RAN, AI, AI-RAN and Open RAN

The Japanese MNO Softbank is taking an active role in trying to bring AI to RAN. In a research story published recently, they explain that AI-RAN integrates AI into mobile networks to enhance performance and enable low-latency, high-security services via distributed AI data centres. This innovative infrastructure supports applications like real-time urban safety monitoring and optimized network throughput. Through the AI-RAN Alliance, SoftBank collaborates with industry leaders to advance technology and create an ecosystem for AI-driven societal and industrial solutions.

This video provides a nice short explanation of what AI-RAN means:

SoftBank's recent developments in AI-RAN technology further its mission to integrate AI with mobile networks, highlighted by the introduction of "AITRAS." This converged solution leverages NVIDIA's Grace Hopper platform and advanced orchestrators to unify vRAN and AI applications, enabling efficient and scalable networks. By collaborating with partners like Red Hat and Fujitsu, SoftBank aims to commercialize AI-RAN globally, addressing the demands of next-generation connectivity. Together, these initiatives align with SoftBank's vision of transforming telecommunications infrastructure to power AI-driven societies. Details are available on SoftBank's page here.

Last month, theNetworkingChannel hosted a webinar looking at 'AI-RAN and Open RAN: Exploring Convergence of AI-Native Approaches in Future Telecommunication Technologies'. The slides have not been shared and the details of the speakers are available here. The webinar is embedded below:

NVIDIA has a lot more technical details available on their blog post here.

Related Posts: 

• Free 6G Training: Panel Discussion on 'Evolving AI Architectures in Support of End-to-end Heterogeneous Next Generation Networks'
• Free 6G Training: Softbank's 12 Challenges for Beyond 5G / 6G
• Private Networks Technology Blog: SoftBank's Private 5G Service that’s Custom-built for Enterprises
• Connectivity Technology Blog: Softbank's Cylindrical Antenna for HAPS to Reduce Handovers
• Connectivity Technology Blog: SoftBank to Promote Non-Terrestrial Network (NTN) Solutions
• Free 6G Training: AI Machine Learning RAN Intelligent Controller for 6G Open RAN
• Free 6G Training: O-RAN Alliance's nGRG Address the Use Cases, AI/ML and Security Aspects of 6G Mobile Networks
• The 3G4G Blog: What Is the Role of AI and ML in the Open RAN and 5G Future? 

3GPP Release 18 Description and Summary of Work Items

The first official release of 3GPP TR 21.918: "Release 18 Description; Summary of Rel-18 Work Items" has been published. It's the first official version of 5G-Advanced. Quoting from the report: 

Release 18 specifies further improvements of the 5G-Avanced system. 

These improvements consist both in enhancements of concepts/Features introduced in the previous Releases and in the introduction of new topics.

Some of the key improvements are:

• a further integration of the Satellite (NTN) access (introduced in Rel-17) in the 5G System (5GS), 
• a more efficient support of Internet of Things (IoT), Machine-Type Communication (MTC), including by satellite coverage
• and also several aspects of proximity communication and location (Sidelink, Proximity, Location and Positioning, better support of the industrial needs (Verticals, Industries, Factories, Northbound API), Multicast and Broadcast Services (MBS), Network Slicing or Uncrewed Aerial Vehicles (UAV).

As for the new topics, some of the key aspects are:

• Energy Efficiency (EE)
• Artificial Intelligence (AI)/Machine Learning (ML)
• eXtended, Augmented and Virtual Reality (XR, AR, VR), immersive communications

The following list is from the v1.0.0 table of contents to make it easier to find the list of topics. If it interests you, download the latest version technical report from the directory here.

5 Satellite / Non-Terrestrial Network (NTN)

5.1 General aspects

5.1.1 User plane: “5G system with satellite backhaul”

5.1.2 Discontinuous coverage: “Satellite access Phase 2”

5.1.3 Radio: "NR NTN enhancements"

5.1.4 Charging and Management aspects of Satelite

5.2 Specific aspects

5.2.1 IoT (Internet of Things) NTN enhancements

5.2.2 Guidelines for Extra-territorial 5G Systems

5.2.3 5G system with satellite access to Support Control and/or Video Surveillance

