MARS model for prediction of short- and long-term global solar radiation

Balalla, Dilki T. and Nguyen-Huy, Thong ORCID: https://orcid.org/0000-0002-2201-6666 and Deo, Ravinesh ORCID: https://orcid.org/0000-0002-2290-6749 (2021) MARS model for prediction of short- and long-term global solar radiation. In: Predictive modelling for energy management and power systems engineering. Elsevier, Amsterdam, Netherlands, pp. 391-436. ISBN 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.


Statistics for USQ ePrint 39838
Statistics for this ePrint Item
Item Type: Book Chapter (Commonwealth Reporting Category B)
Refereed: Yes
Item Status: Live Archive
Additional Information: Permanent restricted access to Published version + Front Matter in accordance with the copyright policy of the publisher.
Faculty/School / Institute/Centre: Current - Faculty of Health, Engineering and Sciences - School of Sciences (6 Sep 2019 -)
Faculty/School / Institute/Centre: Current - Institute for Life Sciences and the Environment - Centre for Applied Climate Sciences (1 Aug 2018 -)
Date Deposited: 06 Oct 2020 05:40
Last Modified: 06 Oct 2020 05:41
Uncontrolled Keywords: solar energy; forecasting
Fields of Research (2008): 05 Environmental Sciences > 0599 Other Environmental Sciences > 059999 Environmental Sciences not elsewhere classified
08 Information and Computing Sciences > 0801 Artificial Intelligence and Image Processing > 080108 Neural, Evolutionary and Fuzzy Computation
Socio-Economic Objectives (2008): E Expanding Knowledge > 97 Expanding Knowledge > 970108 Expanding Knowledge in the Information and Computing Sciences
URI: http://eprints.usq.edu.au/id/eprint/39838

Actions (login required)

View Item Archive Repository Staff Only