Back to Search
Start Over
An urban traffic simulation model for traffic congestion predicting and avoiding.
- Source :
- Neural Computing & Applications; Sep2018, Vol. 30 Issue 6, p1769-1781, 13p
- Publication Year :
- 2018
-
Abstract
- Urban traffic congestion is a common problem that affects many cities around the world. In this paper, an actual urban traffic simulation model (AUTM) for traffic congestion predicting and avoiding is proposed, which includes three key components: the map and transfer (MT) conversion method, the optimized spatial evolution rules, and a congestion-avoidance routing algorithm. Three key techniques are combined in our proposed model: (1) The MT conversion method is proposed to get actual urban cellular spaces, which apply the optimized spatial evolution rules to simulate the vehicular dynamics better. (2) AUTM is proposed for simulating traffic congestion and predicting the effect of adding overpasses and roadblocks. (3) The congestion-avoidance routing algorithm is proposed for vehicles to dynamically update their routes toward their destinations, which can achieve traffic optimization in urban simulations. This paper presents the results of applying this novel model to a large-scale real-world case in different urban traffic congestion situations. Extensive experimental simulations in various actual cities have been carried out. Our results in the extreme case are encouraging: The prediction accuracy of traffic congestions is almost 89%, and the variance of prediction road density is less than 0.15. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 09410643
- Volume :
- 30
- Issue :
- 6
- Database :
- Complementary Index
- Journal :
- Neural Computing & Applications
- Publication Type :
- Academic Journal
- Accession number :
- 131532696
- Full Text :
- https://doi.org/10.1007/s00521-016-2785-7