基于负载预测的多目标优化任务卸载策略

doi:10.19678/j.issn.1000-3428.0066766

摘要/Abstract

摘要：

在车联网中随着智能网联汽车的升级，新兴车载应用对计算能力提出更高要求，车载单元本身的计算能力已远远不够，移动边缘计算(MEC)的出现可以为车辆提供更加可靠的服务。为解决车联网边缘计算中的任务卸载问题，提出基于负载预测的多目标优化卸载策略算法，降低任务时延并实现边缘服务器负载均衡。通过基于自适应优化神经网络的负载预测算法预测MEC服务器的负载，提前感知MEC服务器的负载变化，解决任务卸载滞后问题。以最小化时延及MEC服务器负载均衡为目标，综合考虑通信环境、计算资源、任务量等因素构建多目标优化模型。通过非支配排序遗传算法-Ⅲ（NSGA-Ⅲ）获得最优任务卸载策略。仿真实验结果表明，该算法能对MEC服务器的负载进行较精确的预测。相比MTUOA、NSGA2、QTD和AOS，该算法的任务时延分别降低1.7%、7.3%、12.4%、17.5%，并在MEC服务器负载均衡中取得显著优势，解决MEC服务器负载不均衡的问题。此外，该算法可以根据不同通信小区的通信环境及车辆数等制定差异化的任务卸载方案。

关键词: 车联网, 移动边缘计算, 任务卸载, 负载预测, 负载均衡, 时延

Abstract:

With the upgrading of intelligent connected vehicles in the Internet of Vehicles(IoV), new on-board applications introduce higher requirements for computing power.The computing power of on-board units is far from sufficient. The emergence of Mobile Edge Computing(MEC) can provide more reliable services for vehicles. Aiming at the task offloading problem in edge computing for the IoV, a multi-objective optimization offloading strategy algorithm based on load prediction is proposed to reduce the task delay and realize load balance among edge servers. By using a load prediction algorithm based on adaptive optimization neural networks to predict the load of MEC servers, the load changes of MEC servers are sensed in advance, solving the problem of task offloading lag. A multi-objective optimization model is constructed with the goal of minimizing latency and balancing MEC server load, considering factors such as communication environment, computing resources, and task volume. The optimal task offloading strategy is obtained through the Non-dominated Sorting Genetic Algorithm(NSGA)-Ⅲ (NSGA-Ⅲ). The simulation results show that this algorithm can accurately predict the load of MEC servers. Compared with the MTUOA, NSGA2, QTD, and AOS algorithms, NSGA-Ⅲ reduced task latency by 1.7%, 7.3%, 12.4%, and 17.5%, respectively, and achieved significant advantages in MEC server load balancing, solving the problem of MEC server load imbalance. In addition, the proposed algorithm can develop differentiated task offloading plans based on factors such as the communication environment and number of vehicles in different communication cells.

Key words: Internet of Vehicles(IoV), Mobile Edge Computing(MEC), task offloading, load prediction, load balancing, time delay

彭世明, 林士飏, 贾硕, 杨苗会. 基于负载预测的多目标优化任务卸载策略[J]. 计算机工程, 2024, 50(1): 206-215.

Shiming PENG, Shiyang LIN, Shuo JIA, Miaohui YANG. Multi-Objective Optimization Task Offloading Strategy Based on Load Prediction[J]. Computer Engineering, 2024, 50(1): 206-215.

https://www.ecice06.com/CN/Y2024/V50/I1/206

图/表 10

图1 MEC网络系统架构

Fig.1 Architecture of MEC network system

图2 任务卸载策略编码实例

Fig.2 Coding example of task offloading strategy

图3 迭代次数与RMSE最优值的关系

Fig.3 The relationship between the number of iterations and the optimal value of RMSE

图4 迭代次数与RMSE均值的关系

Fig.4 The relationship between the number of iterations and the RMSE mean

图5 任务数与平均时延的关系

Fig.5 The relationship between the number of tasks and the average time delay

图6 任务数与负载均衡标准差关系

Fig.6 The relationship between the number of tasks and the standard deviation of load balancing

