The all-seeing eye: Using multi-pyranometer arrays and neural networks to estimate direct normal irradiance

Vivek Srikrishnan, Jeffrey R.S. Brownson, George S. Young

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Direct Normal Irradiance (DNI) is a critical component of solar irradiation for estimating Plane of Array (POA) irradiance on flat plate systems as well as for concentrating systems. Current approaches to measuring or estimating DNI suffer from drawbacks of either high equipment costs or low precision. A new approach is proposed, using Artificial Neural Networks to estimate DNI from the irradiance measures of five pyranometers. We consider various neural network topologies and training data sources and analyze the resulting errors. The estimated systems costs are found to be an order of magnitude less than a traditional pyrheliometer setup, with precision and accuracy significantly improved relative to a single pyranometer system.

Original languageEnglish (US)
Title of host publication43rd ASES National Solar Conference 2014, SOLAR 2014, Including the 39th National Passive Solar Conference and the 2nd Meeting of Young and Emerging Professionals in Renewable Energy
PublisherAmerican Solar Energy Society
Pages511-518
Number of pages8
ISBN (Electronic)9781510801790
StatePublished - 2014
Event43rd ASES National Solar Conference 2014, SOLAR 2014, Including the 39th National Passive Solar Conference and the 2nd Meeting of Young and Emerging Professionals in Renewable Energy - San Francisco, United States
Duration: Jul 6 2014Jul 10 2014

Publication series

Name43rd ASES National Solar Conference 2014, SOLAR 2014, Including the 39th National Passive Solar Conference and the 2nd Meeting of Young and Emerging Professionals in Renewable Energy
Volume1

Other

Other43rd ASES National Solar Conference 2014, SOLAR 2014, Including the 39th National Passive Solar Conference and the 2nd Meeting of Young and Emerging Professionals in Renewable Energy
Country/TerritoryUnited States
CitySan Francisco
Period7/6/147/10/14

All Science Journal Classification (ASJC) codes

  • Renewable Energy, Sustainability and the Environment

Fingerprint

Dive into the research topics of 'The all-seeing eye: Using multi-pyranometer arrays and neural networks to estimate direct normal irradiance'. Together they form a unique fingerprint.

Cite this