Matches in SemOpenAlex for { <https://semopenalex.org/work/W4327521519> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W4327521519 endingPage "27110" @default.
- W4327521519 startingPage "27099" @default.
- W4327521519 abstract "Nowadays, mobile application services face the challenges of high speed, low latency and high reliability. The combination of digital twin (DT) technology and mobile edge computing (MEC) network can effectively solve these challenges. DT technology can help MEC network monitor and predict the network states. In this paper, we propose a DT-aided MEC network scenario with deep neural network (DNN) inference as the computing task of end devices (EDs). ED can offload part of DNN layers to MEC server. To allocate communication resources, we propose an algorithm based on asynchronous advantage actor-critic (A3C), which manages the transmission power and channel selection of EDs. Since DNN inference is continuous in real scenes, we consider the continuous DNN inference tasks. We convert the DNN optimal partition point solving problem to a min st-cut problem, and propose a graph theory based DNN optimal partition point solving algorithm to minimize the inference latency. Simulation results show that the proposed algorithm can effectively reduce the inference latency. Compared with actor-critic (AC) and deep Q network (DQN), the proposed algorithm has faster convergence speed and better convergence value. Compared with the traditional one-time DNN model partition algorithm, the proposed algorithm is more suitable for DNN continuous task arrival scenario." @default.
- W4327521519 created "2023-03-17" @default.
- W4327521519 creator A5015025268 @default.
- W4327521519 creator A5021101912 @default.
- W4327521519 creator A5039716922 @default.
- W4327521519 creator A5063911579 @default.
- W4327521519 creator A5075080019 @default.
- W4327521519 date "2023-01-01" @default.
- W4327521519 modified "2023-09-25" @default.
- W4327521519 title "Joint Optimization of DNN Partition and Continuous Task Scheduling for Digital Twin-Aided MEC Network With Deep Reinforcement Learning" @default.
- W4327521519 cites W2046074714 @default.
- W4327521519 cites W2097117768 @default.
- W4327521519 cites W2104237724 @default.
- W4327521519 cites W2118966355 @default.
- W4327521519 cites W2145339207 @default.
- W4327521519 cites W2194775991 @default.
- W4327521519 cites W2195423816 @default.
- W4327521519 cites W2287589736 @default.
- W4327521519 cites W2489939258 @default.
- W4327521519 cites W2587359738 @default.
- W4327521519 cites W2618530766 @default.
- W4327521519 cites W2773498880 @default.
- W4327521519 cites W2902897529 @default.
- W4327521519 cites W2962798832 @default.
- W4327521519 cites W3008352557 @default.
- W4327521519 cites W3021823339 @default.
- W4327521519 cites W3024681024 @default.
- W4327521519 cites W3034270904 @default.
- W4327521519 cites W3042617392 @default.
- W4327521519 cites W3049282540 @default.
- W4327521519 cites W3080667742 @default.
- W4327521519 cites W3096075297 @default.
- W4327521519 cites W3098806383 @default.
- W4327521519 cites W3102962172 @default.
- W4327521519 cites W3111084717 @default.
- W4327521519 cites W3112732217 @default.
- W4327521519 cites W3119602499 @default.
- W4327521519 cites W3130503957 @default.
- W4327521519 cites W3165698711 @default.
- W4327521519 cites W3172890132 @default.
- W4327521519 cites W3202549149 @default.
- W4327521519 cites W3212941463 @default.
- W4327521519 cites W32403112 @default.
- W4327521519 cites W4210698675 @default.
- W4327521519 cites W4315630622 @default.
- W4327521519 doi "https://doi.org/10.1109/access.2023.3257342" @default.
- W4327521519 hasPublicationYear "2023" @default.
- W4327521519 type Work @default.
- W4327521519 citedByCount "0" @default.
- W4327521519 crossrefType "journal-article" @default.
- W4327521519 hasAuthorship W4327521519A5015025268 @default.
- W4327521519 hasAuthorship W4327521519A5021101912 @default.
- W4327521519 hasAuthorship W4327521519A5039716922 @default.
- W4327521519 hasAuthorship W4327521519A5063911579 @default.
- W4327521519 hasAuthorship W4327521519A5075080019 @default.
- W4327521519 hasBestOaLocation W43275215191 @default.
- W4327521519 hasConcept C151319957 @default.
- W4327521519 hasConcept C154945302 @default.
- W4327521519 hasConcept C162307627 @default.
- W4327521519 hasConcept C2776061582 @default.
- W4327521519 hasConcept C2776214188 @default.
- W4327521519 hasConcept C31258907 @default.
- W4327521519 hasConcept C41008148 @default.
- W4327521519 hasConcept C97541855 @default.
- W4327521519 hasConceptScore W4327521519C151319957 @default.
- W4327521519 hasConceptScore W4327521519C154945302 @default.
- W4327521519 hasConceptScore W4327521519C162307627 @default.
- W4327521519 hasConceptScore W4327521519C2776061582 @default.
- W4327521519 hasConceptScore W4327521519C2776214188 @default.
- W4327521519 hasConceptScore W4327521519C31258907 @default.
- W4327521519 hasConceptScore W4327521519C41008148 @default.
- W4327521519 hasConceptScore W4327521519C97541855 @default.
- W4327521519 hasFunder F4320321001 @default.
- W4327521519 hasFunder F4320321470 @default.
- W4327521519 hasLocation W43275215191 @default.
- W4327521519 hasOpenAccess W4327521519 @default.
- W4327521519 hasPrimaryLocation W43275215191 @default.
- W4327521519 hasRelatedWork W2260756217 @default.
- W4327521519 hasRelatedWork W260766989 @default.
- W4327521519 hasRelatedWork W2891655128 @default.
- W4327521519 hasRelatedWork W2959276766 @default.
- W4327521519 hasRelatedWork W2964043796 @default.
- W4327521519 hasRelatedWork W3074294383 @default.
- W4327521519 hasRelatedWork W3111983280 @default.
- W4327521519 hasRelatedWork W3139193008 @default.
- W4327521519 hasRelatedWork W4206669594 @default.
- W4327521519 hasRelatedWork W4295941380 @default.
- W4327521519 hasVolume "11" @default.
- W4327521519 isParatext "false" @default.
- W4327521519 isRetracted "false" @default.
- W4327521519 workType "article" @default.