5G Development: Automation and the Role of Artificial Intelligence

Abstract

5G is expected to be commercially rolled out by 2020 and targets challenging KPI requirements. Due to the increased complexity of the mobile networks, meeting the requirements by the existing manual network operation techniques is infeasible for 5G. Also, the manual daily network operations escalate mobile networks Operation Expenses (OPEX). Without a dramatic increase in OPEX, dealing with the network complexity and meeting the KPIs for each challenging use case is only possible by the realization of autonomous network operation functions. The autonomous networks' components and the intelligent functions are developed with the cutting edge Machine Learning (ML) and Artificial Intelligence (AI) models. Furthermore, to be able to realize the efficient and scalable network automation capabilities, ONAP (Open Network Automation Platform) and OSM (Open Source Management and orchestration) frameworks are proposed for 5G. These frameworks provide a set of plug and play automation functions as well as APIs, which enables the mobile operators to extend the framework capabilities by developing their network automation functions to tackle their individual business and operational challenges. The automated network management and orchestration function, in turn, enables the operators to keep the OPEX to reasonable levels and meet the challenging KPI requirements of 5G. This article as a baseline provides an overview of 4G Long‐Term Evolution (LTE) Self‐Organizing Networks (SON) and presents 5G automation concepts and frameworks. Furthermore, in this article, the prominent 5G automation frameworks namely ONAP and OSM are compared, and evidently, the ONAP framework has enriched network automation functions and stands out as the choice of the majority of the telecommunication industry. Finally, this article summarizes the cutting edges AI models and provides a literature review on AI applications in the scope of mobile network automation.