车联网边缘场景下基于免疫算法的计算卸载优化

doi:10.13229/j.cnki.jdxbgxb.20220193

摘要/Abstract

摘要：

为了解决如何在降低车载终端计算时延的同时保证服务器的低能耗和负载均衡问题，本文首先构建了基于车对车通信的系统模型、时延模型、负载均衡模型、能耗模型和目标优化模型；然后提出了一种基于多目标免疫优化算法的计算卸载方案；最后将本文方案与多种卸载方案进行了对比实验。实验结果表明，本文方案能够有效降低用户的平均卸载时延，优化服务器之间的工作负载并有效降低能耗，且性能较各卸载方案有所提升。

关键词: 车联网, 边缘计算, 计算卸载, 车对车通信, 免疫算法

Abstract:

In order to solve the problem of ensuring low energy consumption and load balancing of servers while reducing the computation latency of vehicle terminals，the system model， delay model， load model，energy consumption model and objective optimization model based on vehicle-to-vehicle communication were constructed in this paper. Then， a computational offloading scheme based on multi-objective immune optimization algorithm was proposed. Finally， this scheme was compared with several offloading scheme. Simulation experiments show that the proposed scheme can effectively reduce the average offloading delay of users，optimize the workload between servers，and reduce energy consumption.The performance of the proposed scheme has been improved compared to other schemes.

Key words: internet of vehicles, edge computing, computing offloading, vehicle-to-vehicle communication, immune algorithm

中图分类号:

TP393.1

朱思峰,蔡江昊,柴争义,孙恩林. 车联网边缘场景下基于免疫算法的计算卸载优化[J]. 吉林大学学报(工学版), 2024, 54(1): 221-231.

Si-feng ZHU,Jiang-hao CAI,Zheng-yi CHAI,En-lin SUN. Computing offloading optimization scheme based on immune algorithm in edge computing scenes of internet of vehicles[J]. Journal of Jilin University(Engineering and Technology Edition), 2024, 54(1): 221-231.