5.2.4 Introduction of the satellite L-/S-band for NR

5.2.5 Other band-related aspects of satellite

6 Internet of Things (IoT), Machine-Type Communication (MTC)

6.1 Personal IoT and Residential networks

6.2 Enhanced support of Reduced Capability (RedCap) NR devices

6.3 NR RedCap UE with long eDRX for RRC_INACTIVE State

6.4 Application layer support for Personal IoT Network

6.5 5G Timing Resiliency System

6.6 Mobile Terminated-Small Data Transmission (MT-SDT) for NR

6.7 Adding new NR FDD bands for RedCap in Rel-18

6.8 Signal level Enhanced Network Selection

6.9 IoT NTN enhancements

7 Energy Efficiency (EE)

7.1 Enhancements of EE for 5G Phase 2

7.2 Network energy savings for NR

7.3 Smart Energy and Infrastructure

8 Uncrewed Aerial Vehicles (UAV), UAS, UAM

8.1 Architecture for UAV and UAM Phase 2

8.2 Architecture for UAS Applications, Phase 2

8.3 NR support for UAV

8.4 Enhanced LTE Support for UAV

9 Sidelink, Proximity, Location and Positioning

9.1 5GC LoCation Services - Phase 3

9.2 Expanded and improved NR positioning

9.3 NR sidelink evolution

9.4 NR sidelink relay enhancements

9.5 Proximity-based Services in 5GS Phase 2

9.6 Ranging-based Service and sidelink positioning

9.7 Mobile Terminated-Small Data Transmission (MT-SDT) for NR

9.8 5G-enabled fused location service capability exposure

10 Verticals, Industries, Factories, Northbound API

10.1 Low Power High Accuracy Positioning for industrial IoT scenarios

10.2 Application enablement aspects for subscriber-aware northbound API access

10.3 Smart Energy and Infrastructure

10.4 Generic group management, exposure and communication enhancements

10.5 Service Enabler Architecture Layer for Verticals Phase 3

10.6 SEAL data delivery enabler for vertical applications

10.7 Rel-18 Enhancements of 3GPP Northbound and Application Layer interfaces and APIs

10.8 Charging Aspects of B2B

10.9 NRF API enhancements to avoid signalling and storing of redundant data

10.10 GBA_U Based APIs

10.11 Other aspects

11 Artificial Intelligence (AI)/Machine Learning (ML)

11.1 AI/ML model transfer in 5GS

11.2 AI/ML for NG-RAN

11.3 AI/ML management & charging

11.4 NEF Charging enhancement to support AI/ML in 5GS

12 Multicast and Broadcast Services (MBS)

12.1 5G MBS Phase 2

12.2 Enhancements of NR MBS

12.3 UE pre-configuration for 5MBS

12.4 Other MBS aspects

13 Network Slicing

13.1 Network Slicing Phase 3

13.2 Enhancement of NSAC for maximum number of UEs with at least one PDU session/PDN connection

13.3 Enhancement of Network Slicing UICC application for network slice-specific authentication and authorization

13.4 Charging Aspects of Network Slicing Phase 2

13.5 Charging Aspects for NSSAA

13.6 Charging enhancement for Network Slice based wholesale in roaming

13.7 Network Slice Capability Exposure for Application Layer Enablement

13.8 Other slice aspects

14 eXtended, Augmented and Virtual Reality (XR, AR, VR), immersive

14.1 XR (eXtended Reality) enhancements for NR

14.2 Media Capabilities for Augmented Reality

14.3 Real-time Transport Protocol Configurations

14.4 Immersive Audio for Split Rendering Scenarios  (ISAR)

14.5 Immersive Real-time Communication for WebRTC

14.6 IMS-based AR Conversational Services

14.7 Split Rendering Media Service Enabler

14.8 Extended Reality and Media service (XRM)

14.9 Other XR/AR/VR items

15 Mission Critical and emergencies

15.1 Enhanced Mission Critical Push-to-talk architecture phase 4

15.2 Gateway UE function for Mission Critical Communication

15.3 Mission Critical Services over 5MBS

15.4 Mission Critical Services over 5GProSe

15.5 Mission Critical ad hoc group Communications

15.6 Other Mission Critical aspects

16 Transportations (Railways, V2X, aerial)

16.1 MBS support for V2X services

16.2 Air-to-ground network for NR

16.4 Interconnection and Migration Aspects for Railways

16.5 Application layer support for V2X services; Phase 3

16.6 Enhanced NR support for high speed train scenario in frequency range 2 (FR2)

17 User Plane traffic and services

17.1 Enhanced Multiparty RTT

17.2 5G-Advanced media profiles for messaging services

17.3 Charging Aspects of IMS Data Channel

17.4 Evolution of IMS Multimedia Telephony Service

17.5 Access Traffic Steering, Switch and Splitting support in the 5G system architecture; Phase 3

17.6 UPF enhancement for Exposure and SBA

17.7 Tactile and multi-modality communication services

17.8 UE Testing Phase 2

17.9 5G Media Streaming Protocols Phase 2

17.10 EVS Codec Extension for Immersive Voice and Audio Services

17.11 Other User Plane traffic and services items

18 Edge computing

18.1 Edge Computing Phase 2

18.2 Architecture for enabling Edge Applications Phase 2

18.3 Edge Application Standards in 3GPP and alignment with External Organizations

19 Non-Public Networks

19.1 Non-Public Networks Phase 2

19.2 5G Networks Providing Access to Localized Services

19.3 Non-Public Networks Phase 2

20 AM and UE Policy

20.1 5G AM Policy

20.2 Enhancement of 5G UE Policy

20.3 Dynamically Changing AM Policies in the 5GC Phase 2

20.4 Spending Limits for AM and UE Policies in the 5GC

20.5 Rel-18 Enhancements of UE Policy

21 Service-based items

21.1 Enhancements on Service-based support for SMS in 5GC

21.2 Service based management architecture

21.3 Automated certificate management in SBA

21.4 Security Aspects of the 5G Service Based Architecture Phase 2

21.5 Service Based Interface Protocol Improvements Release 18

22 Security-centric aspects

22.1 IETF DTLS protocol profile for AKMA and GBA

22.2 IETF OSCORE protocol profiles for GBA and AKMA

22.3 Home network triggered primary authentication

22.4 AKMA phase 2

22.5 5G Security Assurance Specification (SCAS) for the Policy Control Function (PCF)

