	US 12,244,467 B2
	Distributed network traffic data decomposition method
Chaoyun Zhang, Edinburgh (GB); Paul Patras, Edinburgh (GB); and Marco Fiore, Edinburgh (GB)
Assigned to THE UNIVERSITY COURT OF THE UNIVERSITY OF EDINBURGH, Edinburgh (GB)
Appl. No. 17/912,150
Filed by THE UNIVERSITY COURT OF THE UNIVERSITY OF EDINBURGH, Edinburgh (GB)
PCT Filed Mar. 16, 2021, PCT No. PCT/GB2021/050644 § 371(c)(1), (2) Date Sep. 16, 2022, PCT Pub. No. WO2021/186158, PCT Pub. Date Sep. 23, 2021.
Claims priority of application No. 2003857 (GB), filed on Mar. 17, 2020.
Prior Publication US 2023/0134964 A1, May 4, 2023
Int. Cl. H04L 41/147 (2022.01); H04L 41/16 (2022.01); H04L 43/028 (2022.01)

CPC H04L 41/147 (2013.01) [H04L 41/16 (2013.01); H04L 43/028 (2013.01)]

30 Claims

1. A distributed network traffic data decomposition method comprising the steps of:

receiving input data comprising aggregate network traffic data from a plurality of distributed source locations, wherein the aggregate network traffic data includes traffic data comprising a summation over a plurality of services operating over the network;

converting the input data into a format suitable for further analysis by re-arranging and mapping the locations of the plurality of source locations such that the source locations are arranged in a regular grid pattern and separating the aggregate network traffic data into a time-dependent sequence of snapshots;

analysing the converted data with a neural network, comprising a plurality of neural layers, to extract, in a final neural layer of the plurality of neural layers, a first plurality of outputs from the converted data, wherein each output of the first plurality of outputs corresponds to decomposed traffic volume of one service of the plurality of services operating over the network; and

employing 2D convolutions to extract a second plurality of outputs from determined spatiotemporal correlations; and

predicting, based on the first and second plurality of outputs, a future per-service traffic consumption.