图7 任务数与不同通信小区卸载率关系

Fig.7 The relationship between the number of tasks and the offloading rate among different communication cells

图8 任务数与不同通信小区传输时延关系

Fig.8 The relationship between the number of tasks and the transmission time delay among different communication cells

参考文献 29

1	VEGNI A M, LOSCRI V. A survey on vehicular social networks. Communications Surveys & Tutorials, 2015, 17(4): 2397- 2419.
2	ZHAI Y L, SUN W X, WU J Q, et al. An energy aware offloading scheme for interdependent applications in software-defined IoV with fog computing architecture. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(6): 3813- 3823. doi: 10.1109/TITS.2020.3044177
3	MU S D, XIONG Z X, TIAN Y X. Intelligent traffic control system based on cloud computing and big data mining. IEEE Transactions on Industrial Informatics, 2019, 15(12): 6583- 6592. doi: 10.1109/TII.2019.2929060
4	GAO Q, LIN S Y, ZHU G. Joint vehicular and static users multiplexing transmission with hierarchical modulation for throughput maximization in vehicular networks. IEEE Transactions on Intelligent Transportation Systems, 2020, 21(9): 3835- 3847. doi: 10.1109/TITS.2019.2934597
5	LUONG H P, PANDA M, VU H L, et al. Beacon rate optimization for vehicular safety applications in highway scenarios. IEEE Transactions on Vehicular Technology, 2018, 67(1): 524- 536. doi: 10.1109/TVT.2017.2739830
6	GUO H Z, ZHANG J, LIU J J. FiWi-enhanced vehicular edge computing networks: collaborative task offloading. IEEE Vehicular Technology Magazine, 2019, 14(1): 45- 53. doi: 10.1109/MVT.2018.2879537
7	谢人超, 廉晓飞, 贾庆民, 等. 移动边缘计算卸载技术综述. 通信学报, 2018, 39(11): 138- 155.
	XIE R C, LIAN X F, JIA Q M, et al. Survey on computation offloading in mobile edge computing. Journal on Communications, 2018, 39(11): 138- 155.
8	杨天, 杨军. 移动边缘计算中的卸载决策与资源分配策略. 计算机工程, 2021, 47(2): 19- 25. doi: 10.19678/j.issn.1000-3428.0058085
	YANG T, YANG J. Offloading decision and resource allocation strategy in mobile edge computing. Computer Engineering, 2021, 47(2): 19- 25. doi: 10.19678/j.issn.1000-3428.0058085
9	LIU J, MAO Y Y, ZHANG J, et al. Delay-optimal computation task scheduling for mobile-edge computing systems[C]//Proceedings of International Symposium on Information Theory. Washington D. C., USA: IEEE Press, 2016: 1451-1455.
10	SONG Y Z, YAU S S, YU R Z, et al. An approach to QoS-based task distribution in edge computing networks for IoT applications[C]//Proceedings of International Conference on Edge Computing. Washington D. C., USA: IEEE Press, 2017: 32-39.
11	REN J K, YU G D, CAI Y L, et al. Latency optimization for resource allocation in mobile-edge computation offloading. IEEE Transactions on Wireless Communications, 2018, 17(8): 5506- 5519. doi: 10.1109/TWC.2018.2845360
12	ZHANG K, MAO Y M, LENG S P, et al. Optimal delay constrained offloading for vehicular edge computing networks[C]//Proceedings of International Conference on Communications. Washington D. C., USA: IEEE Press, 2017: 1-6.
13	SALEEM U, LIU Y, JANGSHER S, et al. Latency minimization for D2D-enabled partial computation offloading in mobile edge computing. IEEE Transactions on Vehicular Technology, 2020, 69(4): 4472- 4486. doi: 10.1109/TVT.2020.2978027
14	XU X L, GU R H, DAI F, et al. Multi-objective computation offloading for Internet of Vehicles in cloud-edge computing. Wireless Networks, 2020, 26(3): 1611- 1629. doi: 10.1007/s11276-019-02127-y
15	ZHANG J, GUO H Z, LIU J J, et al. Task offloading in vehicular edge computing networks: a load-balancing solution. IEEE Transactions on Vehicular Technology, 2020, 69(2): 2092- 2104. doi: 10.1109/TVT.2019.2959410
