Fuzzy metaheuristic method for allocating employees to project tasks

D.D. Yartsev, M.Yu. Vorotilova, S.V. Mordvin

---

Abstract: Project implementation planning plays a key role in project management, especially in the context of rapidly increasing project complexity and resource constraints.
Aim. This study was to develop a method for optimally distributing project staff across tasks, minimizing staff overload and ensuring adherence to time and budget constraints.
Materials and methods. To solve this problem, we proposed a hybrid method combining the Worm Optimization algorithm, which models the foraging behavior of Caenorhabditis elegans worms, and the fuzzy clustering method FCM, which is used to narrow the solution space. The Python libraries NetworkX, Scikit-Fuzzy, Matplotlib, and Plotly were used to implement the proposed method. To reduce the search space dimensionality, fuzzy clustering FCM was used, enabling the identification of a solution cluster characterizing the most suitable employees in terms of team characteristics.
Results. As part of the study, a software tool in Python has been implemented that enables automated task distribution among performers. A computational experiment has also been conducted to evaluate the effectiveness of the proposed method and compare its results with those of the popular bioinspired Ant Colony Optimization algorithm, which is characterized by similar agent behavior patterns during solution search.
Conclusions. The validation results demonstrate the advantage of the hybrid method over the basic Worm Optimization algorithm and Ant Colony Optimization, as evidenced by lower objective function values and reduced employee overload, confirming the method’s effectiveness in assigning project performers to tasks.

Keywords: human resource management, conditional multicriteria optimization, metaheuristics, “Worm Optimization”, fuzzy clustering

For citation. Yartsev D.D., Vorotilova M.Yu., Mordvin S.V. Fuzzy metaheuristic method for allocating employees to project tasks. News of the Kabardino-Balkarian Scientific Center of RAS. 2026. Vol. 28. No. 1. Pp. 175–187. DOI: 10.35330/1991-6639-2026-28-1-175-187