22.6 Security aspects on User Consent for 3GPP services Phase 2

22.7 SCAS for split-gNB product classes

22.8 Security Assurance Specification for AKMA Anchor Function Function (AAnF)

22.9 Other security-centric items

23 NR-only items

23.1 Not band-centric

23.1.1 NR network-controlled repeaters

23.1.2 Enhancement of MIMO OTA requirement for NR UEs

23.1.3 NR MIMO evolution for downlink and uplink

23.1.4 Further NR mobility enhancements

23.1.5 In-Device Co-existence (IDC) enhancements for NR and MR-DC

23.1.6 Even Further RRM enhancement for NR and MR-DC

23.1.7 Dual Transmission Reception (TxRx) Multi-SIM for NR

23.1.8 NR support for dedicated spectrum less than 5MHz for FR1

23.1.9 Enhancement of NR Dynamic Spectrum Sharing (DSS)

23.1.10 Multi-carrier enhancements for NR

23.1.11 NR RF requirements enhancement for frequency range 2 (FR2), Phase 3

23.1.12 Requirement for NR frequency range 2 (FR2) multi-Rx chain DL reception

23.1.13 Support of intra-band non-collocated EN-DC/NR-CA deployment

23.1.14 Further enhancements on NR and MR-DC measurement gaps and measurements without gaps

23.1.15 Further RF requirements enhancement for NR and EN-DC in frequency range 1 (FR1)

23.1.16 Other non-band related items

23.2 Band-centric

23.2.1 Enhancements of NR shared spectrum bands

23.2.2 Addition of FDD NR bands using the uplink from n28 and the downlink of n75 and n76

23.2.3 Complete the specification support for BandWidth Part operation without restriction in NR

23.2.4 Other NR band related topics

24 LTE-only items

24.1 High Power UE (Power Class 2) for LTE FDD Band 14

24.2 Other LTE-only items

25 NR and LTE items

25.1 4Rx handheld UE for low NR bands (<1GHz) and/or 3Tx for NR inter-band UL Carrier Aggregation (CA) and EN-DC

25.2 Enhancement of UE TRP and TRS requirements and test methodologies for FR1 (NR SA and EN-DC)

25.3 Other items

26 Network automation

26.1 Enablers for Network Automation for 5G phase 3

26.2 Enhancement of Network Automation Enablers

27 Other aspects

27.1 Support for Wireless and Wireline Convergence Phase 2

27.2 Secondary DN Authentication and authorization in EPC IWK cases

27.3 Mobile IAB (Integrated Access and Backhaul) for NR

27.4 Further NR coverage enhancements

27.5 NR demodulation performance evolution

27.6 NR channel raster enhancement

27.7 BS/UE EMC enhancements for NR and LTE

27.8 Enhancement on NR QoE management and optimizations for diverse services

27.9 Additional NRM features phase 2

27.10 Further enhancement of data collection for SON (Self-Organising Networks)/MDT (Minimization of Drive Tests) in NR and EN-DC

27.11 Self-Configuration of RAN Network Entities

27.12 Enhancement of Shared Data ID and Handling

27.13 Message Service within the 5G system Phase 2

27.14 Security Assurance Specification (SCAS) Phase 2

27.15 Vehicle-Mounted Relays

27.16 SECAM and SCAS for 3GPP virtualized network products

27.17 SECAM and SCAS for 3GPP virtualized network products

27.18 MPS for Supplementary Services

27.19 Rel-18 enhancements of session management policy control

27.20 Seamless UE context recovery

27.21 Extensions to the TSC Framework to support DetNet

27.22 Multiple location report for MT-LR Immediate Location Request for regulatory services

27.23 Enhancement of Application Detection Event Exposure

27.24 General Support of IPv6 Prefix Delegation in 5GS

27.25 5G Timing Resiliency System

27.26 MPS when access to EPC/5GC is WLAN

27.27 Data Integrity in 5GS

27.28 Security Enhancement on RRCResumeRequest Message Protection

28 Administration, Operation, Maintenance and Charging-centric Features

28.1 Introduction

28.2 Intent driven Management Service for Mobile Network phase 2

28.3 Management of cloud-native Virtualized Network Functions

28.4 Management of Trace/MDT phase 2

28.5 Security Assurance Specification for Management Function (MnF)

28.6 5G performance measurements and KPIs phase 3

28.7 Access control for management service

28.8 Management Aspects related to NWDAF

28.9 Management Aspect of 5GLAN

28.10 Charging Aspects of TSN

28.11 CHF Distributed Availability

28.12 Management Data Analytics phase 2

28.12 5G System Enabler for Service Function Chaining

28.13 Other Management-centric items

29 Other Rel-18 Topics

If you find them useful then please get the latest document from here.

Related Posts: 

• The 3G4G Blog - Tutorial: A Quick Introduction to 3GPP
• Free 6G Training: Summary of 3GPP Stage-1 Workshop on IMT2030 Use Cases
• Free 6G Training: ATIS Webinar on 'Introduction to 3GPP Release 19 and 6G Planning'
• The 3G4G Blog: 3GPP TSG RAN and TSG SA Release-19 Workshop Summary
• The 3G4G Blog: 3GPP Release 17 Description and Summary of Work Items
• The 3G4G Blog: 3GPP Release 16 Description and Summary of Work Items
• The 3G4G Blog: ATIS Webinar on "3GPP Release 18 Overview: A World of 5G-Advanced"
• The 3G4G Blog: ATIS Webinar on '5G Standards Development Update in 3GPP Release 17 and 18'
• The 3G4G Blog: 3GPP Release-18 Work Moves Into Focus as Release-17 Reaches Maturity
• The 3G4G Blog: An Early View of 3GPP Release-18 5G-Advanced Topics 

AI/ML and Other ICT Industry Trends in the coming decades

At the Brooklyn 6G Summit (B6GS) 2023, top tier economist Dr. Jeff Shen from BlackRock, presented a talk from the industry perspective of AI (Artificial Intelligence) and investment. Jeff Shen, PhD, Managing Director, is Co-CIO and Co-Head of Systematic Active Equity (SAE) at BlackRock. He is a member of the BlackRock Global Operating Committee, BlackRock Systematic (BSYS) Management Committee and the BlackRock Asian Middle Eastern & Allies Network (AMP) Executive Committee.

