US 12,219,395 B2
Wireless parameter limits for predicted vRAN resource loads
Yu Yan, Kirkland, WA (US); Anuj Kalia, Newcastle, WA (US); Sanjeev Mehrotra, Kirkland, WA (US); and Paramvir Bahl, Bellevue, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on May 26, 2022, as Appl. No. 17/825,596.
Prior Publication US 2023/0388856 A1, Nov. 30, 2023
Int. Cl. H04W 28/08 (2023.01); H04L 1/00 (2006.01); H04W 28/02 (2009.01); H04W 28/24 (2009.01)
CPC H04W 28/0942 (2020.05) [H04L 1/0003 (2013.01); H04W 28/0289 (2013.01); H04W 28/24 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for utilizing computing resources in a virtualized radio access network (vRAN), the method comprising:
determining a predicted resource load for a data traffic processing of wireless communication channels served by the vRAN using a trained neural network model, wherein the data traffic processing comprises at least one of physical layer (PHY) data processing or medium access control layer (MAC) processing for a 5G radio access network;
allocating computing resources for the data traffic processing based on the predicted resource load;
determining wireless parameter limits for the wireless communication channels that constrain utilization of the allocated computing resources for the data traffic processing using the trained neural network model, including setting one or more of a maximum number of radio resource units (RUs) per timeslot or a maximum modulation and coding scheme (MCS) index for the wireless parameter limits; and
performing the data traffic processing using the wireless parameter limits to reduce load spikes that cause a violation of real-time deadlines for the data traffic processing.