对等网络中基于模糊集的信任和声望模型

A fuzzy set-based trust and reputation model for P2P networks

在对等网络中,信任可以用于指导实体的协作决策,当前信任建模已成为一个研究焦点.该文提出了一个基于模糊集的信任和声望模型,模型根据实体的经验和其他实体的推荐信息构建对目标实体的信任.模型使用了语义标签来刻画不同的信任级,并能够综合评判不同方面的信任值.实体在采纳信任推荐时,模型利用模糊贴近度来表达推荐的正确度,并据此调整推荐者的影响.使用该模型的文件共享网络仿真实验可以正确地表达对实体的信任,促进具有相同偏好的实体群组的形成,提高交易质量.

In peer-to-peer （P2P） networks, trust plays an important.role in making collaborative decisions. Here, a fuzzy set-based trust and reputation model is proposed for peers to build trust and reputation based on observations and recommendations. In the model, linguistic labels were used for presenting differentiated trust levels, and trust on different aspects in collaborations could be combined. In deducing the target peers＇ reputations, accuracy of recommendations was represented by a fuzzy similarity measure, so an algorithm was introduced to tune corresponding recommenders＇ impacts on the results based on it. The simulation model shows that the trust to peers can be represented. Moreover, the model is effective because it promotes the formation of peer groups with similar preferences and improves the qualities of transactions.