Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313483407> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4313483407 abstract "Collaboration among industrial Internet of Things (IoT) devices and edge networks is essential to support computation-intensive deep neural network (DNN) inference services which require low delay and high accuracy. Sampling rate adaption which dynamically configures the sampling rates of industrial IoT devices according to network conditions, is the key in minimizing the service delay. In this paper, we investigate the collaborative DNN inference problem in industrial IoT networks. To capture the channel variation and task arrival randomness, we formulate the problem as a constrained Markov decision process (CMDP). Specifically, sampling rate adaption, inference task offloading and edge computing resource allocation are jointly considered to minimize the average service delay while guaranteeing the long-term accuracy requirements of different inference services. Since CMDP cannot be directly solved by general reinforcement learning (RL) algorithms due to the intractable long-term constraints, we first transform the CMDP into an MDP by leveraging the Lyapunov optimization technique. Then, a deep RL-based algorithm is proposed to solve the MDP. To expedite the training process, an optimization subroutine is embedded in the proposed algorithm to directly obtain the optimal edge computing resource allocation. Extensive simulation results are provided to demonstrate that the proposed RL-based algorithm can significantly reduce the average service delay while preserving long-term inference accuracy with a high probability." @default.
- W4313483407 created "2023-01-06" @default.
- W4313483407 creator A5015093295 @default.
- W4313483407 creator A5039199386 @default.
- W4313483407 creator A5040136142 @default.
- W4313483407 creator A5045338115 @default.
- W4313483407 creator A5051676242 @default.
- W4313483407 creator A5085346496 @default.
- W4313483407 date "2022-12-31" @default.
- W4313483407 modified "2023-09-28" @default.
- W4313483407 title "Accuracy-Guaranteed Collaborative DNN Inference in Industrial IoT via Deep Reinforcement Learning" @default.
- W4313483407 doi "https://doi.org/10.48550/arxiv.2301.00130" @default.
- W4313483407 hasPublicationYear "2022" @default.
- W4313483407 type Work @default.
- W4313483407 citedByCount "0" @default.
- W4313483407 crossrefType "posted-content" @default.
- W4313483407 hasAuthorship W4313483407A5015093295 @default.
- W4313483407 hasAuthorship W4313483407A5039199386 @default.
- W4313483407 hasAuthorship W4313483407A5040136142 @default.
- W4313483407 hasAuthorship W4313483407A5045338115 @default.
- W4313483407 hasAuthorship W4313483407A5051676242 @default.
- W4313483407 hasAuthorship W4313483407A5085346496 @default.
- W4313483407 hasBestOaLocation W43134834071 @default.
- W4313483407 hasConcept C101403955 @default.
- W4313483407 hasConcept C105795698 @default.
- W4313483407 hasConcept C106189395 @default.
- W4313483407 hasConcept C111919701 @default.
- W4313483407 hasConcept C120314980 @default.
- W4313483407 hasConcept C127413603 @default.
- W4313483407 hasConcept C138236772 @default.
- W4313483407 hasConcept C154945302 @default.
- W4313483407 hasConcept C159886148 @default.
- W4313483407 hasConcept C162307627 @default.
- W4313483407 hasConcept C191544260 @default.
- W4313483407 hasConcept C201995342 @default.
- W4313483407 hasConcept C2776214188 @default.
- W4313483407 hasConcept C2777052490 @default.
- W4313483407 hasConcept C2778456923 @default.
- W4313483407 hasConcept C2780451532 @default.
- W4313483407 hasConcept C33923547 @default.
- W4313483407 hasConcept C37935115 @default.
- W4313483407 hasConcept C41008148 @default.
- W4313483407 hasConcept C79974875 @default.
- W4313483407 hasConcept C97541855 @default.
- W4313483407 hasConceptScore W4313483407C101403955 @default.
- W4313483407 hasConceptScore W4313483407C105795698 @default.
- W4313483407 hasConceptScore W4313483407C106189395 @default.
- W4313483407 hasConceptScore W4313483407C111919701 @default.
- W4313483407 hasConceptScore W4313483407C120314980 @default.
- W4313483407 hasConceptScore W4313483407C127413603 @default.
- W4313483407 hasConceptScore W4313483407C138236772 @default.
- W4313483407 hasConceptScore W4313483407C154945302 @default.
- W4313483407 hasConceptScore W4313483407C159886148 @default.
- W4313483407 hasConceptScore W4313483407C162307627 @default.
- W4313483407 hasConceptScore W4313483407C191544260 @default.
- W4313483407 hasConceptScore W4313483407C201995342 @default.
- W4313483407 hasConceptScore W4313483407C2776214188 @default.
- W4313483407 hasConceptScore W4313483407C2777052490 @default.
- W4313483407 hasConceptScore W4313483407C2778456923 @default.
- W4313483407 hasConceptScore W4313483407C2780451532 @default.
- W4313483407 hasConceptScore W4313483407C33923547 @default.
- W4313483407 hasConceptScore W4313483407C37935115 @default.
- W4313483407 hasConceptScore W4313483407C41008148 @default.
- W4313483407 hasConceptScore W4313483407C79974875 @default.
- W4313483407 hasConceptScore W4313483407C97541855 @default.
- W4313483407 hasLocation W43134834071 @default.
- W4313483407 hasOpenAccess W4313483407 @default.
- W4313483407 hasPrimaryLocation W43134834071 @default.
- W4313483407 hasRelatedWork W2942616607 @default.
- W4313483407 hasRelatedWork W3013760193 @default.
- W4313483407 hasRelatedWork W3014007418 @default.
- W4313483407 hasRelatedWork W3089192431 @default.
- W4313483407 hasRelatedWork W3154105090 @default.
- W4313483407 hasRelatedWork W3179535091 @default.
- W4313483407 hasRelatedWork W3188385896 @default.
- W4313483407 hasRelatedWork W3208790065 @default.
- W4313483407 hasRelatedWork W4226470542 @default.
- W4313483407 hasRelatedWork W4312815336 @default.
- W4313483407 isParatext "false" @default.
- W4313483407 isRetracted "false" @default.
- W4313483407 workType "article" @default.