I.N. Sinitsyn1, Yu.P. Titov2

1, 2 FIC «Informatics and Management» RAS (Moscow, Russia)
1, 2 Moscow Aviation Institute (Moscow, Russia)
1 sinitsin@dol.ru, 2 kalengul@mail.ru

In the modern world, civil aviation is actively developing in the direction of import substitution and the transition to the use of domestic aircraft, which requires the implementation of CALS technologies, including analytical and simulation models. These models depend on many parameters, which makes the task of optimizing hyperparameters relevant.

This work is devoted to the construction of SARIMA models for forecasting passenger and cargo transportation in the Russian Federation. For optimal forecasting of 25 aggregated monthly parameters, separate SARIMA models were developed, and the purpose of the study is to apply modifications of the ant colony method to determine the optimal values of hyperparameters.

The results show the effectiveness of the ant colony method for optimizing the hyperparameters of SARIMA and LSTM models. Optimization was carried out using the MAE and RMSE metrics, with less than 10% of solutions from the Pareto set corresponding to the optimal values. However, for more complex models, the search time for optimal solutions increases significantly, without providing a significant advantage over simple SARIMA models.

The practical significance of the work lies in determining the optimal values ​​of hyperparameters for 25 indicators of passenger and cargo transportation, as well as in forecasting the needs for the aircraft fleet until 2030. The projected growth in demand requires an additional expansion of the aircraft fleet by 30 units per year, which, taking into account the decommissioning, implies the production of 60 new aircraft of all types.

Sinitsyn I.N., Titov Yu.P. Optimization of hyperparameters in CALS systems using the ant colony method using the example of forecasting the volumes of air passenger and cargo transportation. Highly Available Systems. 2025. V. 21. № 1. P. 12−24. DOI: https://doi.org/ 10.18127/j20729472-202501-02 (in Russian)

1. Sinicyn I.N., SHalamov A.S. Lekcii po teorii sistem integrirovannoj logisticheskoj podderzhki. 2-e izd. M.: TORUS PRESS. 2019. 1072 s.
2. SHalamov A.S., Kaal' S.A. Modelirovanie i parametricheskij analiz logistiki sistem vysokoj dostupnosti. Sistemy vysokoj dostupnosti. 2006. № 2. S. 40–7.
3. EMISS Gosudarstvennaya statistika [Elektronnyj resurs]. URL: https://www.fedstat.ru/ (data obrashcheniya: 15.02.2025).
4. Operacionnaya statistika gruppy aviakompanij Aeroflot [Elektronnyj resurs]. URL: https://ir.aeroflot.ru/ru/reporting/traffic-statistics/ (data obrashcheniya: 15.02.2025).
5. Kompleksnaya programma razvitiya aviatransportnoj otrasli Rossijskoj Federacii do 2030 goda [Elektronnyj resurs]. URL: http://static.government.ru/media/acts/files/1202206270017.pdf http://static.government.ru/media/files/PqzpRfozEf6AY4iMiUGkmcWIraxAMbdl.pdf (data obrashcheniya: 15.02.2025).
6. Kommercheskie vozdushnye perevozki, FAVT [Elektronnyj resurs]. URL: https://favt.gov.ru/dejatelnost-aviakompanii-reestr-komercheskie-perevozki (data obrashcheniya: 15.02.2025).
7. Karpenko A.P. Sovremennye algoritmy poiskovoj optimizacii. Algoritmy, vdohnovlennye prirodoj. 2-e izd. M.: Izd-vo MGTU im. Baumana. 2017. 446 s.
8. Sajmon D. Algoritmy evolyucionnoj optimizacii: prakticheskoe rukovodstvo. M.: DMK Press. 2020. 1002 s.
9. Colorni A., Dorigo M., Maniezzo V. Distributed Optimization by Ant Colonies. Proc. First Eur. Conf. on Artific. Life, Paris, France, F.Varela and P.Bourgine (Eds.). Elsevier Publishing. 1992. P. 134–142.
10. Dorigo M., Stützle T. Ant Colony Optimization. Cambridge, Massachusetts: MIT Press. 2004. 321 p.
11. Uslu M.O., Erdoğdu K. Ant Colony Optimization and Beam-Ant Colony Optimization on Traveling Salesman Problem with Traffic Congestion. DEUFMD. 2024. V. 26. № 78. P. 519–527. DOI: 10.21205/deufmd.2024267820
12. Sagban R.F., Ku-Mahamud K.R., Abu Bakar M.S. Reactive max-min ant system with recursive local search and its application to TSP and QAP. Intelligent Automation & Soft Computing. 2017. V. 23. № 1. 127–134. DOI: 10.1080/10798587.2016.1177914
13. YUhimenko B.I., Titov N.A., Ushakov V.O. Razrabotka i issledovanie algoritmov murav'inoj kolonii dlya resheniya nekotoryh zadach kombinatornoj optimizacii. Aktual'nye nauchnye issledovaniya v sovremennom mire. 2020. № 11-2(67). S. 101–115.
14. Črepinšek M., Liu S.-H., Mernik M. Exploration and Exploitation in Evolutionary Algorithms: A Survey. ACM Computing Surveys. 2013. V. 45. № 35. DOI: 10.1145/2480741.2480752
15. Dorigo M., Birattari M. Swarm intelligence. Scholarpedia. 2007. V. 2. № 9. P. 1462.
16. Pellegrini P., Stützle T., Birattari M. A critical analysis of parameter adaptation in ant colony optimization. Swarm intelligence. 2012. V. 6. P. 23–48. DOI: 10.1007/s11721-011-0061-0
17. Danesh M., Danesh S. Optimal design of adaptive neuro-fuzzy inference system using PSO and ant colony optimization for estimation of uncertain observed values. Soft Comput. 2024. V. 28. P. 135–152. DOI: 10.1007/s00500-023-09194-6
18. Semenkina O.E., Semenkin E.S. O sravnenii effektivnosti murav'inogo i geneticheskogo algoritmov pri reshenii zadach kombinatornoj optimizacii. Aktual'nye problemy aviacii i kosmonavtiki. 2011. T. 1. № 7. S. 338–339.
19. Sinicyn I.N., Titov Yu.P. Upravlenie naborami znachenij parametrov sistemy metodom murav'inyh kolonij. Avtomatika i telemekhanika. 2023. № 8. S. 153–168. DOI:10.31857/S000523102308010X
20. Sudakov V.A., Titov Yu.P. Issledovanie modeli parametricheskogo grafa v metode murav'inyh kolonij. Matem. modelirovanie. 2024. T. 36. № 6. S. 21–37
21. Sinicyn I.N., Titov Yu.P. Issledovanie algoritmov ciklicheskogo poiska dopolnitel'nyh reshenij pri optimizacii poryadka sledovaniya giperpa­rametrov metodom murav'inyh kolonij. Sistemy vysokoj dostupnosti. 2023. T. 19. № 1. S. 59–73. DOI: 10.18127/j20729472-202301-05
22. Sinicyn I.N., Titov Yu.P. Issledovanie primeneniya metoda murav'inyh kolonij v mnogokriterial'nyh parametricheskih zadachah. Sistemy vysokoj dostupnosti. 2024. T. 20. № 4. S. 52–63. DOI: 10.18127/j20729472-202404-06