US 11,799,733 B2
Energy usage in a communications network
Armagan Uskudar, Basking Ridge, NJ (US); Premnath Kandhasamy Narayanan, Athlone (IE); Mahmood Osorio, Rockwall, TX (US); James O'Meara, Athlone (IE); Amy De Buitléir, Kilcar (IE); Eugene Gomes, Plano, TX (US); Diego Martos, Plano, TX (US); and Donald Stephen Staudte, Huddinge (SE)
Assigned to TELEFONAKTIEBOLAGET LM ERICSSON (PUBL), Stockholm (SE)
Appl. No. 17/435,969
Filed by Telefonaktiebolaget LM Ericsson (publ), Stockholm (SE)
PCT Filed Oct. 28, 2020, PCT No. PCT/EP2020/080329
§ 371(c)(1), (2) Date Sep. 2, 2021,
PCT Pub. No. WO2022/089741, PCT Pub. Date May 5, 2022.
Prior Publication US 2022/0311675 A1, Sep. 29, 2022
Int. Cl. H04L 29/08 (2006.01); H04L 41/147 (2022.01); H04L 41/16 (2022.01); H04L 43/08 (2022.01)
CPC H04L 41/147 (2013.01) [H04L 41/16 (2013.01); H04L 43/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer implemented method performed by a node in a communications network for determining energy usage in the communications network, the method comprising:
obtaining network data for a plurality of nodes in the communications network and corresponding energy usage measurements for the plurality of nodes, wherein the network data comprises a set of values;
determining parameters that are correlated with the energy usage measurements;
based on the determined parameters, forming a subset of the set of values, wherein each value in the subset is a value for one of the parameters determined to be correlated with the energy usage measurements; and
training a first machine learning (ML) model using a training dataset that comprises the subset of values; and
using the first ML model to output information indicating a predicted amount of energy usage.