Programmable and Customized Intelligence for Traffic Steering in 5G Networks Using Open RAN Architectures

Abstract

5G and beyond mobile networks will support heterogeneous use cases at an unprecedented scale, thus demanding automated control and optimization of network functionalities customized to the needs of individual users. Such fine-grained control of the Radio Access Network (RAN) is not possible with the current cellular architecture. To fill this gap, the Open RAN paradigm and its specification introduce an "open" architecture with abstractions that enable closed-loop control and provide data-driven, and intelligent optimization of the RAN at the userlevel. This is obtained through custom RAN control applications (i.e., xApps) deployed on near-real-time RAN Intelligent Controller (near-RT RIC) at the edge of the network. Despite these premises, as of today the research community lacks a sandbox to build data-driven xApps, and create large-scale datasets for effective Artificial Intelligence (AI) training. In this paper, we address this by introducing ns-O-RAN, a software framework that integrates a real-world, production-grade near-RT RIC with a 3GPP-based simulated environment on ns-3, enabling at the same time the development of xApps and automated large-scale data collection and testing of Deep Reinforcement Learning (DRL)driven control policies for the optimization at the user-level. In addition, we propose the first user-specific O-RAN Traffic Steering (TS) intelligent handover framework. It uses Random Ensemble Mixture (REM), a Conservative Q-learning (CQL) algorithm, combined with a state-ofthe-art Convolutional Neural Network (CNN) architecture, to optimally assign a serving base station to each user in the network. Our TS xApp, trained with more than 40 million data points collected by ns-O-RAN, runs on the near-RT RIC and controls the ns-O-RAN base stations. We evaluate the performance on a large-scale deployment with up to 126 users with 8 base stations, showing that the xApp-based handover improves throughput and spectral efficiency by an average of 50% over traditional handover heuristics, with less mobility overhead.

Sparsity-Aware Intelligent Massive Random Access Control in Open RAN: A Reinforcement Learning Based Approach

“…If the variance is large, it implies that the users in some of the low-priority classes are hardly permitted to access the network, which is not a favorable decision especially for mMTC services with massive users of different priority scores required to access. Thus, the agent can guide the algorithm to learn a policy favorable for massive access control in mMTC services by setting a positive value of the coefficient ρ 1 in the utility function (4).…”

“…The values of the Q-table are updated after each time slot t using the Bellman equation as given by (5) where ̟ and β represent the learning rate and the discount rate, respectively. The update of the Q-table is driven by the system utility function u t as given in (4).…”

“…Mohsen Guizani is with Mohamed Bin Zayed University of Artificial Intelligence, United Arab Emirates (E-mail: mguizani@ieee.org). (Corresponding Author: Sicong Liu) for different scenarios to achieve quality of service (QoS) optimization [3], [4]. It is required by various applications and services, especially mMTC services, that the access of high density and large-scale devices (10 2 /km 2 to 10 7 /km 2 ) to the RAN should be supported, which brings great challenge to random access management [5], [6].…”

Implementação de Estratégias de Handover em um Ambiente de Simulação para Open RAN

“…Também fornece informac ¸ões de enriquecimento, modelos e gerenciamento de modelos de IA/ML para o near-RT RIC, que, por sua vez, retroalimenta o non-RT RIC com informac ¸ões relacionadas às políticas implantadas. O non-RT RIC, portanto, serve como uma plataforma de software para rApps e para a otimizac ¸ão de alto nível da RAN, no que concerne a gerenciamento e controle da rede de acesso via rádio [Dryjański et al 2021, Lacava et al 2022.…”

OpenCare5G: O-RAN in Private Network for Digital Health Applications

“…Called the OpenCare5G Project [ 4 ], it is a highly innovative initiative to study and test healthcare applications in the construction of the first 5G private network. The Open Radio Access Network (O-RAN) utilizes the O-RAN 5G concept [ 3 , 5 , 6 , 7 , 8 , 9 , 10 , 11 , 12 ] to transport health data and to help in the analysis of medical exams by health professionals using local and remote hospital portable devices and equipment.…”