Occupancy Prediction Using Historical Patterns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing home heating systems lack the ability to accurately predict occupancy, leading to inefficient heating as they operate based on pre-set schedules rather than actual occupancy, resulting in energy wastage and discomfort.
Innovation Solution
A method and system for predicting occupancy using historical occupancy patterns by analyzing sensor data to generate a table of past occupancy, comparing recent patterns to similar historical patterns to calculate an occupancy probability for future times, allowing for automated adjustments in heating and other systems based on predicted occupancy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If heating is operated based on pre-set schedules, then the heating system is simple to operate, but energy is wasted when the home is unoccupied
Solution Approach 1:
The system automatically learns and adapts to occupancy patterns without requiring user programming. Sensors detect when the home is occupied or unoccupied, and the controller autonomously adjusts heating operations based on this data, eliminating the need for manual schedule programming while preventing energy waste during unoccupied periods
Solution Approach 2:
The system uses sensor data to provide feedback about actual occupancy conditions to the controller. This feedback loop enables the system to continuously learn from patterns of occupancy and unoccupancy, dynamically adjusting heating operations to match actual usage rather than following fixed predetermined schedules
2Device complexity
If heating is operated based on pre-set schedules, then the system requires minimal programming, but the home may not be warm when occupants are absent or too warm when unnecessary
Solution Approach 1:
The system performs self-programming by automatically learning occupancy patterns from sensor data over time. The controller builds a digital model of when the home is typically occupied or unoccupied without requiring user input, thereby simplifying operation while improving heating reliability by basing decisions on actual rather than assumed patterns
Solution Approach 2:
The system transitions from static predetermined schedules to dynamic adaptive scheduling. The heating operations continuously adapt based on learned occupancy patterns, allowing the system to respond to changing conditions and improve reliability over time while requiring minimal user programming
3Temperature
If intelligent thermostats with variable set point temperatures are used, then temperature control is improved, but occupancy prediction capability is insufficient
Solution Approach 1:
The system replaces simple time-based control mechanisms with sensor-based occupancy detection and pattern recognition algorithms. Instead of relying solely on predetermined temperature schedules, the system uses sensor data to accurately determine actual occupancy conditions, thereby improving prediction accuracy while maintaining temperature control capabilities
Data Source
AI summary
Methods and systems for occupancy prediction using historical occupancy patterns are described. In an embodiment, an occupancy probability is computed by comparing a recent occupancy pattern to historic occupancy patterns. Sensor data for a room, or other space, is used to generate a table of past occupancy which comprises these historic occupancy patterns. The comparison which is performed identifies a number of similar historic occupancy patterns and data from these similar historic occupancy patterns is combined to generate an occupancy probability for a time in the future. In an example, time may be divided into discrete slots and binary values may be used to indicate occupancy or non-occupancy in each slot. An occupancy probability for a defined future time slot then comprises a combination of the binary values for corresponding time slots from each of the identified similar occupancy patterns.