Toward an AI-Enabled O-RAN-based and SDN/NFV-driven 5G& IoT Network Era

Artificial Intelligent Technology has impacted tremendously in the areas of high performance computing, and network and communicatons industries. The advantages of a system applying AI includes performance improvent, optimization, and intelligent or smart AnFor intelligent fesure of 5G, network slicing, provided by Network equipment vendor by applying AI, softwarization and virtualization technologies to the network. For many other industries and applications such as healthcare, agriculture, finance, have benefited from AI technology in particular machine learning and deep learning within AL.With the integration of AI, 5G, and Inernet of Thngs, the industrial applications, smart farms, precision medicine.,smart city. This article focuses on the System architecture and design of open networking solution of the future of 5G, beyond-5G (B5G) or 6G. Among the challenges of an ON system solution, the propriety of radio access network (RAN) is one of essential challenges. The Open-RAN Alliance is formed through the integration of C-RAN Alliance and X-RAN Forum. The O-RAN Alliance mission’s is converting the radio access network industry to become an open networking intelligent, virtualized, and fully interoperable RAN. To realize B5G or 6G by applying O-RAN architecture and ecosystem is called O-RAN based B5G/6G The Integration of O-RAN based 5G RAN part and the SDN/NFV-based softwarization and virtualization of Core Network, Transport Network and Management functions, we can derive a stage of fully Open Networking architecture for the software (AI/M/DL) developers to work.


Introduction
This paper addresses the fusion of AI, 5G, and IoT and how it impacts the Open Networking (ON) ecosystem to the network & communications industry. The softwarization and virtualization are the goals of SDN and NFV respectively. Indeed SDN/NFV hav00e been applied to solve Telco central office re-architected as a datacenter (CORD) (Peterson et al., 2016;Al-Shabibi et al., n.d.) and flexible optical networks (KingA, D., FarrelA, N., Georgalas N., 2015) since 2015 or earlier. But the radio access network (RAN) part do not play an important role until the integration of C-RAN Alliance and X-RAN Forum to become Open-RAN Alliance (O-RAN).
The remaining of this paper is organized as following; Section 2 describes the concepts of open networking, the open standard-based 5G (O-RAN based . Section 3 addresses the advances of AI, ML, DL and shows the differences between AI-enabled network and AI in network. Before the conclusion, Section 4 describes the new era of ON development for 5G/B5G/6G. Before the conclusion we give an example of AI-enabled network feature by network slicing through virtual elements of virtual network.

Open Networking Trends and 5G
It has been a paradigm shift in the network industry, from a proprietary networking with vendor-dependent soft-ware/hardware to vendor-independent open source and white box switches as illustrated in Figure 1 (CNBC, 2019;Telecomscom, 2019) in September, 2019 and granted an operator license. Right now Rakuten is busy in the deployment of base stations and expect to provide the full coverage on for mobile services in 2021.

SDN/NFV-Based 5G
In this article SDN-Based 5G means 5G network is constructed and deployed by using open source code related to SDN/NFV to do the softwarization & virtualization of 5G (Lin, B. S. P., 2020). The open networking architecture of 5G consists of O-RAN and virtual EPC (core network). O-RAN is an open source radio access network subsystem which separates RRH/RRU (remote radio head/remote radio unit) from BBU (baseband unit) and its core network is an available open source EPC. Figure 3 illustrates the open networking architecture of 5G. This open 5G network architecture creates the opportunity to be multi-vender to avoid lock-into one vender with proprietary solution. Also the separation of ORAN and EPC may create the new eco system of 5G industry.  Figure 4 shows the definition of Internet of Things (IoT) and some examples.Currently, majority of Internet of Things (IoT) of the system applications snd services depend on 5G or 4G/LTE or even 3G as the gateway to send data to the destination for computing and applications generation and execution. Figure 5 illustrates example of wireless sensor network (WSN) which collects data and/or signals from devices and use 4G/LTE and 5G as the gateway to network and services platform for further application creation. Its equivalent 4 Layer Model of IoT is shown in Figure 4(Akyildiz, 2017). The 4 layer model consisits of layer 1: sensing and identification, layer 2: network construction, layer 3: information processing and layer 4: integrated application.

The advances of AI, ML, and DL Technology
Artificial intelligent (AI) is a great technology and applications for which existing solutions require better automation or optimization and there is no good solution by using traditional approaches. So, when people say AI in Network really means using AI techniques to assist network operations, configuration, and management or to play a supporting role. On the other hand, Network with machine learning (ML), deep learning (DL) and other AI techniques used to manage network to be predictive and proactive, then AI/ML/DL becomes the driving force of network operations and management or the enabler of network operations. We call this kind of network is an AI-enabled Network (ATIS, 2018; 5G Americas whitepaper, 2019). AI is also an interdisciplinary science with multiple approaches but the advancements in ML and DL are creating a paradigm shift virtually every sector of the technology industry.
This section discusses the definitions of AI, ML, DL and their relationships and differences. AI is algorithms, programs, coding can make machine, objects and things more intelligence through learning and/or training. ML is a subset of AI while DL is a subset of AI and ML.

AI in Network vs AI-Enabled Network
There are two ways to migrate AI software to the existed system. One way is try to use AI algorithms or techniques to assist the system to become more automation, more optimization, and better service. So, AI in network means what AI can assist network to complete network functions. The other way is using AI/ML/DL techniques to complete the network migration. So, AI-enabled Network means AI driven network operation and management. The characteristics of 3 approach to architect and design the network include: Traditional Networking without AI, AI in Network, AI-enabled Network are (Lin, 2019;Lin et al., 2019;B. S. P. Lin, F. J.Lin.& Tung. 2016;Latah, M. & Toker, L. 2018;Wilson, 2019;Wu et al., n.d. 2019); in the following: 1) Traditional Networking with0out AI/ML/DL: reactive, no intelligence, no optimization, error prone, inefficient 2) AI in Network is: semi-active, partial intelligent, local optimization, semi-automated 3) AI-enabled Network is: proactive, intelligent, global optimization, automated, scalable nct.ccsenet.org Network and Communication Technologies Vol. 6, No. 1;2021

The New Era of ON Development for 5G/B5G/6G
The Figure 8 (Ericsson, 2020) illustrates the mobile communication network architecture consists of access network (radio access network/unit and baseband unit), core network, transport network and management system.

An Example of AI-enabled Network -Network Slicing
AI is playing an important role h how 5G or future networks become sliced, supporting uses including IoT and private 5G networks (Nelson, 2020). Network slicing is a form of virtual network architecture. Using the same principles behind SDN and NFV in fixed network. To deliver greater network flexibility by allowing traditional network architecture to be partitioned into virtual elements. Network slicing allows multiple virtual networks. This allows a network operator to support the numerous and varied services envisaged in 5G. The NGMN Standard has proposed a three categories of network slicing including smartphones, autonomous driving, and massive IoT (and other slices) shown in Figure 12

Conclusion
Through the virtualization and softwarization of 5G RAN, TN, CN, and management of configuration, the multi-vendor solution for Open Networking community is becoming possible. AI-enabled network will take proactive, intelligent, and optimal way to manage or take good care of the network.
The remaining research works to be done include: the interfaces, protocol, and others APIs among virtual O-RAN, virtual (NFV) CN, and virtual (SDN/NFV) Management.