Predictive temperature scheduling for a thermostat using machine learning
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 collect and analyze user behavior data from various devices, such as location, network connections, and interactions, to predict occupancy schedules and adjust set point temperatures for energy savings.
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 decreased, but the system lacks the capability to determine user presence or away status accurately
Solution Approach 1:
The patent introduces multiple intermediary devices (mobile devices, computers, televisions, radios) that generate signals indicating user presence or absence. These intermediaries act as mediators between the user and the HVAC system, allowing the thermostat to infer occupancy status without directly observing the user. The signal generator detects user interactions with these devices and transmits presence/absence information to the HVAC controller.
Solution Approach 2:
The patent replaces manual user input mechanisms (mechanical switches, manual scheduling interfaces) with electronic signal detection and machine learning-based automated inference. The system uses electronic signals from various devices, processes them through algorithms, and automatically determines occupancy status, substituting the need for direct mechanical user interaction with the thermostat.
2Measurement precision
If the HVAC system collects and analyzes user behavior data from multiple devices, then occupancy prediction accuracy is improved, but the device complexity and data processing requirements increase
Solution Approach 1:
The patent makes the HVAC controller multi-functional by enabling it to not only control temperature but also to detect, collect, and process signals from multiple different device types (mobile devices, computers, televisions, radios). The controller universally handles various signal formats and sources, integrating them into a unified occupancy determination process through machine learning algorithms.
Solution Approach 2:
The system performs self-service by automatically collecting data from multiple devices, processing the information through machine learning models, and generating occupancy predictions without requiring external intervention. The HVAC system serves itself by implementing the entire data collection, analysis, and decision-making process internally, eliminating the need for separate dedicated data processing systems.
3Extent of automation
If the system uses machine learning to predict user behavior, then automated temperature adjustment is enabled, but the initial setup and model training require significant user information collection
Solution Approach 1:
The patent implements preliminary action by having the system collect and store user behavior data from multiple devices during an initial period before automated temperature adjustment begins. The machine learning model is trained in advance using this accumulated data, so that when automation starts, the model is already prepared to make accurate predictions. This preliminary data collection and model training phase enables subsequent automated operation without continuous user input.
Data Source
AI summary
A heating, ventilation, and air conditioning (HVAC) control device configured to receive a user input for controlling an HVAC system, to determine whether the user input indicates an energy saving occupancy setting, and to identify a first plurality of time entries that are associated with a confidence level for a predicted occupancy status that is less than a predetermined threshold value in the predicted occupancy schedule. The device is further configured to modify the predicted occupancy schedule by setting the first plurality of time entries to an away status when the user input indicates an aggressive energy saving occupancy setting. The device is further configured to modify the predicted occupancy schedule by setting the second plurality of time entries to a present status when the user input indicates a conservative energy saving occupancy setting. The device is further configured to output the modified predicted occupancy schedule.