A Generic Framework for Deploying Video Analytic Services on the Edge
Journal article
Tsakanikas, V. and Dagiuklas, A. (2022). A Generic Framework for Deploying Video Analytic Services on the Edge. IEEE Transactions on Cloud Computing. https://doi.org/10.1109/TCC.2022.3218813
Authors | Tsakanikas, V. and Dagiuklas, A. |
---|---|
Abstract | This paper introduces a novel distributed model for handling in real-time, edge-based Artificial Intelligence analytics, such as the ones required for smart video surveillance. The novelty of the model relies on decoupling and distributing the services into several decomposed functions which are linked together, creating virtual function chains (VFC model). The model considers both computational and communication constraints. Theoretical, simulation and experimental results have shown that the VFC model can enable the support of heavy-load services to an edge environment while improving the footprint of the service compared to state-of-the art frameworks. In detail, results on the VFC model have shown that it can reduce the total edge cost, compared with a Monolithic and a Simple Frame Distribution models. For experimenting on a real-case scenario, a testbed edge environment has been developed, where the aforementioned models, as well as a general distribution framework (Spark ©) and an edge-deployement framework (Kubernetes©), have been deployed. A cloud service has also been considered. Experiments have shown that VFC can outperform all alternative approaches, by reducing operational cost and improving the QoS. Finally, a caching and a QoS monitoring service based on Long-Term-Short-Term models are introduced and evaluated. |
Keywords | edge computing; AI applications; Virtual Function Chaining;caching; cost optimization; long-short term memory; QoS constraints |
Year | 2022 |
Journal | IEEE Transactions on Cloud Computing |
Publisher | Institute of Electrical and Electronics Engineers (IEEE) |
ISSN | 2168-7161 |
Digital Object Identifier (DOI) | https://doi.org/10.1109/TCC.2022.3218813 |
Publication dates | |
02 Nov 2022 | |
Publication process dates | |
Accepted | 28 Oct 2022 |
Deposited | 07 Nov 2022 |
Accepted author manuscript | License File Access Level Open |
Additional information | © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
https://openresearch.lsbu.ac.uk/item/9266y
Download files
65
total views120
total downloads1
views this month1
downloads this month