Loading...

Traffic State Prediction via Macroscopic Fundamental Diagram in an Urban Network

Sabet, Saba | 2020

526 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 53391 (09)
  4. University: Sharif University of Technology
  5. Department: Civil Engineering
  6. Advisor(s): Nassiri, Habibollah
  7. Abstract:
  8. The road authorities of a city have the responsibility of constantly assessing how well their city performs when traffic conditions are taken into account. In many metropolises around the world, if not taken preventive measures, there will be observed a density above the network capacity and a noticeable decrease in the level of service, especially in the morning and evening peak hours. Also, the dynamic congestion pricing of certain areas based on the traffic condition has always been considered significant by urban planning officials. Since this is not possible except by constantly assessing the current traffic state, a variety of methods have been used to predict the future traffic condition in a network according to its current condition. In one of the cost efficient methods for this purpose, by drawing and analyzing the network's macroscopic fundamental diagram, the future state of the network can be predicted to a large extent. This study uses real data of average speed and traffic flow in Tehran's congestion zone, to draw a macroscopic fundamental diagram for this zone and predict the future traffic condition through prediction of traffic flow using ARIMA models and Artificial Neural Networks. The results show that using real speed and flow data, macroscopic fundamental diagram of Tehran can be defined. Also, the traffic flow rate is a function of the flow in the previous hours, working day or holiday, as well as the weather condition. Finally, by having the average speed or density in a certain period of time, it is possible to estimate the traffic condition in the network using the predicted flow rate and the macroscopic fundamental diagram of the network
  9. Keywords:
  10. Traffic Flow Monitoring ; Autoregressive Integrated Moving Average (ARIMA) ; Artificial Neural Network ; Traffic Prediction ; Macroscopic Traffic Flow Model ; Macroscopic Fundamental Diagram ; Tehran Transportation Network

 Digital Object List

 Bookmark