图/表 13

图1

图2

图3

图4

表1

图5

图6

图7

图8

图9

图10

图11

图12

参考文献 22

1	Hussain S M, Yusof K M. Dynamic Q-learning and fuzzy CNN based vertical handover decision for integration of DSRC, mmWave 5G and LTE in Internet of vehicles (IoV)[J]. Journal of Communications, 2021, 16(5): 155-166.
2	Huang Meng-xing, Zhai Qian-hao, Chen Yin-jie, et al. Multi-objective whale optimization algorithm for computation offloading optimization in mobile edge computing[J]. Sensors, 2021, 21(8): No.2628.
3	Xu X, Gu R, Dai F, et al. Multi-objective computation offloading for internet of vehicles in cloud-edge computing[J]. Wireless Networks, 2019, 26(3): 1611-1629.
4	Xu X, Zhang X, Gao H, et al. BeCome: blockchain-enabled computation offloading for iot in mobile edge computing[J]. IEEE Transactions on Industrial Informatics, 2020, 16(6): 4187-4195.
5	苏命峰, 王国军, 李仁发. 边云协同计算中基于预测的资源部署与任务调度优化[J]. 计算机研究与发展, 2021, 58(11): 2558-2570.
	Su Ming-feng, Wang Guo-jun, Li Ren-fa. Resource deployment with prediction and task scheduling optimization in edge cloud collaborative computing[J].Journal of Computer Research and Development, 2021, 58(11): 2558-2570.
6	Vimal S, Khari M, Crespo R G, et al. Energy enhancement using multiobjective ant colony optimization with double Q learning algorithm for IoT based cognitive radio networks[J]. Computer Communications, 2020, 154: 481-490.
7	Abbasi M, Mohammadi P E, Khosravi M R. Workload allocation in IoT-fog-cloud architecture using a multi-objective genetic algorithm[J]. Journal of Grid Computing, 2020, 18(1): 43-56.
8	张鹏, 田辉, 赵鹏涛, 等. 多智能体协作场景下基于强化学习值分解的计算卸载策略[J]. 通信学报, 2021, 42(6): 1-15.
	Zhang Peng, Tian Hui, Zhao Peng-tao, et al. Computation offloading strategy in multi-agent cooperation scenario based on reinforcement learning with value-decomposition[J]. Journal on Communications, 2021, 42(6): 1-15.
9	Fan Q, Ansari N. Towards workload balancing in fog computing empowered IoT[J]. IEEE Transactions on Network Science and Engineering, 2020, 7(1): 253-262.
10	侯琬钰, 孙钰, 李大伟, 等. 基于PUF的5G车联网V2V匿名认证与密钥协商协议 [J]. 计算机研究与发展, 2021, 58(10): 2265-2277.
	Hou Wan-yu, Sun Yu, Li Da-wei,et al.Anonymous authentication and key agreement protocol for 5G-V2V based on PUF[J]. Journal of Computer Research and Development, 2021, 58(10): 2265-2277.
11	宋宇波, 金星妤, 燕锋, 等. 车联网中移动边缘计算的安全高效节能卸载策略[J]. 清华大学学报: 自然科学版, 2021, 61(11): 1246-1253.
	Song Yu-bo, Jin Xing-yu, Yan Feng. Secure and energy efficient offloading of mobile edge computing in the Internet of vehicles[J]. Jounal of Tsinghua Univ(Sci & Technol), 2021, 61(11): 1246-1253.
12	Dai P, Liu K, Feng L, et al. Temporal information services in large-scale vehicular networks through evolutionary multi-objective optimization[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(1): 218-231.
13	程久军, 原桂远, 崔杰, 等. 城市场景中车联网时空数据分析及其通达性方法[J]. 通信学报, 2021, 42(6): 52-61.
	Cheng Jiu-jun, Yuan Gui-yuan, Cui Jie, et al.Spatio-temporal data analysis and accessibility method for IoV in an urban scene[J]. Journal on Communications, 2021, 42(6): 52-61.
14	廖勇, 田肖懿, 蔡志镕, 等. 面向C-V2I的基于边缘计算的智能信道估计[J]. 电子学报, 2021, 49(5): 833-842.
	Liao Yong, Tian Xiao-yi, Cai Zhi-rong, et al. Intelligent channel estimation based on edge computing for C-V2I[J]. Journal on Communications, 2021, 49(5): 833-842.
15	Deb K, Pratap A, Agarwal S, et al. A fast and elitist multiobjective genetic algorithm: NSGA-II[J]. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182-197.
16	Deb K, Jain H. An evolutionary many-objective optimization algorithm using reference-point-based nondominated sorting approach, part Ⅰ: solving problems with box constraints[J]. IEEE Transactions on Evolutionary Computation, 2014, 18(4): 577-601.
17	Jain H, Deb K. An evolutionary many-objective optimization algorithm using reference-point based nondominated sorting approach, part Ⅱ: handling constraints and extending to an adaptive approach[J]. IEEE Transactions on Evolutionary Computation, 2014, 18(4): 602-622.
18	Liu Q, Mo R, Xu X, et al. Multi-objective resource allocation in mobile edge computing using PAES for Internet of Things[J]. Wireless Networks, 2020,46(3): 123-135.
19	张文柱, 曹琲琲, 余静华. 移动边缘计算中一种多用户计算卸载方法[J]. 西安电子科技大学学报, 2020, 47(6): 131-138.
	Zhang Wen-zhu, Cao Bei-bei, Yu Jing-hua. Multi-user computation offloading approach for mobile edge computing[J]. Journal of Xidian University, 2020, 47(6): 131-138.
20	Hussain A, Manikanthan S V, Padmapriya T, et al. Genetic algorithm based adaptive offloading for improving IoT device communication efficiency[J]. Wireless Networks, 2019, 26(4): 2329-2338.
21	Das I, Dennis J E. Normal-boundary intersection: a new method for generating the pareto surface in nonlinear multicriteria optimization problems[J]. SIAM Journal on Optimization, 1998, 8(3): 631-657.
22	Maoguo G, Licheng J, Haifeng D, et al. Multiobjective immune algorithm with nondominated neighbor-based selection[J]. IEEE Transactions on Evolutionary Computation, 2008, 16(2): 225-255.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

参数	数值
边缘服务器数量N	20
任务计算资源c_i /MIPS	1~2上均匀分布
任务存储资源z_i /GB	10~20上均匀分布
服务器计算资源C_j /MIPS	100~200上均匀分布
服务器存储资源Z_j /GB	1000~2000上均匀分布
基于V2V技术的数据传输速率θ_V2V/（Gb·s^-1）	1
基于V2E技术的数据传输速率θ_V2E/（Mb·s^-1）	600
边缘服务器基础功率α/W	300
使用状态下的虚拟机功率β/W	50
空闲状态下的虚拟机功率γ/W	30

[1]	常玉林,徐文倩,孙超,张鹏. 车联网环境下考虑遵从程度的混合流量逐日均衡[J]. 吉林大学学报(工学版), 2023, 53(4): 1085-1093.
[2]	朱思峰,赵明阳,柴争义. 边缘计算场景中基于粒子群优化算法的计算卸载[J]. 吉林大学学报(工学版), 2022, 52(11): 2698-2705.
[3]	曾小华,宋美洁,宋大凤,王越. 基于车联网信息的公交客车行驶工况数据处理方法[J]. 吉林大学学报(工学版), 2021, 51(5): 1692-1699.
[4]	谷远利, 张源, 芮小平, 陆文琦, 李萌, 王硕. 基于免疫算法优化LSSVM的短时交通流预测[J]. 吉林大学学报(工学版), 2019, 49(6): 1852-1857.
[5]	莫元富, 于德新, 郭亚娟. 基于灰色关联的车联网信道负载预测算法[J]. 吉林大学学报(工学版), 2016, 46(5): 1453-1457.
[6]	刘桂霞, 王荣兴, 黄岚, 于哲舟, 周春光. 基于改进克隆选择算法的蛋白质关联图预测[J]. 吉林大学学报(工学版), 2009, 39(05): 1303-1308.