Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Towards a Self-Adaptive Architecture for Federated Learning of Industrial Automation Systems

: Franco, Nicola; Van, Hoai My; Dreiser, Marc; Weiß, Gereon

Preprint urn:nbn:de:0011-n-6360343 (936 KByte PDF)
MD5 Fingerprint: a5833bf353cf75986570531a09cdd11d
© ACM This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution.
Erstellt am: 18.6.2021

Association for Computing Machinery -ACM-; IEEE Computer Society:
16th International Symposium on Software Engineering for Adaptive and Self-Managing Systems, SEAMS 2021. Proceedings : 22-30 May 2021, Virtual
Los Alamitos, Calif.: IEEE Computer Society Conference Publishing Services (CPS), 2021
ISBN: 978-1-6654-0289-7
ISBN: 978-1-6654-0290-3
International Symposium on Software Engineering for Adaptive and Self-Managing Systems (SEAMS) <16, 2021, Online>
Konferenzbeitrag, Elektronische Publikation
Fraunhofer IKS ()
self adaptive systems; federated learning; distributed simplex; industry 4.0; artificial intelligence; AI; machine learning; model optimization

Emerging Industry 4.0 architectures deploy data driven applications and artificial intelligence services across multiple locations under varying ownership, and require specific data protection and privacy considerations to not expose confidential data to third parties. For this reason, federated learning provides a framework for optimizing machine learning models in single manufacturing facilities without requiring access to training data. In this paper, we propose a self-adaptive architecture for federated learning of industrial automation systems. Our approach considers the involved entities on the different levels of abstraction of an industrial ecosystem. To achieve the goal of global model optimization and reduction of communication cycles, each factory internally trains the model in a self-adaptive manner and sends it to the centralized cloud server for global aggregation. We model a multi-assignment optimization problem by dividing the dataset into a number of subsets equal to the number of devices. Each device chooses the right subset to optimize the model at each local iteration. Our initial analysis shows the convergence property of the algorithm on a training dataset with different numbers of factories and devices. Moreover, these results demonstrate higher model accuracy with our self-adaptive architecture than the federated averaging approach for the same number of communication cycles.