دانلود رایگان مقاله توپولوژی در مقیاس آزاد محدود با مشارکت همتای پویا

Abstract

Growth models have been proposed for constructing the scale-free overlay topology to improve the performance of unstructured peer-to-peer (P2P) networks. However, previous growth models are able to maintain the limited scale-free topology when nodes only join but do not leave the network; the case of nodes leaving the network while preserving a precise scaling parameter is not included in the solution. Thus, the full dynamic of node participation, inherent in P2P networks, is not considered in these models. In order to handle both nodes joining and leaving the network, we propose a robust growth model E-SRA, which is capable of producing the perfect limited scale-free overlay topology with user-defined scaling parameter and hard cut-off. Scalability of our approach is ensured since no global information is required to add or remove a node. E-SRA is also tolerant to individual node failure caused by errors or attacks. Simulations have shown that E-SRA outperforms other growth models by producing topologies with high adherence to the desired scale-free property. Search algorithms, including flooding and normalized flooding, achieve higher efficiency over the topologies produced by E-SRA.

6. Conclusion

E-SRA, an efficient algorithm for maintaining the limited scalefree topology with dynamic peer participation, is proposed. It produces the overlay topology which improves the P2P network performance. The user can define scaling and cut-off parameters of the overlay network to achieve the best performance. Nodes with any degrees, including hubs, are allowed to be removed from the network freely. Our approach is tolerant to the removal of nodes in any patterns and partially tolerant to node failures by having the neighbors of the failing nodes connecting to the remaining nodes smartly. Simulations have shown that E-SRA outperforms previous growth models by producing overlay topologies with higher adherence to the scale-free property. And search algorithms, includ-ing the Flooding algorithm and the Normalized Flooding algorithm, achieve better search efficiency over the topologies produced by E-SRA than by previous growth models. In the future, we plan to study the approach to preserve the power-law distribution under simultaneous failures of a group of nodes. And we are also interested in creating growth models which take user behaviors of P2P networks, such as biased access, into consideration.