Long Short Term Memory and Gated Recurrent Unit Predictive Models for Industrial Control Systems
As Operational Technologies (OT) and Internet of Things (IoT) grew popular, Industrial Control Systems (ICS) which are frequently managed through a Supervisory Control and Data Acquisition (SCADA) systems gained importance but simultaneously anomalies in ICS became a security concern. This paper presents a data-driven approach of predictive modeling for Energy Management System logs that exploits the relationship between data elements in the logs and the predictable aspect of communication patterns between devices in ICS networks using the time series structure of their logs. Specifically, two Recurrent Neural Networks - Stacked Long Short Term Memory (LSTM) and Stacked Gated Recurrent Unit (GRU) models - have been employed to model the behavior of these logs and comparison between these models is demonstrated. Various measures like accuracy, loss, memory usage and testing time are implemented to compare the performance of the models.
Disclaimer/Regarding indexing issue:
We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.