©   Yartsev D.D., Vorotilova M.Yu., Mordvin S.V., 2026

References

1. Rubin Yu.B. Management of participation in competition as a field of scientific research. Journal of Modern Competition. 2024. Vol. 18. No. 1(97). Pp. 69–91. DOI: 10.37791/2687-0657-2024-18-1-69-91. (In Russian)
2. Dli M.I., Stoyanova O.V., Belozersky A.Yu. A trajectory assessment model for project management in the field of high-tech industrial products. Journal of Applied Informatics. 2015. Vol. 10. No. 6(60). Pp. 105–117. (In Russian)
3. Komarova L.A., Cheremuhin A.D. Increasing the efficiency of recruitment based on deep neural networks. Journal of Applied Informatics. 2024. Vol. 19. No. 2(110). Pp. 10–22. DOI: 10.37791/2687-0649-2024-19-2-10-22. (In Russian)
4. Bulygina O.V., Yartsev D.D., Kulyasov N.S. et al. Fuzzy bioinspired method for forming a set of candidates for linear positions. Journal of Applied Informatics. 2025. Vol. 20. No. 2(116). Pp. 4–23. DOI: 10.37791/2687-0649-2025-20-2-4-23. (In Russian)
5. Kalinin A.R., Zueva N.A. Creation and application of graph models for employee recruitment tasks. Journal of Applied Informatics. 2025. Vol. 20. No. 3. Pp. 43–65. DOI: 10.37791/2687-0649-2025-20-3-43-65. (In Russian)
6. Glazkova A.S., Tutov S.V., Rozhkov V.V. Formation of personnel potential of chemical enterprises using multi-stage mechanism of target set of applicants of universities. Journal of Modern Competition. 2025. Vol. 19. No. 1. Pp. 38–51. DOI: 10.37791/2687-0657-2025-19-1-38-51. (In Russian)
7. Epikhin A.I. Optimization of working process parameters of marine engines based on the method of multicriteria optimization. Marine Intelligent Technologies. 2023. No. 4-1. Pp. 53–57. DOI: 10.37220/MIT.2023.62A.006. (In Russian)
8. Jayan C.Ya., Malykhnia G.F. Multi-criterion optimization of control process based on DPCA and ANN. Systems analysis in design and management. 2024. Pp. 7–14. DOI: 10.18720/SPBPU/2/id24-492
9. Eremina I.I. Mathematical model for solving the optimization problem of distribution of production and labor resources of an enterprise. X Mezhdunarodnaya nauchno-prakticheskaya konferenciya «ETAP-2023». Naberezhnye Chelny, KFU. 2024. Pp. 608–621. (In Russian)
10. Böðvarsdóttir E.B., Stidsen T. A review of multi-objective optimization methods for personnel rostering problems. Journal of Scheduling. 2025. DOI: 10.1007/s10951-025-00845-0
11. Rodríguez-Ballesteros S., Alcaraz J., Anton-Sanchez L. Metaheuristics for the bi-objective resource-constrained project scheduling problem with time-dependent resource costs: An experimental comparison. Computers & Operations Research. 2024. Pp. 163. DOI: 10.1016/j.cor.2023.106489
12. Yang J., Qiu A., Yang Zh. Fuzzy clustering method with approximate orthogonal regularization. Applied Soft Computing. 2023. Vol. 147. Pp. 110829. DOI: 10.1016/j.asoc.2023.110829
13. Nesamalar K.E., Satheeshkumar J., Amudha T. Efficient DNA-ligand interaction framework using fuzzy C-means clustering based glowworm swarm optimization (FCMGSO) method. Journal of Biomolecular Structure and Dynamics. 2023. Vol. 41. No. 13. Pp. 6249–6261. DOI: 10.1080/07391102.2022.2105958
14. Arnaout J-P. A worm optimization algorithm to minimize the makespan on unrelated parallel machines with sequence-dependent setup times. Annals of Operations Research. 2020. Vol. 285. Pp. 273–293. DOI: 10.1007/s10479-019-03138-w
15. Dli M.I., Puchkov A.Yu., Maksimkin M.V. A software model of an intelligent control system for complex processing of small ore raw materials. Journal of Applied Informatics. 2024. Vol. 19. No. 6(114). Pp. 96–112. DOI: 10.37791/2687-0649-2024-19-6-96-112. (In Russian)
16. Galimullin N.R. Python: using Python to automate everyday tasks. Ekonomika i upravlenie problemy resheniya [Economics and Management: Problems and Solutions]. 2024. Vol. 9. No. 9(150). Pp. 69–76. DOI: 10.36871/ek.up.p.r.2024.09.09.010. (In Russian)
17. Dorigo M., Birattari M., Stützle T. Ant colony optimization. Computational Intelligence Magazine. 2006. Vol. 1. Pp. 28–39. DOI: 10.1109/MCI.2006.329691

Information about the authors

Denis D. Yertsev, Postgraduate Student, Rosinformagrotech;
60, Lesnaya street, Pushkinsky Urban District, Pravdinsky Urban Settlement, Moscow Region, 141261, Russia;
Yarcevdd@me.com, ORCID: https://orcid.org/0009-0009-0760-4783
Margarita Yu. Vorotilova, Postgraduate Student, Branch of the National Research University “Moscow Power Engineering Institute” in Smolensk;
1, Energetichesky proezd, Smolensk, 214013, Russia;
rita.vorotilova@mail.ru, ORCID: https://orcid.org/0009-0001-4646-3540, SPIN-code: 6572-7685
Sergey V. Mordvin, Assistant of the Department, Branch of the National Research University “Moscow Power Engineering Institute” in Smolensk;
1, Energetichesky proezd, Smolensk, 214013, Russia;
mors@1eska.ru, ORCID: https://orcid.org/0009-0005-8121-0716

Funding

The study was performed without external funding.