멀티 에이전트 에지 컴퓨팅 환경에서 확장성을 지원하는딥러닝 기반 동적 스케줄링
Deep Learning-Based Dynamic Scheduling with Multi-Agents Supporting Scalability in Edge Computing Environments
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
클라우드 컴퓨팅은 에지 서버가 동작하는 포그(fog) 레이어가 결합된 에지(edge) 컴퓨팅 아키텍처로 진화하고 있다. 에지 컴퓨팅 아키텍처가관심을 받는 이유는 짧은 통신 지연으로 실시간 IoT 응용을 지원할 수 있기 때문이다. 이와 동시에 인공지능 기술을 도입한 많은 클라우드 작업스케줄링 기법들이 제안되었다. 인공지능 기반의 클라우드 작업 스케줄링 기법은 기존 기법보다 더 좋은 성능을 보이지만 스케줄링 시간이 다소소요된다는 단점이 있다. 이 논문에서는 에지 컴퓨팅 환경에서 분산 딥러닝 학습 기반의 동적 스케줄링 기법을 제안한다. 제안하는 기법은 기존기법보다 스케줄링 시간이 짧은 장점이 있다. 또한 멀티 에이전트를 통한 분산 딥러닝 학습의 효과성을 보이기 위해 확장적인 실험 환경에서 제안기법과 기존 인공지능 기법의 성능일 비교 평가하였다. 성능 실험 결과 기존 인공지능 기반 클라우드 작업 스케줄링 기법보다 짧은 스케줄링 시간을보여 IoT 실시간 응용에 적합함을 보였으며, 확장적인 실험에서도 제안 기법이 완료된 작업의 수에 대하여 우수한 성능을 보임을 증명하였다
Abstract
Cloud computing has been evolved to support edge computing architecture that combines fog management layer with edge servers. The main reason why it is received much attention is low communication latency for real-time IoT applications. At the same time, variouscloud task scheduling techniques based on artificial intelligence have been proposed. Artificial intelligence-based cloud task schedulingtechniques show better performance in comparison to existing methods, but it has relatively high scheduling time. In this paper, wepropose a deep learning-based dynamic scheduling with multi-agents supporting scalability in edge computing environments. The proposedmethod shows low scheduling time than previous artificial intelligence-based scheduling techniques. To show the effectiveness of theproposed method, we compare the performance between previous and proposed methods in a scalable experimental environment. Theresults show that our method supports real-time IoT applications with low scheduling time, and shows better performance in terms ofthe number of completed cloud tasks in a scalable experimental environment.
참고문헌 (19)
- L. Sun, "Edge-Cloud computing and artificial intelligence in internet of medical things : Architecture, technology and application", IEEE Access, 8, pp.101079~101092 (2020)
- U. F. Mustapha, "Sustainable aquaculture development : A review on the roles of cloud computing, internet of things and artificial intelligence(CIA)", Reviews in Aquaculture, 13(4), pp.2076~2091 (2021)
- Y. Pan, "Roles of artificial intelligence in construction engineering and management : A critical review and future trends", Automation in Construction, 122, pp.103517~ (2021)
- G. Ananthanarayanan, "Real-time video analytics : The killer app for edge computing", Computer, 50(10), pp.58~67 (2017)
- K. Cao, "An overview on edge computing research", IEEE Access, 8, pp.85714~85728 (2020)
- W. Shi, "Edge computing : Vision and challenges", IEEE Internet of Things Journal, 3(5), pp.637~646 (2016)
- Q. Luo, "Resource scheduling in edge computing : A survey", IEEE Communications Surveys & Tutorials, 23(4), pp.2131~2165 (2021)
- X. Li, "A hybrid computing solution and resource scheduling strategy for edge computing in smart manufacturing", IEEE Transactions on Industrial Informatics, 15(7), pp.4225~4234 (2019)
- S. Kunal, "An overview of cloud-fog computing : Architectures, applications with security challenges", Security and Privacy, 2(4), pp.e72~ (2019)
- D. Kimovski, "Cloud, fog, or edge : Where to compute?", IEEE Internet Computing, 25(4), pp.30~36 (2021)
- V. Prokhorenko, "Architectural resilience in cloud, fog and edge systems : A survey", IEEE Access, 8, pp.28078~28095 (2020)
- G. Rjoub, "Deep and reinforcement learning for automated task scheduling in large-scale cloud computing systems", Concurrency and Computation: Practice and Experience, 33(23), pp.e5919~ (2021)
- Y. Ran, "DeepEE : Joint optimization of job scheduling and cooling control for data center energy efficiency using deep reinforcement learning", 2019 IEEE 39th International Conference on Distributed Computing Systems (ICDCS), pp.645~655 (2019)
- A. Alqahtani, "End-to-End service level agreement specification for IoT applications", 2018 International Conference on High Performance Computing & Simulation (HPCS), pp.926~935 (2018)
- Q. Liang, "AI on the Edge : Characterizing AI-based IoT applications using specialized edge architectures", 2020 IEEE International Symposium on Workload Characterization (IISWC), pp.145~156 (2020)
- X. Xie, "A transferable approach for partitioning machine learning models on multi-chip-modules", Proceedings of Machine Learning and Systems, 4, pp.370~381 (2022)
- S. Shen, "Statistical characterization of business-critical workloads hosted in cloud datacenters", 2015 15th IEEE, 2015, 465~474
- J. McChesney, "Defog : Fog computing benchmarks", Proceedings of the 4th ACM, 2019, 47~58
- S. Tuli, "Dynamic scheduling for stochastic edge-cloud computing environments using A3C learning and residual recurrent neural networks", IEEE Transactions on Mobile Computing, 21(3), pp.940~954 (2022)