US 11,941,710 B2
Behavioral modeling for power utility automation networks
Maik Guenter Seewald, Nuremberg (DE); Laurent Jean Charles Hausermann, Lyons (FR); and André Guérard, Saint Etienne (FR)
Assigned to CISCO TECHNOLOGY, INC., San Jose, CA (US)
Filed by Cisco Technology, Inc., San Jose, CA (US)
Filed on Jan. 14, 2021, as Appl. No. 17/148,934.
Prior Publication US 2022/0222755 A1, Jul. 14, 2022
Int. Cl. G05B 17/02 (2006.01); G06Q 50/06 (2012.01); H02J 13/00 (2006.01)
CPC G06Q 50/06 (2013.01) [G05B 17/02 (2013.01); H02J 13/00028 (2020.01)] 19 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining, by a device, one or more System Configuration Description Language files regarding a power utility automation network;
obtaining, by the device, training data and traffic data regarding traffic in the power utility automation network, wherein the training data comprises information that is extracted using deep packet inspection from network packets routed through the power utility automation network, further wherein the traffic data comprises synthetic traffic data generated by simulation of the power utility automation network;
training, by the device and using the one or more System Configuration Description Language files, the training data and the traffic data, a machine learning-based behavioral model for the power utility automation network that models traffic in the power utility automation network; and
initiating, by the device, use of the behavioral model in the power utility automation network to identify anomalous traffic behavior in the power utility automation network.