| Summary: | 碩士 === 輔仁大學 === 資訊管理學系 === 87 === Multi-agent systems (MAS) are software programs, which possess the capabilities of autonomy, adaptation, and cooperation. Autonomy means that MAS can react to the change of environment without human’s instruction. Adaptation means that MAS can adapt itself based on the learning from its past experience. Cooperation means that inside MAS, agents can cooperate with other agents to achieve their common objective. In the regard of cooperation, MAS needs cooperation protocols which enable agents to know the ways to cooperate with each other. One typical cooperation protocol is the CNP (contract net protocol).
Agent-based EC (electronic commerce) will play an important role for future EC environment because of the growth of dynamism and complexity in the Internet environment. Therefore, the cooperation of agents is an important issue of agent-based EC.
The traditional MAS design uses the Top-Down methodology, with which MAS designers must handle all the details of the agent cooperation process. The Top-Down methodology mixes the agent task knowledge and the agent cooperation knowledge in agents. Subsequently, the Top-Down Methodology has several drawbacks.
This paper provides another view of MAS design — the Bottom-Up methodology. The Bottom-Up methodology makes it possible that agents are reassembled into multi-agent systems and agents are reused as needed. However, what do we need to successfully support the Bottom-Up design? The key is something that wraps each agent so that it exempts the designers from the careful detailed deployment of cooperation knowledge inside the agent and automates the cooperation process. This thing should be independent of the functions of agents. We name this thing as the Protocol Wrapper. This paper then presents a novel methodology of implementing the Wrapper.
At last, this paper provides an experiment, in which we use our Protocol Wrapper to implement a virtual supply chain and compare our tool with other tools to show our contribution.
|
|---|
