Vodafone and US-based technology company Cirrus360 have successfully tested an AI-driven predictive digital twin technology. This allows engineers to look into the future and see how mobile mast computing will perform even before installing a mobile mast or introducing major upgrades.
predict the outcome
Applying AI inference to predictive digital twins gives engineers a dynamic virtual model of a physical 5G RAN site. You can then simulate future performance and predict outcomes before making costly upgrades or coverage improvements, saving both time and money.
Powered by Cirrus360’s Declarative Digital Twin, the Gabriel™ platform predicts potential hardware or system failures such as memory, cache limitations, and central processing unit (CPU) utilization. Also, predict customer traffic and possible delays at your site before upgrading or deploying a new RAN. This system provides a way to optimize the hardware and pre-tune the software so that everything works seamlessly with silicon chips and other equipment. This approach is particularly useful when implementing Open RAN that combines equipment from multiple vendors.
Vodafone expects Cirrus360’s Declarative Digital Twin to streamline hardware and software testing and optimize existing resources, such as detecting underutilized CPUs. This allows engineers to focus on key tasks, reduce time spent in the lab, and accelerate network deployment. Engineers typically need to test six to eight different RAN configurations before installing or upgrading a mobile network across a country.
Unlike traditional tightly programmed digital twins, declarative digital twins use high-level rule-based descriptions (declarative specifications) to automatically adapt their structure and behavior to the lifecycle of a physical asset. It defines what a system should do, not how it should do it, and enables automatic reconfiguration as physical assets move from design to test to production. It also ensures that boundary rules are followed, increasing accuracy and reliability.
joint test
A joint test conducted by Vodafone and Cirrus360 in the UK and US shows how an open collaborative ecosystem can stimulate greater innovation. Vodafone hopes to expand this partnership to include other vendors, with support for new AI-powered systems such as Cirrus360’s Gabriel™ platform, and access to real-world test environments in Malaga, Spain, and Newbury, UK.
Kyriakos Exadaktylos, Head of Network Architecture and Open RAN at Vodafone, said: “We are building a framework to accelerate the testing and deployment of new innovations in purpose-built silicon and AI in the RAN. Declarative digital twins with AI Reasoning have the potential to further accelerate this process and deliver higher levels of service to our customers.”
“Our declarative digital twin methodology works with AI Reasoning in Cirrus360’s cloud-based Gabriel™ platform to serve as a RAN test-specific AI assistant for system integrators,” added Chaitali Sengupta, co-founder and CEO of Cirrus360.
Cirrus360’s Declarative Digital Twin platform was developed with funding from the U.S. Department of Commerce, the National Telecommunications and Information Administration (NTIA), and the Public Wireless Supply Chain Innovation Fund (PWSCIF).
