Control of a heating/cooling system
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing heating and cooling systems in domestic environments face inefficiencies due to difficulties in accurately predicting occupancy habits, leading to energy waste and discomfort, as current methods either require invasive GPS tracking or rely on sparse data that results in erroneous predictions.
Innovation Solution
A method utilizing a Bayesian topic modeling algorithm to forecast domestic environment occupancy routines by analyzing occupancy-related events across multiple users, allowing for precise setting of heating and cooling systems based on shared habits and patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS tracking is used to detect user position for just-in-time heating and cooling, then the accuracy of occupancy detection is improved, but the device complexity and user inconvenience increase due to constant GPS sensor activation
Solution Approach 1:
The patent replaces the mechanical GPS tracking system with a data-driven predictive model. Instead of using physical GPS sensors to continuously track user position, the system uses statistical analysis of historical occupancy data to predict future occupancy patterns. This substitution eliminates the need for complex hardware while maintaining occupancy detection accuracy.
Solution Approach 2:
The patent creates a virtual model of user occupancy patterns by analyzing and storing historical data. This digital copy of occupancy behavior allows the system to predict future occupancy without requiring real-time physical tracking, thereby reducing device complexity while preserving measurement precision.
2Adaptability or versatility
If individual user data is collected separately for each user, then the adaptability to individual habits is improved, but the reliability of predictions decreases due to sparse data with high variance
Solution Approach 1:
The patent merges data from multiple users to create a collective dataset that provides statistical significance. By combining individual occupancy patterns into a pooled dataset, the system maintains the ability to adapt to individual habits while reducing the variance and increasing the reliability of predictions through larger sample sizes.
Solution Approach 2:
The patent performs preliminary data collection and statistical analysis to establish baseline occupancy patterns before making predictions. By pre-processing and pooling data from multiple users in advance, the system ensures that sufficient statistical significance is achieved before individual user predictions are generated, thereby improving reliability.
3Ease of operation
If manual thermostat settings are used based on user occupancy habits, then the ease of operation is improved, but the loss of energy increases because users cannot timely modify settings when occupancy habits change
Solution Approach 1:
The patent implements a feedback mechanism where the system continuously monitors actual occupancy patterns and automatically adjusts thermostat settings accordingly. This closed-loop feedback allows the system to maintain energy efficiency by dynamically modifying settings based on detected changes in occupancy habits, eliminating the energy waste associated with static manual settings.
Solution Approach 2:
The patent enables the heating/cooling system to automatically adjust its own operation based on detected occupancy patterns. The system performs self-service by autonomously modifying thermostat settings without requiring user intervention, thereby maintaining ease of operation while preventing energy waste through timely adaptations to changing occupancy habits.
Data Source
AI summary
A method for controlling a heating/cooling system located at a home of a user. For a population of users, occurrences of occupancy-related events occurring in the users' homes are detected. Then, occurrences of such occupancy-related events in different timeslots are counted separately for each user of the population. The counts of the various users are then merged and a topic model is applied thereto, to provide probabilities that latent habits give raise to certain sequences of occupancy-related events and proportions of each habit in the home occupancy routine of each user of the population. Thereby, a reliable forecast of the home occupancy routine of each user of the population may be provided. That allows setting the heating/cooling system of each user of the population to fit such reliable forecast, minimizing energy waste and/or maximizing user's comfort.