Abstract: Embodiments of the disclosure provide for determination and/or notifying of when an asset requires maintenance. Such embodiments enable outputting notifications in circumstances where tracked data for operations of an asset indicate or are predicted to violate particular thresholds. Some embodiments receive a feedback data set for an asset, identify a command data set for the asset, determine a delay value based at least in part on the feedback data set and the command data set, determine a command-feedback difference value based at least in part on the feedback data set and the command data set, and output a degradation indicator based at least in part on the delay value and the command-feedback difference value.

Abstract: Method, apparatus and computer program product for comfort model extrapolation. For example, the apparatus includes at least one processor and at least one non-transitory memory including program code. The at least one non-transitory memory and the program code are configured to, with the at least one processor, obtain a plurality of known comfort models including: one or more cross-space comfort models each associated with a primary occupant profile and a known spatial element of one or more known spatial elements, one or more cross-profile comfort models each associated with a secondary occupant profile and an unknown spatial element, and one or more cross-context comfort models each associated with a secondary occupant profile and a known spatial element; and generate a unknown comfort model for the primary occupant profile and the unknown spatial element based on the plurality of known comfort models.

Abstract: Methods, devices, and systems for space conditioning based on weather information are described herein. One device includes a memory, and a processor to execute executable instructions stored in the memory to receive forecasted weather information, determine, based on the forecasted weather information, future weather conditions, determine based on the future weather conditions and historical setpoint data, whether conditioning of a space is expected, and generate an alert in response to conditioning of the space being expected.

Abstract: Method, apparatus and computer program product for comfort model extrapolation. For example, the apparatus includes at least one processor and at least one non-transitory memory including program code. The at least one non-transitory memory and the program code are configured to, with the at least one processor, obtain a plurality of known comfort models including: one or more cross-space comfort models each associated with a primary occupant profile and a known spatial element of one or more known spatial elements, one or more cross-profile comfort models each associated with a secondary occupant profile and an unknown spatial element, and one or more cross-context comfort models each associated with a secondary occupant profile and a known spatial element; and generate a unknown comfort model for the primary occupant profile and the unknown spatial element based on the plurality of known comfort models.

Abstract: Various embodiments described herein relate to providing asset behavior modeling. In this regard, a request to obtain one or more asset insights with respect to an asset is received. In response to the request, a model is executed based on sensor data associated with the asset and asset scenario data associated with different operation scenarios for the asset. The model represents predicted asset behavior of the asset to provide the one or more asset insights. Furthermore, in response to the request, one or more actions are performed based on the one or more asset insights.

Abstract: Systems and methods provide techniques for generating natural language data based on telemetry data. In one embodiments, a method includes at least operations configured to receive telemetry data, wherein the telemetry data includes temporal telemetry vectors; process the temporal telemetry vectors using an encoder model in order to generate a feature vector for the telemetry data; and process the feature vector using a decoder model in order to generate the natural language data.

Abstract: Method, apparatus and computer program product for comfort model extrapolation. For example, the apparatus includes at least one processor and at least one non-transitory memory including program code. The at least one non-transitory memory and the program code are configured to, with the at least one processor, obtain a plurality of known comfort models including: one or more cross-space comfort models each associated with a primary occupant profile and a known spatial element of one or more known spatial elements, one or more cross-profile comfort models each associated with a secondary occupant profile and an unknown spatial element, and one or more cross-context comfort models each associated with a secondary occupant profile and a known spatial element; and generate a unknown comfort model for the primary occupant profile and the unknown spatial element based on the plurality of known comfort models.

Abstract: Methods, devices, and systems for space conditioning based on weather information are described herein. One device includes a memory, and a processor to execute executable instructions stored in the memory to receive forecasted weather information, determine, based on the forecasted weather information, future weather conditions, determine based on the future weather conditions and historical setpoint data, whether conditioning of a space is expected, and generate an alert in response to conditioning of the space being expected.

Abstract: Methods, devices, and systems for space conditioning based on weather information are described herein. One device includes a memory, and a processor to execute executable instructions stored in the memory to receive forecasted weather information, determine, based on the forecasted weather information, future weather conditions, determine based on the future weather conditions and historical setpoint data, whether conditioning of a space is expected, and generate an alert in response to conditioning of the space being expected.

