US 11,671,842 B2
Monitor and predict Wi-Fi utilization patterns for dynamic optimization of the operating parameters of nearby ENBS using the same unlicensed spectrum
Issa Al-Fanek, Montreal (CA); Havish Koorapaty, Saratoga, CA (US); Meral Shirazipour, Santa Clara, CA (US); Heikki Mahkonen, San Jose, CA (US); and Ravi Manghirmalani, Fremont, CA (US)
Assigned to Telefonaktiebolaget LM Ericsson (publ), Stockholm (SE)
Filed by Telefonaktiebolaget LM Ericsson (publ), Stockholm (SE)
Filed on Feb. 23, 2021, as Appl. No. 17/182,823.
Application 17/182,823 is a continuation of application No. 16/075,378, granted, now 10,966,097, previously published as PCT/IB2016/050618, filed on Feb. 5, 2016.
Prior Publication US 2021/0185544 A1, Jun. 17, 2021
Int. Cl. H04W 16/14 (2009.01); H04W 16/18 (2009.01); H04W 24/08 (2009.01); H04W 72/08 (2009.01); H04W 88/10 (2009.01); H04W 74/08 (2009.01); H04W 24/02 (2009.01); H04L 12/26 (2006.01); H04L 43/12 (2022.01)
CPC H04W 16/14 (2013.01) [H04L 43/12 (2013.01); H04W 16/18 (2013.01); H04W 24/02 (2013.01); H04W 24/08 (2013.01); H04W 72/082 (2013.01); H04W 74/0816 (2013.01); H04W 88/10 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method implemented by one or more network devices for determining parameter values for a base station of a cellular network, where the base station operates in a wireless band that is shared with one or more wireless access points, where the parameter values are determined to optimize network performance in a manner that allows for fair coexistence between the base station and the one or more wireless access points, the method comprising:
obtaining proximity information for the one or more wireless access points relative to the base station;
obtaining activity information for the one or more wireless access points;
determining, using a machine learning system, parameter values for the base station based on the proximity information and the activity information; causing the base station to be configured with the parameter values;
obtaining a first network performance indicator, wherein the first network performance indicator indicates a level of network performance before the base station was configured with the parameter values;
obtaining a second network performance indicator, wherein the second network performance indicator indicates a level of network performance after the base station was configured with the parameter values;
determining a measure of how configuring the base station with the parameter values affected network performance based on comparing the first network performance indicator and the second network performance indicator; and
training the machine learning system using the measure of how configuring the base station with the parameter values affected network performance.