16	YAO D H, GUI L, HOU F, et al. Load balancing oriented computation offloading in mobile cloudlet[C]//Proceedings of the 86th Vehicular Technology Conference. Washington D. C., USA: IEEE Press, 2018: 1-6.
17	DAI Y Y, XU D, MAHARJAN S, et al. Joint load balancing and offloading in vehicular edge computing and networks. IEEE Internet of Things Journal, 2019, 6(3): 4377- 4387. doi: 10.1109/JIOT.2018.2876298
18	LUO G Y, YUAN Q, ZHOU H B, et al. Cooperative vehicular content distribution in edge computing assisted 5G-VANET. China Communications, 2018, 15(7): 1- 17. doi: 10.1109/CC.2018.8424578
19	林峰, 段建岚, 李传伟, 等. C-V2X边缘服务器的动态负载均衡算法研究. 计算机工程, 2020, 46(12): 201-206, 221. doi: 10.19678/j.issn.1000-3428.0056602
	LIN F, DUAN J L, LI C W, et al. Research on dynamic load balancing algorithm for C-V2X edge server. Computer Engineering, 2020, 46(12): 201-206, 221. doi: 10.19678/j.issn.1000-3428.0056602
20	余翔, 刘一勋, 石雪琴, 等. 车联网场景下的移动边缘计算卸载策略. 计算机工程, 2020, 46(11): 29-34, 41. doi: 10.19678/j.issn.1000-3428.0056850
	YU X, LIU Y X, SHI X Q, et al. Mobile edge computing offloading strategy under Internet of vehicles scenario. Computer Engineering, 2020, 46(11): 29-34, 41. doi: 10.19678/j.issn.1000-3428.0056850
21	WANG Y T, SHENG M, WANG X J, et al. Mobile-edge computing: partial computation offloading using dynamic voltage scaling. IEEE Transactions on Communications, 2016, 64(10): 4268- 4282.
22	LIANG L P, CHENG W C, ZHANG W, et al. Orthogonal frequency and mode division multiplexing for wireless communications[C]//Proceedings of Global Communications Conference. Washington D. C., USA: IEEE Press, 2019: 1-7.
23	赵海涛, 朱银阳, 丁仪, 等. 车联网中基于移动边缘计算的内容感知分类卸载算法研究. 电子与信息学报, 2020, 42(1): 20- 27.
	ZHAO H T, ZHU Y Y, DING Y, et al. Research on content-aware classification offloading algorithm based on mobile edge calculation in the Internet of vehicles. Journal of Electronics & Information Technology, 2020, 42(1): 20- 27.
24	WU Q, XU X L, ZHAO Q Z, et al. Tasks offloading for connected autonomous vehicles in edge computing. Mobile Networks and Applications, 2022, 27(6): 2295- 2304. doi: 10.1007/s11036-021-01794-6
25	邹卯荣, 傅明, 熊兵. 基于时延与负载的SDN控制器部署模型. 计算机工程, 2019, 45(4): 30- 35. doi: 10.19678/j.issn.1000-3428.0049764
	ZOU M R, FU M, XIONG B. Deployment model of SDN controllers based on time delay and load. Computer Engineering, 2019, 45(4): 30- 35. doi: 10.19678/j.issn.1000-3428.0049764
26	SHAH D, CAMPBELL W, ZULKERNINE F H. A comparative study of LSTM and DNN for stock market forecasting[C]//Proceedings of International Conference on Big Data. Washington D. C., USA: IEEE Press, 2019: 4148-4155.
27	GERS F A. Learning to forget: continual prediction with LSTM[C]//Proceedings of the 9th International Conference on Artificial Neural Networks. Washington D. C., USA: IEEE Press, 1999: 850-855.
28	DEB K, JAIN H. An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part Ⅰ: solving problems with box constraints. IEEE Transactions on Evolutionary Computation, 2014, 18(4): 577- 601. doi: 10.1109/TEVC.2013.2281535
29	刘建华, 罗荣鑫, 刘佳嘉, 等. 基于NSGA2的车联网边缘计算任务卸载方案[J/OL]. 西安理工大学学报: 1-11[2023-03-04]. http://kns.cnki.net/kcms/detail/61.1294.n.20230130.1410.002.html.
	LIU J H, LUO R X, LIU J J, et al. Task offloading scheme of Internet of Vehicles edge computing based on NSGA2 [J/OL]. Journal of Xi'an University of Technology: 1-11[2023-03-04]. http://kns.cnki.net/kcms/detail/61.1294.n.20230130.1410.002.html. (in Chinese)

