Comparison Of Different Approaches In Traffic Forecasting Models For The D-200 Highway In Turkey

Abstract

Short-term traffic estimations have a significant influence in terms of effectively controlling vehicle traffic. In this study, short-term traffic forecasting models have been developed based on different approaches. Seasonal autoregressive integrated moving average (SARIMA), artificial bee colony (ABC) and differential evolution (DE) algorithms are the techniques used in the optimization of models, which have been developed by using observation data for the D-200 highway in Turkey. 80% of the data were used for training, with the remaining data used for testing. The performances of the models were illustrated with mean absolute errors (MAEs), mean absolute percentage errors (MAPEs), the coefficient of determination (R2) and the root-mean-square errors (RMSEs). It is understood that all the models provided consistent and useful results when the developed models were compared with the statistical results. In the models created separately for two lanes, the R2 values of the models were calculated to be approximately 92% for the right lane, which is generally used by heavy vehicles, and 88% for the left lane, which is used by less traffic. Based on the MAE and RMSE values, the model developed by the ABC algorithm gave the lowest error and showed more effective performance than the other approaches. Thus, the ABC model showed that it is appropriate for use on other highways in Turkey.