A short-term traffic flow forecasting method based on Markov chain and grey Verhulst model

The traffic system is a nonlinear and time-varying complex system with the human body being involved. At the same time, the highly uncertain and nonlinear of short-term traffic flow has been presented due to the complicated factors such as road construction, traffic accident, complex weather and trip distribution. et. So the short-term traffic flow prediction is more difficult than the long-term forecast. First of all, aiming at the uncertain and time-varying characteristics of the short-term traffic flow, the main single-model prediction methods and the combination forecast models are summarized and analyzed. Finally, a combined forecasting method based on Markov chain theory and grey Verhuls model with less data demand and parameter is proposed. The experimental results show that the combined model can obtain a high prediction accuracy.