Please wait a minute...
浙江大学学报(工学版)  2026, Vol. 60 Issue (8): 1697-1708    DOI: 10.3785/j.issn.1008-973X.2026.08.009
计算机技术     
面向移动边缘计算的可靠性增强任务部署方法
赵庶旭(),朱祺,王小龙
兰州交通大学 电子与信息工程学院,甘肃 兰州 730070
Reliability-enhanced task deployment method in mobile edge computing environments
Shuxu ZHAO(),Qi ZHU,Xiaolong WANG
School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China
 全文: PDF(1796 KB)   HTML
摘要:

边缘计算环境中存在如边缘服务器和虚拟机故障的风险因素,导致系统可靠性与服务质量降低,为此基于故障感知与可靠性均衡原理,提出时延-可靠性协同优化的任务部署策略. 建立可靠性增强移动边缘计算(MEC)系统模型以及基于服务器负载感知的故障率变化模型. 在减少时延与提高系统可靠性水平之间权衡,找到合适的计算节点部署任务,在能耗约束的条件下实现低时延、高可靠性的任务部署方案. 针对服务器故障率变化的情况,提出可靠性均衡的概念,通过限制边缘服务器的最大资源使用率来保证系统的可靠性,使用可靠性均衡评价指标(DRI)来衡量算法的性能. 仿真实验结果表明,与其他相关算法相比,2种所提算法在系统可靠性上分别平均提升了0.57%和1.09%,在时延上分别平均减少了30.06%和16.86%.

关键词: 移动边缘计算(MEC)可靠性增强可靠性均衡时延任务卸载    
Abstract:

In the edge computing environment, risk factors such as edge server and virtual machine failures could lead to the degradation of system reliability and quality of service. Based on the principle of fault perception and reliability balancing, a task deployment strategy for delay-reliability collaborative optimization was proposed. First, a reliability-enhanced mobile edge computing (MEC) system model and a failure rate variation model based on server load perception were established. Then, by weighing the trade-off between reducing latency and improving the reliability level of the system, suitable computing nodes for task deployment were identified, and a low-latency and high-reliability deployment scheme was achieved under energy consumption constraints. Finally, in view of the change in server failure rate, the concept of reliability equilibrium was introduced, which ensured system reliability by limiting the maximum resource utilization of edge servers, and the degree of reliability imbalance (DRI) was employed to measure algorithm performance. Simulation results demonstrated that, compared with other related algorithms, the two proposed algorithms improved system reliability by 0.57% and 1.09%, and reduced latency by 30.06% and 16.86%, respectively, on average.

Key words: mobile edge computing (MEC)    reliability enhancement    reliability balancing    latency    task offloading
收稿日期: 2025-06-18 出版日期: 2026-07-16
CLC:  TP 391.9  
基金资助: 甘肃省重点研发计划基金资助项目(20YF8GA123).
作者简介: 赵庶旭(1976—),男,教授,博士,从事智能交通、边缘计算研究. orcid.org/0000-0001-8521-5833. E-mail:zhaosx@mail.lzjtu.cn
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章  
赵庶旭
朱祺
王小龙

引用本文:

赵庶旭,朱祺,王小龙. 面向移动边缘计算的可靠性增强任务部署方法[J]. 浙江大学学报(工学版), 2026, 60(8): 1697-1708.

Shuxu ZHAO,Qi ZHU,Xiaolong WANG. Reliability-enhanced task deployment method in mobile edge computing environments. Journal of ZheJiang University (Engineering Science), 2026, 60(8): 1697-1708.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2026.08.009        https://www.zjujournals.com/eng/CN/Y2026/V60/I8/1697

