Mean Velocity Prediction Information Feedback Strategy in Two-Route Systems under ATIS

Abstract

Feedback contents of previous information feedback strategies in advanced traveler information systems are almost real-time traffic information. Compared with real-time information, prediction traffic information obtained by a reliable and effective prediction algorithm has many undisputable advantages. In prediction information environment, a traveler is prone to making a more rational route-choice. For these considerations, a mean velocity prediction information feedback strategy (MVPFS) is presented. The approach adopts the autoregressive-integrated moving average model (ARIMA) to forecast short-term traffic flow. Furthermore, prediction results of mean velocity are taken as feedback contents and displayed on a variable message sign to guide travelers' route-choice. Meanwhile, discrete choice model (Logit model) is selected to imitate more appropriately travelers' route-choice behavior. In order to investigate the performance of MVPFS, a cellular automaton model with ARIMA is adopted to simulate a two-route scenario. The simulation shows that such innovative prediction feedback strategy is feasible and efficient. Even more importantly, this study demonstrates the excellence of prediction feedback ideology.