A systematic approach for end-to-end QoS qualitative diagnosis and quantitative guarantee is proposed to support quality of service （QoS） management on current Internet. An automatic unwatched discretization algorit...A systematic approach for end-to-end QoS qualitative diagnosis and quantitative guarantee is proposed to support quality of service （QoS） management on current Internet. An automatic unwatched discretization algorithm for discretizing continuous numeric-values is brought forth to reshape these QoS metrics and contexts into their discrete forms. For QoS qualitative diagnosis, causal relationships between a QoS metric and its contexts are exploited with K2 Bayesian network （BN） structure learning by treating QoS metrics and contexts as BN nodes. A QoS metric node is qualitatively diagnosed to be causally related to its parent context nodes. To guarantee QoS quantitatively, those causal relationships are next modeled quantitatively by BN parameter learning. Then, BN inference can be carried out on the BN. Finally, the QoS metric is guaranteed to a specific value with certain probability by tuning its causal contexts to suitable values suggested by the BN inference. Our approach is validated to be sound and effective by simulations on a peer-to-peer （P2P） network.展开更多
基金Supported by the National High Technology Research and Development Program of China （No. 2007AA010302, 2009AA012404） the National Basic Research Program of China （No. 2007CB307103）+1 种基金 the National Natural Science Foundation of China （No. 60432010, 60802034） the Specialized Research Fund for the Doctoral Program of Higher Education （No. 20070013026）.
文摘A systematic approach for end-to-end QoS qualitative diagnosis and quantitative guarantee is proposed to support quality of service （QoS） management on current Internet. An automatic unwatched discretization algorithm for discretizing continuous numeric-values is brought forth to reshape these QoS metrics and contexts into their discrete forms. For QoS qualitative diagnosis, causal relationships between a QoS metric and its contexts are exploited with K2 Bayesian network （BN） structure learning by treating QoS metrics and contexts as BN nodes. A QoS metric node is qualitatively diagnosed to be causally related to its parent context nodes. To guarantee QoS quantitatively, those causal relationships are next modeled quantitatively by BN parameter learning. Then, BN inference can be carried out on the BN. Finally, the QoS metric is guaranteed to a specific value with certain probability by tuning its causal contexts to suitable values suggested by the BN inference. Our approach is validated to be sound and effective by simulations on a peer-to-peer （P2P） network.