How are firms reacting to AI? From 'ICT Industry Trends in the coming decades' by Jeff Shen, BlackRock at #B6GS - I am guessing the peak of mobile mention was the peak 5G hype in 2015/16. Hopefully the industry is now much wiser and won't repeat the 6G hype. pic.twitter.com/xjEiDtmSUZ

— Zahid Ghadialy (@zahidtg) November 5, 2023

In his talk he covered the history of how and where AI has been traditionally used and how the thinking around AI has changed over the last few decades. He then presented his view on if AI is just a fad or it's more than that. To illustrate the fact, he provided an example of how Generative AI market is expected to grow from $40 Billion in 2022 to $1.3 Trillion in 2032. 

There are many challenges that AI faces that one should be aware of; namely regulation, cyber threats and ethical concerns. In the US, AI touches the entire economy, from legal to healthcare. In their quarterly reporting, firms are now discussing AI and the larger tech companies are not afraid to grow inorganically in order to get more exposure to the trend. 

You can watch the whole of his talk embedded below, courtesy of IEEE Tv.

Related Posts: 

• Free 6G Training: 'Impact of 6G on Metaverse' from Brooklyn 6G Summit (B6GS) 2023
• Free 6G Training: Qualcomm Keynote on 'Advancing Wireless Innovations towards 6G — from a Device’s Viewpoint' from B6GS 2023
• Operator Watch Blog: Jio 5G - Enabling India to go Digital
• Operator Watch Blog: UScellular 5G Progress and 6G Plans
• The 3G4G Blog: Presentations from 2nd IEEE Open RAN Summit
• The 3G4G Blog: AI/ML Enhancements in 5G-Advanced for Intelligent Network Automation
• The 3G4G Blog: What Is the Role of AI and ML in the Open RAN and 5G Future? 

Presentations from 2nd IEEE Open RAN Summit

The second IEEE SA (Standards Association) Open RAN summit, hosted by the Johns Hopkins University Applied Physics Lab, took place on 9-10 Aug 2023. It covered the topics related to the standardization of Open RAN including O-RAN Alliance, 3GPP, IEEE, various deployment scenarios, testing and integration, Open RAN security, RAN slicing, and RAN optimization among others. 

The videos of the presentations can be viewed on the summit page here or though the video playlist here.

The talk from Dr. Chih-Lin I, O-RAN Alliance TSC Co-Chair and CMCC Chief Scientist, Wireless Technologies on 'AI/ML impact, from 5.5G to 6G' is embedded below:

Related Posts: 

• The 3G4G Blog: Open RAN Terminology and Players
• The 3G4G Blog: O-RAN Introduction for Beginners
• The 3G4G Blog: Accelerating O-RAN Adoption Through Open Source
• The 3G4G Blog: 5G RAN Functional Splits
• The 3G4G Blog: Open RAN Explanation, Videos, White papers and Other Resources 

AI/ML Enhancements in 5G-Advanced for Intelligent Network Automation

Artificial Intelligence (AI) and Machine Learning (ML) has been touted to automate the network and simplify the identification and debug of issues that will arise with increasing network complexity. For this reason 3GPP has many different features that are already present in Release-17 but are expected to evolve further in Release-18. 

I have already covered some of this topics in earlier posts. Ericsson's recent whitepaper '5G Advanced: Evolution towards 6G' also has a good summary on this topic. Here is an extract from that:

Intelligent network automation

With increasing complexity in network design, for example, many different deployment and usage options, conventional approaches will not be able to provide swift solutions in many cases. It is well understood that manually reconfiguring cellular communications systems could be inefficient and costly.

Artificial intelligence (AI) and machine learning (ML) have the capability to solve complex and unstructured network problems by using a large amount of data collected from wireless networks. Thus, there has been a lot of attention lately on utilizing AI/ML-based solutions to improve network performance and hence providing avenues for inserting intelligence in network operations.

AI model design, optimization, and life-cycle management rely heavily on data. A wireless network can collect a large amount of data as part of its normal operations. This provides a good base for designing intelligent network solutions. 5G Advanced addresses how to optimize the standardized interfaces for data collection while leaving the automation functionality, for example, training and inference up to the proprietary implementation to support full flexibility in the automation of the network.

AI/ML for RAN enhancements

Three use cases have been identified in the Release 17 study item related to RAN performance enhancement by using AI/ML techniques. Selected use cases from the Release 17 technical report will be taken into the normative phase in the next releases. The selected use cases are: 1) network energy saving; 2) load balancing; and 3) mobility optimization.

The selected use cases can be supported by enhancements to current NR interfaces, targeting performance improvements using AI/ML functionality in the RAN while maintaining the 5G NR architecture. One of the goals is to ensure vendor incentives in terms of innovation and competitiveness by keeping the AI model implementation specific. As shown in Fig.2 (on the top) an intent-based management approach can be adopted for use cases involving RAN-OAM interactions. The intent will be received by the RAN. The RAN will need to understand the intent and trigger certain functionalities as a result.

