Features of Agent-based Models

TL;DR

This paper introduces a systematic approach using software engineering techniques to compare and evaluate features like network structure and dynamics in agent-based models, improving their design and analysis.

Contribution

It proposes a novel framework employing graph transformations and feature diagrams to assess the impact of model features systematically.

Findings

Framework enables systematic feature comparison

Graph transformations represent model features effectively

Supports better design and validation of ABMs

Abstract

The design of agent-based models (ABMs) is often ad-hoc when it comes to defining their scope. In order for the inclusion of features such as network structure, location, or dynamic change to be justified, their role in a model should be systematically analysed. We propose a mechanism to compare and assess the impact of such features. In particular we are using techniques from software engineering and semantics to support the development and assessment of ABMs, such as graph transformations as semantic representations for agent-based models, feature diagrams to identify ingredients under consideration, and extension relations between graph transformation systems to represent model fragments expressing features.