Research on Network Performance Trade-offs in the Integration of Blockchain and Federated Learning: Architecture, Mechanisms, and Optimization

Rui Li

doi:10.47297/taposatWSP2633-456916.20260701

PDF
导出
分享
收藏
专辑

Research on Network Performance Trade-offs in the Integration of Blockchain and Federated Learning: Architecture, Mechanisms, and Optimization

7卷第1期

浏览量: 0 Downloads: 0

Research on Network Performance Trade-offs in the Integration of Blockchain and Federated Learning: Architecture, Mechanisms, and Optimization
Research on Network Performance Trade-offs in the Integration of Blockchain and Federated Learning: Architecture, Mechanisms, and Optimization
Department of Computer Science and Technology, School of International Education, Guizhou Normal University, Guiyang, Guizhou, 550025, China
2026年7卷第1期页码：77-82
纸质出版：2026-01-30
DOI：10.47297/taposatWSP2633-456916.20260701
Accepted：

Scan QR Code

Rui Li. (2026). Research on Network Performance Trade-offs in the Integration of Blockchain and Federated Learning: Architecture, Mechanisms, and Optimization. 科技理论与实践（英文版）, 7(1), 77-82.

Rui Li.Research on Network Performance Trade-offs in the Integration of Blockchain and Federated Learning: Architecture, Mechanisms, and Optimization[J].Theory and Practice of Science and Technology,2026,07(01):77-82.
Rui Li. (2026). Research on Network Performance Trade-offs in the Integration of Blockchain and Federated Learning: Architecture, Mechanisms, and Optimization. 科技理论与实践（英文版）, 7(1), 77-82. DOI： 10.47297/taposatWSP2633-456916.20260701.

Rui Li.Research on Network Performance Trade-offs in the Integration of Blockchain and Federated Learning: Architecture, Mechanisms, and Optimization[J].Theory and Practice of Science and Technology,2026,07(01):77-82. DOI： 10.47297/taposatWSP2633-456916.20260701.

摘要

Abstract

With the surge in the number of Internet of Things (IoT) devices and the increasingly stringent data privacy regulations

Federated Learning (FL)

as a privacy-preserving distributed machine learning paradigm

has gained widespread attention from academia and industry. However

traditional federated learning relies on a central server for model aggregation

which has inherent defects such as single point of failure (SPoF)

lack of transparency

and vulnerability to security threats such as poisoning attacks

[

]

and Sybil attacks

[

]

where malicious nodes create multiple fake identities to compromise the global model. Blockchain technology

with its decentralized

immutable

and traceable characteristics

has been introduced to solve the aforementioned trust and security issues

forming blockchain-assisted federated learning (BC-FL). Although BC-FL enhances the security and robustness of the system

the introduction of blockchain inevitably brings significant overhead to network performance. There is an essential contradiction between the consensus mechanism delay

block propagation bandwidth consumption

and complex cryptographic operations of blockchain and the requirements of federated learning for high-frequency communication

low latency

and fast convergence

[

]

.This paper aims to provide a detailed review and in-depth theoretical analysis of the network performance trade-offs in the BC-FL system. First

we construct the hierarchical system architecture of BC-FL and propose an improved scheme based on directed acyclic graph (DAG) and sharding. Second

based on the research of Zhang et al.

[

]

we establish an end-to-end mathematical model of latency and communication overhead and quantify the impact of different consensus mechanisms on the training cycle. Third

we deeply analyze the performance requirements differences in two typical scenarios: Internet of Vehicles (IoV) and Internet of Medical Devices (IoMT) and demonstrate the experimental results of customized architectures (such as CPRE-IoV and Med-Q Ledger). The experimental results show that the optimized BC-FL architecture can reduce the model update latency to less than 200ms while ensuring security and maintaining convergence accuracy comparable to traditional FL.

关键词

Keywords

references

Qammar, A., et al. (2022). Securing federated learning with blockchain: A systematic literature review. Artificial Intelligence Review .

Fung, C. (2023). Sybil attacks in federated learning (Doctoral dissertation). University of Stockholm.

Zhang, C., Ji, M., et al. (2025). Optimizing system latency for blockchain-encrypted edge computing in internet of vehicles. Computers, Materials & Continua , 83(2).

Lin, R., et al. (2024). Time-efficient blockchain-based federated learning. IEEE/ACM Transactions on Networking .

Nguyen, D. C., et al. (2021). Federated learning for internet of things: A comprehensive survey. IEEE Communications Surveys & Tutorials , 23(3).

