English

应用科学学报 ›› 2026, Vol. 44 ›› Issue (5): 752-770.doi: 10.3969/j.issn.0255-8297.2026.05.004

• 区块链 • 上一篇    下一篇

基于深度强化学习的分片区块链节点多维评估和智能动态重构方案

孟令洋1, 李鹏1, 孙丽珺1, 杜剑2   

  1. 1. 青岛科技大学 信息科学技术学院, 山东 青岛 266061;
    2. 山东海科物联科技有限公司, 山东 青岛 266061
  • 收稿日期:2026-01-20 出版日期:2026-09-30 发布日期:2026-10-09
  • 通信作者: 孙丽珺，博士，教授，研究方向为边缘智能和区块链网络。E-mail:lijunsun@qust.edu.cn
  • 基金资助:
    国家自然科学基金（No.62571289,No.62172249,No.62472441）；山东省自然科学基金（No.ZR2025MS1089,No.ZR2023MF082）；青岛市自然科学基金（No.23-2-1-164-zyyd-jch,No.24-8-4-zrjj-3-jch）

A Multi-dimensional Evaluation and Intelligent Dynamic Reconfiguration Scheme for Sharded Blockchain Nodes Based on Deep Reinforcement Learning

MENG Lingyang1, LI Peng1, SUN Lijun1, DU Jian2   

  1. 1. College of Information Science and Technology, Qingdao University of Science & Technology, Qingdao 266061, Shandong, China;
    2. Shandong Haike IoT Technology Co., Ltd, Qingdao 266061, Shandong, China
  • Received:2026-01-20 Online:2026-09-30 Published:2026-10-09

PDF

6

摘要： 区块链因吞吐量低、扩展性差，难以实现规模化落地应用。分片技术虽可借助并行处理优化性能，但传统分片方案存在重配置灵活性不足、节点评估维度单一的缺陷，无法兼顾系统吞吐量与安全性。为此，本文提出一种基于深度强化学习的分片区块链节点多维评估和智能动态重构方案，旨在实现分片重配置过程中吞吐量性能与系统安全性的动态平衡。首先设计一种多维评估方法，为节点构建更全面的动态画像，并对分片吞吐量与安全性展开量化分析；其次引入深度强化学习算法，根据系统状态识别响应网络条件的最佳分片策略，同时动态均衡节点分配，最终实现分片重配置的智能自适应调整。实验结果表明，相较于传统方案，本文方法能有效提高吞吐量，降低分片风险，实现吞吐量和安全性的长期动态平衡，为区块链在大规模场景下的应用提供了可行方案。

关键词: 分片区块链, 深度强化学习, 重配置, 节点分配, 扩展性

Abstract: Blockchain suffers from low throughput and poor scalability, thus making it difficult to achieve large-scale practical applications. Although sharding technology can improve performance through parallel processing, traditional sharding schemes have limitations including insufficient reconfiguration flexibility and a single-dimensional node evaluation metric, and cannot balance system throughput and security. To this end, this paper introduced a multi-dimensional node evaluation and intelligent dynamic reconfiguration scheme for sharded blockchain nodes based on deep reinforcement learning (DRL), aiming to balance throughput performance and system security during sharding reconfiguration. Specifically, it designed a multi-dimensional evaluation method to construct more comprehensive dynamic profiles for nodes and quantitatively analyze shard throughput and security. Meanwhile, the DRL algorithm was introduced to identify optimal sharding strategies responsive to network conditions based on system states. Simultaneously, node allocation was dynamically balanced, ultimately achieving intelligent and adaptive adjustment of sharding reconfiguration. The experimental results show that compared with the traditional scheme, the proposed method can effectively improve throughput and reduce sharding risk. Additionally, it achieves a long-term dynamic balance between throughput and security, providing a feasible solution for the application of blockchain in large-scale scenarios.

Key words: sharded blockchain, deep reinforcement learning, reconfiguration, node assignment, scalability

中图分类号: