Umeå universitets logga

umu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
RAVAS: interference-aware model selection and resource allocation for live edge video analytics
Umeå universitet, Teknisk-naturvetenskapliga fakulteten, Institutionen för datavetenskap.ORCID-id: 0000-0001-9249-1633
Chalmers University of Technology, Gothenburg, Sweden.
Ericsson Research, Stockholm, Sweden.
Ericsson Research, Stockholm, Sweden.
Visa övriga samt affilieringar
2023 (Engelska)Ingår i: 2023 IEEE/ACM Symposium on Edge Computing (SEC): Proceedings, Institute of Electrical and Electronics Engineers (IEEE), 2023, s. 27-39Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

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.

Ort, förlag, år, upplaga, sidor
Institute of Electrical and Electronics Engineers (IEEE), 2023. s. 27-39
Nyckelord [en]
Edge Video Analytics, Model Selection, Resource Allocation, Interference-aware GPU Multiplexing
Nationell ämneskategori
Datorsystem
Forskningsämne
datorteknik
Identifikatorer
URN: urn:nbn:se:umu:diva-220744DOI: 10.1145/3583740.3628443ISI: 001164050000003Scopus ID: 2-s2.0-85186111633ISBN: 979-8-4007-0123-8 (tryckt)OAI: oai:DiVA.org:umu-220744DiVA, id: diva2:1836734
Konferens
2023 IEEE/ACM Symposium on Edge Computing (SEC), Wilmington, USA, December 6-9, 2023
Tillgänglig från: 2024-02-11 Skapad: 2024-02-11 Senast uppdaterad: 2024-04-08Bibliografiskt granskad
Ingår i avhandling
1. Edge orchestration for latency-sensitive applications
Öppna denna publikation i ny flik eller fönster >>Edge orchestration for latency-sensitive applications
2024 (Engelska)Doktorsavhandling, sammanläggning (Övrigt vetenskapligt)
Alternativ titel[sv]
Orkestrering av distribuerade resurser för latenskänsliga applikationer
Abstract [en]

The emerging edge computing infrastructure provides distributed and heterogeneous resources closer to where data is generated and where end-users are located, thereby significantly reducing latency. With the recent advances in telecommunication systems, software architecture, and machine learning, there is a noticeable increase in applications that require processing times within tight latency constraints, i.e. latency-sensitive applications. For instance, numerous video analytics applications, such as traffic control systems, necessitate real-time processing capabilities. Orchestrating such applications at the edge offers numerous advantages, including lower latency, optimized bandwidth utilization, and enhanced scalability. However, despite its potential, effectively managing such latency-sensitive applications at the edge poses several challenges such as constrained compute resources, which holds back the full promise of edge computing.

This thesis proposes approaches to efficiently deploy latency-sensitive applications on the edge infrastructure. It partly addresses general applications with microservice architectures and party addresses the increasingly more important video analytics applications for the edge. To do so, this thesis proposes various application- and system-level solutions aiming to efficiently utilize constrained compute capacity on the edge while meeting prescribed latency constraints. These solutions primarily focus on effective resource management approaches and optimizing incoming workload inputs, considering the constrained compute capacity of edge resources. Additionally, the thesis explores the synergy effects of employing both application- and system-level resource optimization approaches together.

The results demonstrate  the effectiveness of the proposed solutions in enhancing the utilization of edge resources for latency-sensitive applications while adhering to application constraints. The proposed resource management solutions, alongside application-level optimization techniques, significantly improve resource efficiency while satisfying application requirements. Our results show that our solutions for microservice architectures significantly improve end-to-end latency by up to 800% while minimizing edge resource usage. Additionally, the results indicate that our application- and system-level optimizations for orchestrating edge resources for video analytics applications can increase the overall throughput by up to 60%. 

Ort, förlag, år, upplaga, sidor
Umeå: Umeå University, 2024. s. 46
Serie
UMINF, ISSN 0348-0542 ; 24.04
Nyckelord
Edge Computing, Resource Management, Latency-Sensitive Applications, Edge Video Analytics
Nationell ämneskategori
Datavetenskap (datalogi)
Forskningsämne
datalogi; datorteknik
Identifikatorer
urn:nbn:se:umu:diva-223021 (URN)978-91-8070-350-5 (ISBN)978-91-8070-351-2 (ISBN)
Disputation
2024-04-29, Hörsal UB.A.240 - Lindellhallen 4, 13:00 (Engelska)
Opponent
Handledare
Anmärkning

Incorrect date of publication on the posting sheet. 

Tillgänglig från: 2024-04-08 Skapad: 2024-04-08 Senast uppdaterad: 2024-04-08Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopusPublisher's full text

Person

Rahmanian, AliElmroth, Erik

Sök vidare i DiVA

Av författaren/redaktören
Rahmanian, AliElmroth, Erik
Av organisationen
Institutionen för datavetenskap
Datorsystem

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 75 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf