FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3136338303> ?p ?o ?g. }

• W3136338303 endingPage "7618" @default.
• W3136338303 startingPage "7605" @default.
• W3136338303 abstract "Performing deep neural network (DNN) inference in real time requires excessive network resources, which poses a big challenge to the resource-limited industrial Internet of things (IIoT) networks. To address the challenge, in this paper, we introduce an end-edge-cloud orchestration architecture, in which the inference task assignment and DNN model placement are flexibly coordinated. Specifically, the DNN models, trained and pre-stored in the cloud, are properly placed at the end and edge to perform DNN inference. To achieve efficient DNN inference, a multi-dimensional resource management problem is formulated to maximize the average inference accuracy while satisfying the strict delay requirements of inference tasks. Due to the mix-integer decision variables, it is difficult to solve the formulated problem directly. Thus, we transform the formulated problem into a Markov decision process which can be solved efficiently. Furthermore, a deep reinforcement learning based resource management scheme is proposed to make real-time optimal resource allocation decisions. Simulation results are provided to demonstrate that the proposed scheme can efficiently allocate the available spectrum, caching, and computing resources, and improve average inference accuracy by 31.4$%$ compared with the deep deterministic policy gradient benchmark." @default.
• W3136338303 created "2021-03-29" @default.
• W3136338303 creator A5022812128 @default.
• W3136338303 creator A5025221904 @default.
• W3136338303 creator A5036159136 @default.
• W3136338303 creator A5045338115 @default.
• W3136338303 creator A5071654735 @default.
• W3136338303 creator A5074854979 @default.
• W3136338303 creator A5091713195 @default.
• W3136338303 date "2021-08-01" @default.
• W3136338303 modified "2023-10-15" @default.
• W3136338303 title "Deep Reinforcement Learning Based Resource Management for DNN Inference in Industrial IoT" @default.
• W3136338303 cites W2101972630 @default.
• W3136338303 cites W2604319603 @default.
• W3136338303 cites W2615459164 @default.
• W3136338303 cites W2761862361 @default.
• W3136338303 cites W2771250869 @default.
• W3136338303 cites W2811266402 @default.
• W3136338303 cites W2898035736 @default.
• W3136338303 cites W2900376989 @default.
• W3136338303 cites W2902952649 @default.
• W3136338303 cites W2913729121 @default.
• W3136338303 cites W2920054549 @default.
• W3136338303 cites W2924948991 @default.
• W3136338303 cites W2942889782 @default.
• W3136338303 cites W2944364052 @default.
• W3136338303 cites W2947710575 @default.
• W3136338303 cites W2964233199 @default.
• W3136338303 cites W2968424451 @default.
• W3136338303 cites W2968782695 @default.
• W3136338303 cites W2974178109 @default.
• W3136338303 cites W2976382054 @default.
• W3136338303 cites W2979680647 @default.
• W3136338303 cites W2979987893 @default.
• W3136338303 cites W2980856918 @default.
• W3136338303 cites W2981114133 @default.
• W3136338303 cites W2989596860 @default.
• W3136338303 cites W2990994567 @default.
• W3136338303 cites W2999562137 @default.
• W3136338303 cites W3010301175 @default.
• W3136338303 cites W3011091971 @default.
• W3136338303 cites W3016146955 @default.
• W3136338303 cites W3021066175 @default.
• W3136338303 cites W3045860335 @default.
• W3136338303 cites W3047371394 @default.
• W3136338303 cites W3059280052 @default.
• W3136338303 cites W3092302056 @default.
• W3136338303 cites W3110381504 @default.
• W3136338303 doi "https://doi.org/10.1109/tvt.2021.3068255" @default.
• W3136338303 hasPublicationYear "2021" @default.
• W3136338303 type Work @default.
• W3136338303 sameAs 3136338303 @default.
• W3136338303 citedByCount "56" @default.
• W3136338303 countsByYear W31363383032021 @default.
• W3136338303 countsByYear W31363383032022 @default.
• W3136338303 countsByYear W31363383032023 @default.
• W3136338303 crossrefType "journal-article" @default.
• W3136338303 hasAuthorship W3136338303A5022812128 @default.
• W3136338303 hasAuthorship W3136338303A5025221904 @default.
• W3136338303 hasAuthorship W3136338303A5036159136 @default.
• W3136338303 hasAuthorship W3136338303A5045338115 @default.
• W3136338303 hasAuthorship W3136338303A5071654735 @default.
• W3136338303 hasAuthorship W3136338303A5074854979 @default.
• W3136338303 hasAuthorship W3136338303A5091713195 @default.
• W3136338303 hasConcept C105795698 @default.
• W3136338303 hasConcept C106189395 @default.
• W3136338303 hasConcept C108583219 @default.
• W3136338303 hasConcept C111919701 @default.
• W3136338303 hasConcept C11413529 @default.
• W3136338303 hasConcept C119857082 @default.
• W3136338303 hasConcept C120314980 @default.
• W3136338303 hasConcept C13280743 @default.
• W3136338303 hasConcept C138236772 @default.
• W3136338303 hasConcept C154945302 @default.
• W3136338303 hasConcept C159886148 @default.
• W3136338303 hasConcept C162307627 @default.
• W3136338303 hasConcept C185798385 @default.
• W3136338303 hasConcept C205649164 @default.
• W3136338303 hasConcept C2776214188 @default.
• W3136338303 hasConcept C2778456923 @default.
• W3136338303 hasConcept C2780609101 @default.
• W3136338303 hasConcept C29202148 @default.
• W3136338303 hasConcept C31258907 @default.
• W3136338303 hasConcept C33923547 @default.
• W3136338303 hasConcept C41008148 @default.
• W3136338303 hasConcept C56086750 @default.
• W3136338303 hasConcept C79974875 @default.
• W3136338303 hasConcept C97541855 @default.
• W3136338303 hasConceptScore W3136338303C105795698 @default.
• W3136338303 hasConceptScore W3136338303C106189395 @default.
• W3136338303 hasConceptScore W3136338303C108583219 @default.
• W3136338303 hasConceptScore W3136338303C111919701 @default.
• W3136338303 hasConceptScore W3136338303C11413529 @default.
• W3136338303 hasConceptScore W3136338303C119857082 @default.
• W3136338303 hasConceptScore W3136338303C120314980 @default.
• W3136338303 hasConceptScore W3136338303C13280743 @default.
• W3136338303 hasConceptScore W3136338303C138236772 @default.
• W3136338303 hasConceptScore W3136338303C154945302 @default.

• next