location in terms of the other functions. Multiple types of inputs can be set up such that during backpropagation, only a subset of the possible inputs are backpropagated to. The activation functions of the neurons represent the physical behavior of the objects in the real world.