Home /Research /RAVAS: Interference-Aware Model Selection and Resource Allocation for Live Edge Video Analytics
OTHER

RAVAS: Interference-Aware Model Selection and Resource Allocation for Live Edge Video Analytics

Ali Rahmanian, Ahmed Ali-Eldin, Selome Kostentinos Tesfatsion, Björn Skubic, Harald Gustafsson, Prashant Shenoy, Erik Elmroth

Year
2023
Citations
6

Abstract

Numerous edge applications that rely on video analytics demand precise, low-latency processing of multiple video streams from cameras. When these cameras are mobile, such as when mounted on a car or a robot, the processing load on the shared edge GPU can vary considerably. Provisioning the edge with GPUs for the worst-case load can be expensive and, for many applications, not feasible.

Keywords

Computer scienceAnalyticsEnhanced Data Rates for GSM EvolutionInterference (communication)Selection (genetic algorithm)Resource allocationResource (disambiguation)Edge deviceResource management (computing)Computer network

Related papers

Browse all OTHER papers