Simulators for system dataset generation in the Edge-to-Cloud Continuum

In the era of the Edge-to-Cloud Continuum paradigm, effectively managing heterogeneous and distributed resources poses significant challenges. Autonomic system operation, supported by Artificial Intelligence (AI) driven resource management and application deployment mechanisms, offers a promising solution. Machine Learning (ML) models are pivotal for this purpose, necessitating large amounts of high- quality data for training, validation, and evaluation. Simulators play a crucial role by generating vast datasets containing diverse data types, facilitating training, testing, and analyzing ML and AI techniques for autonomic system optimization. This paper aims to review existing simulators and identify a candidate simulator suitable for generating datasets within the Edge-to- Cloud Continuum, supporting the development of efficient ML models.