Simulating the actions of commuters using a multi-agent system

Urquhart, Neil; Powers, Simon; Wall, Zoe; Fonzone, Achille; Ge, Jiaqi; Polhill, Gary

Abstract

The activity of commuting to and from a place of work affects not only those travelling but also wider society through their contribution to congestion and pollution. It is desirable to have a means of simulating commuting in order to allow organisations to predict the effects of changes to working patterns and locations and inform decision making. In this paper we outline an agent-based software framework that combines real-world data from multiple sources to simulate the actions of commuters. We demonstrate the framework using data supplied by an employer based in the City of Edinburgh UK. We demonstrate that the BDI-inspired decision making framework used is capable of forecasting the transportation modes to be used. Finally we present a case study, demonstrating the use of the framework to predict the impact of moving staff within the organisation to a new work site.

Citation

Urquhart, N., Powers, S., Wall, Z., Fonzone, A., Ge, J., & Polhill, G. (2019). Simulating the actions of commuters using a multi-agent system. Journal of Artificial Societies and Social Simulation, 22(2), https://doi.org/10.18564/jasss.4007

• Journal Article Type: Article
• Acceptance Date: Feb 2, 2019
• Online Publication Date: Mar 31, 2019
• Publication Date: 2019-03
• Deposit Date: Feb 7, 2019
• Publicly Available Date: Mar 31, 2019
• Journal: Journal of Artificial Societies and Social Simulation
• Print ISSN: 1460-7425
• Publisher: SimSoc Consortium
• Peer Reviewed: Peer Reviewed
• Volume: 22
• Issue: 2
• DOI: https://doi.org/10.18564/jasss.4007
• Keywords: Transport mode choice, transport network, BDI agent,
• Public URL: http://researchrepository.napier.ac.uk/Output/1565737
• Contract Date: Feb 7, 2019