The parallelization of a highway traffic flow simulation

Johnston, C.M.; Chronopoulos, Anthony T.

doi:10.1109/fmpc.1999.750600

Cited by 5 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multi-threading SUMO [7] Microscopic Multi-threading for routing Dynemo [8] Mesoscopic Network distribution through master-slave parallelization Mobiliti [9] Mesoscopic Parallel discrete event with GASNet POLARIS [10] Mesoscopic Multi-threading BEAM [11] Mesoscopic Akka library [12], [13], [14] Mesoscopic Parallel computation on GPUs [15] Macroscopic Distribution of freeway sections on multiple processes of a nCubes2 distributed-memory parallel computer [16] Macroscopic Distribution of highway segments on multiple processes of a Cray T3W distributed-memory parallel computer OTM-MPI [17] Macroscopic Parallel computing on modern mult-node computer systems with MPI for inter-core communication uses GASNet [23] to enable parallel computation on high performance computing resources. POLARIS [10] exploits parallel computation via multi-threading.…”

Section: Microscopicmentioning

confidence: 99%

“…[15] presents a parallel continuum traffc model on an nCubes2 hypercube distributed-memory parallel computer, where a freeway is partitioned into equal segments and assigned to different processors. Similarly, [16] describes a parallel laxmomentum traffc model that divided the freeway into equal segments assigned to different processors of a Cray T3E distributed-memory computer. Although [15] and [16] use parallel computation for macroscopic traffc simulation on distributed-memory computers, they are focused on freeways only.…”

Section: Microscopicmentioning

confidence: 99%

“…Similarly, [16] describes a parallel laxmomentum traffc model that divided the freeway into equal segments assigned to different processors of a Cray T3E distributed-memory computer. Although [15] and [16] use parallel computation for macroscopic traffc simulation on distributed-memory computers, they are focused on freeways only. In addition, the reported studies involve only about 20 miles of freeway, and were executed on older computer systems.…”

Section: Microscopicmentioning

confidence: 99%

See 2 more Smart Citations

Distributed macroscopic traffic simulation with Open Traffic Models

Gomes

Ugirumurera

2020

2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)

View full text Add to dashboard Cite

This paper presents OTM-MPI, an extension of the Open Traffc Models platform (OTM) for running macroscopic traffc simulations in high-performance computing environments. OTM-MPI represents the frst open-source, distributedmemory, macroscopic simulation model developed for modern high performance parallel machines and large networks. Macroscopic simulations are appropriate for studying regional traffc scenarios when aggregate trends are of interest, rather than individual vehicle traces. They are also appropriate for studying the routing behavior of classes of vehicles, such as app-informed vehicles. The network partitioning was performed with METIS. Inter-process communication was done with MPI (messagepassing interface). Results are provided for two networks: one realistic network which was obtained from Open Street Maps for Chattanooga, TN, and another larger synthetic grid network. The software recorded a speed-up ratio of 198 using 256 cores for Chattanooga, and 475 with 1,024 cores for the synthetic network.

show abstract

Section: Microscopicmentioning

confidence: 99%

Section: Microscopicmentioning

confidence: 99%

Section: Microscopicmentioning

confidence: 99%

See 1 more Smart Citation

Distributed macroscopic traffic simulation with Open Traffic Models

Gomes

Ugirumurera

2020

2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)

View full text Add to dashboard Cite

show abstract

“…Multi-threading SUMO [7] Microscopic Multi-threading for routing Dynemo [8] Mesoscopic Network distribution through master-slave parallelization Mobiliti [9] Mesoscopic Parallel discrete event with GASNet POLARIS [10] Mesoscopic Multi-threading BEAM [11] Mesoscopic Akka library [12], [13], [14] Mesoscopic Parallel computation on GPUs [15] Macroscopic Distribution of freeway sections on multiple processes of a nCubes2 distributed-memory parallel computer [16] Macroscopic Distribution of highway segments on multiple processes of a Cray T3W distributed-memory parallel computer OTM-MPI [17] Macroscopic Parallel computing on modern mult-node computer systems with MPI for inter-core communication TABLE I TRAFFIC SIMULATION SOFTWARE on mesoscopic traffic simulation with parallel computation on graphics processing units include [12]- [14].…”

Section: Microscopicmentioning

confidence: 99%

Distributed macroscopic traffic simulation with Open Traffic Models

Gomes

Ugirumurera

2020

Preprint

View full text Add to dashboard Cite

This paper presents OTM-MPI, an extension of the Open Traffic Models platform (OTM) for running macroscopic traffic simulations in high-performance computing environments. Macroscopic simulations are appropriate for studying regional traffic scenarios when aggregate trends are of interest, rather than individual vehicle traces. They are also appropriate for studying the routing behavior of classes of vehicles, such as app-informed vehicles. The network partitioning was performed with METIS. Inter-process communication was done with MPI (message-passing interface). Results are provided for two networks: one realistic network which was obtained from Open Street Maps for Chattanooga, TN, and another larger synthetic grid network. The software recorded a speed-up ratio of 198 using 256 cores for Chattanooga, and 475 with 1,024 cores for the synthetic network.

show abstract

“…Therefore, distributed macroscopic traffic simulation is used in this paper. In [19], 1-step and 2-step algorithms are presented to solve the macroscopic traffic simulation equations with fewer inter-processor communication. In [20], a PC-based distributed macroscopic traffic simulation methodology that can be applicable for real-time estimation of time-variant parameters in freeway traffic flow is presented.…”

Section: Introductionmentioning

confidence: 99%