Neural NILM: Deep Neural Networks Applied to Energy Disaggregation

Abstract

Energy disaggregation estimates appliance-by-appliance electricity consumption from a single meter that measures the whole home's electricity demand. Recently, deep neural networks have driven remarkable improvements in classification performance in neighbouring machine learning fields such as image classification and automatic speech recognition. In this paper, we adapt three deep neural network architectures to energy disaggregation: 1) a form of recurrent neural network called `long short-term memory' (LSTM); 2) denoising autoencoders; and 3) a network which regresses the start time, end time and average power demand of each appliance activation. We use seven metrics to test the performance of these algorithms on real aggregate power data from five appliances. Tests are performed against a house not seen during training and against houses seen during training. We find that all three neural nets achieve better F1 scores (averaged over all five appliances) than either combinatorial optimisation or factorial hidden Markov models and that our neural net algorithms generalise well to an unseen house.

To appear in ACM BuildSys'15, November 4--5, 2015, Seoul

References in corpus (5)

• Sequence to Sequence Learning with Neural Networks
• The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes
• Theano: new features and speed improvements
• NILMTK: An Open Source Toolkit for Non-intrusive Load Monitoring
• End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results

Cited by in corpus (53)

• Scale- and Context-Aware Convolutional Non-intrusive Load Monitoring
• Sequence-to-point learning with neural networks for nonintrusive load monitoring
• A Survey on Non-Intrusive Load Monitoring Methodies and Techniques for Energy Disaggregation Problem
• Improving Non-Intrusive Load Disaggregation through an Attention-Based Deep Neural Network
• Trimming Feature Extraction and Inference for MCU-based Edge NILM: a Systematic Approach
• On the Feasibility of Generic Deep Disaggregation for Single-Load Extraction
• Unsupervised algorithm for disaggregating low-sampling-rate electricity consumption of households
• Mixed-Integer Nonlinear Programming for State-based Non-Intrusive Load Monitoring
• A Step towards Advanced Metering for the Smart Grid: A Survey of Energy Monitors
• Neural Network Ensembles to Real-time Identification of Plug-level Appliance Measurements
• IoT-based Analysis for Smart Energy Management
• Subtask Gated Networks for Non-Intrusive Load Monitoring
• Transfer Learning for Non-Intrusive Load Monitoring
• Appliance Detection Using Very Low-Frequency Smart Meter Time Series
• NILM as a regression versus classification problem: the importance of thresholding
• Non-Intrusive Load Monitoring with Fully Convolutional Networks
• A Comprehensive Review on the NILM Algorithms for Energy Disaggregation
• A Federated Learning Framework for Non-Intrusive Load Monitoring
• Energy Efficient Deep Multi-Label ON/OFF Classification of Low Frequency Metered Home Appliances
• NILMFormer: Non-Intrusive Load Monitoring that Accounts for Non-Stationarity
• Deep Learning Based Energy Disaggregation and On/Off Detection of Household Appliances
• Neighbourhood NILM: A Big-data Approach to Household Energy Disaggregation
• Structured Dictionary Learning for Energy Disaggregation
• Sequence-to-Sequence Load Disaggregation Using Multi-Scale Residual Neural Network
• COLD: Concurrent Loads Disaggregator for Non-Intrusive Load Monitoring
• Towards Data-Driven Electricity Management: Multi-Region Harmonized Data and Knowledge Graph
• Neural Network for NILM Based on Operational State Change Classification
• FederatedNILM: A Distributed and Privacy-preserving Framework for Non-intrusive Load Monitoring based on Federated Deep Learning
• Exploration of Superposition Theorem in Spectrum Space for Composite Event Analysis in an ADN
• Data augmentation for dealing with low sampling rates in NILM
• PowerGAN: Synthesizing Appliance Power Signatures Using Generative Adversarial Networks
• Optimising Parameters in Recurrence Quantification Analysis of Smart Energy Systems
• End-to-end NILM System Using High Frequency Data and Neural Networks
• A Data-Efficient Approach to Behind-the-Meter Solar Generation Disaggregation
• On Metrics to Assess the Transferability of Machine Learning Models in Non-Intrusive Load Monitoring
• Exploring Bayesian Surprise to Prevent Overfitting and to Predict Model Performance in Non-Intrusive Load Monitoring
• Simultaneous Detection of Multiple Appliances from Smart-meter Measurements via Multi-Label Consistent Deep Dictionary Learning and Deep Transform Learning
• Particle Swarm Optimization for Energy Disaggregation in Industrial and Commercial Buildings
• Conv-NILM-Net, a causal and multi-appliance model for energy source separation
• Energy Injection Identification enabled Disaggregation with Deep Multi-Task Learning
• A Deep Learning Technique using Low Sampling rate for residential Non Intrusive Load Monitoring
• Few Labels are all you need: A Weakly Supervised Framework for Appliance Localization in Smart-Meter Series
• More Behind Your Electricity Bill: a Dual-DNN Approach to Non-Intrusive Load Monitoring
• Adversarial Energy Disaggregation for Non-intrusive Load Monitoring
• PHASED: Phase-Aware Submodularity-Based Energy Disaggregation
• Smart Monitoring: remote-monitoring technology of power, gas, and water consumption in Smart Cities
• Nonintrusive Load Monitoring for Machines used in Manufacturing
• Non-intrusive Load Monitoring via Multi-label Sparse Representation based Classification
• Automated Machine Learning: A Case Study on Non-Intrusive Appliance Load Monitoring
• Analysis Co-Sparse Coding for Energy Disaggregation
• Prior Flow Variational Autoencoder: A density estimation model for Non-Intrusive Load Monitoring
• Energy Disaggregation with Semi-supervised Sparse Coding
• Hawk: An Efficient NALM System for Accurate Low-Power Appliance Recognition