计算机科学 ›› 2025, Vol. 52 ›› Issue (3): 359-365.doi: 10.11896/jsjkx.240700140

• 计算机网络 • 上一篇    下一篇

自学习星型链空间自适应分配方法

杜立宽, 刘晨, 王俊陆, 宋宝燕   

  1. 辽宁大学信息学院 沈阳 110031
  • 收稿日期:2024-07-22 修回日期:2024-09-30 出版日期:2025-03-15 发布日期:2025-03-07
  • 通讯作者: 宋宝燕(bysong@lnu.edu.cn)
  • 作者简介:(dulikuan2022@outlook.com)
  • 基金资助:
    国家重点研发计划(2021YFF0901004);辽宁省教育厅高校基本科研项目(理工类)面上项目(揭榜挂帅服务地方项目)(JYTMS20230761);辽宁大学青年科研基金项目(LDYBJB2301);辽宁省应用基础研究计划(2022JH2/101300250)

Self-learning Star Chain Space Adaptive Allocation Method

DU Likuan, LIU Chen, WANG Junlu, SONG Baoyan   

  1. School of Information,Liaoning University,Shenyang 110031,China
  • Received:2024-07-22 Revised:2024-09-30 Online:2025-03-15 Published:2025-03-07
  • About author:DU Likuan,born in 1999,postgraduate.His main research interests include blockchain and reinforcement learning.
    SONG Baoyan,born in 1965,Ph.D,professor,Ph.D supervisor,is a member of CCF(No.08767S).Her main research interests include large-scale graph processing technology,big data processing technology and stream data processing technology.
  • Supported by:
    National Key Research and Development Program of China(2021YFF0901004),General Project(Service Local Project of Unveiling and Recruiting Talents) of Basic Scientific Research Project of Colleges and Universities of Liaoning Provincial Department of Education(Science and Engineering)(JYTMS20230761),Liaoning University Youth Scientific Research Fund Project(LDYBJB2301) and Liao-ning Provincial Applied Basic Research Program(2022JH2/101300250).

摘要: 区块链分片技术是提高区块链系统吞吐量的有效方法。现有的区块链分片方法大多采用静态平行架构分片方案,未解决跨分片交易比例高的问题,导致吞吐量降低以及潜在的无限交易确认延迟。针对这些问题,提出一种基于自学习的星型链空间自适应分配架构。首先,针对区块链分片系统中跨分片交易比例高的问题,提出一种信标链-分片链架构吞吐量模型;其次,综合分片区块链的吞吐量和时延的关系,在星型链空间的动态决策过程中设计星型链空间奖励函数;最后,提出一种分布式多智能体强化学习动态聚类方法,将每个分片作为智能体共同学习合作策略。实验结果表明,所提方法在吞吐量、跨分片交易比率和交易确认延迟等方面,相比现有方法分别约提升31.74%,35.96%和37.13%。

关键词: 区块链, 分片, 深度强化学习, 跨分片交易

Abstract: Blockchain sharding technology is an effective method to improve the throughput of blockchain systems.Existing blockchain sharding methods mostly adopt parallel architecture sharding schemes,which have not solved the problem of high cross-shard transaction ratios,leading to reduced throughput and potential infinite transaction confirmation delays.To address these issues,a self-learning-based star chain space adaptive allocation structure is proposed.Firstly,to address the issue of high cross-shard transaction ratios in blockchain sharding systems,a beacon chain-shard chain architecture throughput model is proposed.Secondly,considering the relationship between the throughput and latency of sharded blockchain,a star chain space dyna-mic decision-making process is designed,with a reward function for star chain space.Finally,a distributed multi-agent reinforcement learning dynamic clustering method is proposed,treating each shard as an agent to collectively learn cooperative strategies.Experimental results show that the proposed method improves throughput,cross-shard transaction ratio,and transaction confirmation delay by approximately 31.74%,35.96%,and 37.13% respectively,compared with existing methods.

