Resilience learning through self adaptation in digital twins of human-cyber-physical systems

Abstract

Human-Cyber-Physical-Systems (HPCS), such as critical infrastructures in modern society, are subject to several systemic threats due to their complex interconnections and interdependencies. Management of systemic threats requires a paradigm shift from static risk assessment to holistic resilience modeling and evaluation using intelligent, data-driven and run-time approaches. In fact, the complexity and criticality of HCPS requires timely decisions considering many parameters and implications, which in turn require the adoption of advanced monitoring frameworks and evaluation tools. In order to tackle such challenge, we introduce those new paradigms in a framework named RESILTRON, envisioning Digital Twins (DT) to support decision making and improve resilience in HCPS under systemic stress. In order to represent possibly complex and heterogeneous HCPS, together with their environment and stressors, we leverage on multi-simulation approaches, combining multiple formalisms, data-driven approaches and Artificial Intelligence (AI) modelling paradigms, through a structured, modular and compositional framework. DT are used to provide an adaptive abstract representation of the system in terms of multi-layered spatially-embedded dynamic networks, and to apply self-adaptation to time-warped What-If analyses, in order to find the best sequence of decisions to ensure resilience under uncertainty and continuous HPCS evolution.