Increasing the Accuracy and Speed of Universal Non-Intrusive Load Monitoring (UNILM) Using a Novel Real- Time Steady-State Block Filter

Jones, Richard; Rodriguez-Silva, Alejandro; Makonin, Stephen

doi:10.1109/isgt45199.2020.9087733

Cited by 5 publications

(2 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Examine transferability of new NILM solutions to real use cases such as [27] • Investigate how other accuracy metrics such as the Matthews Correlation Coefficient (MCC) can be applied to evaluate generalisation…”

Section: Discussionmentioning

confidence: 99%

On Metrics to Assess the Transferability of Machine Learning Models in Non-Intrusive Load Monitoring

Klemenjak¹,

Faustine²,

Makonin³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

To assess the performance of load disaggregation algorithms it is common practise to train a candidate algorithm on data from one or multiple households and subsequently apply cross-validation by evaluating the classification and energy estimation performance on unseen portions of the dataset derived from the same households. With an emerging discussion of transferability in Non-Intrusive Load Monitoring (NILM), there is a need for domain-specific metrics to assess the performance of NILM algorithms on new test scenarios being unseen buildings. In this paper, we discuss several metrics to assess the generalisation ability of NILM algorithms. These metrics target different aspects of performance evaluation in NILM and are meant to complement the traditional performance evaluation approach. We demonstrate how our metrics can be utilised to evaluate NILM algorithms by means of two case studies. We conduct our studies on several energy consumption datasets and take into consideration five state-of-the-art as well as four baseline NILM solutions. Finally, we formulate research challenges for future work.

show abstract

Section: Discussionmentioning

confidence: 99%

On Metrics to Assess the Transferability of Machine Learning Models in Non-Intrusive Load Monitoring

Klemenjak¹,

Faustine²,

Makonin³

et al. 2019

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Moreover, the consistency of these initial activations are dependent on sampling frequency. We consequently preprocess the data using a fast, steady-state blockfilter developed in [23]. This filter imputes the mean value between change-points identified using an adaptive threshold on the raw power and first-differences in the signal.…”

Section: Surprise Methodology For Nilmmentioning

confidence: 99%

Exploring Bayesian Surprise to Prevent Overfitting and to Predict Model Performance in Non-Intrusive Load Monitoring

Jones,

Klemenjak,

Makonin

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Non-Intrusive Load Monitoring (NILM) is a field of research focused on segregating constituent electrical loads in a system based only on their aggregated signal. Significant computational resources and research time are spent training models, often using as much data as possible, perhaps driven by the preconception that more data equates to more accurate models and better performing algorithms. When has enough prior training been done? When has a NILM algorithm encountered new, unseen data? This work applies the notion of Bayesian surprise to answer these questions which are important for both supervised and unsupervised algorithms. We quantify the degree of surprise between the predictive distribution (termed postdictive surprise), as well as the transitional probabilities (termed transitional surprise), before and after a window of observations. We compare the performance of several benchmark NILM algorithms supported by NILMTK, in order to establish a useful threshold on the two combined measures of surprise. We validate the use of transitional surprise by exploring the performance of a popular Hidden Markov Model as a function of surprise threshold. Finally, we explore the use of a surprise threshold as a regularization technique to avoid overfitting in cross-dataset performance. Although the generality of the specific surprise threshold discussed herein may be suspect without further testing, this work provides clear evidence that a point of diminishing returns of model performance with respect to dataset size exists. This has implications for future model development, dataset acquisition, as well as aiding in model flexibility during deployment.

show abstract

A reliable deep learning-based algorithm design for IoT load identification in smart grid

et al. 2021

View full text Add to dashboard Cite

Increasing the Accuracy and Speed of Universal Non-Intrusive Load Monitoring (UNILM) Using a Novel Real- Time Steady-State Block Filter

Cited by 5 publications

References 8 publications

On Metrics to Assess the Transferability of Machine Learning Models in Non-Intrusive Load Monitoring

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

A reliable deep learning-based algorithm design for IoT load identification in smart grid

Contact Info

Product

Resources

About