5G networks are evolving towards a more software-centric architecture, moving away from the traditional hardware-centric network structure to one where software plays a more prominent role in managing and controlling network functions.
As mobile users’ expectations for the quality of their 5G experience increase, so do the demands on network capacity and performance, making advanced testing methodologies crucial to ensure robust real-time performance.
Hoping to reshape the world’s wireless networks, researchers at Rice University in Texas are developing a testing framework called ETHOS that uses software-based machine learning to test the stability, interoperability, energy efficiency, and communications capabilities of 5G radio access networks (RAN).
5G RAN provides wireless connectivity between user devices such as smartphones, tablets and IoT devices and the core network, allowing users to access and connect to a range of services.
ETHOS enables a clever way of testing that looks not only at how well devices communicate with each other, but also how the special features of computer systems and machine learning affect the software that manages wireless networks.
“Current testing methods for wireless products focus primarily on the communications aspect, evaluating aspects such as load testing and channel emulation,” said Rahman Doost Mohammadi, assistant professor of electrical and computer engineering and the project’s principal investigator.
“However, with the increasing trend towards software-based wireless products, it is essential to take a more holistic approach to testing,” Doost Mohammadi added.
The outstanding features of 5G connectivity – high speed, low latency, and high bandwidth – play a key role in providing an optimal and satisfying user experience.
Next, the team plans to test how well it works, using machine learning algorithms for 5G RAN on the NVIDIA-supported Aerial Research Cloud (ARC) platform.
The ARC platform was developed specifically for the latest wireless technologies, making it easy for developers to get started and create new programs that work in real-time networks.
“The broader impact of this project is far-reaching and has the potential to revolutionize software-based and machine learning-enabled wireless product testing by making it more comprehensive and responsive to the complexities of real-world network environments,” said Ashutosh Sabharwal, co-principal investigator on the project.
“By providing advanced tools to assess and ensure the stability, energy efficiency and throughput of industry products, our research will contribute to the successful deployment of 5G and beyond wireless networks,” Sabharwal added.
The project was funded through a $1.9 million grant from the U.S. Department of Commerce’s National Telecommunications and Information Administration (NTIA).
Get the latest news in engineering, technology, space and science with The Blueprint.
By clicking sign up, you agree to this site’s Terms of Use and Privacy Policy.
About the Editor
Sejal Sharma Sejal is a Delhi-based journalist currently focused on reporting on technology and culture. She is particularly passionate about covering Artificial Intelligence and Semiconductor industry and strives to make people understand the power and pitfalls of technology. Outside work, she enjoys playing badminton and spending time with her dog. Please feel free to email us with any comments or feedback on our work.
