基于多智能体深度强化学习的工业无线网络端边协同资源分配

刘晓宇; 许驰; 于海斌; 曾鹏

doi:10.1631/FITEE.2100331

Your Location：

Home >

Browse articles >

基于多智能体深度强化学习的工业无线网络端边协同资源分配

智简无线网络理论与技术专题 | Updated：2022-04-19

- 基于多智能体深度强化学习的工业无线网络端边协同资源分配
  Enhanced Publication
- Multi-agent deep reinforcement learning for end–edge orchestrated resource allocation in industrial wireless networks
- 信息与电子工程前沿（英文） 2022年23卷第1期页码：47-60
- Affiliations：
  
  1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang110016, China
  2.Key Laboratory of Networked Control Systems, Chinese Academy of Sciences, Shenyang110016, China
  3.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang110169, China
  4.University of Chinese Academy of Sciences, Beijing100049, China
- Author bio：
  
  E-mail: liuxiaoyu1@sia.cn;
  ‡Corresponding authors
  E-mail: zp@sia.cn
- Funds：
  
  National Key R&D Program of China(2020YFB1710900);National Natural Science Foundation of China(62173322;61803368;U1908212);China Postdoctoral Science Foundation(2019M661156);Youth Innovation Promotion Association, Chinese Academy of Sciences(2019202)
- DOI：10.1631/FITEE.2100331
  中图分类号： TN929.5;TP18
- 纸质出版日期：2022-01-0 ，
  
  收稿日期：2021-07-05，
  
  录用日期：2021-11-15
- Accepted：
Scan QR Code
刘晓宇, 许驰, 于海斌, 等. 基于多智能体深度强化学习的工业无线网络端边协同资源分配[J]. 信息与电子工程前沿（英文）, 2022,23(1):47-60.

XIAOYU LIU, CHI XU, HAIBIN YU, et al. Multi-agent deep reinforcement learning for end–edge orchestrated resource allocation in industrial wireless networks. [J]. Frontiers of information technology & electronic engineering, 2022, 23(1): 47-60.
刘晓宇, 许驰, 于海斌, 等. 基于多智能体深度强化学习的工业无线网络端边协同资源分配[J]. 信息与电子工程前沿（英文）, 2022,23(1):47-60. DOI： 10.1631/FITEE.2100331.

XIAOYU LIU, CHI XU, HAIBIN YU, et al. Multi-agent deep reinforcement learning for end–edge orchestrated resource allocation in industrial wireless networks. [J]. Frontiers of information technology & electronic engineering, 2022, 23(1): 47-60. DOI： 10.1631/FITEE.2100331.

摘要

边缘人工智能通过协同利用设备侧和边缘侧有限的网络、计算资源，赋能工业无线网络以支持复杂和动态工业任务。面向资源受限的工业无线网络，我们提出一种基于多智能体深度强化学习的资源分配（MADRL-RA）算法，实现了端边协同资源分配，支持计算密集型、时延敏感型工业应用。首先，建立了端边协同的工业无线网络系统模型，将具有感知能力的工业设备作为自学习的智能代理。然后，采用马尔可夫决策过程对端边资源分配问题进行形式化描述，建立关于时延和能耗联合优化的最小系统开销问题。接着，利用多智能体深度强化学习克服状态空间维灾，同时学习关于计算决策、算力分配和传输功率的有效资源分配策略。为了打破训练数据的时间相关性，同时加速MADRL-RA学习过程，设计了一种带经验权重的经验回放方法，对经验进行分类存储和采样。在此基础上，提出步进的

-贪婪方法来平衡智能代理对经验的利用与探索。最后，通过大量对比实验，验证了MADRL-RA算法相较于多种基线算法的有效性。实验结果表明，MADRL-RA收敛速度快，能够学习到有效资源分配策略以实现最小系统开销。

Abstract

Edge artificial intelligence will empower the ever simple industrial wireless networks (IWNs) supporting complex and dynamic tasks by collaboratively exploiting the computation and communication resources of both machine-type devices (MTDs) and edge servers. In this paper

we propose a multi-agent deep reinforcement learning based resource allocation (MADRL-RA) algorithm for end–edge orchestrated IWNs to support computation-intensive and delay-sensitive applications. First

we present the system model of IWNs

wherein each MTD is regarded as a self-learning agent. Then

we apply the Markov decision process to formulate a minimum system overhead problem with joint optimization of delay and energy consumption. Next

we employ MADRL to defeat the explosive state space and learn an effective resource allocation policy with respect to computing decision

computation capacity

and transmission power. To break the time correlation of training data while accelerating the learning process of MADRL-RA

we design a weighted experience replay to store and sample experiences categorically. Furthermore

we propose a step-by-step

-greedy method to balance exploitation and exploration. Finally

we verify the effectiveness of MADRL-RA by comparing it with some benchmark algorithms in many experiments

showing that MADRL-RA converges quickly and learns an effective resource allocation policy achieving the minimum system overhead.

