Matches in SemOpenAlex for { <https://semopenalex.org/work/W4301206543> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4301206543 endingPage "501" @default.
- W4301206543 startingPage "486" @default.
- W4301206543 abstract "Network slicing is a key feature of 5G and beyond networks, allowing the deployment of separate logical networks (network slices), sharing a common underlying physical infrastructure, and characterized by distinct descriptors and behaviors. The dynamic allocation of physical network resources among coexisting slices should address a challenging trade-off: to use resources efficiently while assigning each slice sufficient resources to meet its service level agreement (SLA). We consider the allocation of time-frequency resources from a new perspective: to design a control algorithm capable of learning over the operating network, while keeping the SLA violation rate under an acceptable level during the learning process. For this purpose, traditional model-free reinforcement learning (RL) methods present several drawbacks: low sample efficiency, extensive exploration of the policy space, and inability to discriminate between conflicting objectives, causing inefficient use of the resources and/or frequent SLA violations during the learning process. To overcome these limitations, we propose a model-based RL approach built upon a novel modeling strategy that comprises a kernel-based classifier and a self-assessment mechanism. In numerical experiments, our proposal, referred to as kernel-based RL, clearly outperforms state-of-the-art RL algorithms in terms of SLA fulfillment, resource efficiency, and computational overhead." @default.
- W4301206543 created "2022-10-05" @default.
- W4301206543 creator A5005894115 @default.
- W4301206543 creator A5008187510 @default.
- W4301206543 creator A5043927182 @default.
- W4301206543 creator A5081774524 @default.
- W4301206543 date "2023-01-01" @default.
- W4301206543 modified "2023-10-14" @default.
- W4301206543 title "Model-Based Reinforcement Learning With Kernels for Resource Allocation in RAN Slices" @default.
- W4301206543 cites W2604174486 @default.
- W4301206543 cites W2612074600 @default.
- W4301206543 cites W2736856820 @default.
- W4301206543 cites W2758392317 @default.
- W4301206543 cites W2781839613 @default.
- W4301206543 cites W2783072796 @default.
- W4301206543 cites W2793519446 @default.
- W4301206543 cites W2808617274 @default.
- W4301206543 cites W2898035736 @default.
- W4301206543 cites W2900804979 @default.
- W4301206543 cites W2909897216 @default.
- W4301206543 cites W2916079228 @default.
- W4301206543 cites W2920988370 @default.
- W4301206543 cites W2926170212 @default.
- W4301206543 cites W2940469682 @default.
- W4301206543 cites W2945086780 @default.
- W4301206543 cites W2946073848 @default.
- W4301206543 cites W2951469844 @default.
- W4301206543 cites W2952685986 @default.
- W4301206543 cites W2963863328 @default.
- W4301206543 cites W2964288953 @default.
- W4301206543 cites W2969985720 @default.
- W4301206543 cites W2970759804 @default.
- W4301206543 cites W2979918265 @default.
- W4301206543 cites W2996431531 @default.
- W4301206543 cites W3002189898 @default.
- W4301206543 cites W3016185400 @default.
- W4301206543 cites W3021111496 @default.
- W4301206543 cites W3039237082 @default.
- W4301206543 cites W3080563266 @default.
- W4301206543 cites W3081211774 @default.
- W4301206543 cites W3101749733 @default.
- W4301206543 cites W3111924881 @default.
- W4301206543 cites W3122801138 @default.
- W4301206543 cites W3153842551 @default.
- W4301206543 cites W3173151636 @default.
- W4301206543 cites W4249572517 @default.
- W4301206543 doi "https://doi.org/10.1109/twc.2022.3195570" @default.
- W4301206543 hasPublicationYear "2023" @default.
- W4301206543 type Work @default.
- W4301206543 citedByCount "3" @default.
- W4301206543 countsByYear W43012065432023 @default.
- W4301206543 crossrefType "journal-article" @default.
- W4301206543 hasAuthorship W4301206543A5005894115 @default.
- W4301206543 hasAuthorship W4301206543A5008187510 @default.
- W4301206543 hasAuthorship W4301206543A5043927182 @default.
- W4301206543 hasAuthorship W4301206543A5081774524 @default.
- W4301206543 hasBestOaLocation W43012065431 @default.
- W4301206543 hasConcept C111919701 @default.
- W4301206543 hasConcept C119857082 @default.
- W4301206543 hasConcept C120314980 @default.
- W4301206543 hasConcept C154945302 @default.
- W4301206543 hasConcept C2779960059 @default.
- W4301206543 hasConcept C29202148 @default.
- W4301206543 hasConcept C31258907 @default.
- W4301206543 hasConcept C41008148 @default.
- W4301206543 hasConcept C97541855 @default.
- W4301206543 hasConceptScore W4301206543C111919701 @default.
- W4301206543 hasConceptScore W4301206543C119857082 @default.
- W4301206543 hasConceptScore W4301206543C120314980 @default.
- W4301206543 hasConceptScore W4301206543C154945302 @default.
- W4301206543 hasConceptScore W4301206543C2779960059 @default.
- W4301206543 hasConceptScore W4301206543C29202148 @default.
- W4301206543 hasConceptScore W4301206543C31258907 @default.
- W4301206543 hasConceptScore W4301206543C41008148 @default.
- W4301206543 hasConceptScore W4301206543C97541855 @default.
- W4301206543 hasFunder F4320322930 @default.
- W4301206543 hasIssue "1" @default.
- W4301206543 hasLocation W43012065431 @default.
- W4301206543 hasOpenAccess W4301206543 @default.
- W4301206543 hasPrimaryLocation W43012065431 @default.
- W4301206543 hasRelatedWork W2025035551 @default.
- W4301206543 hasRelatedWork W2092071486 @default.
- W4301206543 hasRelatedWork W2391167130 @default.
- W4301206543 hasRelatedWork W2766695165 @default.
- W4301206543 hasRelatedWork W3074294383 @default.
- W4301206543 hasRelatedWork W3092645890 @default.
- W4301206543 hasRelatedWork W4283067488 @default.
- W4301206543 hasRelatedWork W4287643190 @default.
- W4301206543 hasRelatedWork W4319083788 @default.
- W4301206543 hasRelatedWork W2460246254 @default.
- W4301206543 hasVolume "22" @default.
- W4301206543 isParatext "false" @default.
- W4301206543 isRetracted "false" @default.
- W4301206543 workType "article" @default.