{"title":"A high performance approach with MATSim for traffic road simulation","authors":"Sara Moukir, N. Emad, Stéphane Baudelocq","doi":"10.1109/IIAIAAI55812.2022.00140","DOIUrl":null,"url":null,"abstract":"Road traffic simulation becomes more and more accurate over time. From macroscopic simulations based on fluid equations, for example, to microscopic simulations based on the multi-agent paradigm, innovations have continued to emerge in recent years. Multi-agent models such as MATSim [1], POLARIS [2] or SimMobility [3] have been highlighted lately in response to complex and microscopic simulation requirements. However, this microscopic and large-scale approach requires much higher computing power than that delivered by a home computer. High-performance computing approach can be a relevant response to this kind of problem. MATsim due to its module structure was selected as the basis of our study. We introduce a new concept for the design of parallel algorithm of MATSim. The parallel architectures used as support for the experiments presented are provided by GRID’5000 (or G5K) [4].","PeriodicalId":156230,"journal":{"name":"2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 12th International Congress on Advanced Applied Informatics (IIAI-AAI)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IIAIAAI55812.2022.00140","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Road traffic simulation becomes more and more accurate over time. From macroscopic simulations based on fluid equations, for example, to microscopic simulations based on the multi-agent paradigm, innovations have continued to emerge in recent years. Multi-agent models such as MATSim [1], POLARIS [2] or SimMobility [3] have been highlighted lately in response to complex and microscopic simulation requirements. However, this microscopic and large-scale approach requires much higher computing power than that delivered by a home computer. High-performance computing approach can be a relevant response to this kind of problem. MATsim due to its module structure was selected as the basis of our study. We introduce a new concept for the design of parallel algorithm of MATSim. The parallel architectures used as support for the experiments presented are provided by GRID’5000 (or G5K) [4].