关键词

多智能体深度强化学习端边协同工业无线网络时延能耗

Keywords

Multi-agent deep reinforcement learningEnd–edge orchestratedIndustrial wireless networksDelayEnergy consumption

references

Alfakih T,Hassan MM,Gumaei A,et al.,2020.Task offloading and resource allocation for mobile edge computing by deep reinforcement learning based on SARSA.IEEE Access,8:54074-54084.doi:10.1109/access.2020.2981434http://doi.org/10.1109/access.2020.2981434

Cao ZL,Zhou P,Li RX,et al.,2020.Multiagent deep reinforcement learning for joint multichannel access and task offloading of mobile-edge computing in Industry 4.0.IEEE Int Things J,7(7):6201-6213.doi:10.1109/jiot.2020.2968951http://doi.org/10.1109/jiot.2020.2968951

Chen Y,Liu ZY,Zhang YC,et al.,2021.Deep reinforcement learning-based dynamic resource management for mobile edge computing in industrial Internet of Things.IEEE Trans Ind Inform,17(7):4925-4934.doi:10.1109/tii.2020.3028963http://doi.org/10.1109/tii.2020.3028963

Chu TS,Wang J,Codecà L,et al.,2020.Multi-agent deep reinforcement learning for large-scale traffic signal control.IEEE Trans Intell Transp Syst,21(3):1086-1095.doi:10.1109/tits.2019.2901791http://doi.org/10.1109/tits.2019.2901791

Dai YY,Zhang K,Maharjan S,et al.,2020.Edge intelligence for energy-efficient computation offloading and resource allocation in 5G beyond.IEEE Trans Veh Technol,69(10):12175-12186.doi:10.1109/tvt.2020.3013990http://doi.org/10.1109/tvt.2020.3013990

Feng J,Pei QQ,Yu FR,et al.,2019.Computation offloading and resource allocation for wireless powered mobile edge computing with latency constraint.IEEE Wirel Commun Lett,8(5):1320-1323.doi:10.1109/lwc.2019.2915618http://doi.org/10.1109/lwc.2019.2915618

Foerster JN,Assael YM,de Freitas N,et al.,2016.Learning to communicate with deep multi-agent reinforcement learning.Proc Advances in Neural Information Processing Systems 29, p.2137-2145.

Guo JF,Song ZZ,Cui Y,et al.,2017.Energy-efficient resource allocation for multi-user mobile edge computing.Proc IEEE Global Communications Conf, p.1-7.

He XM,Lu HD,Du M,et al.,2021.QoE-based task offloading with deep reinforcement learning in edge-enabled Internet of Vehicles.IEEE Trans Intell Transp Syst,22(4):2252-2261.doi:10.1109/tits.2020.3016002http://doi.org/10.1109/tits.2020.3016002

Kumar M,Sharma SC,Goel A,et al.,2019.A comprehensive survey for scheduling techniques in cloud computing.J Netw Comput Appl,143:1-33.

Li HL,Xu HT,Zhou CC,et al.,2020.Joint optimization strategy of computation offloading and resource allocation in multi-access edge computing environment.IEEE Trans Veh Technol,69(9):10214-10226.doi:10.1109/tvt.2020.3003898http://doi.org/10.1109/tvt.2020.3003898

Lin CC,Deng DJ,Chih YL,et al.,2019.Smart manufacturing scheduling with edge computing using multiclass deepQ network.IEEE Trans Ind Inform,15(7):4276-4284.doi:10.1109/tii.2019.2908210http://doi.org/10.1109/tii.2019.2908210

Liu KH,Liao WJ,2020.Intelligent offloading for multi-access edge computing: a new actor-critic approach.Proc IEEE Int Conf on Communications, p.1-6.

Liu XY,Xu C,Yu HB,et al.,2021.Deep reinforcement learning-based multi-channel access for industrial wireless networks with dynamic multi-user priority.IEEE Trans Ind Inform,early access.doi:10.1109/TII.2021.3139349http://doi.org/10.1109/TII.2021.3139349

Lowe R,Wu Y,Tamar A,et al.,2017.Multi-agent actor-critic for mixed cooperative-competitive environments.Proc Advances in Neural Information Processing Systems 30, p.6379-6390.

Lu HD,He XM,Du M,et al.,2020.Edge QoE: computation offloading with deep reinforcement learning for Internet of Things.IEEE Int Things J,7(10):9255-9265.doi:10.1109/jiot.2020.2981557http://doi.org/10.1109/jiot.2020.2981557

Naparstek O,Cohen K,2019.Deep multi-user reinforcement learning for distributed dynamic spectrum access.IEEE Trans Wirel Commun,18(1):310-323.doi:10.1109/TWC.2018.2879433http://doi.org/10.1109/TWC.2018.2879433

Porambage P,Okwuibe J,Liyanage M,et al.,2018.Survey on multi-access edge computing for Internet of Things realization.IEEE Commun Surv Tut,20(4):2961-2991.doi:10.1109/comst.2018.2849509http://doi.org/10.1109/comst.2018.2849509

Rashid T,Samvelyan M,de Witt CS,et al.,2018.QMIX: monotonic value function factorisation for deep multi-agent reinforcement learning.Proc 35th Int Conf on Machine Learning, p.4292-4301.

