모바일 엣지컴퓨팅의 서비스 마이그레이션을 위한 최적 경로 알고리즘에 관한 연구
A Study on the Optimal Route Decision Algorithm for Service Migration of Mobile Edge Computing
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
MEC(Mobile Edge Computing)에서 사용자의 이동성 지원 및 서비스의 연속성 보장은 중요한 요소이다. 특히 다양한 네트워크와 이기종의 서비스가 혼재하는 IoT(Internet of Things) 환경에서의 마이그레이션 경로 결정 문제는 더욱 복잡하다. 본 연구에서는 이기종의 다양한 서비스가 혼재하는 환경에서 UE(User Equipment)의 이동에도 끊김없이 서비스를 제공해 사용자의 QoS(Quality of Service)를 높이고자 한다. 이동성 지원을 위해 마이그레이션 비용과 전송비용, 에너지 소비량을 고려한 총비용을 계산하고, UE별 가중치를 설정하여 마이그레이션 여부 및 최적의 경로를 결정한다. NS3로 이기종 서비스가 혼재하는 네트워크 환경을 구축하며, DQN(Deep Q-Network) 알고리즘에 가중치를 설정한 보상의 합으로 성능을 확인한다. 실험을 통해 제안하는 weight-DQN 알고리즘이 다양한 서비스가 혼재하는 환경에서 QoS를 더욱 향상시키는 것을 확인한다.
Abstract
In MEC(Mobile Edge Computing), user mobility support and service continuity guarantee are important factors. In particular, the problem of determining a migration path in an IoT(Internet of Things) environment in which various networks and heterogeneous services coexist is more complicated. In this study, we intend to improve the QoS(Quality of Service) of users by providing services without interruption even when UE(User Equipment) moves in an environment where heterogeneous and various services coexist. To support mobility, the total cost considering the migration cost, transmission cost, and energy consumption is calculated, and weights are set for each UE to determine migration and the optimal path. With NS3, a network environment in which heterogeneous services coexist is established, and performance is confirmed by the sum of compensations with weights set in the DQN(Deep Q-Network) algorithm. Experiments confirm that the proposed algorithm further improves QoS in an environment where various services coexist.
참고문헌 (27)
- Y. Mao, "A survey on mobile edge computing : The communication perspective", IEEE Commun. Surveys Tuts, 19(4), pp.2322~2358 (2017)
- Q. Wu, "Mobile social data learning for user-centric location prediction with application in mobile edge service migration", IEEE Internet Things J, 6(5), pp.7737~7747 (2019)
- 임철수, "저지연 엣지 컴퓨팅 서비스를 위한 시스템 소프트웨어 설계 및 성능 평가", 한국차세대컴퓨팅학회 논문지, 18(6), pp.40~48 (2022), 한국차세대컴퓨팅학회[DOI]
- 선경재, "전술 엣지 클라우드를 위한 IP 이동성 관리 기법 적용 VM 마이그레이션 기법", 한국차세대컴퓨팅학회 논문지, 15(3), pp.50~66 (2019), 한국차세대컴퓨팅학회[DOI]
- In Min-dae, "trends in standardization of edge computing", OSIA Standards & Technology Review, 33(2), pp.17~25 (2020)
- Hong Jung-ha, "Edge Computing Technology Trends", Electronic Communication Trend Analysis, 35(6), pp.78~87 (2020)
- 윤종필, "IoT관점에서의 포그 및 엣지 컴퓨팅 기술분석 및 향후 전망", 한국차세대컴퓨팅학회 논문지, 16(6), pp.26~37 (2020), 한국차세대컴퓨팅학회[DOI]
- Z. Zhao, "Intelligent mobile edge computing with pricing in Internet of Things", IEEE Access, 8, pp.37727~37735 (2020)
- F. Mora-GiMUno, "A Secure Multi-Tier Mobile Edge Computing Model for Data Processing Offloading Based on Degree of Trust", Sensors, 18, pp.3211~ (2018)
- S. Wang, "Dynamic service migration in mobile edge-clouds", 2015 IFIP Networking Conference (IFIP Networking), pp.1~9 (2015)
- S. Wang, "Dynamic service placeMUnt for mobile micro-clouds with predicted future costs", IEEE Transactions on Parallel and Distributed Systems, 28(4), pp.1002~1016 (2016)
- M. G. R. Alam, "Multi-agent and reinforceMUnt learning based code offloading in mobile fog", 2016International Conference on Information Networking (ICOIN), pp.285~290 (2016)
- P. Bellavista, "A migration-enhanced edge computing support for mobile devices in hostile environMUnts", 201713th International Wireless Communications and Mobile Computing Conference (IWCMC), pp.957~962 (2017)
- Y. Qian, "ReinforceMUnt learning-based optimal computing and caching in mobile edge network", IEEE J. Sel. Areas in Commun, 38(10), pp.2343~2355 (2020)
- C. Liu, "Distributed Task Migration Optimization in MUC by Extending Multi-Agent Deep ReinforceMUnt Learning Approach", IEEE Transactions on Parallel and Distributed Systems, 32(7), pp.1603~1614 (2021)
- C. Zhang, "Task migration for mobile edge computing using deep reinforceMUnt learning", Future Generation Computer Systems, 96, pp.111~118 (2019)
- S. W. Park, "A novel deep reinforceMUnt learning based service migration model for mobile edge computing", 2020 IEEE, 2020, 1~8
- W. Yi-Chen, "A Robust Distributed Hierarchical Online Learning Approach for Dynamic MUC Networks", IEEE, 40(2), pp.641~656 (2022)
- B. yang, "Service Migration with High-Order MDP in Mobile Edge Computing", IEEE 2021 13th ICCSN, pp.206~212 (2021)
- I. Sarkar, "Deep ReinforceMUnt Learning for Intelligent Service Provisioning in Software-Defined Industrial Fog Networks", IEEE, 9(18), pp.16953~16961 (2022)
- Dewan, M. A. R., "A quantitative approach for selecting the optimal cloud migration strategy", Journal of Systems and Software, 148, pp.91~104 (2019)
- "MUC-simulator"[URL]
- "ns3-gym"[URL]
- "ns-3"[URL]
- "OpenAI Gym"[URL]
- "프로토콜 버퍼(Protocol Buffers, Protobuf)"[URL]
- "ZeroMQ(ØMQ, 0MQ, ZMQ)"[URL]