Preliminary assessment of two spatio-temporal forecasting technics for hourly satellite-derived irradiance in a complex meteorological context

•Strengths and weaknesses of spatio-temporal VAR and CMV models are analyzed.•CMV forecasts present consistently lower rMAEs excepted for few sites.•STVAR is more accurate than CMV in regions with strong micro-climatic features.•A hybrid spatio-temporal models with a smart blend is argued. This pape...

Full description

Saved in:
Bibliographic Details
Published in:Solar energy 2019-01, Vol.177, p.703-712
Main Authors: André, Maïna, Perez, Richard, Soubdhan, Ted, Schlemmer, James, Calif, Rudy, Monjoly, Stéphanie
Format: Article
Language:English
Subjects:
Autoregressive models
Case studies
Cloud motion vector
Complex meteorological context
Engineering Sciences
Forecasting
Irradiance
Mathematical models
Meteorology
Microclimate
Performance prediction
Photovoltaic cells
Satellite-derived irradiance
Solar energy
Spatio-temporal forecasting
Weather forecasting
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:•Strengths and weaknesses of spatio-temporal VAR and CMV models are analyzed.•CMV forecasts present consistently lower rMAEs excepted for few sites.•STVAR is more accurate than CMV in regions with strong micro-climatic features.•A hybrid spatio-temporal models with a smart blend is argued. This paper examines two spatio-temporal approaches for short-term forecasting of global horizontal irradiance using gridded satellite-derived irradiances as experimental support. The first approach is a spatio-temporal vector autoregressive (STVAR) model combined with a statistical process for optimum selection of input variables. The second is an existing operational cloud motion vector (CMV) model. An evaluation of the predictive performance of these models is presented for a case study area in the Caribbean Islands. This region is characterized by a large diversity of microclimates and land/sea contrasts, creating a challenging solar forecasting context. Using scaled persistence as a reference, we benchmark the performance of the two spatio-temporal models over an extended 220 × 220 km domain, and for three specific, climatically distinct locations within this domain. We also assess the influence of intra-day solar resource variability on model performance. Finally, we present preliminary evidence that a blend of CMV and STVAR forecasts leads to improved accuracy under all conditions.
ISSN:0038-092X
1471-1257
DOI:10.1016/j.solener.2018.11.010