面向智慧城市的多依赖任务计算迁移研究

doi:10.3969/j.issn.0255-8297.2023.03.003

应用科学学报 ›› 2023, Vol. 41 ›› Issue (3): 391-404.doi: 10.3969/j.issn.0255-8297.2023.03.003

面向智慧城市的多依赖任务计算迁移研究

彭凯^1,2, 刘培琛^1,2, 许小龙^2,3, 周星宇^1,2

1. 华侨大学工学院, 福建泉州 362021;
2. 南京大学计算机软件新技术国家重点实验室, 江苏南京 210023;
3. 南京信息工程大学计算机与软件学院, 江苏南京 210044

收稿日期:2022-09-29 出版日期:2023-05-30 发布日期:2023-06-16
通信作者: 许小龙,教授,博导,研究方向为边缘计算、云计算、服务计算等。E-mail:xlxu@nuist.edu.cn E-mail:xlxu@nuist.edu.cn
基金资助:
国家自然科学基金(No. 61902133)；泉州市科技计划项目(No. 2020C050R)；中央高校基础研究基金(No. ZQN-817)资助

Computing Offloading of Multi-dependent Tasks in Smart Cities

PENG Kai^1,2, LIU Peichen^1,2, XU Xiaolong^2,3, ZHOU Xingyu^1,2

1. College of Engineering, Huaqiao University, Quanzhou 362021, Fujian, China;
2. State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, Jiangsu, China;
3. School of Computer and Software, Nanjing University of Information Science and Technology, Nanjing 210044, Jiangsu, China

Received:2022-09-29 Online:2023-05-30 Published:2023-06-16

摘要/Abstract

摘要： 针对智慧城市的时延敏感型多依赖任务调度问题，提出了边缘计算赋能的智慧城市架构，并设计了一种计算迁移方法，以满足任务调度需求。首先建立了多依赖任务模型、任务的时延约束模型以及智慧城市服务器的负载约束模型。然后使用深度强化学习算法训练出可感知任务间依赖关系的智能体，以实时地进行计算迁移决策。一系列实验验证了该方法在时延、能耗优化方面的有效性。

关键词: 智慧城市, 计算迁移, 时延敏感型任务, 多依赖任务, 深度强化学习

Abstract: Aiming at the delay-sensitive multi-dependent task scheduling problem of smart cities, this paper proposes a smart city architecture empowered by edge computing and designs a computation offloading method to meet the scheduling requirements of tasks. Firstly, this paper first establishes a multi-dependent task model, as well as a latency constraint for the task and a load balancing constraint model for the smart city server. Secondly, agents that perceive dependencies between tasks are trained using deep reinforcement learning algorithms to make computational transfer decisions in real-time. Finally, a series of experiments are conducted to verify the effectiveness of this method in latency and energy consumption optimization.

Key words: smart cities, computation offloading, latency-sensitive task, multi-dependency task, deep reinforcement learning

中图分类号:

TP399

彭凯, 刘培琛, 许小龙, 周星宇. 面向智慧城市的多依赖任务计算迁移研究[J]. 应用科学学报, 2023, 41(3): 391-404.

PENG Kai, LIU Peichen, XU Xiaolong, ZHOU Xingyu. Computing Offloading of Multi-dependent Tasks in Smart Cities[J]. Journal of Applied Sciences, 2023, 41(3): 391-404.

