Auswahl der wissenschaftlichen Literatur zum Thema „Zero-Touch Management“

In modern telecommunication sectors, zero touch (Zero-Touch) networks are a novel idea. A combination of quick, context-aware network and service configuration, adaptable new service development, and dynamic, effective resource allocation are required for everyone. An innovative telecommunication management software, Zero-Touch Networks (ZTNs), were released to address these complicated conditions. The primary objective of the zero-touch network is autonomous operation, which is governed by higher layers of policies and regulations and allows for self-configuration, self-monitoring, self-healing and self-optimization without the need for human interaction. This conceptual study document is based on white and grey literature in the Google and Web of Science databases. Text, image, audio and video formats all existed for the data. The manuscripts examined the theories, enabling technologies, problems and difficulties associated with zero touch networks. The primary goal of this manuscript is to provide an overview of ZTN so that aspiring academics, researchers, students and businesspeople can profit from it.

The rapid development of the Internet of Things (IoT) requires network automation, to improve management efficiency and reduce manual operations. Zero-touch network is a promising technology for empowering network management automation by creating virtualized networks for software-based solutions. However, the traditional software-defined network (SDN) technology is not suitable for IoT devices, due to its massive, heterogeneous, and distributed characteristics. In this paper, we introduce digital twin technology (DT) into the IoT, and propose a DT modeling method through ontology and knowledge graph technologies, which maps IoT elements in the digital space and provides the advantages of centralized control, device abstraction, and flexible control of management. Then, referring to the conceptual architecture of a zero-touch network, a DT-based zero-touch management framework suitable for IoT is established. Finally, aiming at specific device management and network optimization problems in the IoT, a zero-touch management scheme with digital twin technology as the core and intention as the driver is proposed, and the effectiveness of the proposed method is demonstrated using an example.

The concept of zero-touch networking involves creating networks that are fully autonomous and require minimal human intervention. This approach is increasingly relevant due to the rapid growth of current cloud architectures, which are beginning to reach their limits due to continuous expansion demands from users and within the network core itself. In response, Fog computing, acting as a smart, localized data center closer to network nodes, emerges as a practical solution to the challenges of expansion and upgrading in existing architectures. Fog computing complements cloud technology. However, the realization of zero-touch networks is still in its early stages, and numerous challenges hinder its implementation. One significant challenge is the NP-hard problem related to resource management. This paper introduces an optimal resource management algorithm based on Federated Learning. The effectiveness of this algorithm is evaluated using the iFogSim simulator within the existing cloud-fog architecture. The results demonstrate that the proposed architecture outperforms the current infrastructure in several key aspects of resource management, including system latency, number of resources processed, energy consumption, and bandwidth utilization.

Fog computing offers an optimal answer to the expansion challenge of today’s networks. It boasts scaling and reduced latency. Since the concept is still nascent, many research questions remain unanswered. One of these is the challenge of Resource Management. There is a pressing need for a reliable and scalable architecture that meets the Resource Management challenge without compromising the Quality of Service. Among the proposed solutions, Artificial Intelligence based path selection techniques and automated link detection methods can provide lasting and reliable answer. An optimal approach for introducing intelligence in the networks is the infusion of Machine learning methods. Such futuristic, intelligent networks form the backbone of the next generation of Internet. These self-learning and self-healing networks are termed as the Zero-Touch networks. This paper proposes FedFog, a Federated Learning based optimal, automated Resource Management framework in Fog Computing for Zero-touch Networks. The paper describes a series of experiments focusing on Quality of Service parameters such as Network latency, Resources processed, Energy consumption and Network usage. The simulation results from these experiments depict superiority of the proposed architecture over traditional, existing architecture.

