MARS model for prediction of short- and long-term global solar radiation
Edited book (chapter)
Chapter Title | MARS model for prediction of short- and long-term global solar radiation |
---|---|
Book Chapter Category | Edited book (chapter) |
ERA Publisher ID | 1821 |
Book Title | Predictive modelling for energy management and power systems engineering |
Authors | Balalla, Dilki T. (Author), Nguyen-Huy, Thong (Author) and Deo, Ravinesh (Author) |
Editors | Deo, Ravinesh, Samui, Pijush and Roy, Sanjiban Sekhar |
Page Range | 391-436 |
Chapter Number | 13 |
Number of Pages | 46 |
Year | 2021 |
Publisher | Elsevier |
Place of Publication | Amsterdam, Netherlands |
ISBN | 9780128177723 |
Web Address (URL) | https://www.elsevier.com/books/predictive-modelling-for-energy-management-and-power-systems-engineering/deo/978-0-12-817772-3 |
Abstract | The intention of this research was to try and address the research question 'Is machine learning algorithm, Multivariate Adaptive Regression Splines model, a versatile forecasting model for solar radiation?' The objective of this chapter is to develop a machine learning (ML) algorithm to validate and assess errors for the method used to forecast solar radiation based on historical data. The specific aims are to construct (1) short-term (daily) global solar radiation model using the MARS algorithm considering the nonlinear behavior of surface-level solar radiation with its predictor variables; and (2) long-term (monthly) global solar radiation model using the MARS algorithm to enable the solar energy assessment over a long-term period and considering. This chapter carried out short-term and long-term solar radiation forecasting model development for regional Queensland. Short-term forecasting provides predictions up to 7 days ahead. These forecasts are valuable for grid operators in order to make important decisions for grid operation. It will provide valuable information regarding the time scheduling of power systems (Wan et al., 2015). Long-term forecasting has been carried out considering 1-month ahead, 3-month, and 6-month ahead forecast. This is useful for energy companies to make decisions and negotiate contracts with energy producers (Martı´n et al., 2010) and also for effective operation and maintenance planning of solar power systems (Koca et al., 2011). The information gathered from the seasonal analysis can be used for studying the seasonal patterns of the solar energy and for Seasonal Thermal Energy Storage (i.e., STES) (Allen et al., 1984) where the heat acquired from solar collectors in hot months can be stored for future use when needed, including during winter months. |
Keywords | solar energy; forecasting |
ANZSRC Field of Research 2020 | 419999. Other environmental sciences not elsewhere classified |
469999. Other information and computing sciences not elsewhere classified | |
Public Notes | Files associated with this item cannot be displayed due to copyright restrictions. |
Byline Affiliations | School of Sciences |
Centre for Applied Climate Sciences | |
Institution of Origin | University of Southern Queensland |
https://research.usq.edu.au/item/q5yq5/mars-model-for-prediction-of-short-and-long-term-global-solar-radiation
237
total views9
total downloads2
views this month0
downloads this month