The Promising Role of Representation Learning for Distributed Computing Continuum Systems

Abstract

The distributed computing continuum systems (DCCS) and representation learning (ReL) are two diverse computer science technologies with their use cases, applications, and benefits. The DCCS helps increase flexibility with improved performance of hybrid IoT-Edge-Cloud infrastructures. In contrast, representation learning extracts the features (meaningful information) and underlying explanatory factors from the given datasets. With these benefits, using ReL for DCCS to improve its performance by monitoring the devices will increase the utilization efficiency, zero downtime, etc. In this context, this paper discusses the promising role of ReL for DCCS in terms of different aspects, including device condition monitoring, predictions, management of the systems, etc. This paper also provides a list of ReL algorithms and their pitfalls which helps DCCS by considering various constraints. In addition, this paper list different challenges imposed on ReL to analyze DCCS data. It also provides future research directions to make the systems autonomous, performing multiple tasks simultaneously with the help of other AI/ML approaches.