Please use this identifier to cite or link to this item:
|Title:||Freeway ramp metering by macroscopic traffic scheduling with particle swarm optimization|
|Source:||Zhao, X.,Xu, J.,Srinivasan, D. (2013). Freeway ramp metering by macroscopic traffic scheduling with particle swarm optimization. Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 : 32-37. ScholarBank@NUS Repository. https://doi.org/10.1109/CIVTS.2013.6612286|
|Abstract:||In this paper, the networked freeway ramp metering problem is addressed using a novel macroscopic traffic scheduling approach. In the proposed method, reference mainstream densities are macroscopically scheduled for each local ramp metering controller. These reference density signals are tracked by the corresponding local controllers using the feedback based algorithm. The considered time is divided into macroscopic time periods. Within each period, reference mainstream density signals are scheduled for local controllers. The optimal networked ramp metering problem is considered as an optimization problem, where these reference signals are regarded as decision variables. The particle swarm optimization (PSO) algorithm is used to find the optimal reference signals, which minimizes the total time spent (TTS) by vehicles within the whole network. The efficiency of the proposed method is demonstrated in case studies. Furthermore, the proposed approach has the advantages of structural simplicity and low implementation cost, and the capability of local feedback based strategy in dealing with realtime traffic conditions is retained. © 2013 IEEE.|
|Source Title:||Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Vehicles and Transportation Systems, CIVTS 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013|
|Appears in Collections:||Staff Publications|
Show full item record
Files in This Item:
There are no files associated with this item.
checked on Dec 13, 2017
checked on Dec 9, 2017
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.