The Implement Of Multi-Agent Based Agile Production Scheduling System

This research direction comes from a Discrete ERP system made by our lab for an automobile company in Dalian. Production scheduling system is the core of ERP, and also the bottleneck of ERP. In the situation of agile and global manufacturing, production scheduling research faces many new problems. A Multi-Agent based Scheduling System (MASS) is presented in this paper to solve the agile scheduling problem.After deeply researching the current research achievements, this paper built multi-agent model which is consisted of TMA, RMA, TA and RA. A hybrid type of Agent is built to make agent individual able to think and active. A hybrid architecture of multi-agent integrates the hierarchy and the heterarchy is also proposed after analyzing. There are horizontal and vertical negotiations in the architecture of MASS in order to overcome drawbacks of hierarchy and heterarchy, and to make the MASS agile and flexible responses capabilities and a feasible, robust and near optimized schedulers.Negotiation mechanism is an important part of this paper. The scheduling result is obtained through the negotiation between different types of agents. This negotiation mechanism is based on Message Report mechanism. Each type of agent has its own message interface which includes some scheduling algorithm and decision function. It is beneficial to decrease the number of negotiation. This negotiation mechanism provides an environment for agents to develop their speciality. It can also integrate good scheduling algorithm and strategy.In the end, a multi-agent scheduling system is built up using distributed object technology. In the support of RMI technology, the communication of agents is implemented. We also did some experiments about agile production environment. The simulation results have successfully shown that the approach is capable of generating feasible schedulers in an agile manufacturing environment. The experiments have also demonstrated that it has incorporated the features of adaptive and agility to changes in production diversity and environment configuration.