Zero Touch Management: A Survey of Network Automation Solutions for 5G and 6G Networks

Abstract

Mobile networks are facing an unprecedented demand for high-speed connectivity originating from novel mobile applications and services and, in general, from the adoption curve of mobile devices. However, coping with the service requirements imposed by current and future applications and services is very difficult since mobile networks are becoming progressively more heterogeneous and more complex. In this context, a promising approach is the adoption of novel network automation solutions and, in particular, of zero-touch management techniques. In this work, we refer to zero-touch management as a fully autonomous network management solution with human oversight. This survey sits at the crossroad between zero-touch management and mobile and wireless network research, effectively bridging a gap in terms of literature review between the two domains. In this paper, we first provide a taxonomy of network management solutions. We then discuss the relevant state-of-the-art on autonomous mobile networks. The concept of zero-touch management and the associated standardization efforts are then introduced. The survey continues with a review of the most important technological enablers for zero-touch management. The network automation solutions from the RAN to the core network, including end-toend aspects such as security, are then surveyed. Finally, we close this article with the current challenges and research directions.

Digital Twin-Enabled Domain Adaptation for Zero-Touch UAV Networks: Survey and Challenges

“…Experience collected by agents, especially in dynamic or time-varying environments, may only be valid temporarily, requiring continuous computation and re-optimization. Virtualization is a key technique for improving the flexibility and efficiency of zero-touch control for wireless networking systems [16]. This requires dedicated computational resources and infrastructure to support synthetic data generation and processing as well as bidirectional communication between twin and physical domain systems.…”

“…The contribution of a readily available, communityoriented DT platform for the purpose of ML-based wireless network experimentation remains a significant open challenge. It is expected that a combination of these tools, combined with data fusion [16] and platform integration [82], can be leveraged for a widely available, high-fidelity DT toolchain optimized for use in the wireless domain.…”

“…Testbed Sharing and Remote Access: Considering the need for open, accessible DT experimentation platforms, we believe it is of critical importance to facilitate remote access and control for a fully realized DT-enabled wireless networking testbed. There remains a lack of testbeds and networking environments to enable validation of AI integration and further research into virtualization for network autonomy [16], especially to support advancement towards zero-touch networking. To address this challenge, we emphasize the contributions made in [82] as discussed in Sec.…”

“…Moreover, in the current practice of wireless engineering, the networking environments are usually assumed to be known at design time, and the resulting control programs may fail when encountering unforeseen conditions. Traditional manual network management has hindered the adoption of new techniques and the evolution of wireless networks, motivating a new paradigm that can enable zero-touch management of UAV-enabled networks, including planning, design and deployment, service delivery, resource management, and endto-end optimization [16].…”

Determining Most Likely Links (MLL) for Network Fault Localization

“…Recent advances in machine learning algorithms/implementations coupled with instrumentation to collect voluminous data have made the ap-plication of machine learning quite fruitful. Indeed machine learning can be fruitfully applied to automate the tasks of network management; this is often referred to as zero-touch network management [4]- [7].…”