Abstract: A machine learning method automates the generation of demand response messages to homeowners for utilities. Electric meter data is used to determine a confidence level that the house is occupied so that demand response messages are not sent to unoccupied houses. Demand response messages are associated with a profile. For an initial deployment of a demand response program, a variety of message profiles are tested to study the effectiveness of the communication. After each demand response event, the profile of each message sent to each user is evaluated to learn more effective approaches for future messages. Over time, the learning of the effectiveness of the message profile provides a more precise and complete behavioral model of the user to assess how to motivate energy savings. Continually updating the behavioral model of the user responses to demand response messages increases the likelihood to engage users to participate in demand response events.

Abstract: Energy consumption measurements from an electrical meter associated with the household indicate energy usage over time for the household. A system determines intra-day usage patterns from the energy consumption measurements, determines an occupancy time and assigns a level of confidence to the occupancy time based on a consistency of the intra-day usage patterns, and adjusts the level of confidence based on additional occupancy information.

Abstract: Systems and methods are disclosed to incorporate humidity measurements into the programming of the thermostatic controller to take into account the effect of humidity on comfort and energy efficiency.

Abstract: Systems and methods are disclosed to incorporate manual changes to the setpoint for a thermostatic controller into the programming of the thermostatic controller to take into account the occupants acclimatization to humidity and temperature for comfort and energy efficiency.

Abstract: A machine learning method automates the generation of demand response messages to homeowners for utilities. Electric meter data is used to determine a confidence level that the house is occupied so that demand response messages are not sent to unoccupied houses. Demand response messages are associated with a profile. For an initial deployment of a demand response program, a variety of message profiles are tested to study the effectiveness of the communication. After each demand response event, the profile of each message sent to each user is evaluated to learn more effective approaches for future messages. Over time, the learning of the effectiveness of the message profile provides a more precise and complete behavioral model of the user to assess how to motivate energy savings. Continually updating the behavioral model of the user responses to demand response messages increases the likelihood to engage users to participate in demand response events.

Abstract: Systems and methods are disclosed to adjust HVAC fan delay to reduce energy usage and to maintain comfort levels for occupants of a house. The system receives measurements of inside temperature over time, determines a duration of a previous run cycle of the HVAC system based on the measurements of the inside temperature and settings of the thermostat, determines a change in temperature inside of the house over the previous run cycle, adjusts a duration of the fan delay of a next run cycle based on the duration of the previous run cycle, temperature, change in temperature, and a time of day.

Abstract: Systems and methods for a multi-function thermostat are described. The multi-function thermostat can function as a smart home automation hub. For example, the multi-function thermostat can control smart devices in communication with the multi-function thermostat. The multi-function thermostat can receive sensor information regarding a structure, and control the smart devices based on the sensor information. Additionally, the multi-function thermostat can control the smart devices based on whether a user is present within the structure. User interfaces presented on a display of the multi-function thermostat can be adjusted and/or customized according to the presence of the user.

Abstract: Systems and methods for a multi-function thermostat are described. The multi-function thermostat can function as a smart home automation hub. For example, the multi-function thermostat can control smart devices in communication with the multi-function thermostat. The multi-function thermostat can receive sensor information regarding a structure, and control the smart devices based on the sensor information. Additionally, the multi-function thermostat can control the smart devices based on whether a user is present within the structure. User interfaces presented on a display of the multi-function thermostat can be adjusted and/or customized according to the presence of the user.

Abstract: A method and apparatus for extensible real-time workflows are described. The present invention allows a user of a transaction processing system, such as a customer relationship management (CRM) tool or an automatic call distribution (ACD), for example, to easily add new event sources without recompiling the core workflow server engine of the transaction processing system. The invention also supports features such as the adding of new services, the exchange of events and parameters with other systems, real-time collection and display of workflow statistical information, the use of a centralized configuration database, incremental loading and unloading of workflows and rules, and exception handling.

Abstract: A method and apparatus for extensible real-time workflows are described. The present invention allows a user of a transaction processing system, such as a customer relationship management (CRM) tool or an automatic call distribution (ACD), for example, to easily add new event sources without recompiling the core workflow server engine of the transaction processing system. The invention also supports features such as the adding of new services, the exchange of events and parameters with other systems, real-time collection and display of workflow statistical information, the use of a centralized configuration database, incremental loading and unloading of workflows and rules, and exception handling.

Abstract: A method and apparatus for extensible real-time workflows are described. The present invention allows a user of a transaction processing system, such as a customer relationship management (CRM) tool or an automatic call distribution (ACD), for example, to easily add new event sources without recompiling the core workflow server engine of the transaction processing system. The invention also supports features such as the adding of new services, the exchange of events and parameters with other systems, real-time collection and display of workflow statistical information, the use of a centralized configuration database, incremental loading and unloading of workflows and rules, and exception handling.