PROJECT TITLE :
Traffic Flow Prediction for Road Transportation Networks With Limited Traffic Data
Obtaining correct information regarding current and close to-term future traffic flows of all links in a very traffic network features a wide range of applications, including traffic forecasting, vehicle navigation devices, vehicle routing, and congestion management. A serious downside in getting traffic flow info in real time is that the vast majority of links is not equipped with traffic sensors. Another drawback is that factors affecting traffic flows, like accidents, public events, and road closures, are typically unforeseen, suggesting that traffic flow forecasting is a difficult task. During this paper, we initial use a dynamic traffic simulator to get flows in all links using on the market traffic info, estimated demand, and historical traffic knowledge available from links equipped with sensors. We tend to implement an optimization methodology to adjust the origin-to-destination matrices driving the simulator. We then use the real-time and estimated traffic information to predict the traffic flows on every converge to thirty min ahead. The prediction algorithm is predicated on an autoregressive model that adapts itself to unpredictable events. As a case study, we tend to predict the flows of a traffic network in San Francisco, CA, USA, employing a macroscopic traffic flow simulator. We use Monte Carlo simulations to guage our methodology. Our simulations demonstrate the accuracy of the proposed approach. The traffic flow prediction errors vary from a median of twopercent for 5-min prediction windows to twelvep.c for thirty-min windows even in the presence of unpredictable events.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here