Key words: Blockchain, Sharding, Deep reinforcement learning, Cross-shard transaction

中图分类号: 

  • TP314
[1]LI X,DONG X,XU X,et al.A Blockchain-Based Scheme for Efficient Medical Data Sharing with Attribute-Based Hierarchical Encryption[C]//WISA.Cham:Springer International Publi-shing,2022:661-673.
[2]WEI W,ZHOU Y,LI D,et al.BEAIV:Blockchain Empowered Accountable Integrity Verification Scheme for Cross-Chain Data[C]//Web Information Systems and Applications.Singapore:Springer Nature Singapore,2023:488-500.
[3]LI X H,LI C,ZHANG G G,et al.A Survey on the Integration of Blockchain and Database Technology [J].Computer Science and Exploration,2023,17(4):761-770.
[4]WU Y,WANG Z,MA Y,et al.Deep reinforcement learning for blockchain in industrial IoT:A survey[J].Computer Networks,2021,191:108004.
[5]HUANG H W,KONG W,PENG X W,et al.Survey on block-chain sharding technology [J].Computer Engineering,2022,48(6):1-10.
[6]LIU X,XIE H,YAN Z,et al.A survey on blockchain sharding[J].ISA Transactions,2023,141:30-43.
[7]WANG J,MA J W,LUO J X.A Blockchain Sharding Schemefor Edge Computing [J].Journal of Internet of Things,2023(7):88-100.
[8]JIA L,LIU Y,WANG K,et al.Estuary:A Low Cross-Shard Blockchain Sharding Protocol Based on State Splitting[J].IEEE Transactions on Parallel and Distributed Systems,2024,35(3):405-420.
[9]ZHANG J,CHEN W,HONG Z,et al.Efficient Execution of Arbitrarily Complex Cross-Shard Contracts for Blockchain Sharding[J].IEEE Transactions on Computers,2024,73(5):1190-1205.
[10]XU Y,SHAO J,SLAATS T,et al.MWPoW+:A Strong Consensus Protocol for Intra-Shard Consensus in Blockchain Sharding[J].ACM Transactions on Internet Technology,2023,23(2):34:1-34:27.
[11]LI M,LIN Y,ZHANG J,et al.CoChain:High ConcurrencyBlockchain Sharding via Consensus on Consensus[C]//IEEE INFOCOM 2023-IEEE Conference on Computer Communications.2023:1-10.
[12]YU B,ZHAO H,ZHOU T,et al.OverShard:Scaling blockchain by full sharding with overlapping network and virtual accounts [J].Journal of Network and Computer Applications,2023,220:103748.
[13]LIU Y,LIU J,VAZ SALLES M A,et al.Building blocks of sharding blockchain systems:Concepts,approaches,and open problems[J].Computer Science Review,2022,46:100513.
[14]MU K,WEI X.EfShard:Toward Efficient State Sharding Blockchain via Flexible and Timely State Allocation[J].IEEE Tran-sactions on Network and Service Management,2023,20(3):2817-2829.
[15]LI M,LUO X,XUE K,et al.A Secure and Efficient Blockchain Sharding Scheme via Hybrid Consensus and Dynamic Management[J].IEEE Transactions on Information Forensics and Security,2024,19:5911-5924.
[16]LUU L,NARAYANAN V,ZHENG C,et al.A Secure Sharding Protocol For Open Blockchains[C]//Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security.New York,NY,USA:Association for Computing Machinery,2016:17-30.
[17]GADIRAJU D S,LALITHA V,AGGARWAL V.An Optimization Framework Based on Deep Reinforcement Learning Approaches for Prism Blockchain[J].IEEE Transactions on Ser-vices Computing,2023,16(4):2451-2461.
[18]KOKORIS-KOGIAS E,JOVANOVIC P,GASSER L,et al.OmniLedger:A Secure,Scale-Out,Decentralized Ledger via Sharding[C]//2018 IEEE Symposium on Security and Privacy(SP).2018:583-598.
[19]ZHANG J,HONG Z,QIU X,et al.SkyChain:A Deep Reinforcement Learning-Empowered Dynamic Blockchain Sharding System[C]//Proc of the 49th International Conference on Pa-rallel Processing.New York,NY,USA:Association for Computing Machinery,2020:1-11.
[20]ZHOU K,ZHANG X,WANG C,et al.Accelerating Cross-Shard Blockchain Consensus via Decentralized Coordinators Service With Verifiable Global States[J].IEEE Transactions on Ser-vices Computing,2024,17(4):1340-1353.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!