|
|
What is CENTRIC?The CENTRIC European project aims to leverage Artificial Intelligence techniques through a top-down, modular approach to wireless connectivity that puts the users’ communication needs and environmental constraints at the center of requirements for the wireless network communications protocol stack design. The CENTRIC project is designing a user-centric AI Air Interface (AI-AI) applying the AI techniques to create and customize tailor-made waveforms, dynamically configure transceivers, and enable appropriate signaling and medium access protocols to support these requirements. The results of CENTRIC will be validated and demonstrated in laboratory prototypes and its breakthroughs will enable future 6G use-cases, such as self-driving vehicles, the internet of nano bio-things, or multi-sensory holographic communications. PROJECT VISIONCENTRIC positions the AI-AI as the essential fabric of future wireless connectivity systems, for benefit of mobile network operators and the private network’s market, which will profit from highly customizable systems wherein different customers have entirely distinct personalized needs. For instance, a university campus is unlikely to have the same connectivity requirements as an indoor smart factory as well as new and radically different communication needs will emerge in the near future. Addressing them with a traditional multi-purpose wireless networks would significantly limit the scope of future applications, and potentially prevent many cutting-edge inventions from fulfilling their potential. The CENTRIC aims at being “future-proof,” endowing the networks of tomorrow with the AI tools to support a range of new applications. CENTRIC will explore and deliver AI-based breakthroughs in some of the most pressing 6G Radio Resource Management (RRM) areas, such as sustainable data management at the wireless edge, Electro-Magnetic Field (EMF) exposure control in novel network architectures and energy savings, seamless interoperability among services and applications, etc. PROJECT OBJECTIVES
• Objective 1 – To develop AI methods for the discovery of novel and efficient waveforms - Machine Learning (ML) techniques that enable the discovery and optimization of tailor-made waveforms - targeting the user communication needs while accounting the radio-front and computing hardware limitations as well as the propagation environment
• Objective 2 – To develop AI methods for the discovery of novel and efficient transceivers - Efficient AI-based transceivers for two particularly challenging use-cases: large-scale extreme massive multiple-input multiple-output (MIMO) deployments - beam-based communications in millimeter-wave (mmWave) spectrum
• Objective 3 – To develop AI methods for the discovery of customized lightweight communication protocols Learning-to-communicate (L2C) techniques based on multi-agent reinforcement learning (MARL), semantic communications, and edge control/caching.
• Objective 4 – To introduce novel end-to-end hardware co-design solutions for energy-efficient AI-native transceivers CENTRIC will explore, design and validate AI accelerators that are based on both standard digital technology and emerging mixed-analog digital platforms based on non-volatile memory elements.
• Objective 5 – To develop training and monitoring environments as enablers for AI-AI deployments - tools for network designers and operators to deploy, train, and monitor AI models - general CENTRIC framework based on digital twins (DT), which encompasses cloud-based agents running networked AI models of physical agent counterparts
• Objective 6 – To validate user-centric AI-AI solutions in a lab setting CENTRIC will define novel testing and benchmarking frameworks for user-centric AI-based communications.
• Objective 7 – To demonstrate and disseminate AI-AI concepts Laboratory proof-of-concept (PoC) implementations to validate the expected gains and shed light on the feasibility and cost of the AI-AI implementation.
|
The ETSI Research Conference was celebrated at ETSI premises in Sophia-Antipolis, France, between 6th and 8th of February 2023. The project CENTRIC was represented in the conference by Technical Project Manager (TPM) Carles Navarro Manchón, from Aalborg University. 6th & 8th of February 2023 The purpose of the conference was to bring together the research community with industry representatives and standardization experts to discuss future technology research and links to standardization developments. The timing of the conference coincided with the Smart Networks and Services Joint Undertaking (SNS-JU) launch of its first phase of 5G and 6G research projects at the beginning of 2023, hence providing an excellent platform for many of the new projects to present their plans and exchange views with standards experts on future standardization roadmaps. During the conference, guidance to researchers on how to facilitate the integration of their research outcomes into commercial system standards was provided. It was emphasized that early involvement with standardization bodies even in the pre-standardization phase of 6G was key to streamline such a process. Multiple tips and tools to tailor project outcomes to standardization were provided, as well as sharing of success stories from previous research projects and programmes. Furthermore, most of the granted projects in Phase 1 of the SNS-JU had a chance to present their research and standardization plans for the coming 3 years, delineating and overview of the most popular research trends to be expected in the near future. Topics such as the integration of non-terrestrial networks in 5G and 6G, the exploitation of sub-THz and THz frequency spectrum, security aspects and, of course, artificial intelligence (AI) were clearly dominant among the granted projects. The CENTRIC project and its standardization plans were presented by CENTRIC’s TPM in the morning of the 8th of February, in a session together with the following Stream B projects: 6G-TANDEM, 6G-NTN, 6G-SHINE, ETHER, SPERIOT, TERRAMETA and TIMES. During the session, Carles outlined the technological outcomes from CENTRIC that are expected to impact standardization, such as: The design of signalling and interfaces to enable AI training and monitoring The development of testing and validation frameworks for AI-based wireless networks components The definition and evaluation of baseline AI-based algorithms (e.g., for CSI enhancement, beam management, etc.) In the short term, CENTRIC will primarily target 5G-Advanced standardization of Rel. 18 at 3GPP, where the introduction of AI in the air interface is currently being studied. On a longer term basis, the project will focus on pre-standardization activities for 6G, such as participation in ETSI Industry Specification Groups, where some of the CENTRIC partners are already highly active.
