Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386570123> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W4386570123 endingPage "109999" @default.
- W4386570123 startingPage "109999" @default.
- W4386570123 abstract "Deep Neural Networks (DNNs) are increasingly used on the edge in mobile and other resource-constrained devices for inference tasks ranging from object detection and image recognition to video processing. Many of these tasks have low latency requirements that cannot be satisfied if they are processed locally due to their high computational complexity. Offloading computation to the edge and cloud offers a way to alleviate this computational latency. Doing so introduces communication delays, which makes offloading a balancing act between the benefits of reduced processing time and the communication delays incurred. Existing algorithms for DNN offloading based on DNN partitioning are optimised for handling successive tasks on a single remote server, and perform sub-optimally when tasks are interleaved, or with multiple servers, or when privacy concerns require local processing of certain DNN layers. A viable alternative are generic computational offloading algorithms (GOAs), which can break down DNN tasks into their components and perform fine-grained offloading. We perform a simulation-based comparison of traditional GOAs with various levels of proactivity and offloading constraints and a naive DNN partitioning approach. We identify key requirements for offloading algorithms in the ability to create processing chains between several remote servers in order to reduce communication overheads, and the ability to prioritise already running tasks. The results confirm the expectations about the shortcomings of DNN partitioning, and show that GOA algorithms can provide a significant performance improvement." @default.
- W4386570123 created "2023-09-10" @default.
- W4386570123 creator A5005093359 @default.
- W4386570123 creator A5016175331 @default.
- W4386570123 creator A5020398303 @default.
- W4386570123 creator A5065110103 @default.
- W4386570123 date "2023-11-01" @default.
- W4386570123 modified "2023-09-29" @default.
- W4386570123 title "A comparative analysis of proactive and reactive methods for privacy-aware interleaved DNN offloading" @default.
- W4386570123 cites W3153674394 @default.
- W4386570123 cites W4224289247 @default.
- W4386570123 cites W4236099117 @default.
- W4386570123 doi "https://doi.org/10.1016/j.comnet.2023.109999" @default.
- W4386570123 hasPublicationYear "2023" @default.
- W4386570123 type Work @default.
- W4386570123 citedByCount "0" @default.
- W4386570123 crossrefType "journal-article" @default.
- W4386570123 hasAuthorship W4386570123A5005093359 @default.
- W4386570123 hasAuthorship W4386570123A5016175331 @default.
- W4386570123 hasAuthorship W4386570123A5020398303 @default.
- W4386570123 hasAuthorship W4386570123A5065110103 @default.
- W4386570123 hasBestOaLocation W43865701231 @default.
- W4386570123 hasConcept C111919701 @default.
- W4386570123 hasConcept C11413529 @default.
- W4386570123 hasConcept C120314980 @default.
- W4386570123 hasConcept C138236772 @default.
- W4386570123 hasConcept C154945302 @default.
- W4386570123 hasConcept C162307627 @default.
- W4386570123 hasConcept C179799912 @default.
- W4386570123 hasConcept C186967261 @default.
- W4386570123 hasConcept C2776214188 @default.
- W4386570123 hasConcept C2778456923 @default.
- W4386570123 hasConcept C2781041963 @default.
- W4386570123 hasConcept C31258907 @default.
- W4386570123 hasConcept C41008148 @default.
- W4386570123 hasConcept C76155785 @default.
- W4386570123 hasConcept C79974875 @default.
- W4386570123 hasConcept C82876162 @default.
- W4386570123 hasConcept C93996380 @default.
- W4386570123 hasConceptScore W4386570123C111919701 @default.
- W4386570123 hasConceptScore W4386570123C11413529 @default.
- W4386570123 hasConceptScore W4386570123C120314980 @default.
- W4386570123 hasConceptScore W4386570123C138236772 @default.
- W4386570123 hasConceptScore W4386570123C154945302 @default.
- W4386570123 hasConceptScore W4386570123C162307627 @default.
- W4386570123 hasConceptScore W4386570123C179799912 @default.
- W4386570123 hasConceptScore W4386570123C186967261 @default.
- W4386570123 hasConceptScore W4386570123C2776214188 @default.
- W4386570123 hasConceptScore W4386570123C2778456923 @default.
- W4386570123 hasConceptScore W4386570123C2781041963 @default.
- W4386570123 hasConceptScore W4386570123C31258907 @default.
- W4386570123 hasConceptScore W4386570123C41008148 @default.
- W4386570123 hasConceptScore W4386570123C76155785 @default.
- W4386570123 hasConceptScore W4386570123C79974875 @default.
- W4386570123 hasConceptScore W4386570123C82876162 @default.
- W4386570123 hasConceptScore W4386570123C93996380 @default.
- W4386570123 hasFunder F4320320847 @default.
- W4386570123 hasLocation W43865701231 @default.
- W4386570123 hasOpenAccess W4386570123 @default.
- W4386570123 hasPrimaryLocation W43865701231 @default.
- W4386570123 hasRelatedWork W2945616868 @default.
- W4386570123 hasRelatedWork W2987375765 @default.
- W4386570123 hasRelatedWork W3006227554 @default.
- W4386570123 hasRelatedWork W3009018976 @default.
- W4386570123 hasRelatedWork W3042877534 @default.
- W4386570123 hasRelatedWork W3184768109 @default.
- W4386570123 hasRelatedWork W4200411065 @default.
- W4386570123 hasRelatedWork W4281678247 @default.
- W4386570123 hasRelatedWork W4287076991 @default.
- W4386570123 hasRelatedWork W4313145167 @default.
- W4386570123 hasVolume "236" @default.
- W4386570123 isParatext "false" @default.
- W4386570123 isRetracted "false" @default.
- W4386570123 workType "article" @default.