Year: 2020
Type: conference-paper
Abstract: This article proposes a method for countering threats in complex distributed systems based on predicting their development.Initially, the relevance of the topic under study is justified: it seems promising to use approaches that have found application in solving problems associated with the management of complex systems.Further, an artificial neural network is proposed for forecasting: its structure is shown, as well as a mathematical model of self-learning, which allows achieving more accurate (with less error) results in the framework of threat prediction (in this case, the level of water rise at gauging stations) in complex distributed systems.Testing was carried out, the purpose of which is to confirm the effectiveness of the proposed solution in the framework of forecasting threats in complex distributed systems: the error of the predicted values from real varies from 9% to 10%, which allows us to predict the flood situation in a few days.
Institution: Ufa State Aviation Technical University
Language: English
Subfield: Environmental Engineering
Field: Environmental Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W3104474331