Transportation energy demand forecasting in Taiwan based on metaheuristic algorithms

A new methodology is suggested in this study to provide optimum forecasting of the future transportation energy demand in Taiwan. The paper introduces a new improved version of Emperor Penguin Optimizer (IEPO) to provide an optimal and suitable forecasting model. The forecasting was based on three different models including linear, exponential, and quadratic where their coefficients have been optimized using the suggested IEPO algorithm which is based on considering the population, the GDP growth rate, and the total annual vehicle-km. The study considers two different scenarios based on curve fitting and projection data. The results indicate that the RMS value for the TED forecasting based on the proposed IEPO algorithm applied to the linear, exponential, and Quadratic for training are 0.0452, 0.0461, and 0.0492, respectively and for testing are 0.0456, 0.0596, and 0.0642, respectively. This shows better results of the optimized exponential method's efficiency. Simulation results showed high efficiency for the proposed IEPO-based transportation energy demand forecasting based on all of the employed models for decision-making in ROC.

Automated summary

This study proposes a new methodology for forecasting future transportation energy demand in Taiwan. The study introduces a new improved version of Emperor Penguin Optimizer (IEPO) to provide an optimal and suitable forecasting model. The algorithms optimize the coefficients of three different models (linear, exponential, and quadratic) based on population, GDP growth rate, and total annual vehicle-km. The results demonstrate that the optimized exponential method shows better efficiency for transportation energy demand forecasting.