Sökning: id:"swepub:oai:DiVA.org:umu-220744" >
RAVAS: interference...
RAVAS: interference-aware model selection and resource allocation for live edge video analytics
-
- Rahmanian, Ali (författare)
- Umeå universitet,Institutionen för datavetenskap,Umeå University
-
- Ali-Eldin Hassan, Ahmed, 1985 (författare)
- Chalmers University of Technology, Gothenburg, Sweden,Chalmers tekniska högskola
-
- Kostentinos Tesfatsion, Selome (författare)
- Ericsson Research, Stockholm, Sweden,Telefonaktiebolaget L M Ericsson,Ericsson
-
visa fler...
-
- Skubic, Björn (författare)
- Ericsson Research, Stockholm, Sweden,Telefonaktiebolaget L M Ericsson,Ericsson
-
- Gustafsson, Harald (författare)
- Ericsson Research, Ericsson AB, Lund, Sweden,Telefonaktiebolaget L M Ericsson,Ericsson
-
- Shenoy, Prashant (författare)
- University of Massachusetts, Massachusetts, USA
-
- Elmroth, Erik (författare)
- Umeå universitet,Institutionen för datavetenskap,Umeå University
-
visa färre...
-
(creator_code:org_t)
- Institute of Electrical and Electronics Engineers (IEEE), 2023
- 2023
- Engelska.
-
Ingår i: 2023 IEEE/ACM Symposium on Edge Computing (SEC). - : Institute of Electrical and Electronics Engineers (IEEE). - 9798400701238 ; , s. 27-39, s. 27-39
- Relaterad länk:
-
https://www.computer...
-
visa fler...
-
https://urn.kb.se/re...
-
https://research.cha...
-
visa färre...
Abstract
Ämnesord
Stäng
- 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. In this paper, we introduce RAVAS, a Real-time Adaptive stream Video Analytics System that enables efficient edge GPU sharing for processing streams from various mobile cameras. RAVAS uses Q-Learning to choose between a set of Deep Neural Network (DNN) models with varying accuracy and processing requirements based on the current GPU utilization and workload. RAVAS employs an innovative resource allocation strategy to mitigate interference during concurrent GPU execution. Compared to state-of-the-art approaches, our results show that RAVAS incurs 57% less compute overhead, achieves 41% improvement in latency, and 43% savings in total GPU usage for a single video stream. Processing multiple concurrent video streams results in up to 99% and 40% reductions in latency and overall GPU usage, respectively, while meeting the accuracy constraints.
Ämnesord
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Datorsystem (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Computer Systems (hsv//eng)
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik -- Kommunikationssystem (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering -- Communication Systems (hsv//eng)
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Edge Video Analytics
- Model Selection
- Resource Allocation
- Interference-aware GPU Multiplexing
- Computer Systems
- datorteknik
Publikations- och innehållstyp
- ref (ämneskategori)
- kon (ämneskategori)
Hitta via bibliotek
Till lärosätets databas