An Agent-Based Decentralised Approach to Disturbances in Rail Systems

Agent-based solutions of various architectures have been increasingly been applied to the Railway Traffic Management problem. This paper proposes a decentralised solution to this problem utilising Belief-Desire-Intention agents exhibiting proactive and reactive behaviours. This approach provides a scalable framework to study and solve problems in uncertain, dynamic environments such as railway systems. The model is applied to schedule data from an existing rail system. The contribution of this work is a fully decentralised model founded on agents that cooperate to solve problems locally without a central authority.