Energy Load Segmentation for HVAC Malfunction Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Residential households face difficulties in identifying the cause of abnormally high electricity usage, often due to equipment malfunctions, particularly in HVAC systems, which are the largest energy consumers, making it challenging to detect and address these issues without professional assistance.
Innovation Solution
A customized analytical algorithmic process using smart meter data, regression analysis, and machine learning clustering algorithms to disaggregate energy loads and identify patterns of high energy usage, flagging potential equipment malfunctions, and prioritizing manual diagnostics for households with significant issues.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional monitoring methods are used, then equipment malfunctions can be detected, but the complexity of the system increases and requires professional assistance
Solution Approach 1:
The system enables households to autonomously monitor and diagnose their own equipment malfunctions using smart meter data and automated algorithms. The diagnostic system performs self-assessment of energy usage patterns, identifies anomalies, and flags potential issues without requiring external professional intervention for the detection phase, thus reducing system complexity while maintaining reliability
Solution Approach 2:
The patent replaces complex mechanical monitoring systems with data-driven computational methods. Instead of using sophisticated sensors and mechanical diagnostic tools, the system uses automated algorithms analyzing electrical signal patterns from standard smart meters to detect equipment malfunctions, thereby reducing hardware complexity while improving detection capability
2Reliability
If comprehensive monitoring of all energy usage is implemented, then all equipment issues can be detected, but the difficulty of detecting and measuring specific malfunctions increases
Solution Approach 1:
The system segments the overall energy consumption into distinct components: base load, variable load, and temperature-dependent load. By separating HVAC-related consumption from other household appliances through this segmentation, the system simplifies the detection of HVAC-specific malfunctions while maintaining comprehensive monitoring coverage of all energy usage
Solution Approach 2:
The patent introduces temperature data as an intermediary variable to mediate between total energy consumption and HVAC equipment status. By correlating energy usage patterns with outdoor temperature data, the system can isolate and identify HVAC-related anomalies without directly measuring HVAC equipment parameters, thereby reducing detection difficulty
3Reliability
If manual diagnostics are performed on all households with high energy usage, then all malfunctions can be identified, but the loss of time increases
Solution Approach 1:
The system performs partial automated diagnostics on all households with high energy usage patterns, flagging only those with confirmed equipment malfunctions for manual inspection. This partial action approach filters out false positives and normal variations, so that manual diagnostics are applied only to a subset of cases that truly require human intervention, thereby reducing overall diagnostic time while maintaining high identification reliability
Solution Approach 2:
The system performs preliminary automated analysis of energy usage patterns, temperature correlations, and load segmentation before referring cases for manual diagnostics. This preliminary action pre-screens and prioritizes households, ensuring that manual diagnostic resources are allocated to cases with the highest probability of equipment malfunction, thus minimizing time loss
Data Source
AI summary
A computer system that includes a processor device and a storage device is configured to determine a base load at a utility customer site using power usage data for the utility customer site, to determine a variable load at the utility customer site during a range of temperature independent days using the power usage data, and to determine a temperature dependent load at the utility customer site that exceeds the variable load and the base load using the power usage data. The computer system is further configured to assign a flag to each time interval that the temperature dependent load exceeds a power usage threshold and to determine if the utility customer site has an equipment malfunction based on a number of the flags assigned within a time period.