POWER USAGE AND RESOURCE OPTIMIZATION USING MACHINE LEARNING

    公开(公告)号:US20240220886A1

    公开(公告)日:2024-07-04

    申请号:US18090284

    申请日:2022-12-28

    申请人: PAYPAL, INC.

    发明人: Adam Inzelberg

    IPC分类号: G06Q10/0631 F24F11/47

    CPC分类号: G06Q10/06312 F24F11/47

    摘要: Various systems, computer-implemented methods, and computer program products are disclosed that use improved machine learning models and techniques for allocating physical resources such as electricity and HVAC systems. These techniques may use data, such as image data, text data, location data, or other similar types of data, indicative of a movement of objects associated with a time period. A machine learning model may extract a first set of features from the data and may determine a physical resource allocation based on the first set of features and a reference dataset. A machine learning model may determine a dynamic configuration of one or more physical resources associated with a physical building space based on the physical resource allocation. These techniques may dynamically configure usage of the one or more physical resources associated with the physical building space based on the physical resource allocation.

    HVAC control system and method
    6.
    发明授权

    公开(公告)号:US12000607B2

    公开(公告)日:2024-06-04

    申请号:US17102929

    申请日:2020-11-24

    申请人: KEPsmart, Inc.

    摘要: A Heating, Ventilation, And Air-Conditioning (HVAC) system comprising: a plurality of external sensors; a plurality of internal sensors; a plurality of valve control boxes; a Smart Metering Unit (SMU) connected to the external sensors, the internal sensors, and the valve control boxes, configured to: receive the sensed data form the external sensors, and the internal sensors; transmit, wirelessly, the received sensed data to a cloud server through a Lobby Control Unit (LCU) over a communication network; receive rules generated by a management platform of the cloud server, wherein the rules are generated by the management platform by using an Artificial Intelligence (AI) algorithm; and transmit the received rules to the plurality of valve control boxes to control the operation of the actuator valves installed at the radiators to turn on and/or turn off a heating and/or a cooling of one or more virtual HVAC zones of the building.

    DYNAMIC VENTILATION CONTROL FOR A BUILDING
    10.
    发明公开

    公开(公告)号:US20240068694A1

    公开(公告)日:2024-02-29

    申请号:US18498856

    申请日:2023-10-31

    摘要: Appropriate ventilation for a building space while maintaining building comfort includes tracking one or more interior environmental conditions within the building space and one or more exterior environmental conditions outside of the building space during operation of the HVAC system. An environmental model for the building space is learned over time based at least in part on these tracked environmental conditions, where the environmental model predicts an environmental state of the building space in response to operation of the HVAC system under various interior and exterior environmental conditions. A maximum allowed ventilation rate that can be achieved without causing the HVAC system to compromise on any of one or more comfort conditions of the building space is predicted using the environmental model. The outdoor air ventilation damper of the HVAC system is then controlled to provide an appropriate ventilation up to or at the predicted maximum allowed ventilation rate.