Learning Agents for Dynamic Supply Network Management

Supply networks rely increasingly on dynamic information flow between organisations. Providing intelligent automated collaboration requires learning capability i.e. an agent should be capable of adapting behaviour as conditions change. This paper proposes a scalable multi-agent system which uses case-based reasoning as a framework for part of its intelligence. Agents operate at two levels: an inter-enterprise level and a product/logistics level. Tests with a simulated system for buyer side operations show that such a buyer agent is capable of learning the best supplier and of adapting if supply conditions change e.g. if average delivery times deteriorate or a new supplier enters the market.