Abstraction Mechanisms Towards Large-Scale Agent-Based Simulations.

摘要

The typically large degrees of interaction in agent-based simulations come at considerable computational costs. In this thesis, we propose an abstraction framework to reduce the run-time of the simulations by learning recurring patterns. We employ machine learning techniques to abstract groups of agents or their behaviours to cut down computational complexity, while preserving the inherent flexibility of agent-based models. The learned abstractions, which subsume the underlying model agents' interactions, are constantly tested for their validity---after all, the dynamics of a system may change over time to such an extent that previously learned patterns would not reoccur. An invalid abstraction is, therefore, removed from the simulation. The creation and removal of abstractions continues throughout the course of a simulation in order to ensure an adequate adaptation to the system dynamics. Experimental results on biological agent-based simulations show that our proposed framework can successfully boost the simulation speed while maintaining the freedom of arbitrary interactions.