Zhang, Y., et al. (2024). Blockchain-based federated learning: A survey and new perspectives. Applied Sciences.

Wang, Z., et al. (2021). A systematic survey of blockchained federated learning. arXiv preprint .

Wang, Z., et al. (2023). Blockchain-based federated learning: A comprehensive survey. Future Internet .

Yuan, S., Cao, B., Sun, Y., Wan, Z., & Peng, M. (2021). Secure and efficient federated learning through layering and sharding blockchain. IEEE Transactions on Network Science and Engineering .

Jia, L., et al. (2024). Estuary: A low cross-shard blockchain sharding protocol. IEEE Transactions on Parallel and Distributed Systems .

Ren, S., Kim, E., & Lee, C. (2024). A scalable blockchain-enabled federated learning architecture for edge computing. PLOS ONE .

Madill, E. W. R., Nguyen, B., Leung, C. K., & Rouhani, S. (2022). ScaleSFL: A sharding solution for blockchain-based federated learning. Proceedings of the 4th ACM International Symposium on Blockchain and Secure Critical Infrastructure .

Xu, J., et al. (2024). Cross-shard transaction processing in blockchain-based federated learning. IEEE Access .

Liu, Y., Liu, A., Lu, Y., et al. (2025). Kronos: A secure and generic sharding blockchain consensus with optimized overhead. NDSS .

Zhang, S., Kong, L., Zhang, Y., et al. (2025). DAG-AFL: Directed acyclic graph-based asynchronous federated learning. arXiv preprint .

Yuan, S., et al. (2025). DAG-based tip selection for FL. arXiv preprint .

Lin, Y., Gao, Z., Du, H., et al. (2023). DRL-based adaptive sharding for blockchain-based federated learning. IEEE Transactions on Communications .

Khan, H., Kavati, R., Pulkaram, S., & Jalooli, A. (2025). End-to-end privacy-aware federated learning for wearable health devices via encrypted aggregation. PMC .

Ali, A., et al. (2025). FL and blockchain-enabled framework for traffic rerouting. IEEE TCE .

Liu, H., et al. (2021). Blockchain and federated learning for collaborative intrusion detection in vehicular edge computing. IEEE Transactions on Vehicular Technology , 70(6).

Fitwi, A., et al. (2022). Latency minimization in blockchain-federated learning for IoV. arXiv preprint .

He, Z., Xu, R., Wang, B., et al. (2025). Integrated blockchain and federated learning for robust security. Symmetry , 17 (7), 1168.

Chen, Y., et al. (2024). Privacy-preserving federated learning in medical IoT: A blockchain approach. IEEE Journal of Biomedical and Health Informatics .

Ravisankar, S., & Maheswar, R. (2025). SecureEdge-MedChain: A post-quantum blockchain and federated learning framework for real-time predictive diagnostics in IoMT. MDPI Sensors .

Luo, J., et al. (2023). Consensus in 6G wireless networks: A review. arXiv .

文章被引用时，请邮件提醒。

Submit

A Federated Learning Framework for Client-Differentiated Adaptive Knowledge Distillation

A Comparative Review of Privacy Protection Techniques in Federated Learning

Intelligent Malware Adversarial Technology Based on Deep Learning

Research on Technologies of Blockchain and Their Cross-Domain Applications:Systematic Exploration Based on Zero-Knowledge Proof and Regulatory Requirements

A Survey of Privacy-Preserving Techniques in Federated Graph Neural Networks

Related Author

Zoufeng Jiang School of Physics and Electronic Science, Hunan University of Science and Technology

Jiayi Li School of Data Science and Artificial Intelligence, Wenzhou Institute of Technology

Yuefu Qiu City University Malaysia, SintokKedah Darul Aman

Kazem Chamran City University Malaysia, SintokKedah Darul Aman

Jinhua Zhou Hong Kong Baptist University, College of Science and Technology, Zhuhai

Lingyu Wang School of Arts and Sciences, China University of Petroleum-Beijing at Karamay

Yurong Guan Huanggang Normal University

Weiyun Xiong Huanggang Normal University

Related Institution

School of Physics and Electronic Science, Hunan University of Science and Technology

School of Data Science and Artificial Intelligence, Wenzhou Institute of Technology

City University Malaysia, SintokKedah Darul Aman

Hong Kong Baptist University, College of Science and Technology, Zhuhai

School of Arts and Sciences, China University of Petroleum-Beijing at Karamay

⁰