Matches in SemOpenAlex for { <https://semopenalex.org/work/W3177552783> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3177552783 abstract "Edge computing enables Mobile Autonomous Systems (MASs) to execute continuous streams of heavy-duty mission-critical processing tasks, such as real-time obstacle detection and navigation. However, in practical applications, erratic patterns in channel quality, network load, and edge server load can interrupt the task flow execution, which necessarily leads to severe disruption of the system's key operations. Existing work has mostly tackled the problem with reactive approaches, which cannot guarantee task-level reliability. Conversely, in this paper we focus on learning-based predictive edge computing to achieve self-resilient task offloading. By conducting a preliminary experimental evaluation, we show that there is no dominant feature that can predict the edge-MAS system reliability, which calls for an ensemble and selection of weaker features. To tackle the complexity of the problem, we propose SeReMAS, a data-driven optimization framework. We first mathematically formulate a Redundant Task Offloading Problem (RTOP), where a MAS may connect to multiple edge servers for redundancy, and needs to select which server(s) to transmit its computing tasks in order to maximize the probability of task execution while minimizing channel and edge resource utilization. We then create a predictor based on Deep Reinforcement Learning (DRL), which produces the optimum task assignment based on application-, network- and telemetry-based features. We prototype SeReMAS on a testbed composed by a drone, mounting a PixHawk flight controller, a Jetson Nano board, and three 802.11n WiFi interfaces. We extensively evaluate SeReMAS by considering an application where one drone offloads high-resolution images for real-time analysis to three edge servers on the ground. Experimental results show that SeReMAS improves task execution probability by $17%$ with respect to existing reactive-based approaches." @default.
- W3177552783 created "2021-07-19" @default.
- W3177552783 creator A5051196445 @default.
- W3177552783 creator A5058335425 @default.
- W3177552783 creator A5086426869 @default.
- W3177552783 date "2021-04-22" @default.
- W3177552783 modified "2023-09-28" @default.
- W3177552783 title "SeReMAS: Self-Resilient Mobile Autonomous Systems Through Predictive Edge Computing" @default.
- W3177552783 cites W2101234009 @default.
- W3177552783 cites W2114623221 @default.
- W3177552783 cites W2518876086 @default.
- W3177552783 cites W2542615301 @default.
- W3177552783 cites W2560647685 @default.
- W3177552783 cites W2746553466 @default.
- W3177552783 cites W2790256744 @default.
- W3177552783 cites W2799072622 @default.
- W3177552783 cites W2899183567 @default.
- W3177552783 cites W2921456883 @default.
- W3177552783 cites W2924948991 @default.
- W3177552783 cites W2961269959 @default.
- W3177552783 cites W2963513677 @default.
- W3177552783 cites W2963719677 @default.
- W3177552783 cites W2964052915 @default.
- W3177552783 cites W2981726317 @default.
- W3177552783 cites W3006657393 @default.
- W3177552783 cites W3033229102 @default.
- W3177552783 cites W3037849673 @default.
- W3177552783 cites W3045975179 @default.
- W3177552783 cites W3047202536 @default.
- W3177552783 cites W3119882941 @default.
- W3177552783 hasPublicationYear "2021" @default.
- W3177552783 type Work @default.
- W3177552783 sameAs 3177552783 @default.
- W3177552783 citedByCount "0" @default.
- W3177552783 crossrefType "posted-content" @default.
- W3177552783 hasAuthorship W3177552783A5051196445 @default.
- W3177552783 hasAuthorship W3177552783A5058335425 @default.
- W3177552783 hasAuthorship W3177552783A5086426869 @default.
- W3177552783 hasConcept C111919701 @default.
- W3177552783 hasConcept C120314980 @default.
- W3177552783 hasConcept C138236772 @default.
- W3177552783 hasConcept C149635348 @default.
- W3177552783 hasConcept C154945302 @default.
- W3177552783 hasConcept C162307627 @default.
- W3177552783 hasConcept C173018170 @default.
- W3177552783 hasConcept C2776061582 @default.
- W3177552783 hasConcept C2778456923 @default.
- W3177552783 hasConcept C31258907 @default.
- W3177552783 hasConcept C31395832 @default.
- W3177552783 hasConcept C41008148 @default.
- W3177552783 hasConcept C41661131 @default.
- W3177552783 hasConcept C79403827 @default.
- W3177552783 hasConcept C79974875 @default.
- W3177552783 hasConcept C93996380 @default.
- W3177552783 hasConceptScore W3177552783C111919701 @default.
- W3177552783 hasConceptScore W3177552783C120314980 @default.
- W3177552783 hasConceptScore W3177552783C138236772 @default.
- W3177552783 hasConceptScore W3177552783C149635348 @default.
- W3177552783 hasConceptScore W3177552783C154945302 @default.
- W3177552783 hasConceptScore W3177552783C162307627 @default.
- W3177552783 hasConceptScore W3177552783C173018170 @default.
- W3177552783 hasConceptScore W3177552783C2776061582 @default.
- W3177552783 hasConceptScore W3177552783C2778456923 @default.
- W3177552783 hasConceptScore W3177552783C31258907 @default.
- W3177552783 hasConceptScore W3177552783C31395832 @default.
- W3177552783 hasConceptScore W3177552783C41008148 @default.
- W3177552783 hasConceptScore W3177552783C41661131 @default.
- W3177552783 hasConceptScore W3177552783C79403827 @default.
- W3177552783 hasConceptScore W3177552783C79974875 @default.
- W3177552783 hasConceptScore W3177552783C93996380 @default.
- W3177552783 hasOpenAccess W3177552783 @default.
- W3177552783 hasRelatedWork W2910439483 @default.
- W3177552783 hasRelatedWork W2945235903 @default.
- W3177552783 hasRelatedWork W2947724686 @default.
- W3177552783 hasRelatedWork W2967734072 @default.
- W3177552783 hasRelatedWork W2980513887 @default.
- W3177552783 hasRelatedWork W3007209942 @default.
- W3177552783 hasRelatedWork W3010612709 @default.
- W3177552783 hasRelatedWork W3013868700 @default.
- W3177552783 hasRelatedWork W3016764502 @default.
- W3177552783 hasRelatedWork W3035252157 @default.
- W3177552783 hasRelatedWork W3043678861 @default.
- W3177552783 hasRelatedWork W3047451018 @default.
- W3177552783 hasRelatedWork W3105381414 @default.
- W3177552783 hasRelatedWork W3128219156 @default.
- W3177552783 hasRelatedWork W3134817847 @default.
- W3177552783 hasRelatedWork W3160527734 @default.
- W3177552783 hasRelatedWork W3166682136 @default.
- W3177552783 hasRelatedWork W3184626072 @default.
- W3177552783 hasRelatedWork W3187219391 @default.
- W3177552783 hasRelatedWork W3187498798 @default.
- W3177552783 isParatext "false" @default.
- W3177552783 isRetracted "false" @default.
- W3177552783 magId "3177552783" @default.
- W3177552783 workType "article" @default.