On Enhancing Network Slicing Life-Cycle Through an AI-Native Orchestration Architecture

Legacy experimental network infrastructures can still host innovative services through novel slicing orchestration architectures. Network architectures available in state-of-the-art have building blocks that structurally change depending on the problem they are trying to solve. In these orchestrators, life-cycle functions of slices experience advances numerous fronts, such as combinatorial methods and Artificial Intelligence (AI). However, many not AI-native, making heterogeneity coexistence use machine learning paradigms for hard. Also, using AI a non-native way makes slice management challenger shallow. Hence, this paper proposes evaluates distributed AI-native architecture delivers capabilities all life cycles slice. Carried experiments suggest lower error models predict Radio Access (RAN) resource consumption deployed over different target domains.