SoftBank Corp partnered with Nvidia and Mavenir Systems to verify communication from vRANs to multi-access edge computing (MEC) applications, showing GPUs can be used with radio access and AI applications.
The operator stated the companies achieved end-to-end communication from user equipment to image processing MEC applications with vRAN components using GPUs on actual equipment.
SoftBank added it is “working on ways to share resources with several applications using GPUs, even though many vRAN accelerators are specialised for vRAN software”.
Using a GPU platform for AI applications, it plans to enable dynamic resource allocation to handle changing RAN and MEC demand, and lower power consumption of its vRAN.
Looking ahead, SoftBank will use GPUs to enable vRAN sites as a MEC locations.
Separately, SoftBank released the results of joint tests conducted with Germany-based SkyFive verifying the radio propagation characteristics between a base station on the ground and an aeroplane-mounted terminal and antenna using the 2GHz band.
The operator expects the data gathered “will enable the prediction of communication quality” at higher altitudes and help design compatible networks.
Original article can be seen at: