Artificial Intelligence in Open-Radio Access Network
Paul H. Masur, Jeffrey H. Reed, Nishith Tripathi
Abstract
This article outlines the proposed open-radio access network (O-RAN) deployment for fifth-generation (5G) wireless networks. O-RAN seeks to supplant hardware-specific radio access network (RAN) components with generic hardware, specialized software, and open signaling interfaces. The virtualization and network slicing features of 5G allow for software to replace previously hardware-specific functions. The software further provides faster analytics, thus supporting 5G's latency requirements and advanced usage scenarios (i.e., enhanced mobile broadband, massive machine type communications, and ultra-reliable low latency communications). Furthermore, as software annexes control of the RAN, there is the freedom to integrate artificial intelligence/machine learning algorithms into RAN management (particularly at the user plane). This integration is one of the goals of O-RAN. Finally, relying on generic hardware and specialized, open-source software eliminates reliance upon specific device manufacturers. This article will provide questions regarding O-RAN's future, with a focus on 5G network device security.