Traffic flow short-term forecasting system design and prototyping: Case study of Riga city

Mihails Savrasovs

Proceedings of the 2017 5th IEEE International Conference on Models and Technologies for Intelligent Transportation Systems (MT-ITS)
DOI: 10.1109/MTITS.2017.8005588
Keywords
: traffic flows, short-term forecasting, traffic models, TFlowFuzzy

Available at IEEE Xplore: REQUEST FULL TEXT Export citation: BibTeX RIS

Abstract

The goal of the paper is to demonstrate the design and prototyping of the short-term forecasting system for Riga city. The key component of the short-term forecasting system is a macroscopic transport model implemented in PTV VISION VISUM simulation software. The aim of the model is to provide the operational data about traffic flows to decision makers in order to control and in future adjust the traffic situation in the urban area. The model receives the data about current traffic flow intensities, the data about current restrictions and limitations in the transport network, data about travel behaviour represented by an origin-destination matrix. Based on the TFlowFuzzy approach the original matrix is calibrated and used to complete short-term forecasting. The paper demonstrates the workflow of the system and provides information about implemented solution and discuss limitations and issues for the future development of the short-term forecasting system. The system could become an important part of the traffic monitoring and control centre of Riga city