FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4293498898> ?p ?o ?g. }

• W4293498898 endingPage "1001" @default.
• W4293498898 startingPage "986" @default.
• W4293498898 abstract "Mobile edge computing (MEC) provides an economical way for the resource-constrained edge users to offload computational workload to MEC servers co-located with the access point (AP). In this article, we consider a hybrid computation offloading scheme that allows edge users to offload workloads by using active RF communications and backscatter communications. We aim to maximize the overall energy efficiency subject to the completion of all workload by jointly optimizing the AP's beamforming and the users' offloading decisions. Considering a dynamic environment, we propose a hierarchical multi-agent deep reinforcement learning (H-MADRL) framework to solve this problem. The high-level agent resides in the AP and optimizes the beamforming strategy, while the low-level user agents learn and adapt individuals' offloading strategies. To further improve the learning efficiency, we propose a novel optimization-driven learning algorithm that allows the AP to estimate the low-level users' actions by solving approximate optimization problem efficiently. Then, the action estimation can be shared with all users and drive them to update individuals' actions independently. Simulation results reveal that our algorithm can improve the system performance by 50%. The learning efficiency and reliability are also improved significantly comparing to the model-free learning methods." @default.
• W4293498898 created "2022-08-29" @default.
• W4293498898 creator A5000861569 @default.
• W4293498898 creator A5018204862 @default.
• W4293498898 creator A5033147284 @default.
• W4293498898 creator A5042460024 @default.
• W4293498898 creator A5043951146 @default.
• W4293498898 creator A5053242519 @default.
• W4293498898 date "2023-01-01" @default.
• W4293498898 modified "2023-10-16" @default.
• W4293498898 title "Hierarchical Multi-Agent Deep Reinforcement Learning for Energy-Efficient Hybrid Computation Offloading" @default.
• W4293498898 cites W2134295053 @default.
• W4293498898 cites W2486013602 @default.
• W4293498898 cites W2624989916 @default.
• W4293498898 cites W2783647977 @default.
• W4293498898 cites W2890053410 @default.
• W4293498898 cites W2898035736 @default.
• W4293498898 cites W2898652425 @default.
• W4293498898 cites W2955706727 @default.
• W4293498898 cites W2963020121 @default.
• W4293498898 cites W2963205726 @default.
• W4293498898 cites W2963334314 @default.
• W4293498898 cites W2964098968 @default.
• W4293498898 cites W2969324740 @default.
• W4293498898 cites W2976580479 @default.
• W4293498898 cites W2985230321 @default.
• W4293498898 cites W2989743749 @default.
• W4293498898 cites W3005150685 @default.
• W4293498898 cites W3009871193 @default.
• W4293498898 cites W3031601957 @default.
• W4293498898 cites W3034730089 @default.
• W4293498898 cites W3042206064 @default.
• W4293498898 cites W3090573937 @default.
• W4293498898 cites W3112164530 @default.
• W4293498898 cites W3115015728 @default.
• W4293498898 cites W3127177591 @default.
• W4293498898 cites W3127516964 @default.
• W4293498898 cites W3133575899 @default.
• W4293498898 cites W3144235125 @default.
• W4293498898 cites W3158558942 @default.
• W4293498898 cites W3174997142 @default.
• W4293498898 cites W3178010443 @default.
• W4293498898 cites W3183673024 @default.
• W4293498898 cites W3187687298 @default.
• W4293498898 cites W3193361248 @default.
• W4293498898 cites W3203682130 @default.
• W4293498898 cites W3215230729 @default.
• W4293498898 cites W3216768220 @default.
• W4293498898 doi "https://doi.org/10.1109/tvt.2022.3202525" @default.
• W4293498898 hasPublicationYear "2023" @default.
• W4293498898 type Work @default.
• W4293498898 citedByCount "2" @default.
• W4293498898 countsByYear W42934988982023 @default.
• W4293498898 crossrefType "journal-article" @default.
• W4293498898 hasAuthorship W4293498898A5000861569 @default.
• W4293498898 hasAuthorship W4293498898A5018204862 @default.
• W4293498898 hasAuthorship W4293498898A5033147284 @default.
• W4293498898 hasAuthorship W4293498898A5042460024 @default.
• W4293498898 hasAuthorship W4293498898A5043951146 @default.
• W4293498898 hasAuthorship W4293498898A5053242519 @default.
• W4293498898 hasConcept C111919701 @default.
• W4293498898 hasConcept C11413529 @default.
• W4293498898 hasConcept C119599485 @default.
• W4293498898 hasConcept C120314980 @default.
• W4293498898 hasConcept C121332964 @default.
• W4293498898 hasConcept C127413603 @default.
• W4293498898 hasConcept C137836250 @default.
• W4293498898 hasConcept C154945302 @default.
• W4293498898 hasConcept C162307627 @default.
• W4293498898 hasConcept C163258240 @default.
• W4293498898 hasConcept C2742236 @default.
• W4293498898 hasConcept C2776061582 @default.
• W4293498898 hasConcept C2778456923 @default.
• W4293498898 hasConcept C2778476105 @default.
• W4293498898 hasConcept C2781041963 @default.
• W4293498898 hasConcept C31258907 @default.
• W4293498898 hasConcept C41008148 @default.
• W4293498898 hasConcept C43214815 @default.
• W4293498898 hasConcept C62520636 @default.
• W4293498898 hasConcept C93996380 @default.
• W4293498898 hasConcept C97541855 @default.
• W4293498898 hasConceptScore W4293498898C111919701 @default.
• W4293498898 hasConceptScore W4293498898C11413529 @default.
• W4293498898 hasConceptScore W4293498898C119599485 @default.
• W4293498898 hasConceptScore W4293498898C120314980 @default.
• W4293498898 hasConceptScore W4293498898C121332964 @default.
• W4293498898 hasConceptScore W4293498898C127413603 @default.
• W4293498898 hasConceptScore W4293498898C137836250 @default.
• W4293498898 hasConceptScore W4293498898C154945302 @default.
• W4293498898 hasConceptScore W4293498898C162307627 @default.
• W4293498898 hasConceptScore W4293498898C163258240 @default.
• W4293498898 hasConceptScore W4293498898C2742236 @default.
• W4293498898 hasConceptScore W4293498898C2776061582 @default.
• W4293498898 hasConceptScore W4293498898C2778456923 @default.
• W4293498898 hasConceptScore W4293498898C2778476105 @default.
• W4293498898 hasConceptScore W4293498898C2781041963 @default.
• W4293498898 hasConceptScore W4293498898C31258907 @default.
• W4293498898 hasConceptScore W4293498898C41008148 @default.

• next