基于协作度的分布式自动协商联盟形成机制

Collaborative-Degree Based Distributed Automatic Negotiation Coalition Formation Mechanism

现有联盟形成的研究中大都没有考虑到不同Agent的协作资源和协作态度不同的异质性,而是假定所有Agent具有相同的协作资源和协作态度.为此提出一种基于协作度的分布式自动协商联盟形成机制(collaborative degree-based distributed automatic negotiation coalition formation mechanism,CDBDN),通过对处在网络拓扑结构中Agent的协作资源和协作态度的描述建立Agent协作度的概念.以分布式的应用环境为背景,建立分布式协商协议(distributed negotiation protocal,DNP)来实现分布式自动协商方式构建联盟.该机制建立了分布式协商协议和引入了Agent协作度,提出基于Agent协作度的协商策略.实验结果表明,该机制在联盟形成的效率、Agent协商效率和个体效用方面都表现出有较好的性能.

Most of current researches on coalition formation do not take into account the heterogeneity of collaboration resources and collaborative attitude of Agents, but assume that all Agents have same collaboration resources and attitude. Apparently that assumption is too restrictive and unrealistic. To this end, a collaborative degree-based distributed automatic negotiation coalition formation mechanism is proposed in this paper. This mechanism consists of three main parts： collaborative degree, distributed negotiation protocol （DNP） and negotiation strategy. At first, the concept of collaborative degree is introduced with the collaboration of resources and collaborative attitude description in network topology. Next, in order to solve the synchronization problem of information flow in distributed application environment, a distributed negotiation protocol is established to achieve distributed auto-negotiation way to build coalition, which can guarantee the convergence of negotiation and do not deadlock. Then, the negotiation strategy based on the degree of collaboration is established to reflect the differences of Agent collaboration resources and collaborative attitude. So, this mechanism establishes distributed negotiation protocols and introduces Agent collaboration degree, and proposes the negotiation strategy based on the degree of collaboration. Finally, experiment results show that the coalition formation efficiency, negotiation efficiency and individual utility of the mechanism are better than other related mechanisms.