LucasNolasco/ST-NILM
ST-NILM is a new integrated architecture based on the Scattering Transform. It has a DCN (Deep Convolutional Network) with analytical wavelet-based non-trained weights, shared with fully connected output networks that perform event detection and multi-label classification of aggregate loads.
This tool helps power utilities or smart home system developers analyze household electricity usage from high-frequency smart meter data. It takes raw electrical waveforms and identifies which appliances are turning on or off, and what type of appliance they are. The output helps understand individual appliance consumption without needing separate meters for each device, allowing for detailed energy monitoring and optimization.
No commits in the last 6 months.
Use this if you need to automatically detect and classify individual appliance events and types from a single aggregate electrical signal, especially when minimizing the required training data is important.
Not ideal if you're looking for a simple plug-and-play solution for basic energy monitoring, or if your electricity data is low-frequency and doesn't capture detailed waveform information.
Stars
12
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Mar 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LucasNolasco/ST-NILM"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
FlexMeasures/flexmeasures
The intelligent & developer-friendly EMS to support real-time energy flexibility apps, rapidly...
ml-energy/zeus
Measure and optimize the energy consumption of your AI applications!
pyaf/load_forecasting
Forecasting electric power load of Delhi using ARIMA, RNN, LSTM, and GRU models
saizk/Deep-Learning-for-Solar-Panel-Recognition
CNN models for Solar Panel Detection and Segmentation in Aerial Images.
FateMurphy/CEEMDAN_LSTM
CEEMDAN_LSTM is a Python project for decomposition-integration forecasting models based on EMD...