PV Validation Hub

Bennet Meyers, Duncan Ragsdale, Kirsten Perry, Michael Deceglie, Matthew Muller, Mehmet Ogut, Sara Miskovich, Mayank Malik

Research output: NRELPoster

Abstract

The Validation Hub will be a clearinghouse for the transfer of novel algorithms and software from the PV research community to industry. Potential algorithms tested in the Hub could include the estimation of various PV loss factors and the detection of various operational issues. The primary function of the Hub will be for developers to submit executable code which will run on hosted data sets. Developers will receive private reports on the accuracy and performance (e.g., run-time) of the submitted algorithms, and public high level summaries will be hosted. These summaries will indicate the organization who submitted the algorithm (e.g., links to GitHub pages, documentation websites, etc.), high-level accuracy metrics, and standardized performance metrics. These results will be stored in a publicly available database, accessible through the Hub, with the ability for users to sort and filter the results. In short, the Hub will be presented to public users as a collection of interactive leaderboards, organized around specific analysis tasks pertinent to the PV data science community. These tasks include things such as the estimation of various PV loss factors and the detection of various operational issues. We will present progress on the development of this hub, including preliminary results of comparative validation of PV data science algorithms and progress towards building the platform itself.
Original languageAmerican English
StatePublished - 2023

Publication series

NamePresented at the PV Performance Modeling and Monitoring Workshop, 9-10 May 2023, Salt Lake City, Utah

NREL Publication Number

  • NREL/PO-5K00-86350

Keywords

  • algorithm
  • photovoltaics
  • validation

Fingerprint

Dive into the research topics of 'PV Validation Hub'. Together they form a unique fingerprint.

Cite this