Ericsson White Paper - 5G Advanced: Evolution towards 6G - https://t.co/9ZKnC8PDxX#Free5Gtraining #Ericsson #5G #B5G #5GAdvanced #6G #5GNR #5GC #Timeline #XR #RedCap #NetworkAutomation #EnergySavings #DeterministicNetworking #IoT pic.twitter.com/eeI4SKvIRC

— Free 5G Training (@5Gtraining) July 21, 2022

AI/ML for physical layer enhancements

It is generally expected that AI/ML functionality can be used to improve the radio performance and/or reduced the complexity/overhead of the radio interface. 3GPP TSG RAN has selected three use cases to study the potential air interface performance improvements through AI/ML techniques, such as beam management, channel state information feedback enhancement, and positioning accuracy enhancements for different scenarios. The AI/ML-based methods may provide benefits compared to traditional methods in the radio interface. The challenge will be to define a unified AI/ML framework for the air interface by adequate AI/ML model characterization using various levels of collaboration between gNB and UE.

AI/ML in 5G core

5G Advanced will provide further enhancements of the architecture for analytics and on ML model life-cycle management, for example, to improve correctness of the models. The advancements in the architecture for analytics and data collection serve as a good foundation for AI/ML-based use cases within the different network functions (NFs). Additional use cases will be studied where NFs make use of analytics with the target to support in their decision making, for example, network data analytics functions (NWDAF)- assisted generation of UE policy for network slicing.

If you are interested in studying this topic further, check out 3GPP TR 37.817: Study on enhancement for data collection for NR and ENDC. Download the latest version from here.

Related Posts: 

• The 3G4G Blog: What Is the Role of AI and ML in the Open RAN and 5G Future?
• The 3G4G Blog: 3GPP Release-18 Work Moves Into Focus as Release-17 Reaches Maturity
• The 3G4G Blog: NWDAF in 3GPP Release-16 and Release-17
• The 3G4G Blog: 5G-Advanced Flagship Features
• The 3G4G Blog: 3GPP's 5G-Advanced Technology Evolution from a Network Perspective Whitepaper
• Free 6G Training: Qualcomm Pushing the boundaries of AI research 

What Is the Role of AI and ML in the Open RAN and 5G Future?

Artificial Intelligence and Machine Learning have moved on from just being buzzwords to bringing much needed optimization and intelligence in devices, networks and infrastructure; whether on site, on the edge or in the cloud.

New Study in 3GPP RAN3 on Artificial Intelligence and Machine Learning in NG-RAN - https://t.co/o4o4kq6Wpp via @3GPPLive #Free5Gtraining #3GPP #5G #ArtificialIntelligence #MachineLearning #AIML #RAN #Algorithms #SON #5GC #5GS pic.twitter.com/pvPlG9HpPC

— Free 5G Training (@5Gtraining) October 15, 2021

Qualcomm has been very active in talking about AI/ML in webinars and on their site. A detailed blog post looking at 'What’s the role of artificial intelligence in the future of 5G and beyond?' is available here. It was posted in time for a Light Reading webinar where Gabriel Brown, Principal Analyst – Mobile Networks and 5G, Heavy Reading and Tingfang Ji, Senior Director, Engineering - Wireless R&D, Qualcomm discuss the topic. The video is embedded below and slide deck is available here.

Standardizing AI/ML in cellular communication systems. From #Qualcomm presentation, The essential role of AI in the 5G future - How machine learning is accelerating wireless innovations in the new decade and beyond - https://t.co/fwxtoKIZKR#Free5Gtraining #3G4G5G #5G #AI #ML pic.twitter.com/YS5w8KXQuw

— Free 5G Training (@5Gtraining) September 27, 2021

Louis Scialabba, Senior Director of Marketing at Mavenir, looking at AI and Analytics spoke at Layer 123 conference on the topic, 'AI/ML for Next Gen 5G Mobile Networks'. His talk is embedded below and a blog post by him on the topic, 'The RIC Opens a New World of Opportunities for CSPs' is available here.

Related Posts: 

• Free 6G Training: Qualcomm Pushing the boundaries of AI research
• The 3G4G Blog: 3GPP Release-18 Work Moves Into Focus as Release-17 Reaches Maturity
• The 3G4G Blog: 5G-Advanced Flagship Features
• Connectivity Technology Blog: 5G Indoor Precise Positioning
• The 3G4G Blog: ITU Standardization Bureau on Machine Learning for 5G
• The 3G4G Blog: AI your Slice to 5G Perfection
• The 3G4G Blog: Qualcomm Explains 5G Millimeter Wave (mmWave) Future & Integrated Access and Backhaul (IAB)
• The 3G4G Blog: Qualcomm Demoes Sub-band Half Duplex (SBHD)
• Connectivity Technology Blog: Super Uplink to improve 5G Coverage and Speeds
• Free 6G Training: One XR Device to Rule Them All! 

5G & AI Powered Smart Hospitals

5G Telehealth has been one of the main driving use cases for upgrading the infrastructure. While some use cases definitely make sense, some others like remote surgery will most likely never happen, at least the way it's depicted today.

At the GSMA Mobile 360 APAC - 5G Industry Community Summit, Michael Fung, Chief Information Officer from CHUK Medical Centre presented a nice talk detailing how they see 5G & AI powered hospitals of the future. The video of his talk is embedded at the bottom of this post.