Ren YJ,Sun YH,Peng MG,2021.Deep reinforcement learning based computation offloading in fog enabled industrial Internet of Things.IEEE Trans Ind Inform,17:4978-4987.doi:10.1109/tii.2020.3021024http://doi.org/10.1109/tii.2020.3021024

Schaul T,Quan J,Antonoglou I,et al.,2016.Prioritized experience replay.Proc 4th Int Conf on Learning Representations.

Shakarami A,Ghobaei-Arani M,Shahidinejad A,2020.A survey on the computation offloading approaches in mobile edge computing: a machine learning-based perspective.Comput Netw,182:107496.doi:10.1016/j.comnet.2020.107496http://doi.org/10.1016/j.comnet.2020.107496

Tang L,He SB,2018.Multi-user computation offloading in mobile edge computing: a behavioral perspective.IEEE Netw,32(1):48-53.doi:10.1109/mnet.2018.1700119http://doi.org/10.1109/mnet.2018.1700119

Wang HN,Liu N,Zhang YY,et al.,2020.Deep reinforcement learning: a survey.Front Inform Technol Electron Eng,21:1726-1744.doi:10.1631/FITEE.1900533http://doi.org/10.1631/FITEE.1900533

Wei YF,Yu FR,Song M,et al.,2019.Joint optimization of caching, computing, and radio resources for fog-enabled IoT using natural actor–critic deep reinforcement learning.IEEE Int Things J,6(2):2061-2073.doi:10.1109/jiot.2018.2878435http://doi.org/10.1109/jiot.2018.2878435

Xiong X,Zheng K,Lei L,et al.,2020.Resource allocation based on deep reinforcement learning in IoT edge computing.IEEE J Sel Area Commun,38(6):1133-1146.doi:10.1109/jsac.2020.2986615http://doi.org/10.1109/jsac.2020.2986615

Xu C,Zeng P,Yu HB,et al.,2021.WIA-NR: ultra-reliable low-latency communication for industrial wireless control networks over unlicensed bands.IEEE Netw,35(1):258-265.doi:10.1109/mnet.011.2000308http://doi.org/10.1109/mnet.011.2000308

Yao XF,Zhou JJ,Lin YZ,et al.,2019.Smart manufacturing based on cyber-physical systems and beyond.J Intell Manuf,30(8):2805-2817.doi:10.1007/s10845-017-1384-5http://doi.org/10.1007/s10845-017-1384-5

Yu HB,Zeng P,Xu C,2021.Industrial wireless control networks: from WIA to the future.Engineering,early access.doi:10.1016/j.eng.2021.06.024http://doi.org/10.1016/j.eng.2021.06.024

Zhang GL,Zhang WQ,Cao Y,et al.,2018.Energy-delay tradeoff for dynamic offloading in mobile-edge computing system with energy harvesting devices.IEEE Trans Ind Inform,14(10):4642-4655.doi:10.1109/tii.2018.2843365http://doi.org/10.1109/tii.2018.2843365

Zhang KQ,Yang ZR,Basar T,2021.Decentralized multi-agent reinforcement learning with networked agents: recent advances.Front Inform Technol Electron Eng,22:802-814.doi:10.1631/FITEE.1900661http://doi.org/10.1631/FITEE.1900661

Zhang P,Peng MG,Cui SG,et al.,2022.Theory and techniques for "intellicise" wireless networks.Front Inform Technol Electron Eng,23(1):1-4.doi:10.1631/FITEE.2210000http://doi.org/10.1631/FITEE.2210000

Zhang YM,Lan XL,Ren J,et al.,2020.Efficient computing resource sharing for mobile edge-cloud computing networks.IEEE/ACM Trans Netw,28(3):1227-1240.doi:10.1109/tnet.2020.2979807http://doi.org/10.1109/tnet.2020.2979807

Zhu XY,Luo YY,Liu AF,et al.,2021.Multiagent deep reinforcement learning for vehicular computation offloading in IoT.IEEE Int Things J,8(12):9763-9773.doi:10.1109/jiot.2020.3040768http://doi.org/10.1109/jiot.2020.3040768

浏览量

231

Downloads

CSCD

文章被引用时，请邮件提醒。

Submit

工具集

关联资源

Multi-agent evaluation for energy management by practically scaling α-rank

A slotted floor acquisition multiple access based Mac protocol for underwater acoustic networks with Rts competition*