{"title":"Vessel traffic flow prediction model based on complex network","authors":"Wen Hang, Mengyuan Xu, Xingyuan Chen, Shaolong Zhou","doi":"10.1109/ICTIS.2015.7232104","DOIUrl":null,"url":null,"abstract":"A complex network structure can describe many real systems, ports system meet characteristics of complex network system. This paper built a new weighted port evolutional network model using vessel traffic flow as the relevance rating affecting port evolution, on the basis of this. It proposed a port vessel traffic flow forecasting model based on complex networks and used vessel traffic volume of Tianjin Port during 2002-2013 years as the experimental data and ultimately verified and predicted it through the use of forecasting model parameters obtained by fitting port network kinetic equations and numerical, as a result, the error between the experimental results calculated by model and actual data is 4.95%, and the average prediction error during 2009-2013 is less than 2%, the fitting of parameters in this model needed to be supported by historical data, so this model is only applicable in short-term prediction with high accuracy.","PeriodicalId":389628,"journal":{"name":"2015 International Conference on Transportation Information and Safety (ICTIS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 International Conference on Transportation Information and Safety (ICTIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICTIS.2015.7232104","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1
Abstract
A complex network structure can describe many real systems, ports system meet characteristics of complex network system. This paper built a new weighted port evolutional network model using vessel traffic flow as the relevance rating affecting port evolution, on the basis of this. It proposed a port vessel traffic flow forecasting model based on complex networks and used vessel traffic volume of Tianjin Port during 2002-2013 years as the experimental data and ultimately verified and predicted it through the use of forecasting model parameters obtained by fitting port network kinetic equations and numerical, as a result, the error between the experimental results calculated by model and actual data is 4.95%, and the average prediction error during 2009-2013 is less than 2%, the fitting of parameters in this model needed to be supported by historical data, so this model is only applicable in short-term prediction with high accuracy.