US 12,477,347 B2
Obtaining samples for learning-based resource management by adjusting flow characteristics
Toni Dimitrovski, Boskoop (NL); Remco Litjens, Voorschoten (NL); Apoorva Arora, Delft (NL); and Haibin Zhang, Voorburg (NL)
Assigned to Koninklijke KPN N.V., Rotterdam (NL); and Nederlandse Organisatie Voor Toegepast-Natuurwetenschappelijk Onderzoek TNO, 's-Gravenhage (NL)
Appl. No. 18/251,979
Filed by Koninklijke KPN N.V., Rotterdam (NL); and Nederlandse Organisatie Voor Toegepast-Natuurwetenschappelijk Onderzoek TNO, The Hague (NL)
PCT Filed Nov. 4, 2021, PCT No. PCT/EP2021/080582
§ 371(c)(1), (2) Date May 5, 2023,
PCT Pub. No. WO2022/101080, PCT Pub. Date May 19, 2022.
Claims priority of application No. 20206693 (EP), filed on Nov. 10, 2020; and application No. 20210544 (EP), filed on Nov. 30, 2020.
Prior Publication US 2023/0413063 A1, Dec. 21, 2023
Int. Cl. H04W 16/10 (2009.01); H04W 28/02 (2009.01)
CPC H04W 16/10 (2013.01) [H04W 28/0268 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A system for obtaining samples for a dynamic resource management system in a wireless network, the dynamic resource management system using supervised learning to estimate resource demand, the system comprising at least one processor configured to:
analyze data for the dynamic resource management system to determine one or more combinations of input values which are not present or underrepresented in the data, the data comprising a plurality of samples, each of the samples comprising flow characteristics and state and/or cell characteristics as input values and a quantity of resources as output value,
adjust one or more flow characteristics of a data flow between a user device and a base station to obtain one of the one or more combinations of input values which are not present or underrepresented in the data,
determine a quantity of resources used for the data flow and actual state and/or cell characteristics relevant to the data flow,
create a new sample based on the used quantity of resources, the adjusted flow characteristics, and the actual state and/or cell characteristics, and
store the new sample in the data.