La maturation de la provision et de la gestion des infrastructures de cloud computing et d'edge computing a engendré le Cloud Edge Computing Continuum (CECC), facilitant le déploiement et la migration d'applications entre les infrastructures cloud centralisées et les infrastructures edge décentralisées. Cette transition a donné vie à des nouveaux cas d'utilisation dans des secteurs tels que l'Internet Industriel des Objets (IIoT), les véhicules autonomes et la réalité augmentée, tous profitant de cette architecture distribuée. Ces domaines d'application requièrent à la fois la scalabilité des centres de données massifs du cloud traditionnel et la faible latence des infrastructures edge computing. Les progrès technologiques, tels que la virtualisation, la conteneurisation et les réseaux 5G, ont facilité le développement d'applications CECC, passant des architectures monolithiques aux microservices. L'orchestration efficace des applications CECC est essentielle pour garantir la performance et optimiser l'utilisation des ressources. Cette thèse propose des solutions pour la gestion automatisée du CECC, se concentrant sur la collecte de données de supervision, la compréhension du fonctionnement des applications et de l'infrastructure, et la prise de décisions sur le placement la migration et l'adaptation des ressources des applications. Dans la première contribution de cette thèse, nous proposons un framework de supervision de services multi-domaines de bout en bout. De tels services consistent en des applications et des fonctions réseau qui s'étendent sur plusieurs domaines technologiques, chacun présentant ses propres intrications uniques. Le système de supervision proposé utilise une structure unifiée des Key Performance Indicators (KPIs), abstrayant efficacement toutes les complexités sous-jacentes. Des tests approfondis dans différents scénarios valident la scalabilité du framework et sa capacité à superviser un grand nombre de services simultanément. La prochaine étape de la thèse impliquait le profilage des applications, dans lequel nous avons mené une étude expérimentale pour explorer le comportement de différents types d'applications dans des environnements cloud-native. Cette étude met en évidence l'incapacité des propriétaires d'applications à configurer les ressources appropriées pour leurs applications afin de fonctionner de manière optimale sans entraîner de gaspillage des ressources d'infrastructure. Ensuite, nous avons utilisé des techniques de machine learning et d'eXplainable AI (XAI) pour construire des modèles capables de prédire la dégradation des performances des applications, en utilisant des ensembles de données générés à partir de notre étude. Lorsque le modèle prédit un déclin des performances de l'application, le module XAI fournit des explications pour la sortie du modèle, facilitant l'identification de la cause profonde de la dégradation du service. Cette cause profonde est ensuite traitée par le gestionnaire d'application.Le parcours de cette thèse s'est conclu par la proposition d'une architecture pour la gestion du cycle de vie des applications CECC. Cette architecture utilise des profils d'application et d'infrastructure pour déployer et migrer des applications tout en tenant compte de l'empreinte carbone du déploiement CECC.Le principal défi réside dans la représentation concrète du profil d'application de manière à pouvoir spécifier les exigences actuelles et futures de l'application. Ce défi a été relevé en représentant efficacement le profil d'application pour faciliter la dérivation des exigences actuelles et futures de l'application
The maturation of cloud computing and edge computing infrastructure provisioning and management has led to the emergence of Cloud Edge Computing Continuum (CECC). CECC enables seamless deployment and migration of applications between centralized cloud infrastructures and decentralized edge infrastructure. This evolution has driven new use cases across industries, including Industrial Internet of Things (IIoT), autonomous vehicles, and augmented reality, all benefiting from this distributed architecture.These use cases require scalability and storage from massive data centers typical of traditional cloud computing, as well as the low latency and high bandwidth offered by edge computing infrastructures. Several factors enable the development and deployment of applications to fully leverage CECC : advancements in application deployment technologies like virtualization and containerization, a shift in application architecture and development methodology towards microservices architectures, and innovations in networking technologies such as 5G mobile networks. Efficiently orchestrating applications within the CECC framework is crucial for meeting performance requirements and optimizing infrastructure resource utilization. This thesis proposes solutions for zero-touch management of CECC, focusing on automated monitoring, profiling, and decision-making processes. These solutions aim to automate application management, facilitating seamless orchestration and resource optimization.In the first contribution, a novel monitoring system for multi-domain services is proposed, utilizing a unified structure for Key Performance Indicators (KPIs) to abstract underlying technologies. This scalable system monitors end-to-end network slices, including Radio Access Network (RAN), Core Network (CN), and Cloud/Edge domains.The second contribution presents results from an experimental study aiming to detect if a tenant's configuration allows running its service optimally. The study provides insights on detecting and correcting performance degradation due to misconfiguration of service resources.Moving towards decision-making of a CECC manager, the third contribution proposes a Zero-Touch Service Management (ZSM) framework featuring a fine-granular computing resource scaler in a cloud-native environment. The scaler uses AI/ML models to predict microservice performances, with an XAI module conducting root-cause analysis for service degradation. Afterwards, the proposed framework scales only the needed resources (i.e., CPU or memory) to overcome the service degradation. Finally, in the last contribution, an architecture of CECC Application Orchestrator is proposed, leveraging applications and infrastructures profiling for efficient management. These profiles represent current and future applications' requirements, guiding decision-making processes (placement, resources scaling. migration) to minimize carbon footprint and deployment costs

The dramatic and much faster than anticipated rise of global sea level temperatures during 2023 em-phasized how little time we have left to fight climate change and reach net-zero greenhouse gas emis-sions. Within our SCENE Joint Initiative, we have joined forces of our research activities to support Swit-zerland in achieving this urgently needed transition towards a sustainable, net-zero future. Involving more than 130 experts from all six institutions of the ETH Domain, SCENE gathers tremendous knowledge and expertise from various disciplines. It has been a pleasure to witness how these research-ers, who previously focused mainly on their specific fields and in many cases had not known each other, started a lively interaction and collaboration, breaking down boundaries between disciplines and insti-tutions from the very beginning of the initiative in January 2023. This collaborative spirit was fostered by our highly engaged Project Management Team, who made sure that SCENE started operations with full speed. We are excited that we could complement the research consortium with a high-profile Advi-sory Board that guides us with their perspectives from industry, public administration, and politics throughout the project. In addition, we established the Expert Hub, our rapid-response team, to swiftly react to inquiries and requests. We are grateful for the entire SCENE consortium for their contributions to the success of this Joint Initiative. Have a look at our team, check for news, and get in touch with us at www.scene-project.ch.