INTELLIGENT METHODS OF AUTONOMOUS NAVIGATION AND COLLECTIVE CONTROL OF DISTRIBUTED SYSTEMS IN MESH NETWORKS
DOI:
https://doi.org/10.28925/2663-4023.2026.34.1307Keywords:
large language models; system logs; anomalies; cybersecurity; data leakage; microservices; BERT; GPT; machine learning; intelligent analysis.Abstract
The relevance of the study is due to the growing role of distributed cyber-physical systems, unmanned platforms and autonomous agents. Their functioning requires reliable navigation, adaptive data exchange and coordinated decision-making in dynamic environments. The use of Mesh networks, which provide decentralized interaction between nodes and increase the system's resilience to failures of individual elements, is of particular importance. The purpose of the study is to analyze and generalize intelligent methods of autonomous navigation and collective management of distributed systems in Mesh networks, as well as to determine the prospects for their practical application. To achieve this goal, the methods of system analysis, comparative evaluation of artificial intelligence algorithms, multi-agent management and decentralized data routing were used. As a result of the study, the features of the application of machine learning, reinforcement learning and collective decision-making methods to ensure autonomous navigation of mobile agents in a distributed information environment were identified. It has been established that the combination of intelligent algorithms with self-organized architecture of Mesh networks contributes to increasing the adaptability, scalability and reliability of the functioning of distributed systems. The feasibility of using multi-agent approaches to coordinate the actions of autonomous nodes in conditions of limited resources and variable network topology is substantiated. The scientific novelty of the work lies in the comprehensive generalization of modern approaches to the integration of intelligent navigation methods and collective control in Mesh networks. The practical significance of the results is associated with the possibility of their use in the development of unmanned systems, robotic complexes, sensor monitoring networks and other distributed information and control systems. Further research should be directed to improving the mechanisms of adaptive interaction of agents and increasing the efficiency of decision-making in complex network environments.
Downloads
References
Klishch, M., Lypak, H., Kunanets, N., Pasichnyk, S., & Lypak, T. (2025). Structure of information system for predicting and interpreting user service state changes. Visnyk of Lviv Polytechnic National University. Information Systems and Networks, 17, 226–238. https://doi.org/10.23939/sisn2025.17.226
Lypak, H., Lypak, T., & Kunanets, N. (2024). Designing an information system based on machine learning for preservation and classification of documentary heritage artifacts. Visnyk of Khmelnytskyi National University. Technical Sciences, 339(4), 176–182. https://doi.org/10.31891/2307-5732-2024-339-4-29
Shovak, M. I. (2023). Taxonomy of anomalies in the context of cyber defense and information protection. In XXI All-Ukrainian Scientific and Practical Conference of Students, Postgraduates and Young Scientists "Theoretical and Applied Problems of Physics, Mathematics and Informatics" (pp. 338–342). Igor Sikorsky KPI. https://ela.kpi.ua/handle/123456789/62588
Chen, S., & Liao, H. (2022). BERT-Log: Anomaly detection for system logs based on pre-trained language model. Applied Artificial Intelligence, 36(1), Article 2145642. https://doi.org/10.1080/08839514.2022.2145642
Guan, W., Cao, J., Qian, S., Gao, J., & Ouyang, C. (2024). LogLLM: Log-based anomaly detection using large language models. arXiv preprint arXiv:2411.08561. https://arxiv.org/abs/2411.08561
Guo, H., Yuan, S., & Wu, X. (2021). LogBERT: Log anomaly detection via BERT. In 2021 International Joint Conference on Neural Networks (IJCNN) (pp. 1–8). IEEE. https://arxiv.org/abs/2103.04475
Hadadi, F., Xu, Q., Bianculli, D., & Briand, L. (2024). Anomaly detection on unstable logs with GPT models. arXiv preprint arXiv:2406.07467. https://arxiv.org/abs/2406.07467
Han, X., Yuan, S., & Trabelsi, M. (2023). LogGPT: Log anomaly detection via GPT. In 2023 IEEE International Conference on Big Data (BigData) (pp. 1117–1122). IEEE. https://arxiv.org/abs/2309.14482
Lee, Y., Kim, J., & Kang, P. (2023). LAnoBERT: System log anomaly detection based on BERT masked language model. Applied Soft Computing, 146, Article 110689. https://doi.org/10.1016/j.asoc.2023.110689
Li, A., Zhao, Y., Qiu, C., Kloft, M., Smyth, P., Rudolph, M., & Mandt, S. (2024). Anomaly detection of tabular data using large language models. arXiv preprint arXiv:2406.16308. https://arxiv.org/abs/2406.16308
Lin, Y., Deng, H., & Li, X. (2024). FastLogAD: Log anomaly detection with mask-guided pseudo anomaly generation and discrimination. arXiv preprint arXiv:2404.08750. https://arxiv.org/abs/2404.08750
Liu, C., He, S., Zhou, Q., Li, S., & Meng, W. (2024). Large language model guided knowledge distillation for time series anomaly detection. arXiv preprint arXiv:2401.15123. https://arxiv.org/abs/2401.15123
Liu, Y., Tao, S., Meng, W., Wang, J., Ma, W., Zhao, Y., Chen, Y., Yang, H., Jiang, Y., & Chen, X. (2024). Interpretable online log analysis using large language models with prompt strategies (LogPrompt). In Proceedings of the 32nd IEEE/ACM International Conference on Program Comprehension (ICPC) (pp. 35–46). https://arxiv.org/abs/2308.07610
Liu, Y., Ji, Y., Tao, S., He, M., Meng, W., Zhang, S., Sun, Y., Xie, Y., Chen, B., & Yang, H. (2024). LogLM: From task-based to instruction-based automated log analysis. arXiv preprint arXiv:2410.09352. https://arxiv.org/abs/2410.09352
Qi, J., Huang, S., Luan, Z., Yang, S., Fung, C., Yang, H., Qian, D., Shang, J., Xiao, Z., & Wu, Z. (2023). LogGPT: Exploring ChatGPT for log-based anomaly detection. In 2023 IEEE Int. Conf. on HPCC/DSS/SmartCity/DependSys (pp. 273–280). IEEE. https://arxiv.org/abs/2309.01189
Xu, R., & Ding, K. (2024). Large language models for anomaly and out-of-distribution detection: A survey. arXiv preprint arXiv:2409.01980. https://arxiv.org/abs/2409.01980
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Олексій Мельник
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
