Models for forecasting growth trends in renewable energy

Abstract

The advantages of renewable energy are that it is low in pollution and sustainable. Energy shortages do not apply to renewable energy. In this study, we primarily forecast growth trends in renewable energy consumption in China. Renewable energy is an emerging technology, and thus this study comprises only 22 pieces of sample data. Because the historical data comprised a small sample and did not fit a normal distribution, big data analysis was not an appropriate prediction method. Therefore, we used three grey prediction models, the GM(1,1) model, the NGBM(1,1) model, and the grey Verhulst model, for theoretical derivation and scientific verification. The accuracy and fitness of the prediction models were compared using regression analysis. Regarding the three indicators of mean absolute error, mean squared error, mean absolute percentage error, this study's comparison of the forecast accuracy of the three grey prediction models and regression analysis indicated that NGMB(1,1) had the highest forecast accuracy, followed by the grey Verhulst model and the GM(1,1) model. Regression analysis exhibited the lowest results. In addition, this study confirmed that, for predictions that use small data samples, the modified grey NGBM(1,1) model and the grey Verhulst model had higher forecast accuracy than the original GM(1,1) model did. The models used in this study for forecasting renewable energy can be applied to predicting energy consumption in other countries, which affords insight into the global trend of energy development.