-
摘要:
在移动互联网中，当用户位置发生改变时，业务迁移可用来提升服务质量(QoS)。基于此，提出一种基于马尔可夫决策过程的边缘云业务迁移算法。与对比算法相比，所提算法考虑了不同业务类型对QoS的差异化需求，并全面考虑了业务迁移过程中的收益及开销。所提算法将业务分为实时和非实时2类，将终端的业务运行状态和与服务器的距离作为状态空间，并基于与业务体验紧密相关的可用速率和时延2个QoS指标构建收益函数，同时将业务迁移过程中的系统资源消耗作为迁移开销，通过最大化全局收益来获取最优迁移策略。通过与对比算法的模拟比较，所提算法在多种场景下都有更高的全局收益。
Abstract:In the mobile Internet, when the user’s location changes, service migration can be used to improve quality of service (QoS). This paper proposed an edge cloud service migration algorithm based on the Markov decision process. Compared with the comparison algorithms, the proposed algorithm considered the differentiated requirements for QoS of different service types and comprehensively analyzed the revenue and cost during service migration. The proposed algorithm divided services into two types: real-time ones and non-real-time ones, took the running state of services on the terminal and the distance between the terminal and the server as the state space, and constructed revenue function based on two QoS indicators of available rates and latency, which were closely related to the service experience. The system resource consumption during the service migration was considered as the migration cost, and the optimal migration strategy was obtained by maximizing the overall revenue. Compared with the comparison algorithms, the proposed algorithm obtained larger overall revenue in various scenarios.
-
Key words:
- service migration /
- Markov decision process /
- quality of service /
- migration cost /
- service type
-
图 7 不同调节参数下迁移开销变化情况
Figure 7. Changes of migration costs with different adjusting parameters
图 8 不同调节参数下全局收益变化情况
Figure 8. Changes of overall revenue with different adjusting parameters
图 10 只有非实时业务时全局收益变化情况
Figure 10. Changes of overall revenue with only non-real-time services
表 1 仿真参数
Table 1. Simulation parameters
实时业务
到达率实时业务
离去率非实时业务
到达率非实时业务
离去率t0/ms $\kappa $ Dm kc pa $ {\partial _1} $/(Mb·s−1) $ {\partial _2} $/(Mb·s−1) a1 a2 b1 b2 Cr Cn $ \lambda $ 0.01 0.005 0.03 0.01 30 0.02 6 0.1 3/4 5 10 0.4 0.6 0.8 0.2 0.3 0.7 0.001 
下载: 导出CSV
-
[1] FOH C H, SRIRAMA S N, WU J S, et al. Guest editors’ introduction: Special section on mobile cloud computing[J]. IEEE Transactions on Cloud Computing, 2019, 7(2): 298-300. doi: 10.1109/TCC.2018.2809260 [2] AISSIOUI A, KSENTINI A, GUEROUI A M, et al. On enabling 5G automotive systems using follow me edge-cloud concept[J]. IEEE Transactions on Vehicular Technology, 2018, 67(6): 5302-5316. doi: 10.1109/TVT.2018.2805369 [3] ADDAD R A, DUTRA D L C, BAGAA M, et al. Fast service migration in 5G trends and scenarios[J]. IEEE Network, 2020, 34(2): 92-98. doi: 10.1109/MNET.001.1800289 [4] BRANDHERM F, WANG L, MÜHLHÄUSER M. A learning-based framework for optimizing service migration in mobile edge clouds[C]//Proceedings of the 2nd International Workshop on Edge Systems, Analytics and Networking. New York: ACM, 2019: 12-17. [5] CHEN M, LI W, FORTINO G, et al. A dynamic service migration mechanism in edge cognitive computing[J]. ACM Transactions on Internet Technology, 2019, 19(2): 30. [6] GAO Z P, JIAO Q D, XIAO K L, et al. Deep reinforcement learning based service migration strategy for edge computing[C]//Proceedings of the IEEE International Conference on Service-Oriented System Engineering. Piscataway: IEEE Press, 2019: 116-121. [7] JIANG X L, SHOKRI-GHADIKOLAEI H, FODOR G, et al. Low-latency networking: Where latency lurks and how to tame it[J]. Proceedings of the IEEE, 2019, 107(2): 280-306. doi: 10.1109/JPROC.2018.2863960 [8] REN J K, YU