NVIDIA released its Aerial wireless software a year ago to join Sionna in creating a suite of open-source tools for 5G and 6G networks. The company has now announced that the combined open-source 5G and 6G tools have surpassed one million downloads. Over 8,000 institutions are currently using these tools.
The tools are being used by universities and research institutions to improve network performance and efficiency. King’s College London researchers used NVIDIA Sionna and Jetson AGX Orin to reduce robot task completion time by up to 52.6 percent. SoftBank integrated a neural receiver into NVIDIA Aerial ACAR, achieving up to 60 percent higher uplink throughput than conventional receivers.
Researchers at ETH Zurich found that tuning neural receivers using local measurements reduced block error rates by more than one third. The University of Leeds reported a 45.6 percent reduction in RAN power consumption using AI to guide base station sleep decisions. CTTC integrated GPU-accelerated radio channel models from NVIDIA Aerial ACAR into the open source 5G-LENA simulator, reducing simulation runtime from approximately three hours to 10-20 minutes while preserving network performance. These advances show how open-source AI tools can make wireless networks more efficient and capable.
