Samsung Electronics as we speak introduced the profitable completion of a multi-cell take a look at at its R&D heart, combining Samsung’s virtualized RAN (vRAN) software program with NVIDIA’s accelerated computing platform. The take a look at validates the efficiency of this built-in answer in a practical community surroundings, marking a key step towards industrial deployment.
Samsung will characteristic this milestone at Mobile World Congress (MWC) 2026 as a part of its broader effort to additional advance AI enhancements into its market-leading, software-driven community portfolio utilizing NVIDIA platforms. The firm will current an AI-RAN demonstration operating on NVIDIA AI infrastructure ― an AI-based downlink efficiency enhance (AI MIMO1 beamformer) that leverages AI algorithms for improved throughput. This demonstration will present how AI can ship larger spectral effectivity for operators, extracting extra capability from present spectrum. Together, these actions mirror Samsung’s management in bringing AI-RAN innovation in direction of commercialization.
“As AI-powered capabilities become integral to meeting the demands of evolving networks and growing traffic needs, Samsung’s vRAN takes center stage with its software-based architecture,” stated Keunchul Hwang, Executive Vice President and Head of Technology Strategy Group, Networks Business at Samsung Electronics. “The successful multi-cell test with NVIDIA is another reinforcement of Samsung’s endeavor and leadership in providing operators with more flexibility and the best performance, with an enriched ecosystem consisting of industry-leading CPU and GPU partners such as NVIDIA.”
The firms are additionally collaborating on driving improvements to allow high-speed connections between the CPU and GPU, by leveraging Samsung’s vRAN and NVIDIA’s unified processor that embeds CPU and GPU right into a single chipset. This permits quick and environment friendly information exchanges between CPU and GPU whereas enabling optimum stability of efficiency and complete price of possession.
Last month, Samsung and NVIDIA continued towards commercialization by finishing the combination of Samsung’s vRAN software program and NVIDIA’s ARC Compact geared up with NVIDIA Grace CPU and NVIDIA L4 GPU. Going ahead, Samsung is dedicated to additional exploring and verifying the synergies that these options carry to superior networks.
“Operators today need AI-native, software-defined infrastructure to stay ahead of evolving connectivity demands. Samsung’s successful multi-cell validation and innovative AI beamforming solution on NVIDIA AI Aerial mark an important milestone towards AI-RAN commercialization,” stated Soma Velayutham, VP of AI and Telecoms, NVIDIA.
By combining its expertise from large-scale industrial vRAN deployments and experience on computing platforms from companions like NVIDIA, Samsung instructions the lead in AI-powered, software-based networks.
Samsung Networks has pioneered the profitable supply of 5G end-to-end options, together with chipsets, radios and cores. Through ongoing analysis and growth, Samsung drives the trade to advance 5G networks with its market-leading product portfolio, from purpose-built RAN, virtualized RAN, Open RAN, AI-RAN, Cloud-native vCore to non-public community options and AI-powered automation instruments and purposes. The firm presently supplies revolutionary community options to cellular operators that ship boundless connectivity to tons of of thousands and thousands of customers worldwide.