G D, HE Y H, et al. Collaborative cloud and edge computing for latency minimization[J]. IEEE Transactions on Vehicular Technology, 2019, 68(5): 5031-5044. doi: 10.1109/TVT.2019.2904244 [9] ANWAR M R, WANG S G, AKRAM M F, et al. 5G-enabled MEC: A distributed traffic steering for seamless service migration of Internet of vehicles[J]. IEEE Internet of Things Journal, 2022, 9(1): 648-661. doi: 10.1109/JIOT.2021.3084912 [10] LI C L, ZHU L, LI W G, et al. Joint edge caching and dynamic service migration in SDN based mobile edge computing[J]. Journal of Network and Computer Applications, 2021, 177: 102966. doi: 10.1016/j.jnca.2020.102966 [11] LIN H W, XU X L, ZHAO J, et al. Dynamic service migration in ultra-dense multi-access edge computing network for high-mobility scenarios[J]. EURASIP Journal on Wireless Communications and Networking, 2020, 2020(1): 191. doi: 10.1186/s13638-020-01805-2 [12] 郭辉, 芮兰兰, 高志鹏. 车辆边缘网络中基于多参数MDP模型的动态服务迁移策略[J]. 通信学报, 2020, 41(1): 1-14. doi: 10.11959/j.issn.1000-436x.2020012GUO H, RUI L L, GAO Z P. Dynamic service migration strategy based on MDP model with multiple parameter in vehicular edge network[J]. Journal on Communications, 2020, 41(1): 1-14 (in Chinese). doi: 10.11959/j.issn.1000-436x.2020012 [13] ZHOU X B, GE S X, QIU T, et al. Energy-efficient service migration for multi-user heterogeneous dense cellular networks[J]. IEEE Transactions on Mobile Computing, 2023, 22(2): 890-905. doi: 10.1109/TMC.2021.3087198 [14] WANG S Q, URGAONKAR R, ZAFER M, et al. Dynamic service migration in mobile edge computing based on Markov decision process[J]. IEEE/ACM Transactions on Networking, 2019, 27(3): 1272-1288. doi: 10.1109/TNET.2019.2916577 [15] YUAN Q, LI J L, ZHOU H B, et al. A joint service migration and mobility optimization approach for vehicular edge computing[J]. IEEE Transactions on Vehicular Technology, 2020, 69(8): 9041-9052. doi: 10.1109/TVT.2020.2999617 [16] LI J, SHEN X M, CHEN L, et al. Service migration in fog computing enabled cellular networks to support real-time vehicular communications[J]. IEEE Access, 2019, 7: 13704-13714. doi: 10.1109/ACCESS.2019.2893571 [17] PENG Y, LIU L, ZHOU Y Q, et al. Deep reinforcement learning-based dynamic service migration in vehicular networks[C]//Proceedings of the IEEE Global Communications Conference. Piscataway: IEEE Press, 2019: 1-6. [18] ABOUAOMAR A, MLIKA Z, FILALI A, et al. A deep reinforcement learning approach for service migration in MEC-enabled vehicular networks[C]//Proceedings of the IEEE 46th Conference on Local Computer Networks. Piscataway: IEEE Press, 2021: 273-280. [19] XU M X, ZHOU Q H, WU H M, et al. PDMA: Probabilistic service migration approach for delay-aware and mobility-aware mobile edge computing[J]. Software:Practice and Experience, 2022, 52(2): 394-414. doi: 10.1002/spe.3014 [20] WANG H M, LI Y X, ZHOU A, et al. Service migration in mobile edge computing: A deep reinforcement learning approach[J]. International Journal of Communication Systems, 2023, 36(1): 1-15. [21] CHIANG K H, SHENOY N. A 2-D random-walk mobility model for location-management studies in wireless networks[J]. IEEE Transactions on Vehicular Technology, 2004, 53(2): 413-424. doi: 10.1109/TVT.2004.823544 [22] SU P, ZHOU W W, GU Q, et al. Network selection algorithm based on spectral bandwidth mapping and an economic model in WLAN & LTE heterogeneous networks[J]. KSII Transactions on Internet and Information Systems, 2015, 9(1): 68-86. -
下载:
点击查看大图
计量
- 文章访问数: 161
- HTML全文浏览量: 81
- PDF下载量: 3
- 被引次数: 0
