Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386634210> ?p ?o ?g. }
Showing items 1 to 82 of
82
with 100 items per page.
- W4386634210 endingPage "16" @default.
- W4386634210 startingPage "1" @default.
- W4386634210 abstract "With the rapid development of edge intelligence cloud (EIC), mobile users are not satisfied with a single artificial intelligence inference service, but require multiple inference services with chain dependencies to process data. Each AI service chain (AISC) is provided as a series of interconnected virtual network functions (VNFs) on-demand deployed on edge servers. However, AISCs experience unpredictable failures and potential attacks in EIC, which may violate different inference requirements of mobile users for reliability, security, and accuracy. To provide reliable AISCs, additional backup VNFs (BVNFs) need to be deployed nearby VNFs in case they experience faults, yet inference accuracy may degrade because these new links between the BVNFs and the VNFs would make AISCs vulnerable to more link attacks that affect data quality. How to optimally deploy VNFs and BVNFs on trusted edge servers, and select secure links to form satisfactory AISCs, meanwhile throughput of receiving requests is maximized while the deployment cost of computing resources used to create VNFs and BVNFs with different model sizes is minimized in real-time, is a challenging problem. In this paper, the problem is first formulated as an integer linear programming and proved to be NP-hard. Then, we consider the problem under two online backup scenarios: one is an on-site scenario where AISC requests from the mobile devices arrive one by one, and link securities between VNFs and corresponding BVNFs are ignored because they are always on the same edge server; another is an off-site scenario where a set of AISC requests are given, and VNFs and BVNFs are deployed on different servers. Finally, two online algorithms with provable competitive ratios are proposed to solve the above two problems in polynomial time. Theoretical analyses and experiments based on real network topologies demonstrate that our algorithms are promising compared to baseline algorithms." @default.
- W4386634210 created "2023-09-13" @default.
- W4386634210 creator A5005318205 @default.
- W4386634210 creator A5012718640 @default.
- W4386634210 creator A5018741551 @default.
- W4386634210 creator A5035919267 @default.
- W4386634210 date "2023-01-01" @default.
- W4386634210 modified "2023-10-18" @default.
- W4386634210 title "Online Security-Aware and Reliability-Guaranteed AI Service Chains Provisioning in Edge Intelligence Cloud" @default.
- W4386634210 doi "https://doi.org/10.1109/tmc.2023.3314580" @default.
- W4386634210 hasPublicationYear "2023" @default.
- W4386634210 type Work @default.
- W4386634210 citedByCount "0" @default.
- W4386634210 crossrefType "journal-article" @default.
- W4386634210 hasAuthorship W4386634210A5005318205 @default.
- W4386634210 hasAuthorship W4386634210A5012718640 @default.
- W4386634210 hasAuthorship W4386634210A5018741551 @default.
- W4386634210 hasAuthorship W4386634210A5035919267 @default.
- W4386634210 hasConcept C110875604 @default.
- W4386634210 hasConcept C111919701 @default.
- W4386634210 hasConcept C120314980 @default.
- W4386634210 hasConcept C121332964 @default.
- W4386634210 hasConcept C136264566 @default.
- W4386634210 hasConcept C154945302 @default.
- W4386634210 hasConcept C162307627 @default.
- W4386634210 hasConcept C162324750 @default.
- W4386634210 hasConcept C163258240 @default.
- W4386634210 hasConcept C172191483 @default.
- W4386634210 hasConcept C2776061582 @default.
- W4386634210 hasConcept C2776214188 @default.
- W4386634210 hasConcept C2778456923 @default.
- W4386634210 hasConcept C2780378061 @default.
- W4386634210 hasConcept C2780945871 @default.
- W4386634210 hasConcept C31258907 @default.
- W4386634210 hasConcept C38652104 @default.
- W4386634210 hasConcept C38822068 @default.
- W4386634210 hasConcept C41008148 @default.
- W4386634210 hasConcept C43214815 @default.
- W4386634210 hasConcept C62520636 @default.
- W4386634210 hasConcept C79974875 @default.
- W4386634210 hasConcept C93996380 @default.
- W4386634210 hasConceptScore W4386634210C110875604 @default.
- W4386634210 hasConceptScore W4386634210C111919701 @default.
- W4386634210 hasConceptScore W4386634210C120314980 @default.
- W4386634210 hasConceptScore W4386634210C121332964 @default.
- W4386634210 hasConceptScore W4386634210C136264566 @default.
- W4386634210 hasConceptScore W4386634210C154945302 @default.
- W4386634210 hasConceptScore W4386634210C162307627 @default.
- W4386634210 hasConceptScore W4386634210C162324750 @default.
- W4386634210 hasConceptScore W4386634210C163258240 @default.
- W4386634210 hasConceptScore W4386634210C172191483 @default.
- W4386634210 hasConceptScore W4386634210C2776061582 @default.
- W4386634210 hasConceptScore W4386634210C2776214188 @default.
- W4386634210 hasConceptScore W4386634210C2778456923 @default.
- W4386634210 hasConceptScore W4386634210C2780378061 @default.
- W4386634210 hasConceptScore W4386634210C2780945871 @default.
- W4386634210 hasConceptScore W4386634210C31258907 @default.
- W4386634210 hasConceptScore W4386634210C38652104 @default.
- W4386634210 hasConceptScore W4386634210C38822068 @default.
- W4386634210 hasConceptScore W4386634210C41008148 @default.
- W4386634210 hasConceptScore W4386634210C43214815 @default.
- W4386634210 hasConceptScore W4386634210C62520636 @default.
- W4386634210 hasConceptScore W4386634210C79974875 @default.
- W4386634210 hasConceptScore W4386634210C93996380 @default.
- W4386634210 hasLocation W43866342101 @default.
- W4386634210 hasOpenAccess W4386634210 @default.
- W4386634210 hasPrimaryLocation W43866342101 @default.
- W4386634210 hasRelatedWork W2804937556 @default.
- W4386634210 hasRelatedWork W2981507084 @default.
- W4386634210 hasRelatedWork W3006227554 @default.
- W4386634210 hasRelatedWork W3009018976 @default.
- W4386634210 hasRelatedWork W3036568761 @default.
- W4386634210 hasRelatedWork W3174690704 @default.
- W4386634210 hasRelatedWork W3211897977 @default.
- W4386634210 hasRelatedWork W4232690962 @default.
- W4386634210 hasRelatedWork W4310080053 @default.
- W4386634210 hasRelatedWork W4318954397 @default.
- W4386634210 isParatext "false" @default.
- W4386634210 isRetracted "false" @default.
- W4386634210 workType "article" @default.