[1]	张俊娜, 李天泽, 赵晓焱, 袁培燕. 一种基于DQN的去中心化优先级卸载策略[J]. 计算机工程, 2024, 50(9): 235-245.
[2]	石琼, 段辉, 师智斌. 基于深度强化学习的可信任务卸载方案[J]. 计算机工程, 2024, 50(8): 142-152.
[3]	张冀, 龚雯雯, 朵春红, 齐国梁. 面向多智能体与双层卸载的车联网卸载算法[J]. 计算机工程, 2024, 50(8): 182-197.
[4]	陈姣, 沈艳. 面向缓存机制的移动边缘计算任务卸载研究[J]. 计算机工程, 2024, 50(7): 194-203.
[5]	杨小东, 李沐紫, 马国祖, 李松谕, 王彩芬. 车联网中支持非法签名定位的无证书匿名认证方案[J]. 计算机工程, 2024, 50(6): 157-165.
[6]	李浩阳, 贺小伟, 王宾, 吴昊, 尤琪. 基于改进Informer的云计算资源负载预测[J]. 计算机工程, 2024, 50(2): 43-50.
[7]	曾耀平, 夏玉婷, 江伟伟, 刘月强. 加权能耗最小化的无人机辅助移动边缘计算策略研究[J]. 计算机工程, 2024, 50(2): 288-297.
[8]	邢丹丹, 曹素珍, 赵晓, 周大伟, 王正. 车联网环境下多接收者匿名签密方案[J]. 计算机工程, 2024, 50(10): 205-215.
[9]	杨建军, 唐东明, 李驹光, 肖宇峰. 基于改进人工蜂鸟算法的MEC任务卸载策略[J]. 计算机工程, 2024, 50(10): 291-301.
[10]	万昊楠, 吴飞, 尹玲. 基于自适应无人机数量的节时部署优化算法[J]. 计算机工程, 2024, 50(10): 302-312.
[11]	杨志军, 黄文洁, 丁洪伟. 连续时间完全-限定(K=2)两级轮询系统性能分析[J]. 计算机工程, 2024, 50(1): 191-197.
[12]	刘向举, 赵犇, 方贤进, 徐杨洋. SDN中基于过程优化的动态负载均衡策略[J]. 计算机工程, 2023, 49(8): 137-145.
[13]	班玉琦, 段利国, 温昊宇, 李爱萍, 赵菊敏. 面向移动感知的计算卸载及资源分配策略研究[J]. 计算机工程, 2023, 49(8): 163-173.
[14]	蔡星娟, 郭彦亨, 赵天浩, 张文生. 基于进化多任务的边缘计算服务部署和任务卸载[J]. 计算机工程, 2023, 49(7): 1-9.
[15]	梅晶, 戴龙宝, 童钊, 邓昕, 王嘉珂. 资源约束下基于Lyapunov优化的自适应卸载算法[J]. 计算机工程, 2023, 49(7): 34-46.

选择文件类型/文献管理软件名称

选择包含的内容