Designing Risk Resilient Networked High-Load Computing
Web-Systems for Information Flow Processing
Nadiia Pasieka
1
, Zora Říhová
2
, Marta Vohnoutová
2
, Nelly Lysenko
1
, Oleksandra
Lysenko
1
, Vasyl Sheketa
3
, Mykola Pasyeka
3
and Nataliia Kulchytska
1
1
Vasyl Stefanyk Precarpathian National University, Ivano-Frankivsk, 76000, Ukraine
2
University of South Bohemia, Branišovská 1645/31a, České Budějovice, 370 05, Czechia
3
National Tech. University of Oil & Gas, Ivano-Frankivsk, 76068, Ukraine
Abstract
Improved models and algorithms for the architecture of a high-loaded risk resilient Web-system, whose
main differences are the possibility of aggregation and sharing of large sets of heterogeneous computing
resources to process information data distributed between geographically separated territories. The
proposed model and algorithms allow the efficient and secure use of additional network resources
connected to the functional network, in contrast to traditional approaches, when these resources are
not available within a single computing node on an independent computing platform. Subsequently,
innovative approaches have been developed to build high-load risk resilient distributed cluster software
systems, which provides a significant increase in the total amount of effective processing of information
flows of the node communication system as a whole. Therefore, the use of this approach is appropriate
for distributed risk-tolerant software systems where rapid loss of information flows is highly
undesirable. Next, algorithms were developed for automated load management of independent
computer platforms of information data flows for efficient scaling (clustering) of risk-resistant software
systems.
Keywords 1
Risky software systems, task distribution, algorithms, architecture, Web-systems.
1. Introduction
Balancing the load on computing nodes provides an even load of hardware and software systems on
independent computing platforms. A risk-resistant software system that balances the computational
load must automatically decide on which node to perform the affective calculations associated with
the new information task. So, the main task of balancing is the process of effective support of the
process of transferring (migration) part or the whole calculation from the most loaded computing
CITRisk’2021: 2nd International Workshop on Computational & Information Technologies for Risk-Informed Systems, September
16–17, 2021, Kherson, Ukraine
EMAIL: pasyekanm@gmail.com (N.Pasieka); zora.rihova@trilogic.cz (Z.Říhová); marta.vohnoutova@gmail.com (M.Vohnoutová);
nelli.lysenko@gmail.com (N.Lysenko); lysenkowa@gmail.com (O.Lysenko); vasylsheketa@gmail.com (V.Sheketa);
pms.mykola@gmail.com (M.Pasieka); nataliia.kulchytska@pnu.edu.ua (N.Kulchytska)
ORCID: 000-0002-4824-2370 (N.Pasieka); 0000-0003-3896-4297 (Z.Říhová); 0000-0002-8915-8626 (M.Vohnoutová);
0000−0002−1029−7843 (N.Lysenko); 0000−0002−1029−7843 (O.Lysenko); 0000−0002−1318−4895 (V.Sheketa);
0000−0002−3058−6650 (M.Pasieka); 0000-0001-9308-6840 (N.Kulchytska)
© 2021 Copyright for this paper by its authors.
Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
CEUR Workshop Proceedings (CEUR-WS.org)