Occupancy Prediction Using Sensor and User Schedule Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Homeowners face inefficiencies and costs due to maintaining furnace and lighting levels when away, as current systems lack accurate occupancy detection, leading to unnecessary resource consumption.
Innovation Solution
A method and system using sensors to detect occupancy, generate predictive schedules, and request user information to refine the schedule, allowing for adjustments to conserve resources when the building is unoccupied.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the furnace is kept operating at a high level to ensure comfort, then user comfort is maintained, but energy consumption increases and resources are wasted
Solution Approach 1:
The system performs preliminary actions by predicting occupancy patterns in advance and pre-adjusting building parameters (temperature, lighting) before the building is actually unoccupied. This allows the furnace to be adjusted to energy-saving levels before occupants leave, ensuring comfort is restored promptly when they return while minimizing energy waste during absence.
Solution Approach 2:
The system implements feedback by continuously monitoring occupancy sensor data, comparing actual occupancy with predictive schedules, and using this information to dynamically adjust building parameters. User feedback through mobile devices further refines the predictive model, creating a closed-loop system that optimizes energy consumption while maintaining comfort based on actual occupancy patterns.
2Loss of energy
If occupancy detection systems are enhanced to improve accuracy, then energy waste is reduced, but system complexity increases
Solution Approach 1:
The system achieves multi-functionality by combining occupancy detection, predictive scheduling, user interaction via mobile devices, and automated control of multiple building parameters (furnace, lighting) into a single integrated platform. This universal system handles diverse functions through a unified architecture, reducing the need for separate specialized systems while maintaining energy optimization capabilities.
Solution Approach 2:
The system performs self-service by automatically analyzing occupancy sensor data, generating predictive schedules, and adjusting building parameters without requiring manual intervention. The predictive scheduling algorithm autonomously learns occupancy patterns and makes intelligent decisions about when to adjust building parameters, reducing the need for complex manual control systems while achieving energy optimization.
3Use of energy by moving object
If manual thermostat adjustment is used to save costs, then energy consumption is reduced, but user comfort may be compromised
Solution Approach 1:
The system performs preliminary action by predicting when the building will be unoccupied and pre-adjusting the thermostat to energy-saving levels before occupants actually leave. This allows the system to maintain comfortable temperatures during occupied periods while achieving energy savings during unoccupied periods, eliminating the need for manual adjustment and ensuring comfort is never compromised.
Solution Approach 2:
The system replaces manual mechanical thermostat adjustment with an automated electronic control system that uses sensor data and predictive algorithms to automatically adjust building parameters. This substitution eliminates the need for users to physically interact with the thermostat while achieving better optimization through continuous automated monitoring and adjustment based on predicted occupancy patterns.
Data Source
AI summary
Methods and systems are described for determining occupancy with user provided information. According to at least one embodiment, a method for determining occupancy with user provided information includes using at least one sensor to detect occupancy in a building over time, determining a predictive schedule based on the occupancy detected with the at least one sensor, and requesting information relevant to the predictive schedule from a user.