Ensemble Machine Learning for Non-Intrusive Load Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-intrusive load monitoring (NILM) and disaggregation of energy usage in households are challenging due to the variety of devices and limited availability of labeled data sets, making it difficult to accurately predict energy usage of target devices like electric vehicles and large appliances from general household energy usage.
Innovation Solution
The use of ensemble machine learning techniques, including multiple trained machine learning models, to predict and disaggregate energy usage of target devices from total source location energy usage, leveraging labeled data and incorporating energy usage patterns from other devices to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional single machine learning models are used for NILM, then the system complexity remains low, but the prediction accuracy deteriorates due to limited labeled data and device diversity
Solution Approach 1:
The patent divides the NILM task into two separate machine learning models: a disaggregation model that predicts energy consumption amounts and a detection model that identifies device states. This segmentation allows each model to specialize in one aspect, improving overall prediction accuracy while managing complexity through functional decomposition
Solution Approach 2:
The patent combines multiple trained machine learning models into an ensemble system that integrates their predictions. By merging the disaggregation model and detection model outputs, the system achieves higher prediction accuracy than individual models could provide alone, resolving the contradiction between accuracy and complexity
2Measurement precision
If more labeled data is collected to improve model training, then the prediction accuracy improves, but the data collection time and resources increase
Solution Approach 1:
The patent performs preliminary training of multiple specialized machine learning models using available labeled data before deployment. The models are pre-trained on disaggregation and detection tasks separately, allowing the system to achieve high prediction accuracy without requiring extensive data collection during actual operation
Solution Approach 2:
The patent changes the training parameters by using different labeled data sets for different model components. The disaggregation model is trained with energy consumption labels while the detection model uses device state labels, maximizing the utility of limited labeled data and improving accuracy without requiring proportional increases in data collection time
Data Source
AI summary
Embodiments implement non-intrusive load monitoring using ensemble machine learning techniques. A first trained machine learning model configured to disaggregate target device energy usage from source location energy usage and a second trained machine learning model configured to detect device energy usage from source location energy usage can be stored, where the first trained machine learning model is trained to predict an amount of energy usage for the target device and the second trained machine learning model is trained to predict when a target device has used energy. Source location energy usage over a period of time can be received, where the source location energy usage includes energy consumed by the target device. An amount of disaggregated target device energy usage over the period of time can be predicted, using the first and second trained machine learning models, based on the received source location energy usage.