Bc²FL: Double-Layer Blockchain-Driven Federated Learning Framework for Agricultural IoT

作     者：Qingyang Ding Xiaofei Yue Qinnan Zhang Zehui Xiong Jinping Chang Hongwei Zheng 

作者机构：School of Management Beijing Union University Beijing China School of Computer Science and Technology Beijing Institute of Technology Beijing China Institute of Artificial Intelligence Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang University Beijing China Information Systems Technology and Design Pillar Singapore University of Technology and Design Tampines Singapore Blockchain and Privacy Computing Technology R&D Department Beijing Academy of Blockchain and Edge Computing Beijing China 

出 版 物：《IEEE Internet of Things Journal》 

年 卷 期：2024年第12卷第4期

页      面：4362-4374页

学科分类：0808[工学-电气工程] 08[工学] 

基　　金：Research and Development Program of Beijing Municipal Education Commission Beijing Social Science Foundation Beijing Natural Science Foundation Education Science Planning Project of Beijing Union University National Key Research and Development Program of China 

主　　题：Blockchains Internet of Things Privacy Computational modeling Federated learning Data models Biological system modeling Adaptation models Accuracy Servers 

摘      要：With the flourishing of the Agricultural Internet of Things (AIoT), analyzing large-volume sensor data has become a regular requirement for agricultural decision-making. Federated learning (FL), which facilitates scattered AIoT devices to train models collaboratively, has gained significant attention. However, traditional FL poses challenges in AIoT scenarios, such as wide geo-distribution, heterogeneous data distribution, and high-device risks. Existing works tend to be one-sided and remain unclear on how to tackle these issues thoroughly in AIoT. To fill the gap, we present Bc2FL, a double-layer blockchain-based FL framework, which enhances both learning efficiency and security for AIoT. The double-layer blockchain, coupled with a two-stage consensus algorithm, drives the hierarchical FL process to enable efficient and reliable agricultural knowledge-sharing. In addition, Bc2FL adopts an adaptive model aggregation algorithm to dynamically tune noise levels based on the model quality, further improving the learning security and model credibility. Finally, the extensive experimental results demonstrate that Bc2FL not only improves the model accuracy by up to 21.17% compared with the state-of-the-art baselines, but also enhances the privacy protection within an additional error of only 2.1%.