Vahana.jl - A framework (not only) for large-scale agent-based models

2024-06-20

arXiv.org

AI Summary

Traditional agent-based models (ABMs) encounter computational bottlenecks as agent counts and network complexity grow, while existing platforms fail to leverage modern distributed hardware efficiently. This paper introduces Vahana.jl—a high-performance, open-source ABM framework designed for large-scale synchronous graph dynamical systems. Its core innovation lies in the first deep integration of formal synchronous graph dynamical system modeling with Julia’s native parallel and distributed computing capabilities, enabling scalable multi-node simulation and REPL-driven interactive modeling. Compared to mainstream ABM platforms, Vahana.jl achieves substantial gains in throughput and scalability, supporting efficient, near-real-time simulation of ultra-large social networks—e.g., million-node graphs—that exceed the capacity of single-machine execution. The implementation is publicly available, and empirical validation has been conducted on canonical social network scenarios.

Technology Category

• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Social Networks and Social Media: Computational social science
• Economics, Online Markets and Human Computation: The sharing economy

Abstract

Agent-based models (ABMs) offer a powerful framework for understanding complex systems. However, their computational demands often become a significant barrier as the number of agents and complexity of the simulation increase. Traditional ABM platforms often struggle to fully exploit modern computing resources, hindering the development of large-scale simulations. This paper presents Vahana.jl, a high performance computing open source framework that aims to address these limitations. Building on the formalism of synchronous graph dynamical systems, Vahana.jl is especially well suited for models with a focus on (social) networks. The framework seamlessly supports distribution across multiple compute nodes, enabling simulations that would otherwise be beyond the capabilities of a single machine. Implemented in Julia, Vahana.jl leverages the interactive Read-Eval-Print Loop (REPL) environment, facilitating rapid model development and experimentation.

Problem

• Addresses computational limitations in large-scale agent-based models
• Enables distributed simulations across multiple compute nodes
• Facilitates rapid development of network-focused agent-based models

Innovation

• Framework for large-scale agent-based models
• Uses synchronous graph dynamical systems formalism
• Distributes simulations across multiple compute nodes