There have also been some other discussions on 5G & healthcare recently. Here are the links if you want to explore this topic further:

• Video: UK5G Presents Health & Social Care Panel Session
• Video: Telecoms Europe 5G 2021 - What can 5G do for healthcare?
• Video: Ericsson - 5G Connected Ambulance
• Video: 5G Healthcare Application for Smart Hospital - Tseung Kwan O Hospital
• Article: Vodafone Germany launches real-time network in the first 5G hospital 

Service Level Agreements for 5G and Beyond: Overview, Challenges and Enablers of 5G-Healthcare Systems - https://t.co/axJ05r2VqX via U.S. FDA (@US_FDA)#Free5Gtraining #5G #5GTechnology #5GUseCases #5GHealthcare #Healthcare #SLA #Cybersecurity #5Gsecurity pic.twitter.com/O9c0GEemt4

— Free 5G Training (@5Gtraining) December 6, 2021

The US FDA recently published a one pager looking at how Service level agreements (SLAs) can enable 5G-enabled medical device use cases by documenting how a medical device communication requirement is met by the unique characteristics of 5G networks and the roles and responsibilities of the stakeholders involved in offering safe and effective 5G-enabled healthcare to patients.

IEEE Access has a detailed paper on this topic by the same authors. Quoting from the abstract:

Service level agreements (SLAs) can enable 5G-enabled medical device use cases by documenting how a medical device communication requirements are met by the unique characteristics of 5G networks and the roles and responsibilities of the stakeholders involved in offering safe and effective 5G-enabled healthcare to patients. However, there are gaps in this space that should be addressed to facilitate the efficient implementation of 5G technology in healthcare. Current literature is scarce regarding SLAs for 5G and is absent regarding SLAs for 5G-enabled medical devices. This paper aims to bridge these gaps by identifying key challenges, providing insight, and describing open research questions related to SLAs in 5G and specifically 5G-healthcare systems. This is helpful to network service providers, users, and regulatory authorities in developing, managing, monitoring, and evaluating SLAs in 5G-enabled medical systems.

Here is the video from GSMA 5G Industry Community Summit Part 2:

Related Posts:

• The 3G4G Blog: 5G Remote Surgery and Telehealth Solutions
• The 3G4G Blog: Banana and Egg gets 5G Telesurgery
• Operator Watch Blog: Vodafone Deutschland (Germany) Continues 5G Use Cases Innovation
• Operator Watch Blog - China Mobile on The Next Phase of 5G: Progress, Challenges, and Opportunities 

5G-Advanced Flagship Features

I am starting to get a feeling that people may be becoming overwhelmed with all the new 5G features and standards update. That is why this presentation by Mikael Höök, Director Radio Research at Ericsson, at Brooklyn 6G Summit (B6GS) caught my attention. 

The talk discusses the network infrastructure progress made in the previous two years to better illustrate the advanced 5G timeline to discovering 6G requirements. At the end of the talk, there was a quick summary of the four flagship features that are shown in the picture above. The talk is embedded below, courtesy of IEEE TV

In addition to this talk, October 2021 issue of Ericsson Technology Review covers the topic "5G evolution toward 5G advanced: An overview of 3GPP releases 17 and 18". You can get the PDF here.

I have covered the basics of these flagship features in the following posts:

• AI/ML (link)
• RedCap (link)
• XR (link)
• Network Energy Efficiency (link)

Please feel free to add your thoughts as comments below.

Related Posts: 

• The 3G4G Blog: An Early View of 3GPP Release-18 5G-Advanced Topics
• The 3G4G Blog: 3GPP's 5G-Advanced Workshop Summary
• The 3G4G Blog: 3GPP's 5G-Advanced Technology Evolution from a Network Perspective Whitepaper
• The 3G4G Blog: '5G RAN Release 18 for Industry Verticals' Webinar Highlights
• The 3G4G Blog: 3GPP RAN Plenary Update and Evolution towards 5G-Advanced
• The 3G4G Blog: Initiative to Remove Non-inclusive terms from 3GPP Specifications
• The 3G4G Blog: 3GPP Release 16 Description and Summary of Work Items
• The 3G4G Blog: 3GPP Standards on Edge Computing
• The 3G4G Blog: Artificial Intelligence (AI) / Machine Learning (ML) in 5G Challenge by ITU
• The 3G4G Blog: ITU Standardization Bureau on Machine Learning for 5G
• The 3G4G Blog: Introduction to 5G Reduced Capability (RedCap) Devices
• The 3G4G Blog: 5G eXtended Reality (5G-XR) in 5G System (5GS)
• The 3G4G Blog: Energy Consumption in Mobile Networks and RAN Power Saving Schemes 

3GPP's 5G-Advanced Technology Evolution from a Network Perspective Whitepaper

China Mobile, along with a bunch of other organizations including China Unicom, China Telecom, CAICT, Huawei, Nokia, Ericsson, etc., produced a white paper on what technology evolutions will we see as part of 5G-Advanced. This comes not so long after the 3GPP 5G-Advanced Workshop which a blogged about here.

The abstract of the whitepaper says:

The commercialization of 5G networks is accelerating globally. From the perspective of industry development drivers, 5G communications are considered the key to personal consumption experience upgrades and digital industrial transformation. Major economies around the world require 5G to be an essential part of long-term industrial development. 5G will enter thousands of industries in terms of business, and technically, 5G needs to integrate DOICT (DT - Data Technology, OT - Operational Technology, IT - Information Technology and CT - Communication Technology) and other technologies further. Therefore, this white paper proposes that continuous research on the follow-up evolution of 5G networks—5G-Advanced is required, and full consideration of architecture evolution and function enhancement is needed.

