At present, all walks of life are using the advanced cloud platform technologies and network connection services to digitalize and automate the transformation of service to improve the service agility and the flexibility. In the field of mobile communications, although operators have been exploring, researching and deploying applications in automation of network management and service provision for many years, however, it cannot solve the problems of high network energy consumption, complex multi-standard interoperation, high operational cost and low efficiency. At the same time, as the network evolves in the direction of programmable, software-driven, service-oriented architectures, the complexity and scale of network operation and maintenance (OAM) have reached an unprecedented height. The introduction of new services and technologies also puts forward more stringent requirements for the agility of network operations, and operators urgently need a more comprehensive, intelligent, scalable and affordable network automated OAM system.
The automation of network OAM has different granularity, which can be the automation of task, function or process, or the automation of network and service life cycle management. At present, the level of 5G network OAM automation of is low, most of which rely on program-solidified expert rules and automatic scheduling flows. In some scenarios, the 5G network OAM still need to rely on manual operations. Network OAM automation based on intelligent means is still “fragmented” and “plug-in”. “Fragmented” refers to a use-case driven approach to achieve a higher degree of automation and less manual intervention for certain functions, for example, base station self-starting in SON, neighborhood relationship self-optimization, PCI self-optimization, MRO, etc. “Plug-in” refers to the collection and summary of relevant data to the network management or related platform for training, and the model is sent to the corresponding network element to generate the intelligence required for OAM. This “chimney-type” automated system and R&D model can enhance the automation level of network management to a certain extent under the existing network structure, but due to the limitations of the existing network structure, the difficulty of ensuring the validity and real-time nature of data, and the difficulty of interoperability and sharing of data between different vendors, , the efficiency of network automation is low and the effect is difficult to meet expectations.
In the future, the 6G network will construct a brand-new automated network OAM system through the network digital twin, and realize the high-level “autonomy” of the whole network life cycle. The digital twin network is a network system consisting of physical network entities and their twin digital networks that can be mapped in real time. The digital twin entity of the network is the dynamic modeling or mirror copy in digital space of the real network entity. The digital domain generates perceptual and cognitive intelligence through rich historical and real-time data as well as advanced algorithmic models. It can continuously optimize and simulate the optimal state of physical networks, issue the corresponding OAM operations in advance, correct the physical network automatically, and solve the network element or network fault in advance to achieve the effect of “cure future disease”. Then it can form a closed loop through the collection of corrected data to evaluate the operation and maintenance results. Through this closed-loop interaction between digital and physical domains, cognitive intelligence, and automatic OAM operations, networks can quickly recognize and adapt to complex and dynamic environments, and realize the “autonomy” of planning, building, maintaining, optimizing and curing the whole life cycle of the network.
China Mobile’s “Digital Twin Network (DTN) White Paper”, released in September by 2021, sets out the concept and definition of “Digital Twin Network (DTN)”, and gives the reference architecture of DTN, key enabling technologies, the capability classification system and typical application scenarios [1]. On the basis of this, this paper further researches and explores the digital twin network for 6G wireless network autonomy, introduces the related basic concepts of 6G wireless network autonomy, clarifies the technical features, designs the network architecture, plans the key technology system, and illustrates the whole lifecycle autonomy of 6G wireless networks based on digital twin networks through specific case studies. Finally, the key technical problems which need to be further studied and solved are put forward.