Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384112103> ?p ?o ?g. }
Showing items 1 to 57 of
57
with 100 items per page.
- W4384112103 abstract "We seek the best traffic allocation scheme for the edge-cloud computing network that satisfies constraints and minimizes the cost based on burstable billing. First, for a fixed network topology, we formulate a family of integer programming problems with random parameters describing the various traffic demands. Then, to overcome the difficulty caused by the discrete feature of the problem, we generalize the Gumbel-softmax reparameterization method to induce an unconstrained continuous optimization problem as a regularized continuation of the discrete problem. Finally, we introduce the Gumbel-softmax sampling network to solve the optimization problems via unsupervised learning. The network structure reflects the edge-cloud computing topology and is trained to minimize the expectation of the cost function for unconstrained continuous optimization problems. The trained network works as an efficient traffic allocation scheme sampler, remarkably outperforming the random strategy in feasibility and cost function value. Besides testing the quality of the output allocation scheme, we examine the generalization property of the network by increasing the time steps and the number of users. We also feed the solution to existing integer optimization solvers as initial conditions and verify the warm-starts can accelerate the short-time iteration process. The framework is general with solid performance, and the decoupled feature of the random neural networks is adequate for practical implementations." @default.
- W4384112103 created "2023-07-13" @default.
- W4384112103 creator A5004999564 @default.
- W4384112103 creator A5032908281 @default.
- W4384112103 creator A5046335655 @default.
- W4384112103 creator A5046807824 @default.
- W4384112103 date "2023-07-11" @default.
- W4384112103 modified "2023-09-24" @default.
- W4384112103 title "Neural Quantile Optimization for Edge-Cloud Computing" @default.
- W4384112103 doi "https://doi.org/10.48550/arxiv.2307.05170" @default.
- W4384112103 hasPublicationYear "2023" @default.
- W4384112103 type Work @default.
- W4384112103 citedByCount "0" @default.
- W4384112103 crossrefType "posted-content" @default.
- W4384112103 hasAuthorship W4384112103A5004999564 @default.
- W4384112103 hasAuthorship W4384112103A5032908281 @default.
- W4384112103 hasAuthorship W4384112103A5046335655 @default.
- W4384112103 hasAuthorship W4384112103A5046807824 @default.
- W4384112103 hasBestOaLocation W43841121031 @default.
- W4384112103 hasConcept C111919701 @default.
- W4384112103 hasConcept C11413529 @default.
- W4384112103 hasConcept C126255220 @default.
- W4384112103 hasConcept C137836250 @default.
- W4384112103 hasConcept C154945302 @default.
- W4384112103 hasConcept C188441871 @default.
- W4384112103 hasConcept C33923547 @default.
- W4384112103 hasConcept C41008148 @default.
- W4384112103 hasConcept C50644808 @default.
- W4384112103 hasConcept C56086750 @default.
- W4384112103 hasConcept C79974875 @default.
- W4384112103 hasConceptScore W4384112103C111919701 @default.
- W4384112103 hasConceptScore W4384112103C11413529 @default.
- W4384112103 hasConceptScore W4384112103C126255220 @default.
- W4384112103 hasConceptScore W4384112103C137836250 @default.
- W4384112103 hasConceptScore W4384112103C154945302 @default.
- W4384112103 hasConceptScore W4384112103C188441871 @default.
- W4384112103 hasConceptScore W4384112103C33923547 @default.
- W4384112103 hasConceptScore W4384112103C41008148 @default.
- W4384112103 hasConceptScore W4384112103C50644808 @default.
- W4384112103 hasConceptScore W4384112103C56086750 @default.
- W4384112103 hasConceptScore W4384112103C79974875 @default.
- W4384112103 hasLocation W43841121031 @default.
- W4384112103 hasOpenAccess W4384112103 @default.
- W4384112103 hasPrimaryLocation W43841121031 @default.
- W4384112103 hasRelatedWork W1987021796 @default.
- W4384112103 hasRelatedWork W2089095906 @default.
- W4384112103 hasRelatedWork W2137434397 @default.
- W4384112103 hasRelatedWork W2163000239 @default.
- W4384112103 hasRelatedWork W2187613024 @default.
- W4384112103 hasRelatedWork W2209011256 @default.
- W4384112103 hasRelatedWork W2807131660 @default.
- W4384112103 hasRelatedWork W2921003940 @default.
- W4384112103 hasRelatedWork W2990278782 @default.
- W4384112103 hasRelatedWork W3200240795 @default.
- W4384112103 isParatext "false" @default.
- W4384112103 isRetracted "false" @default.
- W4384112103 workType "article" @default.