Xi Li's research while affiliated with NEC Laboratories Europe and other places

Publications (34)

Preprint
Battery life for collaborative robotics scenarios is a key challenge limiting operational uses and deployment in real life. Mission-Critical tasks are among the most relevant and challenging scenarios. As multiple and heterogeneous on-board sensors are required to explore unknown environments in simultaneous localization and mapping (SLAM) tasks, b...
Chapter
Meeting 5G high bandwidth rates, ultra-low latencies, and high reliabilities requires of network infrastructures that automatically increase/decrease the resources based on their customers' demand. An autonomous and dynamic management of a 5G network infrastructure represents a challenge, as any solution must account for the radio access network, d...
Article
This paper proposes a dynamic pricing and revenue-driven service federation strategy based on a Deep Q-Network (DQN) to instantly and automatically decide federation across different service provider domains, each introduces dynamic service prices offering to its customers and towards other domains. A dynamic pricing model is considered in this wor...
Article
Empowered by network softwarization, 5G systems have become the key enabler to foster the digital transformation of the vertical industries by expanding the scope of traditional mobile networks and enriching the network service offerings. To make this a reality, we propose an automation solution for vertical services provisioning and hierarchical S...
Article
Full-text available
Private 5G networks has become a popular choice of various vertical industries to build dedicated and secure wireless networks in industry environments to deploy their services with enhanced service flexibility and device connectivity to foster industry digitalization. This article proposes multiple multi-domain solutions to deploy private 5G netwo...
Article
Full-text available
5G is playing a paramount role in the digital transformation of the industrial sector, offering high-bandwidth, reliable, and low-latency wireless connectivity to meet the stringent and critical performance requirements of manufacturing processes. This work analyzes the applicability of 5G technologies as key enablers to support, enhance, and even...
Technical Report
Full-text available
This white paper on AI and ML as enablers of beyond 5G (B5G) networks is based on contributions from 5G PPP projects that research, implement and validate 5G and B5G network systems. The white paper introduces the main relevant mechanisms in Artificial Intelligence (AI) and Machine Learning (ML), currently investigated and exploited for 5G and B5G...
Article
Full-text available
This article introduces the key innovations of the 5Growth service platform to empower vertical industries with an AI-driven automated 5G end-to-end slicing solution that allows industries to achieve their service requirements. Specifically, we present multiple vertical pilots (Industry 4.0, transportation, and energy), identify the key 5G requirem...
Article
This article presents a system for 5G networks that makes it possible to meet the diverse needs of vertical industries simultaneously sharing the same physical infrastructure. Orchestration, network slicing, edge computing, and federation are key technologies enabling industry verticals to have their own virtual networks, which might require aggreg...
Article
The 5G-Transformer (5GT) project proposes a network function virtualization (NFV)-/software-defined networking (SDN)-based architecture to manage the end-to-end (E2E) deployment of composite NFV network services (NSs), which may involve multiple administrative domains (ADs), and hence require NS federation (NSF) capabilities. At the architectural l...
Conference Paper
This paper presents the design of the 5GT Service Orchestrator (SO), which is one of the key components of the 5G-TRANSFORMER (5GT) system for the deployment of vertical services. Depending on the requests from verticals, the 5GT-SO offers service or resource orchestration and federation. These functions include all tasks related to coordinating an...
Article
Network densification over space and spectrum is expected to be key to enabling the requirements of next generation mobile systems. The pitfall is that radio resource allocation becomes substantially more complex. In this paper we propose LaSR, a practical multi-connectivity scheduler for OFDMA-based multi-RAT systems. LaSR makes optimal discrete c...
Chapter
Network slicing for 5G allows mobile network operators (MNOs) to open their physical network infrastructure platform to the concurrent deployment of multiple logical self‐contained networks, orchestrated in different ways according to their specific service requirements. The end goal of network slicing in 5G mobile networks is to be able to realize...
Article
This article dives into the design of the next generation mobile transport networks to simultaneously support the needs of various vertical industries with diverse range of networking and computing requirements. Network slicing has emerged as the most promising approach to address this challenge by enabling per-slice management of virtualized resou...
Article
Full-text available
Cloud Radio Access Network (C-RAN) will become a main building block for 5G. However, the stringent requirements of current fronthaul solutions hinder its large-scale deployment. In order to introduce C-RAN widely in 5G, the next generation fronthaul \agsrev{interface} (NGFI) will be based on a cost-efficient packet-based network with higher path d...
Article
5G requires a redesign of transport networks in order to feed the increasingly bandwidth hungry radio access networks and to benefit from the performance/cost efficiency provided by the integration of both backhaul and fronthaul segments over the same transport substrate as well as the incorporation of cloud RAN architectures. In addition, to incre...
Article
This article proposes an innovative architecture design for a 5G transport solution (dubbed 5G-Crosshaul) targeting the integration of existing and new fronthaul and backhaul technologies and interfaces. At the heart of the proposed design lie an SDN/NFV-based management and orchestration entity (XCI), and an Ethernet-based packet forwarding entity...
Article
This paper presents the control and data plane architecture design for a 5G transport solution (5G-Crosshaul) with the aim of integrating the fronthaul and backhaul network segments in a common transport stratum. The control plane relies on the Software-defined networking/Network Functions Virtualization concept to control and orchestrate the diffe...
Conference Paper
A transport network for 5G envisions integrating the fronthaul and backhaul segments (namely 5G-Crosshaul) into a single transport network. This requires a fully integrated and unified management of fronthaul and backhaul resources in a sharable, scalable and flexible way. The integrated and unified management of the transport network resources fol...

