XLXiang Li

Xiang Li

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xiang Li has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • AI-Native Management and Orchestration in O-RAN: Enabling the Path to Intelligent 6G Automation

    by Ting Li, Qi Sun, Jinri Huang, Yang Wang, Xiang Li, Nan Li, Chih-Lin I

    On the path toward 6G, three trends, including radio access networks (RANs) cloudification, the convergence of communication and computing, as well as the adoption of artificial intelligence (AI), are reshaping the landscape of management and orchestration (M&O) for RAN. The RAN M&O should evolve itself to accommodate the requirements of the trend with intelligent automation for 6G. Toward this end, O-RAN has pioneered at this front with its proposed M&O framework called service management and orchestration (SMO). Building upon O-RAN, this paper further proposed an AI-native RAN SMO framework with the capability to support communication and computing convergence. The effectiveness and the superiority of the proposed framework was demonstrated in a vehicle-to-everything (V2X) scenario. Simulations showed that, thanks to the capability of joint communication and computing resource orchestration from the framework, AI-empowered algorithms could greatly improve the system performance in terms of latency of the computing tasks. In particular, under the arrival rate of 0.4 with a 500-B payload, our approach achieves over 35% latency reduction compared with benchmarks, and the gain increases to about 50% when the payload size varies within [350, 650] B.


  • Enabling Mobile AI Agent in 6G Era: Architecture and Key Technologies

    by Ziqi Chen, Qi Sun, Nan Li, Xiang Li, Yang Wang, Chih-Lin ⅰ

    With the advent of mobile networks, we are witnessing an unprecedented shift in the landscape of mobile network services, evolving from traditional voice calls to advanced AI services. This paper delves into the intricacies of this evolution, particularly emphasizing the deep integration of AI Agents into 6G networks. Despite recent researches in using large language model (LLM) and artificial intelligence (AI) agent for network automation, the fundamental mobile AI agent use cases, their network requirements, potential network architecture and enabling technologies for supporting the pervasive AI agents in 6G ear are largely unexplored. In this article, we present an in-depth analysis of typical mobile AI agent use cases in 6G, consisting of AI agent-based 6G network automation, handheld personalized agents, connected robotics and autonomous systems, and wearable AI agent. Then, we elucidate a novel system architecture that supports identified use cases. The article also addresses core aspects of enabling technologies, including 6G agent and application agent collaboration, efficient model and memory management, coordinated agent-to-agent communication and support of multi-modal data transmission. Finally, two future research directions: security and privacy protection and AI agent tailored communication are discussed. This article lays a foundation for understanding the role of 6G in realizing the full potential of AI agents in various applications.


  • Communication and Computing Integrated RAN: A New Paradigm Shift for Mobile Network

    by Yuhong Huang, Nan Li, Qi Sun, Xiang Li, Jinri Huang, Ziqi Chen, Xiaofei Xu, I Chih-Lin

    The Radio Access Network (RAN) consists of numerous base stations that serve as access points for the end users to communicate with application services. Along with the increasingly powerful computing capability in base stations, and the stringent requirements from new services exemplified by augmented reality (AR) and virtual reality (VR), it is realistic and desirable to leverage the spare computing resource in the base stations to deploy such latency sensitive services. This concept, named Communication and Computing Integrated RAN (CCIR), is proposed in this article. CCIR is aimed to providing communication service and computing service in a holistic manner. This article presents design principles, logical architecture, and key enabling technologies of CCIR. Field trials on the computing resource migration among different base stations are conducted to demonstrate feasibility and effectiveness of CCIR. It is observed that the system performance is improved in terms of spectral efficiency and throughput due to the holistic orchestration and scheduling in CCIR.


  • Communication-Computing Built-in-Design in Next-Generation Radio Access Networks: Architecture and Key Technologies

    by Fengxian Guo, Mugen Peng, Nan Li, Qi Sun, Xiang Li

    The edge computing paradigm presents a promising solution for low-latency and high-throughput data processing, which is critical for future life-changing applications, such as autonomous driving and metaverse. Concurrently, the current radio access network (RAN) is evolving toward virtualization, intelligence, and flexibility, making it an ideal edge computing platform. However, the full potential of such a synergistic system has not yet been unleashed due to the lack of coordination between communication and computing. To better support diverse applications, this article proposes a communication-computing co-design approach for the next-generation RAN to embrace computing in a built-in manner. At a high level, we overview the features of communication and computing, identify the efforts and limitations of the current system, and introduce the designed architecture. From the perspective of communication and computing coordination, key technologies are introduced, including internetworking for computing terminals, traffic steering, and mobility management. A use case referring to mobility management is studied to verify the effectiveness of the built-in approach. We outline some critical challenges, thereby indicating future potential research directions in future RAN.