A method of multicriteria data stream distribution in telecommunication networks based on an evolutionary approach

I. Syvolovskyi; О.  Komar

doi:10.36910/6775-2524-0560-2025-59-41

I. Syvolovskyi https://orcid.org/0000-0002-4592-0965
О. Komar https://orcid.org/0009-0002-2994-6556

DOI: https://doi.org/10.36910/6775-2524-0560-2025-59-41

Keywords: telecommunication systems, evolutionary approach, genetic algorithm, encoding, stream, node, traffic, workload, resource intensity, optimization, algorithm implementation, distribution of data streams, solution, scheduling problem

Abstract

The article presents a method of multicriteria decision-making for the distribution of data streams in telecommunication systems, developed on the basis of the modified genetic algorithm NSGA-III. The proposed model takes into account the dynamic nature of the load, resource constraints, the possibility of delegating tasks between clusters, and predicting peak traffic surges. The problem is formalized as a generalized scheduling problem with a set of criteria, including minimizing the use of node resources, load balancing, and reducing the number of delegated streams. The architecture of the system with the logic of stream processing and interaction of cluster coordinators is described. The developed algorithm includes adaptive updating of reference directions, hybrid ranking taking into account the probability of overload, and dynamic adjustment of the mutation rate according to the predicted load. The effectiveness of the proposed approach is confirmed by calculating the fitness function and analyzing the resulting Pareto fronts. It is substantiated that the method allows maintaining high flexibility and accuracy of data stream (load) distribution in the variable environment of telecommunication networks

References

1. Abdallah W., Val T. (2020). Genetic-Voronoi algorithm for coverage of IoT data collection networks. 30th International Conference on Computer Theory and Applications (ICCTA), Alexandria, Egypt, 2020. PP. 16-22.
2. Bernardino R., Paias A. (2018). Metaheuristics based on decision hierarchies for the traveling purchaser problem. International Transactions in Operational Research, 25(4), 2018. PP. 1269-1295. DOI: https://doi.org/10.1111/itor.12330
3. Blank J., Deb K. (2020) Pymoo: Multi-Objective Optimization. IEEE Access, Vol. 8, 2020. PP. 89497-89509.
4. Blank J., Deb K., Dhebar Y., Bandaru S., Seada H. (2012). Generating well-spaced points on a unit simplex for evolutionary many-objective optimization. IEEE Transactions on Evolutionary Computation, 25(1), 2021. PP. 48-60.
5. Cheng R., Jin Y., Olhofer M., Sendhoff B. (2016). A reference vector guided evolutionary algorithm for many-objective optimization. IEEE Transactions on Evolutionary Computation, 20(5), 2016. PP. 773-791.