Abstract: Methods, devices, and systems for energy consumption modeling are described herein. One device includes a memory, and a processor configured to execute executable instructions stored in the memory to assign energy consumption data to an on state and an off state of a device, generate a model configured to predict a future state of the device and a duration of the future state based on a duration of a current state of the device, a duration of a previous state of the device, and operating conditions of the device, and predict a future energy consumption of the device using the assigned energy consumption data and the generated model.

Abstract: A hydronic heating system that may depend on pressure in the system for smooth operation. The pressure may be monitored. Pressure in the system may indicate health of the heating system. Certain pressures or variations of pressures may indicate one or more conditions in the system which may be good or adverse. An example of an adverse condition may be leakage of fluid from the system. Analyzes of pressures detected in the heating system may be performed by a computer programmed to indicate conditions of the system that are reflected by the detected pressures.

Abstract: Methods, devices, and systems for space conditioning based on weather information are described herein. One device includes a memory, and a processor to execute executable instructions stored in the memory to receive forecasted weather information, determine, based on the forecasted weather information, future weather conditions, determine based on the future weather conditions and historical setpoint data, whether conditioning of a space is expected, and generate an alert in response to conditioning of the space being expected.

Abstract: A system and approach using geofencing events for controlling temperature in a building for comfort of a user upon his or her arrival to the building. A decision may be made when to use a direct trigger by an incoming geofencing event and when to use a time of arrival prediction casted by an outgoing geofencing event. One or more geofences may be placed optimally based on the trigger decision and other aspects related to commuting patterns of the user.

Abstract: A system and approach using geofencing events for controlling temperature in a building for comfort of a user upon his or her arrival to the building. A decision may be made when to use a direct trigger by an incoming geofencing event and when to use a time of arrival prediction casted by an outgoing geofencing event. One or more geofences may be placed optimally based on the trigger decision and other aspects related to commuting patterns of the user.

Abstract: A hydronic heating system that may depend on pressure in the system for smooth operation. The pressure may be monitored. Pressure in the system may indicate health of the heating system. Certain pressures or variations of pressures may indicate one or more conditions in the system which may be good or adverse. An example of an adverse condition may be leakage of fluid from the system. Analyses of pressures detected in the heating system may be performed by a computer programmed to indicate conditions of the system that are reflected by the detected pressures.

Abstract: Methods, devices, and systems for energy consumption modeling are described herein. One device includes a memory, and a processor configured to execute executable instructions stored in the memory to assign energy consumption data to an on state and an off state of a device, generate a model configured to predict a future state of the device and a duration of the future state based on a duration of a current state of the device, a duration of a previous state of the device, and operating conditions of the device, and predict a future energy consumption of the device using the assigned energy consumption data and the generated model.

Abstract: Methods and devices for scheduling operation of residential energy consumption devices are described herein. One device includes a memory and a processor. The processor can be configured to execute executable instructions stored in the memory to form a number of chains of residential energy consumption devices, wherein each of the number of chains includes different devices, determine which of the number of chains has a largest total energy consumption over a particular period of time, and determine, for the devices in the chain having the largest total energy consumption over the particular period of timed of time, an operational schedule having a lowest possible cost.

Abstract: Methods, devices, and systems for energy consumption modeling are described herein. One device includes a memory, and a processor configured to execute executable instructions stored in the memory to assign energy consumption data to an on state and an off state of a device, generate a model configured to predict a future state of the device and a duration of the future state based on a duration of a current state of the device, a duration of a previous state of the device, and operating conditions of the device, and predict a future energy consumption of the device using the assigned energy consumption data and the generated model.

Abstract: Methods, devices, and systems for energy consumption modeling are described herein. One device includes a memory, and a processor configured to execute executable instructions stored in the memory to assign energy consumption data to an on state and an off state of a device, generate a model configured to predict a future state of the device and a duration of the future state based on a duration of a current state of the device, a duration of a previous state of the device, and operating conditions of the device, and predict a future energy consumption of the device using the assigned energy consumption data and the generated model.

Abstract: Methods and devices for scheduling operation of residential energy consumption devices are described herein. One device includes a memory and a processor. The processor can be configured to execute executable instructions stored in the memory to form a number of chains of residential energy consumption devices, wherein each of the number of chains includes different devices, determine which of the number of chains has a largest total energy consumption over a particular period of time, and determine, for the devices in the chain having the largest total energy consumption over the particular period of timed of time, an operational schedule having a lowest possible cost.