UDC 004.7
MULTITHREADED IMPLEMENTATION OF GENETIC ALGORITHM FOR MULTI-OBJECTIVE QOS ROUTING IN SOFTWARE-DEFINED NETWORKS
D. A. Perepelkin, Dr. in technical sciences, Professor, CAD Department, Dean of Computer Engineering Faculty, RSREU, Ryazan, Russia;
orcid.org/0000-0003-4775-5745, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
A. N. Saprykin, Ph.D. (in technical sciences), associate professor, CAD Department, RSREU, Ryazan, Russia; orcid.org/0000-0002-3882-1301, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
A. A. Tikhonov, student, RSREU, Ryazan, Russia;
orcid.org/0009-0006-7128-8795, e-mail: This email address is being protected from spambots. You need JavaScript enabled to view it.
The problem of multi-objective Quality of Service (QoS) routing in software-defined networks (SDN) is considered. The aim of the work is to develop and evaluate the performance of a high-performance algorithm for finding optimal routes that satisfy a set of heterogeneous metrics. Due to NP-completeness of multi-objective optimization problem and limited applicability of classical algorithms, multithreaded implementation of genetic algorithm is proposed, focused on the efficient use of multiprocessor systems computational resources. An additive criterion with normalization and weight distribution considering the requirements of different traffic classes is used for metric aggregation. A comparative testing with Dijkstra's and Multi-Constrained Optimal Path (MCOP) algorithms on network topologies of various scales is conducted. The proposed multithreaded modification of genetic algorithm is shown to provide a significant speedup compared to MCOP and to maintain acceptable route quality, especially in large-scale networks (500 – 1000 nodes), demonstrating prospects for application in modern network infrastructures.
Key words: : software-defined networks, genetic algorithm, QoS routing, multithreading, multi-objective optimization.