Thermostat Detection via Energy Usage Pattern Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Residential buildings often consume excessive energy for heating and cooling due to the lack of programmed thermostats, and existing methods to determine the presence and functionality of these thermostats are costly and inefficient, requiring manual surveys or additional hardware.
Innovation Solution
A computer-implemented method that analyzes energy usage data to determine whether a premises has a programmed thermostat by calculating statistical features such as seasonality, trend, and autocorrelation, and classifies the data using clustering and regression models to provide tailored consumer information for reducing energy consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual surveys or additional hardware are used to determine thermostat presence, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent replaces manual survey methods and additional hardware with an automated computational system that analyzes existing energy usage data. Statistical algorithms and machine learning models process utility company data to detect thermostat presence and functionality, eliminating the need for physical site visits or specialized detection equipment.
Solution Approach 2:
The system creates a virtual model of thermostat behavior by analyzing patterns in energy consumption data. Instead of physically detecting the thermostat, the system infers its presence and status by comparing actual energy usage patterns against expected patterns from trained statistical models, effectively creating a digital twin of the thermostat's functional state.
2Loss of information
If manual surveys are conducted to identify unprogrammed thermostats, then information completeness is improved, but loss of time increases
Solution Approach 1:
The system performs preliminary analysis by continuously processing energy usage data in the background using pre-trained statistical models. When data becomes available, the analysis is already complete or near-complete, allowing for immediate identification of unprogrammed thermostats without requiring time-consuming field surveys.
Solution Approach 2:
The system enables utility companies to automatically identify and prioritize customer accounts with unprogrammed thermostats without external intervention. The statistical models self-adjust and refine their detection capabilities over time using historical data, reducing the need for manual verification and follow-up surveys.
3Productivity
If targeted energy efficiency campaigns are implemented, then productivity is improved, but loss of information increases due to selective data usage
Solution Approach 1:
The system applies different analysis methods and data processing techniques to different customer segments based on their specific energy usage patterns. Instead of using a uniform approach for all customers, the statistical models adapt their parameters and thresholds to local characteristics of each premises, improving detection accuracy while maintaining targeted efficiency.
Data Source
AI summary
The disclosure provides a computer-implemented method and system of reducing commodity usage by providing tailored consumer information to the consumer. The method utilizes neural network and machine learning techniques to calculate and cluster statistical data to classify the premises for desired observable condition, including the presence of a programmed thermostat. A score is determined that corresponds to at least one of: (i) a present state of an observable condition, (ii) a non-present state of the observable condition, and (iii) a degree of a condition of the observable condition, to provide tailored consumer information associated to the consumer's usage of the commodity.