|
• L. Herman dos Santos, C. J.aca-Rubio, R. Kotaba, Y. Song, T. Abrao, P. Popovski. "EMF Exposure Mitigation in RIS-Assisted Multi-Beam Communications", 2023 IEEE Global Communications Conference - arXiv:2305.05229v2 [eess.SP] 11 May 2023
• L. Herman dos Santos, C. J.aca-Rubio, R. Kotaba, Y. Song, T. Abrao, P. Popovski. "OnRMap: An Online Radio Mapping Approach for Large Intelligent Surfaces", IEEE International Conference on Communications 2023: Workshop on Near-Field Localization and Communication for 6G,
• M. Zecchin, S. Park, O. Simeone, M. Kountouris, D.Gesbert. "Robust PAC $^ m $: Training Ensemble Models Under Model Misspecification and Outliers." arXiv preprint arXiv:2203.01859. March 2022
• M. Zhu, C. Feng, C. Guo, Z. Liu, N. Jiang, and O. Simeone, ``Information Bottleneck-Inspired Type Based Multiple Access for Remote Estimation in IoT Systems,'' IEEE Signal Processing Letters, vol. 30, pp. 403-407, April 2023.
• K. M. Cohen, S. Park, O. Simeone, P. Popovski, and S. Shamai, ``Guaranteed Dynamic Scheduling of Ultra-Reliable Low-Latency Traffic via Conformal Prediction,'' IEEE Signal Processing Letters, vol. 30, pp. 473-477, May 2023.
• T. Raviv, S. Park, O. Simeone, and N. Shlezinger, ``Modular Model-Based Bayesian Learning for Uncertainty-Aware and Reliable Deep MIMO Receivers,'' in Proc. IEEE International Conference on Communications, 28 May – 1 June 2023, Rome, Italy.
• Malandrino, F., Di Giacomo, G., Karamzade, A., Levorato, M., & Chiasserini, C. F. (2022). Matching DNN Compression and Cooperative Training with Resources and Data Availability. ArXiv. /abs/2212.02304
• M. Krouka, A. Elgabli, C. B. Issaid and M. Bennis, "Communication-Efficient Second-Order Newton-Type Approach for Decentralized Learning," 2023 IEEE Wireless Communications and Networking Conference (WCNC), Glasgow, United Kingdom, 2023, pp. 1-7, doi: 10.1109/WCNC55385.2023.10118646.
• S. Mostafa, M. Bennis, M. K. Abdel-Aziz. "Cooperative Navigation via Relational Graphs and State Abstraction", IEEE Networking Letters - Journal - June 6, 2023
• A. Ghalkha, C. Ben Issaid, A. Elgabli, M. Bennis. DIN: A Decentralized Inexact Newton Algorithm for Consensus Optimization, IEEE International Conference on Communications, Sustainable Communications for Renaissance - Rome, Italy, 28 May – 01 June 2023
|
Eurescom coordinates European project for new 6G network stack design Eurescom joins forces with eleven more organizations to implement CENTRIC – a project funded by Smart Networks and Services Joint Undertaking (SNS JU) under Horizon Europe. The project performs research and innovation in the area of 6G network stack design. June 6, 2023 Heidelberg, Germany – Eurescom GmbH, a leading European provider of project management services for research and development in the information and communications technologies sector, announced the company joined forces with eleven more organisations to implement CENTRIC, a project that investigates new 6G network stack design. As part of CENTRIC, Eurescom acts as the project coordinator. Funded by Horizon Europe, CENTRIC is one of 35 new projects launched by Smart Networks and Services Joint Undertaking (SNS JU), which the European Commission (EC) established in 2021 to support the development of smart communication components, systems, and networks considered essential in building out a first-class European supply chain for advanced 5G and 6G technologies. The project aims to leverage artificial intelligence techniques through a top-down, modular approach to wireless connectivity, putting the users’ communication needs and the environmental constraints at the centre of the network stack design. The results will be validated and demonstrated in the context of future 6G use cases, such as multi-sensory holographic communications, and self-operated vehicles. “Eurescom is pleased to partner with leading vendors, research institutes and universities to drive a key EC-funded research and innovation project that aims to promote user-centric communication services, by achieving break-throughs in energy efficient user equipment and cellular networks as well as lowering exposure to electromagnetic fields in future radio systems”, said Dr. Halid Hrasnica from Eurescom and CENTRIC project coordinator. “User-centricity is of paramount importance to realise future mobile telecommunication services that are accepted by all members of society and business.”
|
About Eurescom GmbHEurescom is a leading European provider of management and support services in the high-tech area, with a focus on information and communications technologies. Eurescom’s mission is to enable innovation through collaboration. The company has over three decades of experience managing multinational collaborative R&D projects, programmes, and initiatives in the ICT sector. The services of Eurescom include launching, managing and supporting international research and development programmes and projects as well as providing the administrative infrastructure for technology initiatives.
|
You are welcome to forward this mail to other people you think might be interested! To not miss out any news about the CENTRIC project and its partners, follow us on social media:
|
CENTRIC-SNS project has received funding from the European Horizon Europe Programme for research, technological development and demonstration under grant agreement 101096379.
|
This mail has been generated from mailing lists of registered interested people and sent by MailPoet under the General Data Protection Regulation of the EU, learn more about our DPD.
|
|
|
|
|