Energy-Friendly Federated Neural Architecture Search for Industrial Cyber-Physical Systems

The rapid evolution of Industrial Cyber-Physical Systems (ICPS) with cloud-fog automation calls for the deployment of Deep Neural Networks (DNNs) on edge devices to enable intelligent and autonomous decision-making. However, the resource constraints, heterogeneity, and dynamic nature of edge devices pose limitations to the efficient deployment of DNNs. Federated Learning-based Neural Architecture Search (FL-NAS) has been proposed to address these limitations, but achieving an effective balance between the generalized global model and personalized local models remains a non-trivial task due to <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">suboptimal aggregation of homogeneous neural blocks, knowledge waste of heterogeneous neural blocks, and high communication and energy overhead</i>. In this paper, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F²NAS</i>, an energy-friendly federated neural architecture search framework tailored for ICPS. The fine-grained aggregation strategy adapts weights for each device during aggregation, enhancing the global and personalized local models. The bidirectional knowledge transfer mechanism leverages heterogeneous neural blocks, promoting knowledge sharing among local and global models. The adaptive communication strategy optimizes interactions between edge devices and the cloud server based on model performance, reducing energy costs while maintaining effective model collaboration. Extensive experiments demonstrate that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F²NAS</i> outperforms baselines by up to 30.31% in accuracy on edge devices, 38.75% on the cloud server, and achieves a 65.2% reduction in energy consumption. When applied to the surface defect detection task in ICPS, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F²NAS</i> surpasses other baselines by up to 13.38% and 302.46% for edge devices and cloud servers, respectively, and reduces energy consumption by 44.8%.