As mobile carriers around the world transition to software-driven, cloud-native architectures, deploying single-server virtualized RAN (vRAN) has become essential, and to help providers meet these demands and future-proof their infrastructure, Samsung claims to have completed the industry’s first commercial call over vRAN.
The CE giant believes the ability to run RAN and AI workloads on fewer, more powerful servers will be critical as carriers accelerate their transition to software-driven, flexible architectures while seeking more sustainable infrastructure. Additionally, Samsung believes that vRAN can help reduce the physical space required for equipment, improve energy efficiency, and make networks more adaptable to changing and evolving needs.
In particular, single-server deployments can reduce the operator’s total cost of ownership. Single-server vRAN allows carriers to consolidate network elements that previously required multiple servers and simplify management of complex site configurations.
vRAN is powered by the new Intel Xeon 6 system-on-chip (SoC) 6700P-B processor series with up to 72 cores and runs on the live networks of US Tier 1 carriers. This move was completed just a few months after the first wave of Intel Xeon 6 SoCs became commercially available, and builds on Samsung’s previous achievement of completing the industry’s first end-to-end call in a lab environment using Intel Xeon 6 SoCs in 2024.
Samsung said it is committed to pushing the boundaries of network virtualization by providing carriers with “exceptional” performance and reliability. This new achievement is expected to prove vRAN as the platform of choice for next-generation networks, strengthen vRAN’s “leadership in AI-native network technology,” and pave the way for an AI-driven 6G future that delivers higher network performance and increased efficiency.
In the demonstration, cloud-native vRAN powered by Intel’s latest Xeon SoC was run on a single Hewlett Packard Enterprise commercial off-the-shelf (COTS) server powered by Wind River’s cloud platform. As a result, on Samsung’s AI-powered vRAN single server with enhanced processors, carriers can now integrate software-driven network elements such as mobile core, radio access, transport, and security that traditionally required multiple servers, Samsung said.
It further added that this vRAN approach not only reduces network power consumption, capital expenditures (Capex), and operational expenditures (Opex), but also accelerates carrier adoption of AI-RAN and AI services, accelerating 6G readiness due to its flexibility and automation capabilities.
Daryl Schoolar, analyst and director at Recon Analytics, assessed what this move means for the mobile industry, saying, “The success of this first call is an important milestone for the industry. By demonstrating multiple network functions run on next-generation processing technology, Samsung is showing what future networks will look like: more cloud-native, more scalable, and significantly more efficient.”
“This achievement moves the industry beyond theoretical performance improvements to practical, deployable innovations that carriers around the world can leverage to modernize their networks, accelerate automation, and better support AI-driven use cases.”
“This breakthrough represents a major advance in network virtualization and efficiency,” said June Moon, executive vice president and head of network business R&D at Samsung Electronics. “It confirms the real-world readiness of this cutting-edge technology under live network conditions and demonstrates that single-server vRAN deployments are possible.” [withstand] Stringent performance and reliability standards demanded by major carriers.
“Not only are we deploying more sustainable and cost-effective networks, we are also building the foundation to more easily leverage the full power of AI capabilities with end-to-end software-driven network solutions and prepare for 6G.”
“Featuring higher core counts and built-in acceleration for AI and vRAN, the Intel Xeon 6 SoC gives carriers the compute foundation for AI-native, future-ready networks,” said Cristina Rodriguez, vice president and general manager of Networks and Edge at Intel. “This joint effort with River will enable us to strengthen the integration of RAN and AI workloads and accelerate innovation while reducing power consumption and overall costs.”
