Bring Reinforcement-learning Into Radio Light Network for Massive Connections

Informacje na temat projektu

6G BRAINS

Identyfikator umowy o grant: 101017226

DOI

10.3030/101017226

Projekt został zamknięty

Data podpisania przez KE 8 Grudnia 2020

Data rozpoczęcia 1 Stycznia 2021

Data zakończenia 31 Grudnia 2023

Finansowanie w ramach

• INDUSTRIAL LEADERSHIP - Leadership in enabling and industrial technologies - Information and Communication Technologies (ICT)

Koszt całkowity

€ 5 671 971,25

Wkład UE

€ 5 671 971,25

Koordynowany przez

EURESCOM-EUROPEAN INSTITUTE FOR RESEARCH AND STRATEGIC STUDIES IN TELECOMMUNICATIONS GMBH
Germany

Periodic Reporting for period 2 - 6G BRAINS (Bring Reinforcement-learning Into Radio Light Network for Massive Connections)

Okres sprawozdawczy: 2022-07-01 do 2023-12-31

Podsumowanie kontekstu i ogólnych celów projektu

Ubiquitous smart wireless connectivity is critical for future large-scale industrial tasks, services, assets and devices. Very significantly improved connectivity needs to be unlocked through novel spectrum combinations and the fully autonomous management of the underlying network resources by applying online Artificial Intelligence (AI) at multiple decision layers.
6G BRAINS aims to bring AI-driven multi-agent deep reinforcement learning (DRL) to perform resource allocation over and beyond massive machine-type communications with new spectrum links including THz and optical wireless communications to enhance the performance with regard to capacity, reliability and latency for future industrial networks.
6G BRAINS will deliver a novel comprehensive cross-layer DRL driven resource allocation solution to support the massive connections over device-to-device (D2D) assisted highly dynamic cell-free network enabled by Sub-6 GHz/mmWave/THz/OWC and high resolution 3D Simultaneous Localization And Mapping (SLAM) of up to 1 mm accuracy. The enabling technologies in 6G BRAINS focus on four major aspects:
- Enhanced new spectrum links: OWC and THz
- AI-driven D2D cell free network architecture for highly dynamic and ultra-dense connectivity
- AI-based end-to-end directional network slicing with guaranteed QoS over highly dynamic networks
- AI-driven data fusion for 3D indoor position mapping through heterogeneous location methods enabling 1 mm location position accuracy and 1° orientation accuracy.
The proposed solution will be validated by proof-of-concept trials. The primary and secondary applications of THz and OWC technologies for a very broad spectrum of scenarios will be evaluated at BOSCH’s self-contained smart factory. The developed technologies will be widely applicable to various vertical sectors such as Industry 4.0 intelligent transportation, eHealth and others. In particular, new business opportunities emerging in 6G BRAINS will be identified for follow-up exploitation activities. The results of 6G BRAINS are expected to create a solid basis for future projects and global standardisation for B5G and 6G technologies in areas relevant to industrial environments.

Prace wykonane od początku projektu do końca okresu sprawozdawczego oraz najważniejsze dotychczasowe rezultaty

The project delivered the following innovations:
Multi-agent Deep Reinforcement Learning Scheme Specifications, Workflows and how to apply to:
- General modelling of the mobile network
- RAN Scheduler
- Joint-Slicing Scheduler
- AI driven cell-free Scheduler with IAB
- D2D Clustering Control

3D Laser measurement at a factory with 3D cloud scanner and 3D hand scanner
- Obtained a raytracing model that allows simulations with spatial consistency over different bands, providing an accurate geometrical representation of the environment from the propagation properties for precise localization applications.

Specifications and Upgrade of Multiband Channel Sounder for Quad-Band Measurements at Sub-6 GHz + mmWave + THz + OWC in Industry Scenarios
- Used for validation and calibration of the obtained ray tracing model

Design of an Artificial Intelligence (AI) based scheduler for Cell-Free (CF) Networks with Integrated Access and Backhaul (IAB) and intelligent beam steering
- ultra-dense dynamic CF Network includes a cluster of Device to Device (D2D) User terminals (UE) and human-centric control interfaces

E2E Network Slicing Control Enablers
- Design and prototyping of enabling technologies for E2E network slicing across RAN and Core network segments
- Algorithm design of AI-based radio link control and RAN slice scheduler
- Integration aspects of Management-Orchestration and Cognitive Plane

Prototype platform for DRL

Enablers for 3D localisation
- 3D Localisation and Mapping
- Sensor fusion operations using Location Database (LD) Location Server (LS) and a Deep Reinforcement Learning (DRL) application to improve location accuracy
- Integration of Blockchain Location Ledger technologies for sharing position data

Furthermore the project key achievements are:
Description of use cases enabled by 6G BRAINS

Consolidated list of requirements for 6G primary use cases

Definition of logical and functional architecture; definition of major components; description of functional workflows
- Architecture separation in several planes

Proof of concept KPI/performance measurement setup and test cases for primary use cases

Specification of localisation architecture; design of three main means of distance estimation
- ToA using mmWaves uplink transmissions,
- RSS using OWC downlink transmissions
- AoA using mmWave transmissions from a Digital Twin model of the environment coverage area

Techno-economic analysis of the main market needs and their functional and technical requirements of three types of 5G/6G Use Cases
- Industry 4.0 Smart Agriculture, and Smart Transportation/Aviation
- Provide guidance for future 6G BRAINS research and innovation activities

Dissemination, communication, exploitation
- Scientific publications at conferences journals, etc.
- 6G Architecture Workshop accepted at Globecom 2022
- Active engagement in 5G PPP bodies and work groups, Pre-Standardisation, 5G Architecture, Software Networks, Vision and Societal Challenges, SME, Trials, Test, Measurement and KPIs Validation (Contributions to 6G KPIs)
- Exploitation survey among partners
- Standardisation and dialog with industry associations

Innowacyjność oraz oczekiwany potencjalny wpływ (w tym dotychczasowe znaczenie społeczno-gospodarcze i szersze implikacje społeczne projektu)

The progress beyond the state of the art can be derived from the main innovations and key achievements listed above.
Beyond that the final expected results will address and cover:
- Current challenges in networks, beyond 5G (B5G), 6G, Terahertz (THz), Optical Wireless Communications (OWC)
- Artificial Intelligence (AI), Multi-agent Deep Reinforcement Learning applied in future networks
- Highly Dynamic Ultra-Dense Device-to-Device (D2D) Cell-free Networks,
- Grant Free-Non-Orthogonal Multiple Access (GF-NOMA),
- End-to-End (E2E) Slicing,
- Integrated Access Backhaul (IAB),
- Industrial Virtual Assistant (IVA),
- Simultaneous Localization and Mapping (SLAM),
- Massive Machine Type Communication (mMTC) and Ultra-Reliable Low Latency Communication (URLLC) service types.

Project Logo