Determination of broadband atmospheric turbidity from global irradiance or photovoltaic power data using deep neural nets
Photovoltaic technologies provide significant capacity to electric grids, however, resource variability and production uncertainty complicate power balancing and reserve management. A crucial step in predicting solar generation is determining clear-sky irradiance. Clear-sky attenuation can be modele...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-10-01
|
Series: | Energy and AI |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2666546823000241 |
_version_ | 1797660143371943936 |
---|---|
author | Dax K. Matthews |
author_facet | Dax K. Matthews |
author_sort | Dax K. Matthews |
collection | DOAJ |
description | Photovoltaic technologies provide significant capacity to electric grids, however, resource variability and production uncertainty complicate power balancing and reserve management. A crucial step in predicting solar generation is determining clear-sky irradiance. Clear-sky attenuation can be modeled using broadband atmospheric turbidity factors, but model accuracy is dependent on the measurements used to determine the current and future state of aerosol loading and water vapor content, which requires close proximity measurements, in time and space, to account for turbidity variability. Such measurements, though, are only available in near real-time at a limited, and decreasing, number of sites. This paper proposes a new method for estimating time-varying local turbidity conditions from more readily available pyranometer or PV output data. The method employs a long short-term memory recurrent neural network to distill the turbidity-driven signal from global irradiance (or global irradiance driven) observations, despite an inherent dampening issue. The method is developed to operate in near real-time for solar forecasting applications. Validation examines the ability of the method to (1) reproduce turbidity estimates derived from historical measurements of beam irradiance under clear-sky conditions; and (2) provide input for clear-sky models in the form of persistence forecasts generated from daily mean values. |
first_indexed | 2024-03-11T18:25:30Z |
format | Article |
id | doaj.art-dd79b469b10742d18af7268ba2f1d912 |
institution | Directory Open Access Journal |
issn | 2666-5468 |
language | English |
last_indexed | 2024-03-11T18:25:30Z |
publishDate | 2023-10-01 |
publisher | Elsevier |
record_format | Article |
series | Energy and AI |
spelling | doaj.art-dd79b469b10742d18af7268ba2f1d9122023-10-14T04:45:25ZengElsevierEnergy and AI2666-54682023-10-0114100252Determination of broadband atmospheric turbidity from global irradiance or photovoltaic power data using deep neural netsDax K. Matthews0University of Hawaii at Manoa, Hawaii Natural Energy Institute (HNEI), 1680 East West Road, POST 109, Honolulu, 96822, HI, USAPhotovoltaic technologies provide significant capacity to electric grids, however, resource variability and production uncertainty complicate power balancing and reserve management. A crucial step in predicting solar generation is determining clear-sky irradiance. Clear-sky attenuation can be modeled using broadband atmospheric turbidity factors, but model accuracy is dependent on the measurements used to determine the current and future state of aerosol loading and water vapor content, which requires close proximity measurements, in time and space, to account for turbidity variability. Such measurements, though, are only available in near real-time at a limited, and decreasing, number of sites. This paper proposes a new method for estimating time-varying local turbidity conditions from more readily available pyranometer or PV output data. The method employs a long short-term memory recurrent neural network to distill the turbidity-driven signal from global irradiance (or global irradiance driven) observations, despite an inherent dampening issue. The method is developed to operate in near real-time for solar forecasting applications. Validation examines the ability of the method to (1) reproduce turbidity estimates derived from historical measurements of beam irradiance under clear-sky conditions; and (2) provide input for clear-sky models in the form of persistence forecasts generated from daily mean values.http://www.sciencedirect.com/science/article/pii/S2666546823000241Solar power forecastingBroadband atmospheric turbidityClear-sky modeling |
spellingShingle | Dax K. Matthews Determination of broadband atmospheric turbidity from global irradiance or photovoltaic power data using deep neural nets Energy and AI Solar power forecasting Broadband atmospheric turbidity Clear-sky modeling |
title | Determination of broadband atmospheric turbidity from global irradiance or photovoltaic power data using deep neural nets |
title_full | Determination of broadband atmospheric turbidity from global irradiance or photovoltaic power data using deep neural nets |
title_fullStr | Determination of broadband atmospheric turbidity from global irradiance or photovoltaic power data using deep neural nets |
title_full_unstemmed | Determination of broadband atmospheric turbidity from global irradiance or photovoltaic power data using deep neural nets |
title_short | Determination of broadband atmospheric turbidity from global irradiance or photovoltaic power data using deep neural nets |
title_sort | determination of broadband atmospheric turbidity from global irradiance or photovoltaic power data using deep neural nets |
topic | Solar power forecasting Broadband atmospheric turbidity Clear-sky modeling |
url | http://www.sciencedirect.com/science/article/pii/S2666546823000241 |
work_keys_str_mv | AT daxkmatthews determinationofbroadbandatmosphericturbidityfromglobalirradianceorphotovoltaicpowerdatausingdeepneuralnets |