We will present our multi-agent, large-scale, vehicle routing simulation framework that we use to analyze and predict commuter's behaviour within large cities. The proposed multi-agent simulation framework has several important practical applications related to modelling specific types of car travel across various geographic regions. Possible use cases include include logistic process optimization, marketing (targeted out of home advertisements location of billboards and optimization of the content for both static and dynamic media), optimization of business locations (shopping malls, restaurants, stores) or public administration (locations of schools, routes and highways management). As a use case scenario outcomes of a large scale simulation of a Canadian city will be presented. This simulation model enables identify the most frequently used roads and intersections by commuters driving their own cars (the most typical means in most North American cities) along with their demographic profiles. The analysis takes into account socioeconomic and demographic spatial data of commuters as well as their behavioral attributes.

In the second part of presentation we will show a use scenario for large scale optimization of logistic services within a delivery/distributions company.

Przemysław Szufel is an Assistant Professor in Decision Support and Analysis Unit at Warsaw School of Economics and a member of Lab for Computational Methods in Industrial Mathematics in Fields Institute Centre for Quantitative Analysis and Modelling,

His current research focuses on methods for execution of large-scale simulations for numerical experiments and optimization, in particular in the area of heterogeneous spatial transportation systems. He is working on asynchronous algorithms for parallel execution of large-scale simulation in the cloud and distributed computational environments. He is an author or a co-author of several Open Source tools for high performance and numerical simulation (such as KissCluster, D MASON, Isislab SOF, SilverDecisions, PyCX), and actively participates in their development. He is also a co-author of various algorithms for distributed simulation models (such as AKG, AOCBA).