5G system and beyond targets a large number of emerging applications and services that will create extra overhead on network traffic. These industrial verticals have aggressive, contentious, and conflicting requirements that make the network have an arduous mission for achieving the desired objectives. It is expected to get requirements with close to zero time latency, high data rate, and network reliability. Fortunately, a ray of hope comes shining the way of telecom providers with the new progress and achievements in machine learning, cloud computing, micro-services, and the ETSI ZSM era. For this reason there is a colossal impetus from industry and academia toward applying these techniques by creating a new concept called CCN environment that can cohabit and adapt according to the network and resource state, and perceived KPIs. In this article, we pursue the aforementioned concept by providing a unified hierarchical closed-loop network and service management framework that can meet the desired objectives. We propose a cloud-na-tive simulator that accurately mimics cloud-native environments, and enables us to quickly evaluate new frameworks and ideas. The simulation results demonstrate the efficiency of our simulator for parroting the real testbeds in various metrics.

中文翻译：

---

超越5G云原生环境中基于AI的资源管理


5G 系统及更高版本的目标是大量新兴应用和服务，这将给网络流量带来额外的开销。这些工业垂直领域具有积极的、有争议的和相互冲突的要求，使得网络在实现预期目标方面肩负着艰巨的使命。预计会得到接近零时延、高数据速率和网络可靠性的要求。值得庆幸的是，机器学习、云计算、微服务、ETSI ZSM时代的新进展和成果，给电信运营商的前进之路带来了一线希望。因此，工业界和学术界通过创建一个称为 CCN 环境的新概念来应用这些技术，该环境可以根据网络和资源状态以及感知的 KPI 共存和适应。在本文中，我们通过提供能够满足预期目标的统一分层闭环网络和服务管理框架来追求上述概念。我们提出了一个云原生模拟器，它可以准确地模拟云原生环境，并使我们能够快速评估新的框架和想法。模拟结果证明了我们的模拟器在各种指标上模仿真实测试台的效率。