Modeling And Realization Of Multi-Agent Based Supply Chain System

With the development of Information Technology, supply chain management system has not being an isolate as before, each of the distributed members of the supply chain in the far distance can be linked to others. The successful implementation of supply chain management can integrate the business of internal departments and node enterprises, so as to can enhance the market competitiveness and response capabilities of the supply chain system. Nowadays, the research of supply chain system is becoming a hot spot. Agent is the entity which has some properties such as autonomy, adaptation and cooperation, and runs in dynamic environment, it develops from artificial intelligence, and has all kinds of personal attributes, such as faith, intent, expectation, goal, promise, ability, and so on. It can apperceive the environment and react to the environment. Multi-Agent System (MAS) is a dynamic system formed by some related Agents in an open and distributed environment. The Multi-Agent system includes several Agent entities, each Agent has independent function, but they must achieve some task by cooperating with each other. With the deeply studying of multi-agent system, the researchers found that there are a lot of common characteristics between the multi-agent system and supply chain system, so , using Multi-Agent system to achieve supply chain system has become the recognized research trend. Petri Net technology is suitable for modeling the coincidence and asynchronous system, its advantages is the main reason of being chosen as the modeling method, it is strictly separates ready and running state of actions, and has much more expression ability and flexible features. It has strong analysis technology and measure, such as reachability analysis and invariant analysis, these analysis methods can be applied to analyze all kinds of action characteristics of system model and the performance of computer model. However, due to the shortcomings of classical Petri Net, it is not suitable for modeling complex systems. Nevertheless, with the development of Petri net theory, several of high-level Petri Net has been founded, the shortcomings of Petri Net will be gradually improved, and Petri Net and high-level Petri Net are more effective for system modeling.This paper analyzes the characteristics of the supply chain and the supply chain system, and points out the similarities between the supply chain system and Multi-Agent system. After analyzing the feasibility about the complex system with Petri Net technology, the paper uses the extension Petri Net of the Agent conception to analysis and modeling all part of supply chain system, integrates these parts to a complete supply chain model. According to the model, the paper chooses a widely using development environment -Java Agent DEvelopment Framework (JADE) - to develop the prototype system of supply chain system, the prototype system can validate the rationality of the analysis and the system.