Modeling of reliability of reliability of functioning of objects of network infrastructure of cyber-physical system

In the framework of this study, a structural model of an industrial cyber-physical system architecture was constructed using cloud computing as a basic platform. The presented model details the cyber-physical system on four levels of abstraction, combining all the elements on the basis of the multi-agent approach. The proposed approach based on the data mining methods of the monitoring system allows searching and identifying vulnerable from the point of view of reliability elements of the network infrastructure of a cyber-physical system based on the cloud platform. To conduct a consolidated assessment of the current state of network elements, the study developed a model for ensuring the reliability of network infrastructure facilities, presented in the form of a weighted multigraph forming a plan for collecting, analyzing and verifying data received from the monitoring system. At the same time, the parameters of ensuring reliability for hotel components and nodes, both the infrastructure of the cyber-physical system and the cloud platform, are selected as the vertices of the graph. As arcs of the graph, the relations between the established reliability criteria are presented, reflecting the relationship between the state and the operating parameters of the associated nodes of the infrastructure of a cyber-physical system, taking into account the current parameters of circulating data flows. This will allow you to identify system segments that require reconfiguration, which will reduce the overhead required to make changes. At the same time, the neural network approach is used to predict the uninterrupted infrastructure of the cyber-physical system. The use of the proposed hybrid approach made it possible to predict the behavior of the infrastructure over time and warn of possible failures in the operation of individual components and critical nodes.