This collaboration aims to revolutionize the industry by validating AI and ML algorithms’ performance and addressing interoperability challenges while also enhancing wireless performance through accurate channel state information.Â
In a strategic collaboration aimed at advancing the integration of artificial intelligence (AI) and machine learning (ML) into advanced wireless communications systems, Keysight has partnered with the University of Malaga (UMA). This partnership, focusing on 6G research and development, has successfully developed a method for incorporating these algorithms into design and measurement tools. The primary goal is to validate their performance and accelerate their adoption within the industry.
Javier Campos, R&D Engineer at Keysight, highlighted the current challenges in the industry, stating, “Many network operators and vendors are already using AI and machine learning in their networks. But, so far, there has been no support from wireless standards on how AI and machine learning should be deployed.” This lack of standardisation has led to interoperability issues among equipment vendors. The collaboration with UMA aims to address this challenge.
One of the key areas where AI and ML can significantly enhance wireless performance is in providing accurate channel state information (CSI). CSI encompasses the known properties and conditions of the communication link, and it plays a vital role in adapting transmissions to optimize performance in real-time. Traditionally, calculating and reporting accurate CSI has been resource-intensive, making it an ideal candidate for integrating AI and ML.While AI has been around for quite a long time, the industry has now been able to identify concrete use cases, like optimizing CSI feedback, where AI can deliver huge gains in performance, resource utilization, and energy efficiency.
The researchers developed an AI/ML model to enhance CSI feedback, aiming to reduce the amount of information transmitted over the air while maintaining optimal performance. They collaborated with Keysight to validate their ML model’s superiority over traditional digital signal processing (DSP) for CSI feedback. Utilizing the company’s digital twin platform, integrated with PathWave System Design (SystemVue) modeling tools, the researchers evaluated their model under various test conditions, demonstrating its superior performance.
The collaboration has not only validated the AI models. Still, it has also resulted in the development of an interface that allows any AI/ML algorithm conforming to common AI/ML APIs and frameworks to be imported into the company’s SystemVue. Both are actively working to introduce this innovation to the 3GPP RAN-1 standards body, facilitating the incorporation of AI/ML-based standards into the industry. Their joint efforts aim to enhance usability and measurements, ultimately bringing this transformative technology to the forefront. The partnership has yielded significant contributions to 3GPP Release 18, the first release focused on AI/ML enhancements for the air interface. This ongoing collaboration promises to make further advancements in the future and extend the application of these findings to various tools, empowering wireless researchers worldwide.
