Matches in SemOpenAlex for { <https://semopenalex.org/work/W4384157961> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4384157961 abstract "We consider the problem of designing and training a neural network-based orchestrator for fog computing service deployment. Our goal is to train an orchestrator able to optimize diversified and competing QoS requirements, such as blocking probability and service delay, while potentially supporting thousands of fog nodes. To cope with said challenges, we implement our neural orchestrator as a Deep Set (DS) network operating on sets of fog nodes, and we leverage Deep Reinforcement Learning (DRL) with invalid action masking to find an optimal trade-off between competing objectives. Illustrative numerical results show that our Deep Set-based policy generalizes well to problem sizes (i.e., in terms of numbers of fog nodes) up to two orders of magnitude larger than the ones seen during the training phase, outperforming both greedy heuristics and traditional Multi-Layer Perceptron (MLP)-based DRL. In addition, inference times of our DS-based policy are up to an order of magnitude faster than an MLP, allowing for excellent scalability and near real-time online decision-making." @default.
- W4384157961 created "2023-07-14" @default.
- W4384157961 creator A5011458485 @default.
- W4384157961 creator A5021764238 @default.
- W4384157961 creator A5036893834 @default.
- W4384157961 creator A5038421080 @default.
- W4384157961 creator A5038468421 @default.
- W4384157961 creator A5057533274 @default.
- W4384157961 creator A5078624775 @default.
- W4384157961 date "2023-06-19" @default.
- W4384157961 modified "2023-09-24" @default.
- W4384157961 title "DRL-FORCH: A Scalable Deep Reinforcement Learning-based Fog Computing Orchestrator" @default.
- W4384157961 cites W2114623221 @default.
- W4384157961 cites W2617931713 @default.
- W4384157961 cites W2903362341 @default.
- W4384157961 cites W2951469844 @default.
- W4384157961 cites W2956490995 @default.
- W4384157961 cites W3004790966 @default.
- W4384157961 cites W3037164854 @default.
- W4384157961 cites W3133765947 @default.
- W4384157961 cites W3173424115 @default.
- W4384157961 cites W3189481398 @default.
- W4384157961 cites W4205451253 @default.
- W4384157961 cites W4206179170 @default.
- W4384157961 cites W4283313650 @default.
- W4384157961 cites W4285087766 @default.
- W4384157961 cites W4285196348 @default.
- W4384157961 cites W4288070065 @default.
- W4384157961 cites W4310608581 @default.
- W4384157961 cites W4315629711 @default.
- W4384157961 cites W4320029416 @default.
- W4384157961 doi "https://doi.org/10.1109/netsoft57336.2023.10175398" @default.
- W4384157961 hasPublicationYear "2023" @default.
- W4384157961 type Work @default.
- W4384157961 citedByCount "0" @default.
- W4384157961 crossrefType "proceedings-article" @default.
- W4384157961 hasAuthorship W4384157961A5011458485 @default.
- W4384157961 hasAuthorship W4384157961A5021764238 @default.
- W4384157961 hasAuthorship W4384157961A5036893834 @default.
- W4384157961 hasAuthorship W4384157961A5038421080 @default.
- W4384157961 hasAuthorship W4384157961A5038468421 @default.
- W4384157961 hasAuthorship W4384157961A5057533274 @default.
- W4384157961 hasAuthorship W4384157961A5078624775 @default.
- W4384157961 hasConcept C105339364 @default.
- W4384157961 hasConcept C105795698 @default.
- W4384157961 hasConcept C106189395 @default.
- W4384157961 hasConcept C111919701 @default.
- W4384157961 hasConcept C115903868 @default.
- W4384157961 hasConcept C120314980 @default.
- W4384157961 hasConcept C127705205 @default.
- W4384157961 hasConcept C153083717 @default.
- W4384157961 hasConcept C154945302 @default.
- W4384157961 hasConcept C159886148 @default.
- W4384157961 hasConcept C31258907 @default.
- W4384157961 hasConcept C33923547 @default.
- W4384157961 hasConcept C41008148 @default.
- W4384157961 hasConcept C48044578 @default.
- W4384157961 hasConcept C50644808 @default.
- W4384157961 hasConcept C5119721 @default.
- W4384157961 hasConcept C60908668 @default.
- W4384157961 hasConcept C97541855 @default.
- W4384157961 hasConceptScore W4384157961C105339364 @default.
- W4384157961 hasConceptScore W4384157961C105795698 @default.
- W4384157961 hasConceptScore W4384157961C106189395 @default.
- W4384157961 hasConceptScore W4384157961C111919701 @default.
- W4384157961 hasConceptScore W4384157961C115903868 @default.
- W4384157961 hasConceptScore W4384157961C120314980 @default.
- W4384157961 hasConceptScore W4384157961C127705205 @default.
- W4384157961 hasConceptScore W4384157961C153083717 @default.
- W4384157961 hasConceptScore W4384157961C154945302 @default.
- W4384157961 hasConceptScore W4384157961C159886148 @default.
- W4384157961 hasConceptScore W4384157961C31258907 @default.
- W4384157961 hasConceptScore W4384157961C33923547 @default.
- W4384157961 hasConceptScore W4384157961C41008148 @default.
- W4384157961 hasConceptScore W4384157961C48044578 @default.
- W4384157961 hasConceptScore W4384157961C50644808 @default.
- W4384157961 hasConceptScore W4384157961C5119721 @default.
- W4384157961 hasConceptScore W4384157961C60908668 @default.
- W4384157961 hasConceptScore W4384157961C97541855 @default.
- W4384157961 hasLocation W43841579611 @default.
- W4384157961 hasOpenAccess W4384157961 @default.
- W4384157961 hasPrimaryLocation W43841579611 @default.
- W4384157961 hasRelatedWork W1596201972 @default.
- W4384157961 hasRelatedWork W1608069547 @default.
- W4384157961 hasRelatedWork W2364921833 @default.
- W4384157961 hasRelatedWork W2385146268 @default.
- W4384157961 hasRelatedWork W2953167564 @default.
- W4384157961 hasRelatedWork W3102103141 @default.
- W4384157961 hasRelatedWork W3213838085 @default.
- W4384157961 hasRelatedWork W4286713570 @default.
- W4384157961 hasRelatedWork W4312263439 @default.
- W4384157961 hasRelatedWork W4286693834 @default.
- W4384157961 isParatext "false" @default.
- W4384157961 isRetracted "false" @default.
- W4384157961 workType "article" @default.