Simulation of a multi-agent protocol for task allocation in cooperative design

To achieve high performance in agent-based cooperative design, the effective allocation of design agents to distributed and cooperative design tasks becomes a crucial issue. This research extends the well-known contract net protocol for decentralized task allocation in cooperative engineering design. Since the contract net protocol only provides a generic framework for agents to exchange and evaluate information, it does not prescribe any specific coordination policies for cooperative engineering design. By adding a set of agent selection and task selection policies, this research addresses issues in agent-based cooperative engineering design such as: How is an agent selected to carry out a design task? How can an agent select from among a list of design tasks which to bid for? Through a series of colored Petri-net simulation experiments, the performance of these selection policies are measured and evaluated. Smith (1980) noted that the contract net protocol is particularly suitable for executing different (sub-)tasks simultaneously while ensuring effective resource allocation and focused decision. Results from the coloured Petri-net simulations have shown that these properties are preserved in the proposed protocol