Signal Processing on PV Time-Series Data: Robust Degradation Analysis Without Physical Models

Research output: Contribution to journalArticlepeer-review

16 Scopus Citations

Abstract

A novel unsupervised machine learning approach for analyzing time-series data is applied to the topic of photovoltaic system degradation rate estimation, sometimes referred to as energy-yield degradation analysis. This approach only requires a measured power signal as an input-no irradiance data, temperature data, or system configuration information are required. We present results on a dataset that was previously analyzed and presented by National Renewable Energy Laboratory using RdTools, validating the accuracy of the new approach and showing increased robustness to data anomalies while reducing the data requirements to carry out the analysis.

Original languageAmerican English
Article number8939335
Pages (from-to)546-553
Number of pages8
JournalIEEE Journal of Photovoltaics
Volume10
Issue number2
DOIs
StatePublished - 2020

Bibliographical note

Publisher Copyright:
© 2011-2012 IEEE.

NREL Publication Number

  • NREL/JA-5K00-75031

Keywords

  • computer aided analysis
  • data analysis
  • distributed power generation
  • photovoltaic systems
  • statistical learning

Fingerprint

Dive into the research topics of 'Signal Processing on PV Time-Series Data: Robust Degradation Analysis Without Physical Models'. Together they form a unique fingerprint.

Cite this