Forecasting renewable energy generation with a novel flexible nonlinear multivariable discrete grey prediction model

Yuanping Ding and Yaoguo Dang

Energy, 2023, vol. 277, issue C

Abstract: Accurate prediction of renewable energy generation can provide a reference for policymakers to formulate energy development strategies. However, it is difficult to predict the renewable energy generation due to its nonlinear feature. Given this situation, this paper presents a novel flexible nonlinear multivariable discrete grey prediction model with power exponential terms and adjustable time power item. To improve the generalization ability and avoid the over-fitting problem, the hold-out cross validation method and Grey Wolf Optimizer are designed to solve hyper-parameters. For validation purpose, the novel model is implemented to predict the hydropower and total renewable energy generation in China. Results show that the new model has higher prediction accuracy than other competing models, and the prediction accuracy of the model in two cases is at least 57.5995% and 42.3322% higher than similar grey models. The findings also indicate that the hydropower and total renewable energy generation will reach 1469346.28 GWh and 2711622.04 GWh in 2023 with an average growth rate of 3.0232% and 8.6909%, respectively, and the share of hydropower generation is projected to fall to 54.1870% in 2023. Based on the superior modeling performance, the prediction model can be extended for renewable energy generation prediction in other countries.

Keywords: Multivariable discrete grey prediction model; Renewable energy generation; Nonlinear; Hold-out cross validation method (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (8)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544223010587
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:277:y:2023:i:c:s0360544223010587

DOI: 10.1016/j.energy.2023.127664

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().