This white paper first analyzes the network evolution architecture of 5G-Advanced and expounds on the technical development direction of 5G-Advanced from the three characteristics of Artificial Intelligence, Convergence, and Enablement. Artificial Intelligence represents network AI, including full use of machine learning, digital twins, recognition and intention network, which can enhance the capabilities of network's intelligent operation and maintenance. Convergence includes 5G and industry network convergence, home network convergence and space-air-ground network convergence, in order to realize the integration development. Enablement provides for the enhancement of 5G interactive communication and deterministic communication capabilities. It enhances existing technologies such as network slicing and positioning to better help the digital transformation of the industry.

The paper can be downloaded from China Mobile's website here or from Huawei's website here. A video of the paper launch is embedded below:

Nokia's Antti Toskala wrote a blog piece providing the first real glimpse of 5G-Advanced, here.

Related Posts: 

• The 3G4G Blog: '5G RAN Release 18 for Industry Verticals' Webinar Highlights
• The 3G4G Blog: 3GPP's 5G-Advanced Workshop Summary
• Operator Watch Blog: China Mobile on The Next Phase of 5G: Progress, Challenges, and Opportunities
• Connectivity Technology Blog: Ericsson Explains Internet of Drones and 3GPP UAV Roadmap
• The 3G4G Blog: 3GPP RAN Plenary Update and Evolution towards 5G-Advanced
• The 3G4G Blog: Introduction to 5G Reduced Capability (RedCap) Devices
• The 3G4G Blog: 3GPP Standards on Edge Computing
• Connectivity Technology Blog: 5G Drone Cell Towers
• Free 6G Training: Pre-Study of B5G and 6G in China
• Free 6G Training: China's IMT-2030 (6G) Promotion Group Releases 6G Whitepaper
• The 3G4G Blog: Real-life 5G Use Cases for Verticals from China
• The 3G4G Blog: 5G Remote Surgery and Telehealth Solutions
• Free 6G Training: China Mobile on the 5G/6G Connectivity Transformation for Sustainability
• Free 6G Training: Nokia Bell Labs on Augmenting Human Potential in the 6G Era
• Free 6G Training: Huawei talks about Beyond 5G, 5.5G and 6G
• The 3G4G Blog: Nokia veterans Harri Holma and Antti Toskala explain 5G Basics 

ITU Standardization Bureau on Machine Learning for 5G

Last year I blogged about Global ITU AI/ML 5G Challenge on the theme “How to apply ITU's ML architecture in 5G networks".  The grand challenge finale happened in December. All the recording and presentations are available here.

Back in October, Bilel Jamoussi from ITU presented a keynote to the 2020 IEEE 5G World Forum plenary session where he addressed the challenges of applying machine learning in networks, ITU’s ML toolkit, and ITU’s AI/ML in 5G Competition. IEEE Tv shared the presentation only in April so the competition part is a bit outdated. It does nevertheless an interesting 20 minute talk.

ITU Recommendation Y.3174, Framework for data handling to enable machine learning in future networks including IMT-2020 is available here.

Related Posts: 

• The 3G4G Blog: Artificial Intelligence (AI) / Machine Learning (ML) in 5G Challenge by ITU
• The 3G4G Blog: IMT-2020 (5G) Requirements 

Artificial Intelligence (AI) / Machine Learning (ML) in 5G Challenge by ITU

ITU is conducting a global ITU AI/ML 5G Challenge on the theme “How to apply ITU's ML architecture in 5G networks". If you don't know the difference between AI & ML, this picture from the old blog post may help.

The ITU website says:

Artificial Intelligence (AI) will be the dominant technology of the future and will impact every corner of society. In particular, AI / ML (machine learning) will shape how communication networks, a lifeline of our society, will be run. Many companies in the ICT sector are exploring how to make best use of AI/ML. ITU has been at the forefront of this endeavour exploring how to best apply AI/ML in future networks including 5G networks. The time is therefore right to bring together the technical community and stakeholders to brainstorm, innovate and solve relevant problems in 5G using AI/ML. Building on its standards work, ITU is conducting a global ITU AI/ML 5G Challenge on the theme “How to apply ITU's ML architecture in 5G networks". 

Participants will be able to solve real world problems, based on standardized technologies developed for ML in 5G networks. Teams will be required to enable, create, train and deploy ML models (such that participants will acquire hands-on experience in AI/ML in areas relevant to 5G). Participation is open to ITU Member States, Sector Members, Associates and Aca​demic Institutions and to any individual from a country that is a member of ITU. ​ ​

There are also some cash prizes, etc. There are various topics with presentation slides & recordings freely available. 

I found the slides from ITU AI/ML in 5G Challenge —”Machine Learning for Wireless LANs + Japan Challenge Introduction” (link) very interesting. There are many other topics including AR / VR / XR, etc, as well.

Have a look at the ITU website here.


Related Posts:

• The 3G4G Blog: An Introduction to Vehicle to Everything (V2X) and Cellular V2X (C-V2X)
• The 3G4G Blog: 5G Remote Surgery and Telehealth Solutions
• The 3G4G Blog: 5G eXtended Reality (5G-XR) in 5G System (5GS)
• The 3G4G Blog: Real-life 5G Use Cases for Verticals from China

How Cellular IoT and AI Can Help to Overcome Extreme Poverty in a Climate-resilient Way

The Democratic Republic ofthe Congo (DRC) is the second largest country in Africa and it has a significant potential for agricultural development as the country has more land (235 million hectares) than Kenya, Malawi, Tanzania, and Zambia, combined, of which only 3.4% is cultivated.

Despite this, around 13 millions of Congolese live in extreme food insecurity, among them 5 millions acutely malnourished children. Current assessments show the trend is increasing.

