In a groundbreaking collaboration, Keysight Technologies and the University of Malaga (UMA) are joining forces to harness the power of artificial intelligence (AI) and machine learning (ML) for advanced wireless communications systems. With a keen focus on 6G research and development, this partnership has successfully devised a method to integrate AI and ML algorithms into design and measurement tools. This integration aims to validate their performance and accelerate industry-wide adoption, addressing interoperability challenges and paving the way for standardized deployment of AI and ML in the wireless sector.
Bridging the gap in wireless standards
Many network operators and vendors have already begun leveraging AI and ML in their networks to enhance performance and efficiency. However, the absence of clear wireless standards for deploying AI and ML has posed significant interoperability challenges among equipment vendors. Javier Campos, R&D Engineer at Keysight, explains, “This situation creates a lot of interoperability problems among equipment vendors and having a standard that isn’t optimized for AI/ML technology – this is the challenge we have been working with the university to solve.”
Enhancing Wireless Performance with AI
One of the critical strategies for optimizing wireless performance revolves around providing and utilizing accurate channel state information (CSI). CSI encompasses a communications link’s known channel properties and conditions, enabling real-time adjustments to transmissions to maintain optimal performance. This component is pivotal in achieving reliable communications with high data rates and multi-antenna systems. Traditionally, calculating and reporting accurate CSI has been computationally and resource-intensive, making it an ideal candidate for integrating AI and ML into the network.
Campos highlights the potential of AI in this context, stating, “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.”
AI-powered CSI feedback enhancement
Recognizing CSI as a prime use case benefiting from AI and ML, wireless researchers at UMA developed an AI/ML model for CSI feedback enhancement. Mari Carmen Aguayo, Professor at Universidad de Málaga and Head of the Institute of Telecommunication Research (TELMA), elaborates, “What we are doing is reducing the information you have to send over the air to provide accurate CSI from the user equipment to the base station.” This reduction is achieved through AI algorithms that compress the required information into minimal quantities, ensuring optimal performance with the least data transmission.
To validate the superiority of their ML model over traditional digital signal processing (DSP) for CSI feedback, UMA researchers turned to Keysight for a digital twin platform. This platform emulated the performance of their model under real-world conditions, allowing for comprehensive testing under various fading profiles and test scenarios.
Opening doors for AI/ML-based standards
Through their collaborative efforts, Keysight and UMA have developed an interface that enables the integration of any AI/ML algorithm adhering to common AI/ML APIs and frameworks into Keysight’s SystemVue, a modeling tool. This breakthrough paves the way for the entire industry to utilize AI and ML algorithms effectively. To facilitate this integration process, Keysight and UMA are actively working to introduce this innovation to the 3rd Generation Partnership Project Radio Access Network (3GPP RAN-1) standards body.
Campos states, “Together, we look forward to progressing in the different areas that 3GPP is studying. We are working to have better usability and measurements to get the insights needed to bring this new technology to the industry.”
Contributions to 3GPP release 18
Following the successful validation of their AI models, UMA and Keysight presented these innovations, along with associated measurement best practices, to the 3GPP as part of Release 18. This marks the first 3GPP release that delves into AI/ML enhancements for the air interface, underlining the significance of their work in shaping the future of wireless communications.
A continual partnership for the future
The partnership between UMA and Keysight is far from over. Their collaboration is set to continue with plans to make further contributions and expand their findings to additional Keysight tools. Their ultimate goal is to empower wireless researchers across the globe to harness the potential of AI and ML in shaping the future of advanced wireless communications.
The collaboration between Keysight Technologies and the University of Malaga represents a significant leap forward in integrating AI and ML into advanced wireless communications systems. Their efforts address interoperability challenges and lay the foundation for standardized deployment of AI and ML in the wireless industry, promising enhanced performance, resource utilization, and energy efficiency in the era of 6G wireless technology.
