Tree-based ensemble methods for predicting PV power generation and their comparison with support vector regression

Ahmad, Muhammad ORCID: https://orcid.org/0000-0002-7269-4369, Mourshed, Monjur ORCID: https://orcid.org/0000-0001-8347-1366 and Rezgui, Yacine ORCID: https://orcid.org/0000-0002-5711-8400 2018. Tree-based ensemble methods for predicting PV power generation and their comparison with support vector regression. Energy 164 , pp. 465-474. 10.1016/j.energy.2018.08.207

Preview

PDF - Published Version Available under License Creative Commons Attribution Non-commercial No Derivatives. Download (1MB) | Preview

Abstract

The variability of renewable energy resources, due to characteristic weather fluctuations, introduces uncertainty in generation output that are greater than the conventional energy reserves the grid uses to deal with the relatively predictable uncertainties in demand. The high variability of renewable generation makes forecasting critical for optimal balancing and dispatch of generation plants in a smarter grid. The challenge is to improve the accuracy and the confidence level of forecasts at a reasonable computational cost. Ensemble methods such as random forest (RF) and extra trees (ET) are well suited for predicting stochastic photovoltaic (PV) generation output as they reduce variance and bias by combining several machine learning techniques while improving the stability; i.e. generalisation capabilities. This paper investigated the accuracy, stability and computational cost of RF and ET for predicting hourly PV generation output, and compared their performance with support vector regression (SVR), a supervised machine learning technique. All developed models have comparable predictive power and are equally applicable for predicting hourly PV output. Despite their comparable predictive power, ET outperformed RF and SVR in terms of computational cost. The stability and algorithmic efficiency of ETs make them an ideal candidate for wider deployment in PV output forecasting.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Engineering
Subjects:	T Technology > TA Engineering (General). Civil engineering (General)
Publisher:	Elsevier
ISSN:	0360-5442
Funders:	European Commission
Date of First Compliant Deposit:	6 September 2018
Date of Acceptance:	28 August 2018
Last Modified:	26 Jul 2023 12:10
URI:	https://orca.cardiff.ac.uk/id/eprint/114636

Citation Data

Cited 136 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item