US 12,445,866 B2
Selection and optimization of prediction algorithms for 3GPP network data analytics function (NWDAF)
Olivier Forceville, Isere (FR); and Charlotte Aurianne Teetsov, Isere (FR)
Assigned to Hewlett Packard Enterprise Development LP, Spring, TX (US)
Filed by Hewlett Packard Enterprise Development LP, Spring, TX (US)
Filed on Nov. 7, 2022, as Appl. No. 18/053,147.
Claims priority of application No. 22306139 (EP), filed on Jul. 29, 2022.
Prior Publication US 2024/0040402 A1, Feb. 1, 2024
Int. Cl. H04W 24/02 (2009.01); H04L 41/147 (2022.01)
CPC H04W 24/02 (2013.01) [H04L 41/147 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computing device, comprising:
a memory; and
a processor configured to execute machine readable instructions stored in the memory for performing a method comprising:
deconstructing a received subscription request into a plurality of analysis tasks;
creating at least one group of the analysis tasks based on common attributes of the analysis tasks;
creating a analysis prediction workload for each group of the analysis tasks;
deriving a prediction time window from a prediction period contained in the subscription request;
categorizing each single analysis prediction workload by type in which each type has a same prediction time window; and
selecting a short term or long term forecasting algorithm for executing each single analysis prediction workload based on whether the prediction time window is short term or long term, in which short term is defined as below a threshold value and long term is defined as at or above the threshold value;
wherein when the prediction time window is short term, executing the single analysis prediction workload with the selected forecasting algorithm requesting a lower amount of data for predicting in the short term than would be requested for predicting in the long term.