Phased: Phase-Aware Submodularity-Based Energy Disaggregation

  title={Phased: Phase-Aware Submodularity-Based Energy Disaggregation},
  author={Faisal M. Almutairi and Aritra Konar and Ahmed S. Zamzam and Nicholas D. Sidiropoulos},
  journal={Proceedings of the 5th International Workshop on Non-Intrusive Load Monitoring},
Energy disaggregation is the task of discerning the energy consumption of individual appliances from aggregated measurements, which holds promise for understanding and reducing energy usage. In this paper, we propose PHASED, an optimization approach for energy disaggregation that has two key features: PHASED (i) exploits the structure of power distribution systems to make use of readily available measurements that are neglected by existing methods, and (ii) poses the problem as a minimization… 

Figures and Tables from this paper

P: Phase-Aware Submodularity-Based Energy Disaggregation
P is proposed, an optimization approach for energy disaggregation that exploits the structure of power distribution systems to make use of readily available measurements that are neglected by existing methods and poses the problem as a minimization of a dierence of submodular functions.


Scalable Energy Disaggregation Via Successive Submodular Approximation
This paper proposes a supervised, non-parametric framework for energy disaggregation and demonstrates that the problem is equivalent to maximizing a set-function subject to combinatorial constraints, which is NP-hard in its general form.
Energy Disaggregation via Discriminative Sparse Coding
This paper develops a method, based upon structured prediction, for discriminatively training sparse coding algorithms specifically to maximize disaggregation performance, and demonstrates how these disaggregation results can provide useful information about energy usage.
Structured Dictionary Learning for Energy Disaggregation
H hierarchical methods are designed to replace the task of overall energy disaggregation among the devices with a recursive disaggregation task involving device subgroups, and show that these methods lead to improved performance as compared to baseline.
REDD : A Public Data Set for Energy Disaggregation Research
The Reference Energy Disaggregation Data Set (REDD), a freely available data set containing detailed power usage information from several homes, is presented, aimed at furthering research on energy disaggregation.
Energy Disaggregation via Learning Powerlets and Sparse Coding
A new supervised algorithm is proposed, which in the learning stage, automatically extracts signature consumption patterns of each device by modeling the device as a mixture of dynamical systems, and forms a dictionary that consists of extracted power signatures across all devices.
Non-Intrusive Energy Disaggregation Using Non-Negative Matrix Factorization With Sum-to-k Constraint
An approach based on Sum-to-k constrained non-negative matrix factorization (S2K-NMF) is proposed, which is able to effectively extract perceptually meaningful sources from complex mixtures.
A Survey on Non-Intrusive Load Monitoring Methodies and Techniques for Energy Disaggregation Problem
An up to date overview of NILM system and its associated methods and techniques for energy disaggregation problem is presented and the review of the state-of-the art NILm algorithms are reviewed.
Towards reproducible state-of-the-art energy disaggregation
A rewrite of the disaggregation API and a new experiment API are described which lower the barrier to entry for algorithm developers and simplify the definition of algorithm comparison experiments, and the release of NILMTK-contrib is described; a new repository containing NIL MTK-compatible implementations of 3 benchmarks and 9 recent disaggregation algorithms.
Data Requirements for Applying Machine Learning to Energy Disaggregation
NILM performance can be significantly limited when the data sampling rate is too low or when the number of distinct houses in the dataset is too small, and it is indicated that higher quality datasets should be used to expedite the progress of NILM research.
Neural NILM: Deep Neural Networks Applied to Energy Disaggregation
Three deep neural network architectures are adapted to energy disaggregation and it is found that all three neural nets achieve better F1 scores than either combinatorial optimisation or factorial hidden Markov models and that the neural net algorithms generalise well to an unseen house.