2D Transformations of Energy Signals for Energy Disaggregation.
Abstract
The aim of Non-Intrusive Load Monitoring is to estimate the energy consumption of individual electrical appliances by disaggregating the overall power consumption that has been sampled from a smart meter at a house or commercial/industrial building. Last decade's developments in deep learning and the utilization of Convolutional Neural Networks have improved disaggregation accuracy significantly, especially when utilizing two-dimensional signal representations. However, converting time series' to two-dimensional representations is still an open challenge, and it is not clear how it influences the performance of the energy disaggregation. Therefore, in this article, six different two-dimensional representation techniques are compared in terms of performance, runtime, influence on sampling frequency, and robustness towards Gaussian white noise. The evaluation results show an advantage of two-dimensional imaging techniques over univariate and multivariate features. In detail, the evaluation results show that: first, the active and reactive power-based signatures double Fourier based signatures, as well as outperforming most of the other approaches for low levels of noise. Second, while current and voltage signatures are outperformed at low levels of noise, they perform best under high noise conditions and show the smallest decrease in performance with increasing noise levels. Third, the effect of the sampling frequency on the energy disaggregation performance for time series imaging is most prominent up to 1.2 kHz, while, above 1.2 kHz, no significant improvements in terms of performance could be observed.
AI evidence extraction
Main findings
Six 2D time-series representation techniques were compared for NILM using smart-meter sampled power signals. The evaluation indicated 2D imaging techniques had advantages over univariate and multivariate features; active/reactive power-based signatures performed best at low noise, while current/voltage signatures performed best under high noise. Sampling frequency effects were most prominent up to 1.2 kHz, with no significant performance improvements above 1.2 kHz.
Outcomes measured
- Energy disaggregation performance (non-intrusive load monitoring)
- Runtime
- Influence of sampling frequency on performance
- Robustness to Gaussian white noise
Suggested hubs
- smart-meters (0.7)Study focuses on smart-meter sampled power consumption signals for non-intrusive load monitoring.
View raw extracted JSON
{
"study_type": "engineering",
"exposure": {
"band": null,
"source": "smart meter",
"frequency_mhz": null,
"sar_wkg": null,
"duration": null
},
"population": null,
"sample_size": null,
"outcomes": [
"Energy disaggregation performance (non-intrusive load monitoring)",
"Runtime",
"Influence of sampling frequency on performance",
"Robustness to Gaussian white noise"
],
"main_findings": "Six 2D time-series representation techniques were compared for NILM using smart-meter sampled power signals. The evaluation indicated 2D imaging techniques had advantages over univariate and multivariate features; active/reactive power-based signatures performed best at low noise, while current/voltage signatures performed best under high noise. Sampling frequency effects were most prominent up to 1.2 kHz, with no significant performance improvements above 1.2 kHz.",
"effect_direction": "unclear",
"limitations": [],
"evidence_strength": "insufficient",
"confidence": 0.74,
"peer_reviewed_likely": "yes",
"keywords": [
"non-intrusive load monitoring",
"energy disaggregation",
"smart meter",
"deep learning",
"convolutional neural networks",
"2D signal representations",
"sampling frequency",
"Gaussian white noise"
],
"suggested_hubs": [
{
"slug": "smart-meters",
"weight": 0.6,
"reason": "Study focuses on smart-meter sampled power consumption signals for non-intrusive load monitoring."
}
]
}AI can be wrong. Always verify against the paper.
Comments
Log in to comment.
No comments yet.
NNEMF synthesis
Synthesis pending.