摘要:In recent years, various applications of Peer-to-Peer (P2P) computing have been widely used because of its unique advantages, which have played an important role in commerce, communications and other fields. The P2P system is essentially a distributed system, without central servers. Each peer is both client and server, who have the same status. However, some features of P2P networks, such as autonomy, dynamic, and heterogeneity lead to an important problem, namely unreliable quality of service. Unreliable quality of service is usually presented as providing false or unreliable service, impacting customer satisfaction. The establishment of trust models which evaluates capabilities of peers can measure the service capacity of a peer, and identify malicious behavior, thereby reducing the risk of interaction and being an effective technique to ensure the overall availability of P2P networks. A trust model named METrust in P2P networks based on the recommendation is proposed. In METrust, a peer selects recommendation peers whose evaluation criteria are similar, and evaluation criteria of peers are determined through the AHP method (Analytic Hierarchy Process). Each peer in the network has a unique credibility of recommendation, and two trust parameters for updating the credibility of recommendation are introduced, namely updating range and updating strength. METrust proposes algorithms to compute the trust of peers. Simulations show that, the trust model METrust can identify malicious peers, and improve the quality of service in P2P networks effectively.