Matches in SemOpenAlex for { <https://semopenalex.org/work/W4220806559> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W4220806559 abstract "Abstract Deep neural network (DNN) inference task offloading is an essential problem of edge intelligence, which faces the challenges of limited computing resources shortage of edge devices and the dynamics of edge networks. In this article, the DNN inference task offloading problem in queue‐based multi‐device and multi‐server collaborative edge computing is investigated. To support efficient collaborative inference, we formulate a multi‐objective optimization problem that minimizes the average delay and maximizes average inference accuracy. Due to time‐varying queue load states and random task arrival, it is challenging to solve this optimization problem. Thus, a deep reinforcement learning based task offloading algorithm, named LSTM‐TD3, is proposed to solve the formulated problem. Specifically, LSTM‐TD3 incorporates the long short‐term memory (LSTM) and twin delayed deep deterministic policy gradient algorithm (TD3), and can leverage long‐term environment information to efficiently explore the optimal task offloading solution. Finally, we compared the performance of LSTM‐TD3 with TD3 (without LSTM) and random offloading algorithms, and simulation results show the LSTM‐TD3 reduce the average inference delay by up to , and the accuracy is better than other algorithms." @default.
- W4220806559 created "2022-04-03" @default.
- W4220806559 creator A5024036244 @default.
- W4220806559 creator A5042382734 @default.
- W4220806559 creator A5045338115 @default.
- W4220806559 creator A5071654735 @default.
- W4220806559 date "2022-03-10" @default.
- W4220806559 modified "2023-10-02" @default.
- W4220806559 title "Learning‐based deep neural network inference task offloading in multi‐device and multi‐server collaborative edge computing" @default.
- W4220806559 cites W2064675550 @default.
- W4220806559 cites W2191948661 @default.
- W4220806559 cites W2604319603 @default.
- W4220806559 cites W2896180420 @default.
- W4220806559 cites W2897807975 @default.
- W4220806559 cites W2913740539 @default.
- W4220806559 cites W2979679572 @default.
- W4220806559 cites W2980856918 @default.
- W4220806559 cites W2981114133 @default.
- W4220806559 cites W2995920492 @default.
- W4220806559 cites W3004316932 @default.
- W4220806559 cites W3006403513 @default.
- W4220806559 cites W3006851618 @default.
- W4220806559 cites W3011134162 @default.
- W4220806559 cites W3021309758 @default.
- W4220806559 cites W3039881978 @default.
- W4220806559 cites W3059280052 @default.
- W4220806559 cites W3087275496 @default.
- W4220806559 cites W3092302056 @default.
- W4220806559 cites W3096445331 @default.
- W4220806559 cites W3105504538 @default.
- W4220806559 cites W3136338303 @default.
- W4220806559 cites W3141828974 @default.
- W4220806559 cites W3193491167 @default.
- W4220806559 cites W3205260830 @default.
- W4220806559 cites W3209283715 @default.
- W4220806559 cites W4236099117 @default.
- W4220806559 doi "https://doi.org/10.1002/ett.4485" @default.
- W4220806559 hasPublicationYear "2022" @default.
- W4220806559 type Work @default.
- W4220806559 citedByCount "4" @default.
- W4220806559 countsByYear W42208065592022 @default.
- W4220806559 countsByYear W42208065592023 @default.
- W4220806559 crossrefType "journal-article" @default.
- W4220806559 hasAuthorship W4220806559A5024036244 @default.
- W4220806559 hasAuthorship W4220806559A5042382734 @default.
- W4220806559 hasAuthorship W4220806559A5045338115 @default.
- W4220806559 hasAuthorship W4220806559A5071654735 @default.
- W4220806559 hasConcept C111919701 @default.
- W4220806559 hasConcept C11413529 @default.
- W4220806559 hasConcept C137836250 @default.
- W4220806559 hasConcept C138236772 @default.
- W4220806559 hasConcept C153083717 @default.
- W4220806559 hasConcept C154945302 @default.
- W4220806559 hasConcept C162307627 @default.
- W4220806559 hasConcept C162324750 @default.
- W4220806559 hasConcept C187736073 @default.
- W4220806559 hasConcept C2776214188 @default.
- W4220806559 hasConcept C2780451532 @default.
- W4220806559 hasConcept C41008148 @default.
- W4220806559 hasConcept C50644808 @default.
- W4220806559 hasConcept C79974875 @default.
- W4220806559 hasConcept C97541855 @default.
- W4220806559 hasConceptScore W4220806559C111919701 @default.
- W4220806559 hasConceptScore W4220806559C11413529 @default.
- W4220806559 hasConceptScore W4220806559C137836250 @default.
- W4220806559 hasConceptScore W4220806559C138236772 @default.
- W4220806559 hasConceptScore W4220806559C153083717 @default.
- W4220806559 hasConceptScore W4220806559C154945302 @default.
- W4220806559 hasConceptScore W4220806559C162307627 @default.
- W4220806559 hasConceptScore W4220806559C162324750 @default.
- W4220806559 hasConceptScore W4220806559C187736073 @default.
- W4220806559 hasConceptScore W4220806559C2776214188 @default.
- W4220806559 hasConceptScore W4220806559C2780451532 @default.
- W4220806559 hasConceptScore W4220806559C41008148 @default.
- W4220806559 hasConceptScore W4220806559C50644808 @default.
- W4220806559 hasConceptScore W4220806559C79974875 @default.
- W4220806559 hasConceptScore W4220806559C97541855 @default.
- W4220806559 hasIssue "7" @default.
- W4220806559 hasLocation W42208065591 @default.
- W4220806559 hasOpenAccess W4220806559 @default.
- W4220806559 hasPrimaryLocation W42208065591 @default.
- W4220806559 hasRelatedWork W3013760193 @default.
- W4220806559 hasRelatedWork W3014007418 @default.
- W4220806559 hasRelatedWork W3131458535 @default.
- W4220806559 hasRelatedWork W3162668736 @default.
- W4220806559 hasRelatedWork W3166603227 @default.
- W4220806559 hasRelatedWork W3214097103 @default.
- W4220806559 hasRelatedWork W4210851126 @default.
- W4220806559 hasRelatedWork W4281678247 @default.
- W4220806559 hasRelatedWork W4285338583 @default.
- W4220806559 hasRelatedWork W4376601996 @default.
- W4220806559 hasVolume "33" @default.
- W4220806559 isParatext "false" @default.
- W4220806559 isRetracted "false" @default.
- W4220806559 workType "article" @default.