In the southern provinces formerly known as "Katanga" the needs in maize for human consumption sum up to 700,000 tons per year, while the local production barely amounts to 120,000 tons per year. This means the provinces have to resort to importing food from neighboring countries, which represents a huge burden on the region's economy.

Another aspect of the problem is that 80% of the local production is made by women farmers, and the biggest challenge they face is the lack of daily agronomic monitoring and guidance. There is only a limited amount of agriculture experts in the region and without assistance, the farmers’ average output is at best one ton per hectare. However, field trials have proven that by using smart farming technology they can easily produce up to 6 tons per hectare year over year with the right sustainable approach and support. Artificial intelligence (AI), the Internet of Things (IoT) and big data analytics underpinned by mobile connectivity can even do more. They bring significant potential for capturing carbon, optimizing water, pesticide and fertilizer usage, and reducing soil erosion. Thus, African women can not only provide the solution to the local food gap/insecurity but also become the primary protectors of their environment.

The basic technical concept is not new. Back in 2016 Ooredoo Myanmar launched Site Pyo, a mobile agriculture information service for smallholder farmers. At its core Site Pyo is a weather forecast app that was enhanced with weather-dependent advice for ten crops, from seed selection to harvesting and storage. In addition the app displays the actual market prices for these crops. GSMA as a co-funder of the project celebrates Site Pyo as a big success, but it seems to be limited to Myanmar. Why?

„A lot of customization needs to be done to adapt the application functionality for a particular region“, says Dieu-Donné Okalas Ossami, CEO of „e-tumba“, a French Start-up specialized in smart farming solutions for Sub-Sahara Africa. His company partners with iTK, a spin-off from CIRAD, the French Institute for tropical agronomy. The iTK crop-specific predictive models are based on years of agronomic data, but have originally been designed for big farmers. To meet the demands of women in Katanga requires more granular data for both, input and output.

As in case of Site Pyo weather predictions are important, but in addition there are data feeds from sensors on the spot. Weather stations measure constantly temperature and rainfall while sensors in the soil report its saturation with water, nitrogen and potassium.

„A typical real-time advice that our software provides is to delay the harvest for some additional days to maximize the yield“, explains Okalas Ossami. „However, even for two neighboring fields the particular advices are often different.“ 

Also the communication channels need to be taylored. Many women farmers are illiterate. For them the advice must be translated into the local language they speak and transmitted to their phones as a voice message. Those who can read and write will receive the notifications through short message service.

The mobile connectivity that links all elements of the system is realized by the mobile network operators present in the region.

Infographic: The Technical Environment Behind the Project

„Actually NB-IoT would fit to our use case“, says Okalas Ossami, „but it is not available. And there is neither LoRa nor SigFox.“ Hence, the sensors are using data connections of 3G and 4G radio access technology. In case of network outage or missing coverage a local field technician must collect the sensor data manually and transfer it to the data center through alternative channels.

It is the same field technician who installs the sensors. The woman farmers receive a basic training to understand how the system works, but they do not need to care about technical components - except keeping their mobile phones charged.

Here comes another important aspect into the game: How can the women trust this technical environment?

In case of Site Pyo the operator Ooredoo observed a quickly increasing user community measured by the number of app downloads. However, there was no indication to which extend the Myanmar farmers really used the app. The e-tumba solution addresses this gap by partnering with the non-government organization „Anzafrika“.

Anzafrika is present in the villages where the people live. One of its major targets is to overcome the extreme poverty by developing the regional economy. A key factor for this is that the smallholder farmers do not just see the market prices for their crops, but get real access to large, stable and long-term markets where these prices are paid. Anzafrika is brokering contracts between the woman farmers and large multinational corporations committed to the Economics of Mutuality, growing human, social and natural capital. The business model behind this concept was outlined by Bruno Roche and Jay Jakub in their book „Completing Capitalism:Heal Business to Heal the World“. Instead of focusing on greenhouse gas emissions (output) they insist that climate-resilient business models must measure the input needed for manufacturing goods. As an example: For one hot cup of coffee the greenhouse gas emissions are extremely low, but 3.4 liters of water are needed (most for packaging, processing and drinking) and 12 gram of top soil will be eroded. These are (among others) the expenses paid by the planet that are not taken into account by a carbon tax.

Coffee plantations are monocultures with all the known disadvantages resulting form this kind of farming. In the past the Congolese women farmers have grown maize as a monoculture. Now, with advice from Anzafrika and e-tumba they transitioned from an „all-maize“ sustenance crop to a semi-industrial „maize-sorghum“ production. This helps to minimize the top soil erosion and thus, to remunerate the natural capital involved in the process.  

Regarding the human and social capital Anzafrika monitors how the overall situation in the villages  is improving. The focus is on progress in well-beeing, satisfaction and health not just for the women farmers, but for their entire communities.

In 2019 smart farming technology have been tested and deployed with a group of 150 women in the province of Lualaba. Now, in 2020, their number is expected to rise to 500 and after 6 years the stunning target of 100,000 participants shall be met. A look at the download numbers of Site Pyo (206,000 in the course of one year) shows that these numbers are not over-optimistic.

The partnership between Anzafrika, e-tumba and iTK is now considered as a best international practice, as indicated by Patrick Gilabert, UNIDO Representative to the European Union in Brussels. It fully aligns with the development of new comprehensive strategies for Africa that aim at creating a partnership of equals and mutual interest through agriculture, trade and investment partnerships.

UNIDO, as the UN convener for the implementation of the “Industrial Decade for Development of Africa” (IDDA 3) is always ready to join forces with innovative partners.