Thermostat Machine Learning for Predictive Occupancy Scheduling
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, hindering energy-saving benefits and component wear reduction due to inability to automatically adjust set point temperatures.
Innovation Solution
Employing machine learning to collect and analyze user behavior data from various devices, predicting occupancy schedules to adjust set point temperatures for energy savings and reducing wear on HVAC components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If the HVAC system automatically adjusts set point temperatures without user input, then energy saving benefits and component wear reduction are improved, but user comfort may deteriorate if adjustments are made while users are present
Solution Approach 1:
The system performs preliminary actions by predicting user occupancy status in advance using machine learning models trained on historical data from multiple devices. This allows the HVAC system to proactively adjust temperatures before users arrive or leave, ensuring energy savings are achieved without compromising comfort during occupied periods
Solution Approach 2:
The system implements feedback mechanisms by continuously collecting data from multiple devices (smartphones, tablets, computers, televisions) and using machine learning to analyze user behavior patterns. This feedback loop enables the system to learn from actual user presence and adjust predictions, thereby improving both energy efficiency and comfort over time
2Measurement precision
If the HVAC system collects and analyzes data from multiple user devices, then prediction accuracy is improved, but device complexity and data processing requirements increase
Solution Approach 1:
The system applies universality by using a single machine learning framework that can process data from multiple different device types (smartphones, tablets, computers, televisions). This multi-functional approach allows the same predictive model to leverage diverse data sources without requiring separate systems for each device type, thereby improving prediction accuracy while managing complexity through a unified architecture
Solution Approach 2:
The machine learning model serves as an intermediary that mediates between raw data from multiple devices and the HVAC control system. This intermediary layer processes, integrates, and analyzes data from various sources, transforming complex multi-device data into actionable occupancy predictions without requiring direct complex interactions between all devices and the HVAC system
Data Source
AI summary
A heating, ventilation, and air conditioning (HVAC) control device configured to generate the machine learning model using the first set of weights and the second set of weights. The machine learning model is configured to output a probability that a user is present at the space based on an input that identifies a day of the week and a time of a day. The device is further configured to determine a probability that a user is present at the space for a predicted occupancy schedule using the machine learning model, to determine an occupancy status based on a determined probability that a user is present at the space, and to set a predicted occupancy status in the predicted occupancy schedule based on a determined occupancy status for each time entry. The device is further configured to output the predicted occupancy schedule.