Conceptual Modelling of Criticality of Critical Infrastructure Nth Order Dependency Effect Using Neural Networks
Authors:
- 23 February 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 127-131
Abstract
This paper presents conceptual modelling of the criticality of critical infrastructure (CI) n th order dependency effect using neural networks. Incidentally, critical infrastructures are usually not stand-alone, they are mostly interconnected in some way thereby creating a complex network of infrastructures that depend on each other. The relationships between these infrastructures can be either unidirectional or bidirectional with possible cascading or escalating effect. Moreover, the dependency relationships can take an n th order, meaning that a failure or disruption in one infrastructure can cascade to n th interconnected infrastructure. The n th -order dependency and criticality problems depict a sequential characteristic, which can result in chronological cyber effects. Consequently, quantifying the criticality of infrastructure demands that the impact of its failure or disruption on other interconnected infrastructures be measured effectively. To understand the complex relational behaviour of n th order relationships between infrastructures, we model the behaviour of n th order dependency using Neural Network (NN) to analyse the degree of dependency and criticality of the dependent infrastructure. The outcome, which is to quantify the Criticality Index Factor (CIF) of a particular infrastructure as a measure of its risk factor can facilitate a collective response in the event of failure or disruption. Using our novel NN approach, a comparative view of CIFs of infrastructures or organisations can provide an efficient mechanism for Critical Information Infrastructure Protection and resilience (CIIPR) in a more coordinated and harmonised way nationally. Our model demonstrates the capability to measure and establish the degree of dependency (or interdependency) and criticality of CIs as a criterion for a proactive CIIPR.Keywords
This publication has 7 references indexed in Scilit:
- Modelling methodologies for analysing critical infrastructuresJournal of Simulation, 2018
- Preliminary interdependency analysis: An approach to support critical-infrastructure risk-assessmentReliability Engineering & System Safety, 2017
- Modeling the Dynamics of Human Brain Activity with Recurrent Neural NetworksFrontiers in Computational Neuroscience, 2017
- A multi-criteria decision analysis approach for importance identification and ranking of network componentsReliability Engineering & System Safety, 2017
- A new mathematical framework and spatial decision support system for modeling cascade interdependency of critical infrastructure during geo-disastersJournal of Earth Science, 2017
- Identifying critical infrastructure sectors and their dependencies: An Indian scenarioInternational Journal of Critical Infrastructure Protection, 2014
- Causes of the 2003 Major Grid Blackouts in North America and Europe, and Recommended Means to Improve System Dynamic PerformanceIEEE Transactions on Power Systems, 2005