Matches in SemOpenAlex for { <https://semopenalex.org/work/W3081964860> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3081964860 endingPage "107528" @default.
- W3081964860 startingPage "107528" @default.
- W3081964860 abstract "Traffic Optimization (TO) is a well-known and established topic in datacenters with the fundamental goal of operating networks efficiently. Traditional TO heuristics may suffer from performance penalty as it mismatches actual traffic, while Artificial Intelligence (AI) which has undergone a renaissance recently is gradually being applied to the network optimization and has shown excellent advantages. However, the current AI technologies (e.g., DGN, DRL, DBA, etc.) have difficulty in adapting to the dynamic and variable characteristics of the network due to their lack of generalization ability, which limits the development of intelligent networks. As Graph Neural Network (GNN) can support relational reasoning and combinatorial generalization, we research how to model and optimize traffic in datacenters with GNN in this paper. First, we proposed a GNN model for reasoning Flow Completion Time (FCT), which is able to provide accurate estimation of never-seen network states. Then we designed a GNN-based optimizer for TO, which can be used to in flow routing, flow scheduling and topology management. Finally, the experimental results verify that the GNN model has a high inference accuracy, and the GNN-based optimizer can significantly reduce the average / p10 (the 10th percentile) FCT. Therefore, GNN has a great potential in network modeling and optimization, and has a wide range of applications." @default.
- W3081964860 created "2020-09-08" @default.
- W3081964860 creator A5034664468 @default.
- W3081964860 creator A5082575321 @default.
- W3081964860 creator A5089450416 @default.
- W3081964860 date "2020-11-01" @default.
- W3081964860 modified "2023-10-02" @default.
- W3081964860 title "Traffic modeling and optimization in datacenters with graph neural network" @default.
- W3081964860 cites W2020629400 @default.
- W3081964860 cites W2062832101 @default.
- W3081964860 cites W2091053569 @default.
- W3081964860 cites W2117884704 @default.
- W3081964860 cites W2141810662 @default.
- W3081964860 cites W2257979135 @default.
- W3081964860 cites W2512877821 @default.
- W3081964860 cites W2549627699 @default.
- W3081964860 cites W2560361359 @default.
- W3081964860 cites W2594041104 @default.
- W3081964860 cites W2595032667 @default.
- W3081964860 cites W2606725858 @default.
- W3081964860 cites W2620303912 @default.
- W3081964860 cites W2620725079 @default.
- W3081964860 cites W2625191576 @default.
- W3081964860 cites W2792281126 @default.
- W3081964860 cites W2886938859 @default.
- W3081964860 cites W2887603607 @default.
- W3081964860 cites W2887702059 @default.
- W3081964860 cites W2963091558 @default.
- W3081964860 cites W2963222872 @default.
- W3081964860 cites W2964084343 @default.
- W3081964860 cites W3015370673 @default.
- W3081964860 cites W4237515752 @default.
- W3081964860 cites W4249923717 @default.
- W3081964860 doi "https://doi.org/10.1016/j.comnet.2020.107528" @default.
- W3081964860 hasPublicationYear "2020" @default.
- W3081964860 type Work @default.
- W3081964860 sameAs 3081964860 @default.
- W3081964860 citedByCount "12" @default.
- W3081964860 countsByYear W30819648602020 @default.
- W3081964860 countsByYear W30819648602021 @default.
- W3081964860 countsByYear W30819648602022 @default.
- W3081964860 countsByYear W30819648602023 @default.
- W3081964860 crossrefType "journal-article" @default.
- W3081964860 hasAuthorship W3081964860A5034664468 @default.
- W3081964860 hasAuthorship W3081964860A5082575321 @default.
- W3081964860 hasAuthorship W3081964860A5089450416 @default.
- W3081964860 hasConcept C111919701 @default.
- W3081964860 hasConcept C126255220 @default.
- W3081964860 hasConcept C127705205 @default.
- W3081964860 hasConcept C134306372 @default.
- W3081964860 hasConcept C154945302 @default.
- W3081964860 hasConcept C177148314 @default.
- W3081964860 hasConcept C206729178 @default.
- W3081964860 hasConcept C2776214188 @default.
- W3081964860 hasConcept C33923547 @default.
- W3081964860 hasConcept C41008148 @default.
- W3081964860 hasConcept C50644808 @default.
- W3081964860 hasConceptScore W3081964860C111919701 @default.
- W3081964860 hasConceptScore W3081964860C126255220 @default.
- W3081964860 hasConceptScore W3081964860C127705205 @default.
- W3081964860 hasConceptScore W3081964860C134306372 @default.
- W3081964860 hasConceptScore W3081964860C154945302 @default.
- W3081964860 hasConceptScore W3081964860C177148314 @default.
- W3081964860 hasConceptScore W3081964860C206729178 @default.
- W3081964860 hasConceptScore W3081964860C2776214188 @default.
- W3081964860 hasConceptScore W3081964860C33923547 @default.
- W3081964860 hasConceptScore W3081964860C41008148 @default.
- W3081964860 hasConceptScore W3081964860C50644808 @default.
- W3081964860 hasLocation W30819648601 @default.
- W3081964860 hasOpenAccess W3081964860 @default.
- W3081964860 hasPrimaryLocation W30819648601 @default.
- W3081964860 hasRelatedWork W1522517976 @default.
- W3081964860 hasRelatedWork W1756885467 @default.
- W3081964860 hasRelatedWork W1971541091 @default.
- W3081964860 hasRelatedWork W2034983601 @default.
- W3081964860 hasRelatedWork W2386387936 @default.
- W3081964860 hasRelatedWork W2560284304 @default.
- W3081964860 hasRelatedWork W2884576438 @default.
- W3081964860 hasRelatedWork W2885094885 @default.
- W3081964860 hasRelatedWork W2905364337 @default.
- W3081964860 hasRelatedWork W3042941765 @default.
- W3081964860 hasVolume "181" @default.
- W3081964860 isParatext "false" @default.
- W3081964860 isRetracted "false" @default.
- W3081964860 magId "3081964860" @default.
- W3081964860 workType "article" @default.