Design Pattern and Challenges of Federated Learning with Applications in Industrial Control System

Abstract

Federated Learning (FL) appeared as an encouraging approach for handling decentralized data. Creating a FL system needs both machine learning (ML) knowledge and thinking about how to design system software.Researchers have focused a lot on the ML side of FL, but have not paid enough attention to designing the software architecture. So, in this survey, a set of design patterns is described to tackle the design issues. Design patterns are like reusable solutions for common problems that come up when designing software architecture. This paper focuses on (1) design patterns such as architectures, frameworks, client selection protocols, personalization techniques, and model aggregation techniques that are building blocks of the FL system. It inquires about tradeoffs and working principles accompanying each design aspect, providing insights into their effect on the scalability, performance, or security process; (2) elaborates challenges faced in the design and execution of FL systems such as communication efficiency, statistical/system heterogeneity, or security/privacy concerns. It additionally investigates continuous exploration efforts and distinguishes future examination headings to take out the design challenges and upgrade the adequacy of the frameworks, and (3) depicts some FL applications used in industrial control systems along with their limitations that pave a new research gap for industry professionals. This comprehensive study provides a valuable resource for researchers, practitioners, and system designers interested in understanding the design aspects and challenges associated with FL.