图 1  面向移动边缘计算的任务部署模型图
图 2  移动边缘计算系统模型图
图 3  应用程序有向无环图层次模型
图 4  可靠性增强的低时延任务卸载算法流程图
图 5  可靠性均衡的低时延任务卸载算法流程图
图 6  边缘服务器故障率变化曲线
图 7  服务器最大压力值对算法性能的影响
图 8  正可调因子对算法性能的影响
图 9  不同工作流对算法性能的影响
图 10  故障率变化因子对算法性能的影响
图 11  边缘服务器数量对算法性能的影响
NmecRsys
RandomRRRGreedyLLRELLRBRETO
30.94800.96190.95510.95450.97010.9544
40.96280.96700.96170.96650.97340.9641
50.96250.96950.96310.97160.97670.9661
60.96430.96910.96520.96970.97730.9679
70.96450.96960.96920.97230.97790.9692
80.96420.96820.97020.97360.97870.9697
表 1  边缘服务器数量对系统可靠性的影响
NmecTavg/s
RandomRRRGreedyLLRELLRBRETO
31.12380.48530.34440.42990.45760.4034
41.04170.49140.31090.43540.44910.3702
50.99450.49640.30440.43510.45720.3718
60.92940.48270.28180.39980.43330.3528
70.89480.47320.26980.34510.40780.3529
80.85900.47430.26140.34470.40980.3554
表 2  边缘服务器数量对平均时延的影响
图 12  随机减少的边缘服务器数量对算法性能的影响
1 谢人超, 廉晓飞, 贾庆民, 等 移动边缘计算卸载技术综述[J]. 通信学报, 2018, 39 (11): 138- 155
XIE Renchao, LIAN Xiaofei, JIA Qingmin, et al Survey on computation offloading in mobile edge computing[J]. Journal on Communications, 2018, 39 (11): 138- 155
doi: 10.11896/jsjkx.250100058
2 CHEN L, XU Y, LU Z, et al IoT microservice deployment in edge-cloud hybrid environment using reinforcement learning[J]. IEEE Internet of Things Journal, 2021, 8 (16): 12610- 12622
doi: 10.1109/JIOT.2020.3014970
3 MAZLAMI G, CITO J, LEITNER P. Extraction of microservices from monolithic software architectures [C]// Proceedings of the IEEE International Conference on Web Services. Honolulu: IEEE, 2017: 524–531.
4 ARAL A, BRANDIĆ I Learning spatiotemporal failure dependencies for resilient edge computing services[J]. IEEE Transactions on Parallel and Distributed Systems, 2021, 32 (7): 1578- 1590
doi: 10.1109/TPDS.2020.3046188
5 KUMARI P, KAUR P A survey of fault tolerance in cloud computing[J]. Journal of King Saud University: Computer and Information Sciences, 2021, 33 (10): 1159- 1176
doi: 10.1016/j.jksuci.2018.09.021
6 BIRKE R, GIURGIU I, CHEN L Y, et al. Failure analysis of virtual and physical machines: patterns, causes and characteristics [C]// Proceedings of the 44th Annual IEEE/IFIP International Conference on Dependable Systems and Networks. Atlanta: IEEE, 2014: 1–12.
7 RAY K, BANERJEE A Prioritized fault recovery strategies for multi-access edge computing using probabilistic model checking[J]. IEEE Transactions on Dependable and Secure Computing, 2023, 20 (1): 797- 812
doi: 10.1109/TDSC.2022.3143877
8 LONG T, MA Y, XIA Y, et al. A mobility-aware and fault-tolerant service offloading method in mobile edge computing [C]// Proceedings of the IEEE International Conference on Web Services. Barcelona: IEEE, 2022: 67–72.
9 LIU H, CAO L, PEI T, et al A fast algorithm for energy-saving offloading with reliability and latency requirements in multi-access edge computing[J]. IEEE Access, 2020, 8: 151- 161
doi: 10.1109/ACCESS.2019.2961453
10 LIU J, ZHOU A, LIU C, et al Reliability-enhanced task offloading in mobile edge computing environments[J]. IEEE Internet of Things Journal, 2022, 9 (13): 10382- 10396
doi: 10.1109/JIOT.2021.3115807
11 SAMANTA A, ESPOSITO F, NGUYEN T G Fault-tolerant mechanism for edge-based IoT networks with demand uncertainty[J]. IEEE Internet of Things Journal, 2021, 8 (23): 16963- 16971
doi: 10.1109/JIOT.2021.3075681
12 LIU J, ZHANG Q Offloading schemes in mobile edge computing for ultra-reliable low latency communications[J]. IEEE Access, 2018, 6: 12825- 12837
doi: 10.1109/ACCESS.2018.2800032
13 ZHAO H, DENG S, LIU Z, et al Distributed redundant placement for microservice-based applications at the edge[J]. IEEE Transactions on Services Computing, 2022, 15 (3): 1732- 1745
doi: 10.1109/TSC.2020.3013600
