Deep Reinforcement Learning based Task Scheduling in Mobile Blockchain for IoT Applications

Yang Gao, Wenjun Wu, Haixiang Nan, Yang Sun, Pengbo Si
{"title":"Deep Reinforcement Learning based Task Scheduling in Mobile Blockchain for IoT Applications","authors":"Yang Gao, Wenjun Wu, Haixiang Nan, Yang Sun, Pengbo Si","doi":"10.1109/ICC40277.2020.9148888","DOIUrl":null,"url":null,"abstract":"Nowadays, the Internet of Things (IoT) has developed rapidly. To deal with the security problems in some of the IoT applications, blockchain has aroused lots of attention in both academia and industry. In this paper, we consider the mobile blockchain supporting IoT applications, and the mobile edge computing (MEC) is deployed at the Small-cell Base Station (SBS) as a supplement to enhance the computation ability of IoT devices. To encourage the participation of the SBS in the mobile blockchain networks, the long-term revenue of the SBS is considered. The task scheduling problem maximizing the long-term mining reward and minimizing the resource cost of the SBS is formulated as a Markov Decision Process (MDP). To achieve an efficient intelligent strategy, the deep reinforcement learning (DRL) based solution named policy gradient based computing tasks scheduling (PG-CTS) algorithm is proposed. The policy mapping from the system state to the task scheduling decision is represented by a deep neural network. The episodic simulations are built and the REINFORCE algorithm with baseline is used to train the policy network. According to the training results, the PG-CTS method is about 10% better than the second-best method greedy. The generalization ability of PG-CTS is proved theoretically, and the testing results also show that the PG-CTS method has better performance over the other three strategies, greedy, first-in-first-out (FIFO) and random in different environments.","PeriodicalId":106560,"journal":{"name":"ICC 2020 - 2020 IEEE International Conference on Communications (ICC)","volume":"27 19 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"14","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"ICC 2020 - 2020 IEEE International Conference on Communications (ICC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICC40277.2020.9148888","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 14

Abstract

Nowadays, the Internet of Things (IoT) has developed rapidly. To deal with the security problems in some of the IoT applications, blockchain has aroused lots of attention in both academia and industry. In this paper, we consider the mobile blockchain supporting IoT applications, and the mobile edge computing (MEC) is deployed at the Small-cell Base Station (SBS) as a supplement to enhance the computation ability of IoT devices. To encourage the participation of the SBS in the mobile blockchain networks, the long-term revenue of the SBS is considered. The task scheduling problem maximizing the long-term mining reward and minimizing the resource cost of the SBS is formulated as a Markov Decision Process (MDP). To achieve an efficient intelligent strategy, the deep reinforcement learning (DRL) based solution named policy gradient based computing tasks scheduling (PG-CTS) algorithm is proposed. The policy mapping from the system state to the task scheduling decision is represented by a deep neural network. The episodic simulations are built and the REINFORCE algorithm with baseline is used to train the policy network. According to the training results, the PG-CTS method is about 10% better than the second-best method greedy. The generalization ability of PG-CTS is proved theoretically, and the testing results also show that the PG-CTS method has better performance over the other three strategies, greedy, first-in-first-out (FIFO) and random in different environments.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于深度强化学习的物联网移动区块链任务调度
如今,物联网(IoT)发展迅速。为了解决一些物联网应用中的安全问题,区块链已经引起了学术界和工业界的广泛关注。本文考虑支持物联网应用的移动区块链,并在小蜂窝基站(SBS)上部署移动边缘计算(MEC)作为补充,增强物联网设备的计算能力。为了鼓励SBS参与移动区块链网络,考虑了SBS的长期收入。将长期挖掘回报最大化和资源成本最小化的任务调度问题表述为马尔可夫决策过程(MDP)。为了实现高效的智能策略,提出了基于深度强化学习(DRL)的策略梯度计算任务调度(PG-CTS)算法。用深度神经网络表示从系统状态到任务调度决策的策略映射。建立情景模拟模型,采用带基线的强化算法对策略网络进行训练。从训练结果来看,PG-CTS方法比第二好的贪心方法要好10%左右。从理论上证明了PG-CTS的泛化能力,测试结果也表明PG-CTS方法在不同环境下比贪心、先进先出和随机三种策略具有更好的性能。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Full Duplex MIMO Digital Beamforming with Reduced Complexity AUXTX Analog Cancellation Cognitive Management and Control of Optical Networks in Dynamic Environments Offloading Media Traffic to Programmable Data Plane Switches Simultaneous Transmitting and Air Computing for High-Speed Point-to-Point Wireless Communication A YouTube Dataset with User-level Usage Data: Baseline Characteristics and Key Insights
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1