Appliance Status Analysis Device Low Sampling Frequency NILM
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing Non-Intrusive Load Monitoring (NILM) technologies face challenges in obtaining accurate and efficient analysis results in real-world environments due to low sampling rates of electricity usage information.
Innovation Solution
The electrical appliance status analysis device and method categorize appliances into high-correlation and low-correlation types based on correlation coefficients, using different data preprocessing methods and machine learning models for each type to generate appliance status analysis models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If wireless network transmission is used for total electrical load information, then installation cost is reduced and ease of use is improved, but transmission efficiency and signal quality become unstable due to distance and obstructions
Solution Approach 1:
The patent introduces a local server as an intermediary device that receives total electrical load information via wireless network and stores it locally. This mediator bridges the gap between the wireless transmission system and the analysis system, allowing the actual analysis to use locally stored data rather than relying on continuous unstable wireless transmission.
2Loss of energy
If low sampling frequency is used due to transmission limitations, then energy consumption is reduced and transmission stability is improved, but analysis accuracy deteriorates
Solution Approach 1:
The patent segments the analysis process into two distinct pathways: one for high-correlation appliances using raw sequence data and another for low-correlation appliances using feature data. This segmentation allows the system to optimize for each type separately, maintaining high accuracy for both while working within transmission constraints.
Solution Approach 2:
The patent applies different analysis methods tailored to specific appliance types based on their correlation characteristics. High-correlation appliances receive full-precision analysis using sequence data, while low-correlation appliances use feature-based analysis. This local quality approach ensures each appliance type gets the appropriate level of analysis precision.
3Device complexity
If same machine learning model architecture is used for all appliance types, then device complexity is reduced and manufacturing is simplified, but analysis accuracy for different appliance types deteriorates
Solution Approach 1:
The patent implements a dynamic model selection mechanism that automatically chooses between two different analysis approaches based on the correlation coefficient of each appliance type. The system adapts its analysis methodology rather than using a fixed single model, allowing optimal performance across diverse appliance types while maintaining manageable complexity through automated selection.
Data Source
AI summary
An electrical appliance status analysis device and method are provided. Based on the correlation between appliance status sequence data and electricity meter sequence data, appliances are categorized into high-correlation appliances and low-correlation appliances. For high-correlation appliances, training is conducted using the first-type model directly based on the appliance status sequence data and electricity meter sequence data. For low-correlation appliances, features are extracted to produce appliance status feature data and electricity meter feature data, which are then combined with user information feature data to train a second-type model. This method remains applicable at low sampling frequencies. Even when the data sampling rate is below 1 Hz, the resulting appliance status analysis models provide accurate analysis results, addressing the limitations of NILM technology in analyzing data with low sampling frequency.