Appliance Detection via User Feedback and Dynamic Signatures
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional electric meters cannot provide itemized power consumption information for individual appliances, leading to difficulties in managing and determining power consumption causes, and existing nonintrusive load monitoring (NILM) technologies face challenges in accurately detecting unknown appliances due to varying power consumption signatures across different locations and newly released models.
Innovation Solution
A method and system that utilizes user feedback information to update a dynamic power consumption signature database and employs a search algorithm to automatically detect appliances by calculating confidence factors and weighted values based on voltage and current changes, allowing for accurate identification of appliances and their operating states using a single smart meter.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a power consumption monitoring device is installed at each socket, then individual appliance power consumption information can be obtained, but construction cost increases significantly
Solution Approach 1:
The patent segments the power consumption signal into individual appliance signatures through signal processing techniques. By analyzing transient and steady-state characteristics of the aggregate power signal, the system separates and identifies individual appliance consumption patterns without requiring physical segmentation or multiple sensors.
Solution Approach 2:
The patent introduces an intermediary processing layer (signal processing and analysis algorithms) between the single smart meter and the individual appliances. This intermediary extracts appliance-specific information from the aggregate power consumption signal, enabling individual appliance monitoring through a single measurement point.
2Productivity
If conventional NILM technology uses average power consumption signatures, then detection can be performed, but accuracy decreases for appliances in different locations and newly released models
Solution Approach 1:
The patent implements a dynamic signature database that continuously updates appliance power consumption signatures based on user feedback and new data. The system adapts to newly released appliances and location-specific variations by learning from actual consumption patterns, making the detection system dynamic rather than static.
Solution Approach 2:
The patent incorporates user feedback mechanisms where users confirm or correct appliance identifications. This feedback loop continuously refines and updates the power consumption signature database, improving detection accuracy over time and adapting to new appliance models and location-specific characteristics.
3Measurement precision
If the signature database is updated manually for new appliances, then detection accuracy can be maintained, but time consumption and operational complexity increase
Solution Approach 1:
The patent enables the system to automatically update its own signature database through user feedback and continuous learning. When users confirm appliance identities or provide corrections, the system automatically incorporates this information into the database, eliminating the need for manual intervention in database maintenance.
Solution Approach 2:
The patent performs preliminary signal analysis and appliance identification to prepare candidate matches before user confirmation. By pre-processing and organizing potential appliance identifications, the system reduces the time and effort required for database updates while maintaining high accuracy.
Data Source
Figure 1~2
Figure 3~4
Figure 5
AI summary
A method and system for detecting an appliance based on users' feedback information, particularly a nonintrusive load monitoring method and system based on a user's feedback information and a joint strategic decision search algorithm are disclosed. By means of obtaining the users' feedback information on an appliance inputted by users or a search result of the appliances being confirmed by the users to generate a mapping between the model of the appliances and at least one load signature of each model of appliances; the users' feedback information is recorded into a smart meter or a cloud computing system, and a mathematical analysis is further used to compute an occurrence of any one signature of the appliance and the identification rate of each signature; then the joint strategic decision search algorithm automatically identifies various models of appliances and analyzes the operating states of the electric appliances in homes or offices.