Multi-agent technology for planning, scheduling, and resource allocation

Abstract

A large number of hot applications are reducible to combinatorial models. Almost all of them are at least NP-hard and cannot be solved in a traditional way. We consider an agent-based approach to solve a set of planning and scheduling applications under real time and temporal constraints. The problem is formalised as a contract allocation task over a set of companies and specified as an auction-based competition of agents managed by a meta-agent. The contributions are: the multi-agent system architecture; knowledge-based specification of real time and temporal constraints; and a knowledge-based auction management model.