Non-Intrusive Load Monitoring Toolkit (nilmtk)

A repository of awesome Non-Intrusive Load Monitoring(NILM) with code.

The super-state hidden Markov model disaggregator that uses a sparse Viterbi algorithm for decoding. This project contains the source code that was use for my IEEE Transactions on Smart Grid journal paper.

An Non-Intrusive Load Disaggregation method based on Neural Network. A sequence-to-sequence model and a sequence-to-point model are proposed.

A new CNN architecture to perform detection, feature extraction, and multi-label classification of loads, in non-intrusive load monitoring (NILM) approaches, with a single model for high-frequency signals.

⚠️ This repository is no longer actively maintained. It previously dealt with Non-Intrusive Load Monitoring (NILM), focusing on predicting household appliance status from aggregated power load data. We explored different thresholding methods and evaluated deep learning models for regression and classification tasks.

A reimplementation of Jack Kelly's rectangles neural network architecture based on Keras and the NILMToolkit.

Electrical Devices Identification Model (EDIM) for the identification of electrical devices by analyzing their energy consumption profiles.

Overview of research papers with focus on low frequency NILM employing DNNs

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.

An aided linear integer programming (ALIP) non-intrusive load monitoring (NILM) algorithm.

NILM performance evaluation functions use in the Springer Energy Efficiency journal paper.

Supervised NILM using multiple-choice knapsack problem (MCKP).

The AMBAL-based NILM Trace generator (for NILMTK)

Master's Dissertation: Unsupervised Low-Frequency NILM for Industrial Loads

This repository is the code basis for the paper titled "Using Deep Learning and Knowledge Transfer to Disaggregate Energy Consumption"

The C++ code for my Computing MSc energy disaggregation project

WaveNILM as published at ICASSP 2019

Complete set of electrical parameters, including energy consumption, power quality, and all harmonic contents (up to 2kHz). Time-synchronous data reported from real buildings and appliances at 1 second intervals.