In the realm of cluster operation, continuously validating and optimizing the configuration requires access to accurate cluster behavioral models. Network Digital Twins (NDTs) have emerged as a paradigm to provide such accurate, live representations of network systems. To capture the live state, NDTs need to anticipate the cluster behavior in a faster than real-time manner. With increasingly complex clusters, classical NDTs relying on detailed handcrafted simulators become too slow to fulfill this task. Leveraging measurements from the actual system demonstrates the potential to create more highlevel, lightweight NDTs that are still fairly accurate. Nonetheless, the degree of abstraction required to create fast and accurate data-driven NDTs is not well understood. To address this, our work investigates the impact of different abstraction levels on modeling accuracy. We develop and compare three Network Digital Twins of a Kubernetes Cluster - a Twin based on a Handcrafted Simulator, a Decentralized Data-driven Twin, abstracting individual system components, and a Centralized Data-driven Twin, abstracting the system as a whole. Our results show that Data-driven Twins improve the performance prediction by 18-53% over the handcrafted one, with the Centralized Twin surpassing the Decentralized Twin in accuracy by 35% and speed by two orders of magnitude.

Cluster orchestrators such as Kubernetes (K8s) provide many knobs that cloud administrators can tune to conFigure their system. However, different configurations lead to different levels of performance, which additionally depend on the application. Hence, finding exactly the best configuration for a given system can be a difficult task. A particularly innovative approach to evaluate configurations and optimize desired performance metrics is the use of Digital Twins (DT). To achieve good results in short time, the models of the cloud network functions underlying the DT must be minimally complex but highly accurate. Developing such models requires detailed knowledge about the system components and their interactions. We believe that a data-driven paradigm can capture the actual behavior of a network function (NF) deployed in the cluster, while decoupling it from internal feedback loops. In this paper, we analyze the HTTP load balancing function as an example of an NF and explore the data-driven paradigm to learn its behavior in a K8s cluster deployment. We develop, implement, and evaluate two approaches to learn the behavior of a state-of-the-art load balancer and show that Machine Learning has the potential to enhance the way we model NF behaviors.

Programmability and softwarization advocate the emerging era of open-source platforms, which embraced by both industry and academia is foreseen as a vital pillar in the construction of next generation mobile networks. Such a valuable open-source project is OpenAirInterface (OAI), which provides a standard compliant mobile network infrastructure, merely based on general purpose hardware computers. While OAI is nowadays widely used by industry and research institutes in proof-of-concept or commercial wireless testbeds, an analysis of the complex functions within the platform is yet to be performed in a large scale. We believe that further research is required to demystify the capabilities of existing tools and present guidelines that alleviate the enhancement and development of additional features. In this context, in this work we shed light on one of the crucial components of any mobile system, namely resource scheduling, while providing an analysis of the available code and instructions to ease the development of new scheduling algorithms based on OAI. Moreover, we demonstrate a performance evaluation of up to 10 UEs for existing and newly implemented scheduling algorithms. Results show, that the development of additional algorithms in OAI is achievable and the experimental behavior follows the theory. Our implementation and observations can serve as a basis for research in the field, and foster the elaboration of theoretical concepts and emerging 5G solutions in practical testbeds.