参考文献

[1] Yin C T, Xiong Z, Chen H, et al. A literature survey on smart cities [J]. Science China Information Sciences, 2015, 58(10): 1-18.
[2] 邹骁锋, 阳王东, 容学成, 等. 面向大数据处理的数据流编程模型和工具综述[J]. 大数据, 2020, 6(3): 59-72 Zou X F, Yang W D, Rong X C, et al. A survey of dataflow programming models and tools for big data processing [J]. Big Data Research, 2020, 6(3): 59-72. (in Chinese)
[3] 李艾青. 面向组件化流程服务的工作流引擎设计与实现[D]. 成都: 电子科技大学, 2022.
[4] Zhang L, Wu J, Mumtaz S, et al. Edge-to-edge cooperative artificial intelligence in smart cities with on-demand learning offloading [C]//2019 IEEE Global Communications Conference (GLOBECOM), Waikoloa, 2019: 1-6.
[5] Mao Y Y, You C S, Zhang J, et al. A survey on mobile edge computing: the communication perspective [J]. IEEE Communications Surveys & Tutorials, 2017, 19(4): 2322-2358.
[6] Lin L, Liao X F, Jin H, et al. Computation offloading toward edge computing [J]. Proceedings of the IEEE, 2019, 107(8): 1584-1607.
[7] Shakarami A, Ghobaei-Arani M, Shahidinejad A. A survey on the computation offloading approaches in mobile edge computing: a machine learning-based perspective [J]. Computer Networks, 2020, 182: 107496.
[8] 陈玉平, 刘波, 林伟伟, 等. 云边协同综述[J]. 计算机科学, 2021, 48(3): 259-268. Chen Y P, Liu B, Lin W W, et al. Survey of cloud-edge collaboration [J]. Scientific Journal of Computer Science, 2021, 48(3): 259-268. (in Chinese)
[9] 许小龙, 方子介, 齐连永, 等. 车联网边缘计算环境下基于深度强化学习的分布式服务卸载方法[J]. 计算机学报, 2021, 44(12): 2382-2405. Xu X L, Fang Z J, Qi L Y, et al. A deep reinforcement learning-based distributed service off loading method for edge computing empowered internet of vehicles [J]. Chinese Journal of Computers, 2021, 44(12): 2382-2405. (in Chinese)
[10] 朱思峰, 蔡江昊, 柴争义, 等. 车联网云边协同计算场景下的多目标优化卸载决策[J]. 通信学报, 2022, 43(6): 223-234. Zhu S F, Cai J H, Chai Z Y, et al. Multi-objective optimal offloading decision for cloud-edge collaborative computing scenario in Internet of vehicles [J]. Journal on Communications, 2022, 43(6): 223-234. (in Chinese)
[11] Tian S J, Chi C, Long S Q, et al. User preference-based hierarchical offloading for collaborative cloud-edge computing [J]. IEEE Transactions on Services Computing, 2021, 16(1): 684-697.
[12] Pan L, Liu X, Jia Z H, et al. A multi-objective clustering evolutionary algorithm for multiworkflow computation offloading in mobile edge computing [J]. IEEE Transactions on Cloud Computing, 2021. DOI: 10.1109/TCC.2021.3132175.
[13] Qu G J, Wu H M, Li R D, et al. DMRO: a deep meta reinforcement learning-based task offloading framework for edge-cloud computing [J]. IEEE Transactions on Network and Service Management, 2021, 18(3): 3448-3459.
[14] 马堉银, 郑万波, 马勇, 等. 一种基于深度强化学习与概率性能感知的边缘计算环境多工作流卸载方法 [J]. 计算机科学, 2021, 48(1): 40-48. Ma Y Y, Zheng W B, Ma Y, et al. Multi-workflow offloading method based on deep reinforcement learning and probabilistic performance-aware in edge computing environment [J]. Computer Science, 2021, 48(1): 40-48. (in Chinese)
[15] Wang Z Y, Schaul T, Hessel M, et al. Dueling network architectures for deep reinforcement learning [C]//International conference on machine learning, New York, 2016: 1995-2003.
[16] Xu X L, Shen B W, Ding S, et al. Service offloading with deep Q-network for digital twinningempowered Internet of vehicles in edge computing [J]. IEEE Transactions on Industrial Informatics, 2020, 18(2): 1414-1423.

面向智慧城市的多依赖任务计算迁移研究

Computing Offloading of Multi-dependent Tasks in Smart Cities

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

编辑推荐

Metrics

本文评价

[1]	莫瑞超, 许小龙, 何强, 刘琦, 赵庆展. 面向车联网边缘计算的智能计算迁移研究[J]. 应用科学学报, 2020, 38(5): 779-791.
[2]	张金, 冯帆, 孙承君, 宫晓利. 一种基于计算迁移的智能终端商标识别方法[J]. 应用科学学报, 2018, 36(4): 667-678.