A Cloud-Based On-Line Disaggregation Algorithm for Home Appliance Loads

Abstract

In this work, we address the problem of providing fast and on-line households appliance load detection in a nonintrusive way from aggregate electric energy consumption data. Enabling on-line load detection is a relevant research problem as it can unlock new grid services such as demand-side management and raises interactivity in energy awareness possibly leading to more green behaviours.To this purpose, we propose an On-line-NILM (Non-Intrusive Load Monitoring) machine learning algorithm combining two methodologies: i) Unsupervised event-based profiling and ii) Markov chain appliance load modelling. The event-based part performs event detection through contiguous and transient data segments, events clustering and matching. The resulting features are used to build household-specific appliance models from generic appliance models. Disaggregation is then performed on-line using an Additive Factorial Hidden Markov Model from the generated appliance model parameters. Our solution is implemented on the cloud and tested with public benchmark datasets. Accuracy results are presented and compared with literature solutions, showing that the proposed solution achieves on-line detection with comparable detection performance with respect to non on-line approaches.

Non-Intrusive Load Disaggregation by Convolutional Neural Network and Multilabel Classification

“…Furthermore, it is necessary to specify a detail that is relevant to the practical importance of these services. With the exception of the method described in [48], all other methods require knowledge of the consumption of individual equipment throughout the training period for a given user. The application of these methods therefore requires the installation of measuring devices for individual household appliances, and that these have been recording energy consumption throughout the training period.…”

“…Among the supervised techniques, several neural network architectures have been proposed, such as Multi Layer Perceptron (MLP) [29], Convolutional Neural Network (CNN) [30][31][32][33][34][35][36], Recurrent Neural Network (RNN) [30,[37][38][39], Extreme Learning Machine [40], techniques based on Support Vector Machines (SVM) [16,41], K-Nearest Neighbors (kNN) [41,42] naive Bayes classifiers [15], Random Forest classifier [43] and Conditional Random Fields [44]. Among the unsupervised techniques, it was mainly those based on Hidden Markov Model that were used in this field [26,28,[45][46][47][48], although clustering techniques were also used [49,50].…”

Designing Sustainable Smart Cities: Cooperative Energy Management Systems and Applications

“…The use of smart metering data [114,115] collected in a city will provide an important perspective, and the popularization of various measuring devices and home electric appliances with communication functions corresponding to well-established protocols such as ECHONET-Lite [116] or SEP2.0 [117] will further contribute to monitoring the controllable demand. The estimation technique of appliance-wise energy consumption by utilizing the information of aggregated electricity demand collected at a single sensor, the so-called energy disaggregation or nonintrusive appliance load monitoring (NILM) [118][119][120][121][122][123][124][125][126][127][128], will also contribute to further flexible demand-side energy management.…”

Non-Intrusive Load Monitoring via Deep Learning Based User Model and Appliance Group Model

“…The observation in HMM usually refers to power readings or differential power readings, while the hidden states may represent one or a group of appliances. In References [14,23], FHMM has been used for NILM, which contains several independent Markov chains evolving in parallel. Each appliance could be modeled as a single Markov chain in FHMM, and the observation is a joint function of all appliances [23].…”