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

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 proceeding › Conference 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 language	English (US)
Title of host publication	43rd 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
Publisher	American Solar Energy Society
Pages	511-518
Number of pages	8
ISBN (Electronic)	9781510801790
State	Published - 2014
Event	43rd 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 2014 → Jul 10 2014

Publication series

Name	43rd 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
Volume	1

Other

Other	43rd 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/Territory	United States
City	San Francisco
Period	7/6/14 → 7/10/14

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 7 Affordable and Clean Energy

All Science Journal Classification (ASJC) codes

Renewable Energy, Sustainability and the Environment

Cite this

Srikrishnan, V., Brownson, J. R. S., & Young, G. S. (2014). The all-seeing eye: Using multi-pyranometer arrays and neural networks to estimate direct normal irradiance. In 43rd 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 (pp. 511-518). (43rd 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; Vol. 1). American Solar Energy Society.

Srikrishnan, Vivek ; Brownson, Jeffrey R.S. ; Young, George S. / The all-seeing eye : Using multi-pyranometer arrays and neural networks to estimate direct normal irradiance. 43rd 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. American Solar Energy Society, 2014. pp. 511-518 (43rd 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).

@inproceedings{2c50ca25ff87484e9fbcc856d2b554ef,

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

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.",

author = "Vivek Srikrishnan and Brownson, \{Jeffrey R.S.\} and Young, \{George S.\}",

note = "Publisher Copyright: Copyright {\textcopyright} 2014 by American Solar Energy Society.; 43rd 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 ; Conference date: 06-07-2014 Through 10-07-2014",

year = "2014",

language = "English (US)",

series = "43rd 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",

publisher = "American Solar Energy Society",

pages = "511--518",

booktitle = "43rd 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",

}

Srikrishnan, V, Brownson, JRS & Young, GS 2014, The all-seeing eye: Using multi-pyranometer arrays and neural networks to estimate direct normal irradiance. in 43rd 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. 43rd 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, vol. 1, American Solar Energy Society, pp. 511-518, 43rd 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, 7/6/14.

The all-seeing eye: Using multi-pyranometer arrays and neural networks to estimate direct normal irradiance. / Srikrishnan, Vivek; Brownson, Jeffrey R.S.; Young, George S.
43rd 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. American Solar Energy Society, 2014. p. 511-518 (43rd 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; Vol. 1).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - The all-seeing eye

T2 - 43rd 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

AU - Srikrishnan, Vivek

AU - Brownson, Jeffrey R.S.

AU - Young, George S.

PY - 2014

Y1 - 2014

N2 - 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.

AB - 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.

UR - https://www.scopus.com/pages/publications/84944722807

UR - https://www.scopus.com/pages/publications/84944722807#tab=citedBy

M3 - Conference contribution

AN - SCOPUS:84944722807

T3 - 43rd 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

SP - 511

EP - 518

BT - 43rd 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

PB - American Solar Energy Society

Y2 - 6 July 2014 through 10 July 2014

ER -

Srikrishnan V, Brownson JRS, Young GS. The all-seeing eye: Using multi-pyranometer arrays and neural networks to estimate direct normal irradiance. In 43rd 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. American Solar Energy Society. 2014. p. 511-518. (43rd 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).

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

Abstract

Publication series

Other

UN SDGs

All Science Journal Classification (ASJC) codes

Other files and links

Fingerprint

Cite this