Heating, ventilation, and air conditioning system control using adaptive occupancy scheduling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing HVAC systems rely on user-provided scheduling information to determine occupancy, which is not always available, preventing them from automatically adjusting set point temperatures for energy savings and comfort, as they lack the ability to predict user presence or absence without user input.
Innovation Solution
An adaptive HVAC control system that uses machine learning to predict user absence and return times based on historical occupancy patterns, allowing it to adjust temperatures for energy savings and comfort without user input, by training a model with occupancy history and set point temperature data to determine optimal settings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If existing HVAC systems rely on user-provided scheduling information to determine occupancy, then they can adjust set point temperatures for energy savings, but they cannot operate effectively when users do not provide this information
Solution Approach 1:
The HVAC system uses machine learning models to automatically learn and predict user occupancy patterns from historical data, enabling the system to self-determine when users are present or away without requiring direct user input. This allows the system to autonomously adjust temperatures for energy savings while adapting to individual user behaviors.
2Loss of energy
If HVAC systems automatically adjust set point temperatures without knowing user presence, then energy savings can be achieved, but user comfort may be affected
Solution Approach 1:
The system incorporates user feedback mechanisms where users can indicate when the system's occupancy predictions are incorrect. This feedback is used to retrain and improve the machine learning models, ensuring that temperature adjustments align with actual user presence and maintain comfort while achieving energy savings.
3Measurement precision
If HVAC systems require user input for scheduling information, then accurate occupancy data can be obtained, but user convenience is reduced
Solution Approach 1:
The system automatically collects and analyzes historical occupancy data from various sources (motion sensors, user device locations, calendar events) to build predictive models without requiring users to manually provide scheduling information. This eliminates the burden of user input while maintaining accurate occupancy determination through pattern recognition.
Data Source
AI summary
An adaptive Heating, Ventilation, and Air Conditioning (HVAC) control device configured to identify timestamps over a time period when a space is unoccupied, to identify a set point temperature for each timestamp, and to train a machine learning model using the timestamps and corresponding set point temperatures. The device is further configured to determine a timestamp that corresponds with the current day, to input the timestamp into the machine learning model, and to obtain HVAC control settings from the machine learning model in response to inputting the timestamp into the machine learning model. The HVAC control settings include a return time and a set point temperature. The device is further configured to operate the HVAC system at the set point temperature until the return time.