Modelling Weekend Traffic With Weather Conditions Using Various Equation Type And Differential Evolution Algorithm

Abstract

In weekends, amount of passenger car traffic is usually higher than weekday because of the activity-based traveling on some highways. Forecasting of this traffic, might help to local authorities to take safety precautions decisions on a road segments. This study aims to compose models to forecast weekend traffics using weather conditions and average weekday traffic variables. For this aim, two main models were composed: The Saturday traffic model and the Sunday traffic model. The Saturday traffic model variables are mean weekday daily traffic, maximum temperatures of Saturday and precipitations. The Sunday model is a linear model with only one variable: the predicted traffic values from the Saturday traffic model. In the modeling Saturday traffics, six-month (from January to June) data, which belongs to year 2015 and Ankara Kinkkale highway in Turkey, were used and 2014-March data were used for testing the models. The used temperatures were normalized and the precipitations data were involved as logical (0 or 1) inputs in models. To find best equation type for Saturday traffic model, four various equation forms were selected: (1) Linear, (2) polynomial-1, (3) polynomial-2, (4) multiplicative equation from. The linear and polynomial-1 have three, multiplicative has four, and polynomial -2 equation has five coefficients need to be determinate. Differential evolution algorithm was utilized to determinate best fitted values for these coefficients. Performance of the models were calculated using mean square error and coefficient of determination. The model with the polynomial-2 equation has minimum errors for the modelling stage and R-2 value is around 0.80. The model with the polynomial-2 showed the best performance on testing stage (R-2=0.96). These results show that the weekend traffic is related to weather conditions and it can be modeled convenient equation form and differential evolution algorithm.