Citations

... The concept of network identifying problems by itself and fixing them and only sending technicians to the failure site only when there are single-point of hardware failures (i.e. there is no hardware redundancy) is not practiced [5,6]. Tools for self-managed networks are not developed either. ...
... Such an approach enables the automation and softwarization of the service provisioning process. For example, in [15], authors propose an automation solution for ...
... Under the umbrella of the 5G-Public-Private-Partnership (5G-PPP) and the European Research Council (ERC), the European networking community has been focusing on how 5G and beyond 5G architectures can support the Industry 4.0. 5G-DIVE [8] and 5Growth [9], are two examples of platforms that manage the adequate resource provisioning and allocation of services like remote control in Industry 4.0. More recent European research projects [10] as Daemon [11] and Hexa-X [12] also provide support to Industry 4.0 applications by bringing intelligence to the network in order to meet strict constraints as reliability. ...
... The deployment of 5G networks mainly includes two parts: the radio access network (RAN) and the core network (Zhu and Xiang, 2016;Wang et al., 2017). Currently, 5G network deployment methods can be roughly divided into five categories: enterprise self-built, licensed spectrum, shared base station, unique user plane management (UPF)/MEC, and network slicing (Ahmad, 2019;Li et al., 2021). In order to meet the needs of communication networks and reduce construction costs, different deployment and construction plans are proposed according to the actual situation. ...
... Other approaches such as Support Vector Machine (SVM), or Bayesian sequential testing require human intervention that may be, given the limited intuition, flawed, and erroneous. Furthermore, DNN units are also expected to be part of the communication devices as they are the cornerstone of many solutions for different communication problems such as slice management and anomaly detection [31]. Therefore, a DNN-based NLoS identifier appears to be a reasonable choice. ...
... 5G-TRANSFORMER (2017-2020) [41] E-health, media, and entertainment, automotive , NS design and organization Create a 5G network architecture centered on SDN/NFV that tailored to certain vertical sectors. 5GMobix (2018-2021) [42] Associated and autonomous driving ...
... According to this 5Growth architecture, which is based on the European Telecommunications Standards Institute (ETSI) NFV architecture and specifications, the AIMLP performs model training, while other building blocks, e.g. VS, SO or RL are responsible for the ML inference tasks [32]. For AI/ML activities, 5Growth stack components rely on (i) the available VoMS, which is the block of the 5Growth architecture in charge of collecting monitoring data from deployed network services and NFV infrastructure (NFVI); and (ii) the integrated data engineering pipeline in charge of data ingestion, data processing, analysis, visualization, and data management. ...
... However, no concrete algorithms for VNF deployment or routing mapping were proposed. Also, some studies such as [Baranda 2020, Valcarenghi 2018 discuss the challenges associated with incorporating trust into multi-administrative domains. ...
... However, the deployment used for experiments does not include the WAN (i.e., inter-DC) network scenario [47] or does not reproduce realistic cloud and network deployments [48][49] since making use of emulation platforms at data plane level, e.g., Mininet. On the other hand, some experimental initiatives have tackled the deployment and the management of vertical services that may span multiple provider domains [50] [51]. However, in these works, neither latency-awareness features nor end-to-end monitoring to guarantee reliability are addressed for established service chains. ...
... Nevertheless, an accurate placement strategy demands for proactive resource allocation in order to decide optimal amount of computing, memory and storage resources to support the provisioning of various robotic applications, both onto the robots and edge/cloud platforms. The 5G orchestrator can be built relying on existing open source orchestrator platforms such as Open Source MANO (OSM) or leveraging on opensource orchestration platforms developed for instance in [24] [25]. From a system architecture perspective, the 5G orchestrator consists of three layers: service layer, orchestration layer and resource layer. ...