The growing complexity of communication networks and the explosion of network traffic have made the task of managing these networks exceedingly hard. A potential approach for striking this increasing complexity is to build an autonomous self-driving network that can measure, analyze and control itself in real time and in an automated fashion with- out direct human intervention. In this thesis, we focus on realizing such an autonomous network leveraging state-of-the-art networking technologies along with artificial intelli- gence and machine learning techniques. Toward this goal, we exploit different learning paradigms to automate network management. First, we propose supervised machine learning methods to detect increases in delays in mobile broadband networks. Further, considering the challenges of supervised learning in networking applications, we present a novel real-time distributed architecture for detecting anomalies in mobile network data in an unsupervised fashion. It also involves a collaborative framework for knowledge sharing between the distributed probes in the network to improve the overall system accuracy. Second, we propose a novel deep reinforcement learning based control framework for op- timizing resources utilization while minimizing performance degradation in multi-slice Radio Access Network (RAN) through a set of diverse control actions. We explore both centralized and distributed control architectures. Last, we design a framework for timely collecting telemetry, detecting and attributing outages in mobile networks. We evaluate our framework on a software defined virtualised testbed that resembles a cloudified mobile network.

Open Source MANO is a helpful tool to manage and orchestrate the instantiation of core network setups, like Network Service (NS) instances of our SimulaMet OpenAirInterface Virtual Network Function (VNF) for Enhanced Packet Cores (EPC). We furthermore extended our NS with VNF instances of Programming Protocol-independent Packet Processors (P4) switches, in order to allow for in-band telemetry. With in-band telemetry, it is possible to flexibly add, process, and remove telemetry information to traffic within the packet core, in order to allow for fine-granular evaluation of the system performance and the users' experienced quality of service. In our presentation and demo, we would like to provide an overview of our ongoing work on P4-based in-band telemetry in an OSM-orchestrated 4G core, which is used for detecting performance problems and anomalies in the network based on machine learning. We would furthermore like to demonstrate the details of our setup to the audience in a live demo.