HVAC Thermostat Scheduling Using Machine Learning and User Device Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing HVAC systems lack the capability to determine whether a user is present or away without user input, leading to inefficiencies in energy consumption and wear on components, as they cannot automatically adjust set point temperatures without this information.
Innovation Solution
Employing machine learning to predict user behavior and preferences by collecting data from user devices, such as location, network connections, and interactions, to generate a predicted occupancy schedule for adjusting set point temperatures and optimizing energy usage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If the HVAC system automatically adjusts set point temperatures without user input, then energy consumption is reduced and component wear is minimized, but user comfort may be compromised when users are actually present
Solution Approach 1:
The system uses occupancy sensors and user device data as feedback mechanisms to detect whether users are present or away. This feedback loop allows the HVAC system to adjust set point temperatures based on actual occupancy status, reducing energy consumption when spaces are unoccupied while maintaining comfort when users are present. The continuous monitoring and adjustment process resolves the contradiction by making temperature control contingent on real-time occupancy information.
Solution Approach 2:
The system automatically determines occupancy status using sensors and user device data without requiring explicit user input or manual scheduling. This self-service capability enables the HVAC system to autonomously adjust temperatures based on detected occupancy, reducing energy consumption while maintaining comfort through automated decision-making rather than user-provided schedules.
2Loss of energy
If the HVAC system requires users to provide scheduling information in advance, then it can optimize energy savings, but many users never provide this information resulting in lost energy benefits
Solution Approach 1:
The system eliminates the need for users to manually provide scheduling information by automatically determining occupancy status through sensors and user device data. This self-service approach captures energy savings opportunities without requiring user action, as the system independently monitors occupancy and adjusts temperatures accordingly, resolving the contradiction between energy optimization and ease of operation.
Solution Approach 2:
The system introduces intermediary mechanisms (occupancy sensors, user device data collection, and automated processing) that bridge the gap between user presence and HVAC control. These intermediaries automatically extract occupancy information without requiring direct user input, enabling energy savings while maintaining ease of operation by removing the manual scheduling burden from users.
3Reliability
If the HVAC system makes conservative temperature adjustments, then user comfort is maintained, but energy saving benefits are reduced
Solution Approach 1:
The system dynamically adjusts temperature set points based on real-time occupancy status rather than using fixed conservative values. When occupancy is detected, temperatures are maintained for comfort; when unoccupied, temperatures are adjusted aggressively for energy savings. This dynamic approach resolves the contradiction by making temperature control adaptive to actual conditions rather than statically conservative.
Solution Approach 2:
The system performs preliminary temperature adjustments before users return by detecting occupancy status in advance through sensors and user device data. When the system determines users are away, it proactively adjusts temperatures toward energy-saving set points. This preliminary action enables aggressive energy savings while maintaining comfort, as the system prepares temperature adjustments ahead of user arrival rather than reacting conservatively after users return.
Data Source
AI summary
A heating, ventilation, and air conditioning (HVAC) control device configured to collect event data from the one or more devices and to populate time entries in an occupancy history log with the event data. The event data includes a timestamp indicating a time when an event occurred, a set point temperature value for the HVAC system, and an occupancy status indicating whether a space is occupied. The device is further configured to identify blank time entries in the occupancy history log and to populate the blank time entries by forward filling the occupancy history log using event data from another time entry in the occupancy history log. The device is further configured to output the populated occupancy history log.