Softwarization, programmable network control and the use of all-encompassing controllers acting at different timescales are heralded as the key drivers for the evolution to next-generation cellular networks. These technologies have fostered newly designed intelligent data-driven solutions for managing large sets of diverse cellular functionalities, basically impossible to implement in traditionally closed cellular architectures. Despite the evident interest of industry on Artificial Intelligence (AI) and Machine Learning (ML) solutions for closed-loop control of the Radio Access Network (RAN), and several research works in the field, their design is far from mainstream, and it is still a sophisticated and often overlooked operation. In this paper, we discuss how to design AI/ML solutions for the intelligent closed-loop control of the Open RAN, providing guidelines and insights based on exemplary solutions with high-performance record. We then show how to embed these solutions into xApps instantiated on the O-RAN near-real-time RAN Intelligent Controller (RIC) through OpenRAN Gym, the first publicly available toolbox for data-driven O-RAN experimentation at scale. We showcase a use case of an xApp developed with OpenRAN Gym and tested on a cellular network with 7 base stations and 42 users deployed on the Colosseum wireless network emulator. Our demonstration shows the high degree of flexibility of the OpenRAN Gym-based xApp development environment, which is independent of deployment scenarios and traffic demand.
翻译:尽管工业界对无线电接入网络(RAN)的人工智能(AI)和机器学习(ML)的闭路控制(ML)解决方案有明显的兴趣,而且在实地开展了一些研究工作,但其设计离主流还很远,而且仍是一个复杂且经常被忽视的操作。在本文中,我们讨论如何为开放RAN的智能闭路控制设计AI/ML解决方案,以提供基于具有高性能记录的示范性解决方案的指南和洞察力。我们然后展示如何将这些解决方案嵌入O-RAN的近实时RAN智能控制(RIC)和机器学习(ML)解决方案,通过O-RAN的开关控制(RAN Intellicental Contractor),通过O-RAN Gym,这是数据驱动的 O-RAN 实验的首个公开工具箱,而且经常被忽视。在本文中,我们讨论了如何设计以智能闭路路径控制对开放RAN的远程网络进行智能测试,在比例上,我们用已部署的OrampA A型网络展示了我们所部署的高环境。