Feature: RF
If we turn to wireless networks, however, these are inherently
complex, generate enormous amounts of data and have grown in complexity with each new generation of technology, all of which make AI an ideal tool to optimise wireless networks.
AI in 5G networks As the 5G technology matures, AI and ML are already being introduced for study by the standardisation body 3GPP (3rd Generation Partnership Project), which maintains cellular standards. Applications of AI under consideration are primarily in the air interface, including network energy saving, load balancing and mobility optimisation. Potential uses in the air interface are so numerous that a small subset has been selected for study in the upcoming 3GPP Release 18, including channel state information feedback, beam management and positioning. It is important to note that 3GPP is not developing AI/ML models, but it seeks to create common frameworks and evaluation methods for such models that are introduced into different air interface functions. Outside of the 3GPP and the air interface, the O-RAN
Artificial intelligence in
5G and 6G By Sarah LaSelva, Director of 6G Marketing, Keysight Technologies
T
he artificial intelligence (AI) revolution is here. Already widely applied in some business and manufacturing models, users are also seeing the power and potential of deep neural networks and machine learning (ML) through everyday applications like ChatGPT. ChatGPT is a language
model trained on Internet-based texts and books, allowing it to generate human-like responses. Tis type of application is a perfect example of the strengths of AI – it can optimise an output to a complex scenario based on large sets of training data.
16 February 2024
www.electronicsworld.co.uk
Alliance is exploring how AI/ML can be used to improve network management. The Alliance, in general, is looking into ways to transform radio access networks (RAN) to open, intelligent, virtualised and interoperable networks. However, its architecture also has a unique feature called the RAN Intelligent Controller (RIC) that is designed to host AI/ML optimisation applications. RIC can host xApps, which run in near real time, and rApps, which do not run in real time. xApps for improving spectral efficiency and energy efficiency and rApps for network orchestration that leverage AI already exist today. More xApps/ rApps and applications using AI/ML in the RIC will become available as the O-RAN ecosystem grows and matures.
AI-native 6G networks 6G is in its infancy, but it is already clear that AI/ML will be fundamental in all aspects of future wireless systems. On the network side, the term “AI native” is used widely in the industry, despite not being officially defined. One way of looking at these AI-native networks is to extrapolate the diagram in Figure 1 based on current trends of virtualisation and disaggregation of the RAN. Each block of the network is likely to contain AI/ML models that will vary from vendor to vendor and application to application; see Figure 2. AI-native networks can also mean networks that were built to
natively-run AI/ML models. Consider the design flow in Figure 3: In traditional 5G networks, the air interface is made up of different processing blocks, each designed by humans; in 5G Advanced, each block will leverage ML to optimise a specific function; in 6G, it’s likely that AI will design the entire air interface using deep neural networks.
AI/ML optimisation Building on the idea that AI/ML can be used to improve network management orchestration, 6G looks to leverage
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44
