Towards a Reference Architecture Model for Industrial Edge Computing

TL;DR

This paper proposes a comprehensive reference architecture model for industrial edge computing, aiming to standardize understanding and guide future research and development in manufacturing and automation.

Contribution

It introduces the RAMEC model, which identifies 210 views on edge computing in industrial manufacturing, filling a gap in existing reference models.

Findings

210 views identified in the RAMEC model

Supports classification of research and standardization efforts

Aids in understanding the multi-dimensional problem space

Abstract

In the context of the digital transformation of the industry, whole value chains get connected across various application domains; as long as economic, ecologic, or social benefits arise to do so. Under the umbrella of the Industrial Internet of Things (IIoT), traditional Operational Technology (OT) approaches are replaced or at least augmented by Information and Communication Technology (ICT) systems to facilitate this development. To meet industrial requirements, for example, related to privacy, determinism, latency, or autonomy, established Cloud Computing mechanisms are being moved closer to data sources and actuators. Depending on the context, this distributed Cloud Computing paradigm is named Edge Computing or Fog Computing and various challenges have been subject to several publications. However, a proper reference model that describes the multi-dimensional problem space which is being spanned by this paradigm, seems still to be undefined. Such a model should provide orientation, put work in relation and support the identification of current and future research issues. This paper aims to fill this gap with a focus on industrial automation and follows analog models that have been developed for specific domains such as the Smart Grid Architecture Model (SGAM) and the Reference Architecture Model Industrie 4.0 (RAMI4.0). The proposed Reference Architecture Model Edge Computing (RAMEC) identifies 210 views on the Edge Computing paradigm in the manufacturing domain. Future iterations of this model might be used for the classification of relevant research, standardization, and development activities.