Matches in SemOpenAlex for { <https://semopenalex.org/work/W2783238505> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2783238505 abstract "In this paper, we propose a two-layer framework to learn the optimal handover (HO) controllers in possibly large-scale wireless systems supporting mobile Internet-of-Things (IoT) users or traditional cellular users, where the user mobility patterns could be heterogeneous. In particular, our proposed framework first partitions the user equipments (UEs) with different mobility patterns into clusters, where the mobility patterns are similar in the same cluster. Then, within each cluster, an asynchronous multi-user deep reinforcement learning scheme is developed to control the HO processes across the UEs in each cluster, in the goal of lowering the HO rate while ensuring certain system throughput. In this scheme, we use a deep neural network (DNN) as an HO controller learned by each UE via reinforcement learning in a collaborative fashion. Moreover, we use supervised learning in initializing the DNN controller before the execution of reinforcement learning to exploit what we already know with traditional HO schemes and to mitigate the negative effects of random exploration at the initial stage. Furthermore, we show that the adopted global-parameter-based asynchronous framework enables us to train faster with more UEs, which could nicely address the scalability issue to support large systems. Finally, simulation results demonstrate that the proposed framework can achieve better performance than the state-of-art on-line schemes, in terms of HO rates." @default.
- W2783238505 created "2018-01-26" @default.
- W2783238505 creator A5009164482 @default.
- W2783238505 creator A5026608908 @default.
- W2783238505 creator A5036016529 @default.
- W2783238505 creator A5076042378 @default.
- W2783238505 creator A5080546910 @default.
- W2783238505 date "2018-01-06" @default.
- W2783238505 modified "2023-10-17" @default.
- W2783238505 title "Handover Control in Wireless Systems via Asynchronous Multi-User Deep Reinforcement Learning" @default.
- W2783238505 cites W1497754119 @default.
- W2783238505 cites W1777239053 @default.
- W2783238505 cites W1989449561 @default.
- W2783238505 cites W1994777229 @default.
- W2783238505 cites W2037527348 @default.
- W2783238505 cites W2056985365 @default.
- W2783238505 cites W2084175025 @default.
- W2783238505 cites W2097747115 @default.
- W2783238505 cites W2113586398 @default.
- W2783238505 cites W2127218421 @default.
- W2783238505 cites W2145339207 @default.
- W2783238505 cites W2155027007 @default.
- W2783238505 cites W2173564293 @default.
- W2783238505 cites W2184814841 @default.
- W2783238505 cites W2252143850 @default.
- W2783238505 cites W2295761692 @default.
- W2783238505 cites W2342840547 @default.
- W2783238505 cites W2542284998 @default.
- W2783238505 cites W2553109721 @default.
- W2783238505 cites W2554536553 @default.
- W2783238505 cites W2612194121 @default.
- W2783238505 cites W2736856820 @default.
- W2783238505 cites W2964043796 @default.
- W2783238505 cites W778657980 @default.
- W2783238505 doi "https://doi.org/10.48550/arxiv.1801.02077" @default.
- W2783238505 hasPublicationYear "2018" @default.
- W2783238505 type Work @default.
- W2783238505 sameAs 2783238505 @default.
- W2783238505 citedByCount "2" @default.
- W2783238505 countsByYear W27832385052018 @default.
- W2783238505 crossrefType "posted-content" @default.
- W2783238505 hasAuthorship W2783238505A5009164482 @default.
- W2783238505 hasAuthorship W2783238505A5026608908 @default.
- W2783238505 hasAuthorship W2783238505A5036016529 @default.
- W2783238505 hasAuthorship W2783238505A5076042378 @default.
- W2783238505 hasAuthorship W2783238505A5080546910 @default.
- W2783238505 hasBestOaLocation W27832385051 @default.
- W2783238505 hasConcept C111852164 @default.
- W2783238505 hasConcept C114466953 @default.
- W2783238505 hasConcept C120314980 @default.
- W2783238505 hasConcept C151319957 @default.
- W2783238505 hasConcept C154945302 @default.
- W2783238505 hasConcept C165696696 @default.
- W2783238505 hasConcept C199360897 @default.
- W2783238505 hasConcept C203479927 @default.
- W2783238505 hasConcept C31258907 @default.
- W2783238505 hasConcept C38652104 @default.
- W2783238505 hasConcept C41008148 @default.
- W2783238505 hasConcept C48044578 @default.
- W2783238505 hasConcept C555944384 @default.
- W2783238505 hasConcept C6557445 @default.
- W2783238505 hasConcept C76155785 @default.
- W2783238505 hasConcept C77088390 @default.
- W2783238505 hasConcept C86803240 @default.
- W2783238505 hasConcept C97541855 @default.
- W2783238505 hasConceptScore W2783238505C111852164 @default.
- W2783238505 hasConceptScore W2783238505C114466953 @default.
- W2783238505 hasConceptScore W2783238505C120314980 @default.
- W2783238505 hasConceptScore W2783238505C151319957 @default.
- W2783238505 hasConceptScore W2783238505C154945302 @default.
- W2783238505 hasConceptScore W2783238505C165696696 @default.
- W2783238505 hasConceptScore W2783238505C199360897 @default.
- W2783238505 hasConceptScore W2783238505C203479927 @default.
- W2783238505 hasConceptScore W2783238505C31258907 @default.
- W2783238505 hasConceptScore W2783238505C38652104 @default.
- W2783238505 hasConceptScore W2783238505C41008148 @default.
- W2783238505 hasConceptScore W2783238505C48044578 @default.
- W2783238505 hasConceptScore W2783238505C555944384 @default.
- W2783238505 hasConceptScore W2783238505C6557445 @default.
- W2783238505 hasConceptScore W2783238505C76155785 @default.
- W2783238505 hasConceptScore W2783238505C77088390 @default.
- W2783238505 hasConceptScore W2783238505C86803240 @default.
- W2783238505 hasConceptScore W2783238505C97541855 @default.
- W2783238505 hasLocation W27832385051 @default.
- W2783238505 hasOpenAccess W2783238505 @default.
- W2783238505 hasPrimaryLocation W27832385051 @default.
- W2783238505 hasRelatedWork W1596201972 @default.
- W2783238505 hasRelatedWork W1767718647 @default.
- W2783238505 hasRelatedWork W1788737569 @default.
- W2783238505 hasRelatedWork W1986253068 @default.
- W2783238505 hasRelatedWork W2128417237 @default.
- W2783238505 hasRelatedWork W2358639633 @default.
- W2783238505 hasRelatedWork W2364921833 @default.
- W2783238505 hasRelatedWork W2385146268 @default.
- W2783238505 hasRelatedWork W2944431808 @default.
- W2783238505 hasRelatedWork W3021124033 @default.
- W2783238505 isParatext "false" @default.
- W2783238505 isRetracted "false" @default.
- W2783238505 magId "2783238505" @default.
- W2783238505 workType "article" @default.