Solving 5G And 6G Challenges With Artificial Intelligence

Wireless networks are inherently complex, generate massive amounts of data, and have grown in complexity with each new generation of technology. This combination of large data sets and complexity makes wireless networks an ideal candidate for AI.

People are receiving first-hand experiences of the power and potential of deep neural networks and machine learning (ML) as the technology begins to reach a level of maturity that allows it to be used outside of research labs. Two prime examples are Descript AI, a software application that uses AI and ML to transcribe spoken words, and ChatGPT, a large language model (LLM) trained on vast amounts of data and used to generate human-like text. These are examples of how AI can take a complex problem, like human speech, and output an optimized answer when it has been trained on massive data sets.

AI’s core strength as a tool is its ability to optimize complex scenarios, and wireless networks are ripe for optimization.

How is AI being used in 5G networks?

As 5G matures, AI and ML are already being introduced for study by the 3rd Generation Partnership Project (3GPP), the standardization body that maintains cellular standards.

AI applications under consideration are primarily in the air interface, including network energy saving, load balancing, and mobility optimization. Potential use cases 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 (CSI) feedback, beam management, and positioning.

It is important to note that 3GPP is not developing AI/ML models. Instead, it seeks to create common frameworks and evaluation methods for AI/ML models being added into different air interface functions.

Outside of the 3GPP and the air interface, O-RAN Alliance explores how AI/ML can improve network orchestration. For example, O-RAN Alliance has a unique feature in its architecture called the RAN Intelligent Controller (RIC), designed to host AI/ML optimization applications. The RIC can host xApps, which run in near real-time, and rApps, which run in non-real-time. xApps for improving spectral 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.

Fig. 1: O-RAN network.

How will 6G leverage AI?

6G is in its infancy, but it is already clear that AI/ML will be a fundamental part of 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 to look at these AI-native networks is to extrapolate the diagram above (figure 1) based on current trends of virtualization and the RAN (Radio Access Network) disaggregation. Each network block will likely contain AI/ML models varying from vendor to vendor and application to application (figure 2).

Fig. 2: O-RAN 6G network.

AI-native networks can also mean networks built to run AI/ML models natively. Consider the design flow below (figure 3). In traditional 5G networks, the air interface comprises different processing blocks designed by humans. In 5G Advanced, each block will leverage ML to optimize a specific function. In 6G, AI may design the entire air interface using deep neural networks.

Fig. 3: Progression from AI-infused to AI-native networks.

How will AI be used for optimization?

Building on the idea that AI/ML can improve network management orchestration, 6G looks to leverage AI and ML to solve optimization challenges. For example, AI could optimize the power consumption of the network by turning on and off components based on real-time operating conditions.

Today, xApps and rApps accomplish this at a base station level by turning on and off power-hungry components like power amplifiers when they are not in use. However, the ability of AI to quickly solve challenging computing problems and analyze large amounts of data opens the possibility of optimizing our networks at a more extensive, city-wide, or national scale.

Entire base stations could be turned off during low use, and cells reconfigured to service real-time demand in an energy-optimized way using the least possible resources. It is not possible to reconfigure base stations and city-wide networks in this way today—it takes days or weeks to reconfigure and test any changes made to network configurations. Though, advances in different AI techniques remain promising and are top of mind for infrastructure providers.

Wireless networks will not wait for 6G to start leveraging the power of AI. Active research is happening across the entire ecosystem to develop new models and integrate them into the wireless systems of both today and tomorrow. However, these models are still new and must be evaluated for rigor and reliability.

Properly training AI models on diverse data sets, quantifying their improvement over traditional techniques, and defining new test methodology for AI-enabled modules are critical steps that must be taken as this new tech is adopted.

As AI models and testing best practices mature, there is no doubt that AI will revolutionize wireless communications in the next 5-10 years with and that we will witness more innovative applications for AI in 5G and 6G networks.