INTELLIGENT MICROSERVICE ARCHITECTURE FOR ADAPTIVE REAL-TIME INTERACTIVE GAME CONTENT GENERATION
DOI:
https://doi.org/10.53920/ITS-2026-1-2Keywords:
adaptive content generation, microservice architecture, cloud computing, stream data processing, AI pipeline, procedural content generation, real-time systemsAbstract
The article investigates modern technologies for implementing adaptive interactive game content generation under high-load conditions and real-time operation requirements. The relevance of the research is determined by the rapid development of intelligent gaming platforms, cloud-native architectures, data stream processing technologies, artificial intelligence systems, and procedural content generation methods. Traditional approaches to game content creation have significant limitations related to low adaptability, scalability complexity, high generation latency, and insufficient personalization of user interaction.
The paper proposes an intelligent microservice architecture for adaptive content generation based on the integration of cloud computing technologies, telemetry data stream processing, AI-driven orchestration, and procedural environment generation. The developed system provides autonomous decision-making regarding dynamic difficulty adjustment, event generation, scenario adaptation, and optimization of generation parameters depending on player behavior.
A mathematical model of adaptive content generation considering player behavioral characteristics, reaction speed, engagement level, performance indicators, and emotional activity is proposed. To ensure scalability, a microservice approach based on Kubernetes, Docker, Apache Kafka, and FastAPI technologies is implemented. The study also presents an AI pipeline organization method for automated content generation using reinforcement learning and real-time stream analytics.
An experimental evaluation of the proposed approach was conducted by comparing it with classical procedural generation systems and monolithic architectures. The obtained results demonstrate a 31% reduction in average generation latency, a 43% increase in system scalability, a 27% improvement in user engagement, and enhanced AI pipeline stability under high-load conditions.
The practical significance of the research lies in the possibility of applying the proposed architecture during the development of modern interactive platforms, game engines, web-oriented multiplayer systems, metaverse environments, and AI-driven entertainment applications.
References
1. Hunicke R. The case for dynamic difficulty adjustment in games // Proceedings of the ACM SIGCHI International Conference on Advances in Computer Entertainment Technology. 2021. DOI: https://doi.org/10.1145/1178477.1178573.
2. Togelius J., Yannakakis G. N., Stanley K. O., Browne C. Search-based procedural content generation: a taxonomy and survey // IEEE Transactions on Computational Intelligence and AI in Games. 2021. DOI: https://doi.org/10.1109/TCIAIG.2011.2148116.
3. Завгородній В. В., Завгородня Г. А., Валявська Н. О., Адаменко В. С., Дороговцев Є. В., Несмачний П. В. Метод автоматичної генерації контенту на основі процедурних алгоритмів // Вчені записки Таврійського національного університету імені В. І. Вернадського. Серія: технічні науки. 2022. Т. 33(72), №1. С. 91–96. DOI: https://doi.org/10.32838/2663-5941/2022.1/15.
4. Yannakakis G. N., Togelius J. Artificial intelligence and games. Springer Nature Switzerland AG, 2022. DOI: https://doi.org/10.1007/978-3-319-63519-4.
5. Завгородня Г. А., Завгородній В. В. Метод генерації ігрового контенту за допомогою нейромереж // Механіка та математичні методи. 2026. Т. 8, №1. С. 54–68. DOI: https://doi.org/10.31650/2618-0650-2026-8-1-54-68.
6. Liapis A., Yannakakis G. N., Togelius J. Procedural personas as critics for dungeon generation // Applications of Evolutionary Computation. 2021. DOI: https://doi.org/10.1007/978-3-319-16549-3_27.
7. Dragoni N., Lanese I., Larsen S. T., Mazzara M., Mustafin R., Safina L. Microservices: yesterday, today, and tomorrow // Present and Ulterior Software Engineering. 2017. DOI: https://doi.org/10.1007/978-3-319-67425-4_12.
8. Stonebraker M., et al. The end of an architectural era (it’s time for a complete rewrite) // Communications of the ACM. 2020. DOI: https://doi.org/10.1145/3226595.3226637.
9. Akidau T., et al. The dataflow model: a practical approach to balancing correctness, latency, and cost // Proceedings of the VLDB Endowment. 2021. DOI: https://doi.org/10.14778/2824032.2824076.
10. Завгородня Г. А., Завгородній В. В. Архітектура інформаційної технології реалізації системи автономної адаптивної генерації контенту на основі методів машинного навчання // Вісник Херсонського національного технічного університету. 2026. №2(96). С. 248–255. DOI: https://doi.org/10.35546/kntu2078-4481.2026.2.30.
11. Завгородня Г., Завгородній В., Ткаченко О., Савченко А. Методологія розроблення системи адаптивної генерації контенту // Технології та інжиніринг. 2025.
Т. 26, №5. С. 21–30. DOI: https://doi.org/10.30857/2786-5371.2025.5.2.
12. Завгородня Г., Завгородній В., Голубенко О., Антоненко А. Засоби забезпечення масштабованості та автономності системи адаптивної генерації контенту // Технології та інжиніринг. 2025. Т. 26, №6. С. 21–31. DOI: https://doi.org/10.30857/2786-5371.2025.6.2.
13. Brown T. B., et al. Language models are few-shot learners // Advances in Neural Information Processing Systems. 2020. DOI: https://doi.org/10.48550/arXiv.2005.14165.
14. Silver D., Schrittwieser J., Simonyan K., et al. Mastering the game of Go without human knowledge // Nature. 2021. DOI: https://doi.org/10.1038/nature24270.
15. Amershi S., Begel A., Bird C., et al. Software engineering for machine learning: a case study // IEEE/ACM International Conference on Software Engineering. 2022. DOI: https://doi.org/10.1109/ICSE-SEIP.2019.00042.
16. Dean J., Ghemawat S. MapReduce: simplified data processing on large clusters // Communications of the ACM. 2021. DOI: https://doi.org/10.1145/1327452.1327492.
17. Zhou N., Georgiou Y., Pospieszny M., et al. Container orchestration on HPC systems through Kubernetes // Journal of Cloud Computing. 2021. DOI: https://doi.org/10.1186/s13677-021-00231-z.
18. Merkel D. Docker: lightweight Linux containers for consistent development and deployment // Linux Journal. 2020. URL: https://www.seltzer.com/margo/teaching/CS508.19/papers/merkel14.pdf.
19. Haarnoja T., et al. Soft actor-critic: off-policy maximum entropy deep reinforcement learning // International Conference on Machine Learning. 2020. DOI: https://doi.org/10.48550/arXiv.1801.01290.
20. Shahrdar S., Menezes R., Nojoumian M. A survey on trust prediction in social networks using machine learning and artificial intelligence // IEEE Access. 2022. DOI: https://doi.org/10.1109/ACCESS.2020.3009445.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Ганна Анатоліївна ЗАВГОРОДНЯ, Валерій Вікторович ЗАВГОРОДНІЙ
This work is licensed under a Creative Commons Attribution 4.0 International License.
