Towards Blockchain-based Hierarchical Federated Learning for Cyber-Physical Systems

Cyber-physical systems (CPS) have evolved over the years and are now integrated into intelligent manufactory. The Internet of Things (IoT) has played a significant role in the advancement of such systems. CPS have become more intelligent and self-automated with the aid of advances in Artificial Intelligence (AI). Automating the process of CPS management requires that AI and secure transaction processing be integrated within all stakeholders, including the cloud, fog, edge, network, storage, and industrial devices. This integration necessitates the distribution and decentralization of the self-configuring, self-managing, self-healing, and self-governing process in CPS. This paper presents a blockchain-based hierarchical federated learning (HFL) solution that maintains quick, secure, and accurate decision-making for industrial machines. A two-stage federated learning (FL) algorithm, where during the first stage, industrial devices are grouped into clusters and perform local ML training. Local models are shared with network edge devices and a set of global models are created using FL averaging. During the second stage, a main global model is created from the distributed first-stage global models using a FL aggregating algorithm. Blockchain is used to verify and validate the trained models on the edge. System evaluations are performed to compare the proposed HFL solution against traditional FL in terms of training accuracy and network overhead.