14 TULI S, CASALE G, JENNINGS N R. PreGAN: preemptive migration prediction network for proactive fault-tolerant edge computing [C]// Proceedings of the IEEE INFOCOM 2022 - IEEE Conference on Computer Communications. London: IEEE, 2022: 670–679.
15 LONG T, CHEN P, XIA Y, et al A deep deterministic policy gradient-based method for enforcing service fault-tolerance in MEC[J]. Chinese Journal of Electronics, 2024, 33 (4): 899- 909
doi: 10.23919/cje.2023.00.105
16 SONG L, SUN G, YU H. An approach for fault tolerance in multi-access edge computing [C]// Proceedings of the IEEE 2nd International Conference on Deep Learning and Computer Vision. Jinan: IEEE, 2025: 1–5.
17 PARK T, YOU M, KIM J, et al Fatriot: fault-tolerant MEC architecture for mission-critical systems using a SmartNIC[J]. Journal of Network and Computer Applications, 2024, 231: 103978
doi: 10.1016/j.jnca.2024.103978
18 International Organization for Standardization. Road vehicles - functional safety: ISO 26262 [S]. Geneva: International Organization for Standardization, 2017.
19 BARI M F, BOUTABA R, ESTEVES R, et al Data center network virtualization: a survey[J]. IEEE Communications Surveys and Tutorials, 2013, 15 (2): 909- 928
doi: 10.1109/SURV.2012.090512.00043
20 XIE G, ZENG G, CHEN Y, et al Minimizing redundancy to satisfy reliability requirement for a parallel application on heterogeneous service-oriented systems[J]. IEEE Transactions on Services Computing, 2020, 13 (5): 871- 886
doi: 10.1109/TSC.2017.2665552
21 BURKE E K, KENDALL G. Search methodologies: introductory tutorials in optimization and decision support techniques [M]. Boston: Springer, 2014: 273–316.
22 TONG Z, DENG X, CHEN H, et al DDMTS: a novel dynamic load balancing scheduling scheme under SLA constraints in cloud computing[J]. Journal of Parallel and Distributed Computing, 2021, 149: 138- 148
doi: 10.1016/j.jpdc.2020.11.007
23 GABI D, ISMAIL A S, ZAINAL A, et al Orthogonal Taguchi-based cat algorithm for solving task scheduling problem in cloud computing[J]. Neural Computing and Applications, 2018, 30 (6): 1845- 1863
doi: 10.1007/s00521-016-2816-4
24 KHATAVKAR B, BOOPATHY P. Efficient WMaxMin static algorithm for load balancing in cloud computation [C]// Proceedings of the Innovations in Power and Advanced Computing Technologies (i-PACT). Vellore: IEEE, 2018: 1–6.
25 邵苏杰, 吴磊, 钟成, 等 面向多工作流的基于容器的边缘微服务选择机制[J]. 电子与信息学报, 2022, 44 (11): 3748- 3756
SHAO Sujie, WU Lei, ZHONG Cheng, et al Container based microservice selection for multi-workflow in edge computing paradigm[J]. Journal of Electronics and Information Technology, 2022, 44 (11): 3748- 3756
doi: 10.11999/JEIT220267
[1] 肖永清,卢榆博,杨星盟,魏建威,苏琳,郝欣健,余官定. 多层边缘计算网络中任务卸载与资源分配联合优化[J]. 浙江大学学报(工学版), 2025, 59(12): 2506-2515.
[2] 李姣军,喻涛,周继华,杨凡,赵涛,吴天舒,马兹林. 动态不确定场景下认知工业物联网的资源分配策略[J]. 浙江大学学报(工学版), 2024, 58(5): 960-966.
[3] 陈俊杰,李洪均,朱晓军. 采用Benders分解的5G核心网用户面动态部署算法[J]. 浙江大学学报(工学版), 2023, 57(3): 625-631.
[4] 陈中,徐晓,王海伟,罗宏浩,陈轩. 基于备用边缘节点的居民区用电任务卸载优化策略[J]. 浙江大学学报(工学版), 2021, 55(5): 917-926.
[5] 王尧尧, 顾临怡, 陈柏, 吴洪涛. 水下机器人-机械手系统非奇异终端滑模控制[J]. 浙江大学学报(工学版), 2018, 52(5): 934-942.
[6] 张超, 王磊, 陈杏藩, 赵辛. 复用双轴光纤陀螺仪[J]. J4, 2013, 47(12): 2184-2187.
[7] 刘志坤, 刘忠, 付学志, 宁小玲. 改进的变步长自适应滤波及Eckart加权抑噪算法[J]. J4, 2012, 46(6): 1014-1020.
[8] 孙坚栋,蒋静坪. 具有时延和丢包的网络控制系统的镇定[J]. J4, 2011, 45(9): 1593-1597.
[9] 杨洪勇, 李晓. 时延多智能体系统的编队控制[J]. J4, 2010, 44(7): 1355-1360.
[10] 徐元欣, 王洋, 朱帅, 等. SAToIP的联合自适应时钟恢复机制及性能分析[J]. J4, 2010, 44(2): 283-288.
[11] 吕冬明 张培勇 严晓浪 郑丹丹 何仙娥. 新型时延可控时钟网络驱动器及其应用[J]. J4, 2008, 42(8): 1350-1354.
[12] 杨克己 田少华. 基于机器微视觉的超声辐射力测量技术[J]. J4, 2008, 42(2): 197-202.
[13] 陈宁宁 朱轶强 蒋静坪. 基于Internet的网络控制系统H∞鲁棒控制[J]. J4, 2007, 41(2): 249-253.
[14] 孙晖 朱善安. 基于时延自相关预处理的Hilbert-Huang变换解调[J]. J4, 2005, 39(12): 1998-2001.