Thermostat Occupancy Prediction Correction for HVAC Setpoint Control
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, interactions, and network connections to generate a predicted occupancy schedule, allowing the HVAC system to adjust temperatures for energy savings and reduce wear.
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 the user's comfort level may be affected when the user is actually present
Solution Approach 1:
The system performs preliminary actions by adjusting temperatures in advance based on predicted occupancy. The machine learning model predicts when users will be away, and the HVAC system proactively adjusts temperatures before the user leaves, ensuring energy savings are achieved without compromising comfort when users are actually present.
Solution Approach 2:
The system implements feedback by continuously monitoring actual occupancy data and comparing it with predicted occupancy. When discrepancies are detected (e.g., user is present but predicted as away), the system learns from this feedback and corrects its predictions, thereby improving both energy efficiency and user comfort over time.
2Measurement precision
If the HVAC system requires user input for scheduling information, then accurate occupancy data is obtained, but users may never provide this information leading to system inefficiency
Solution Approach 1:
The system practices self-service by automatically collecting occupancy data from various sources (mobile device locations, network connections, smart home devices) without requiring explicit user input. The machine learning model processes this collected data to generate accurate occupancy predictions, making the system both easy to operate and data-accurate.
Solution Approach 2:
The system uses intermediary data sources such as mobile device locations, network connection types, and interactions with other smart home devices to indirectly determine occupancy status. These intermediaries provide the occupancy information needed for accurate temperature adjustment without requiring direct user input about their schedules.
3Loss of energy
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 the confidence level of occupancy predictions. When the machine learning model is highly confident that users are away, the system makes aggressive temperature adjustments for maximum energy savings. When confidence is lower or occupancy is uncertain, the system makes conservative adjustments to maintain comfort, thereby adapting its flexibility to the situation.
Data Source
AI summary
A heating, ventilation, and air conditioning (HVAC) control device is configured to record a plurality of actual occupancy statuses, to determine a plurality of corresponding predicted occupancy statuses, and to compare the plurality of predicted occupancy statuses to the plurality of actual occupancy statuses. The device is further configured to identify conflicting occupancy statuses based on the comparison. A conflicting occupancy status indicates a difference between an actual occupancy status and a corresponding predicted occupancy status. The device is further configured to identify timestamps corresponding with the conflicting occupancy statuses, to identify historical occupancy statuses corresponding with the identified timestamps, and to update the conflicting occupancy statuses in the predicted occupancy schedule with the historical occupancy statuses.