Forecasting energy consumption in Taiwan using hybrid nonlinear models

• Published in: Energy (Oxford) Vol. 34; no. 10; pp. 1438 - 1446
• Main Author: Pao, H.T.
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.10.2009; Elsevier
• Subjects: Applied sciences; Artificial neural networks; Economic data; Electric energy; Encompassing test; Energy; Energy consumption; Energy economics; Exact sciences and technology; Fossil fuels and derived products; Gas; General, economic and professional studies; Methodology. Modelling; Multi-step-ahead forecasting; SEGARCH models; Asia; Taiwan; Energy consumption; SEGARCH models; Multi-step-ahead forecasting; Encompassing test; Artificial neural networks; Methodology; Energy economy; Time series; Neural network; Modeling; Forecasting; Petroleum; Case study; Non linear model; Electric power consumption; Hybrid model; Artificial intelligence
• ISSN: 0360-5442
• DOI: 10.1016/j.energy.2009.04.026

The total consumption of electricity and petroleum energies accounts for almost 90% of the total energy consumption in Taiwan, so it is critical to model and forecast them accurately. For univariate modeling, this paper proposes two new hybrid nonlinear models that combine a linear model with an artificial neural network (ANN) to develop adjusted forecasts, taking into account heteroscedasticity in the model's input. Both of the hybrid models can decrease round-off and prediction errors for multi-step-ahead forecasting. The results suggest that the new hybrid model generally produces forecasts which, on the basis of out-of-sample forecast encompassing tests and comparisons of three different statistic measures, routinely dominate the forecasts from conventional linear models. The superiority of the hybrid ANNs is due to their flexibility to account for potentially complex nonlinear relationships that are not easily captured by linear models. Furthermore, all of the linear and nonlinear models have highly accurate forecasts, since the mean absolute percentage forecast error (MAPE) results are less than 5%. Overall, the inclusion of heteroscedastic variations in the input layer of the hybrid univariate model could help improve the modeling accuracy for multi-step-ahead forecasting.