Telekommunikatsiya tarmoqlarining sifatli ishlashini ta'minlashda sun'iy intellektning o'rni
Abstract
Zamonaviy telekommunikatsiya tarmoqlari tobora murakkablashib, katta hajmdagi ma'lumotlarni real vaqt rejimida qayta ishlashni talab qilmoqda. Ushbu tadqiqotda sun'iy intellekt (AI) va mashinaviy o'qitish (ML) algoritmlaridan tarmoq monitoringi, anomaliyalarni aniqlash, nosozliklarni oldindan bashorat qilish va xizmat sifatini (QoS) oshirishda foydalanish imkoniyatlari o'rganildi. 50 000 ta kuzatuv nuqtasidan iborat dataset ustida Random Forest, XGBoost va LSTM modellari taqqoslab sinab ko'rildi. Tajriba natijalari LSTM modelining eng yuqori aniqlikka (93,1%) erishganini ko'rsatdi. Model nosozliklarni o'rtacha 47 daqiqa oldin aniqlay oldi. Tadqiqot natijalari shuni tasdiqlaydiki, AI asosidagi boshqaruv tizimlari zamonaviy, jumladan 5G va istiqbolli 6G tarmoqlarida infratuzilmaning samarali ishlashini ta'minlovchi muhim komponentga aylanib bormoqda.
Kalit so'zlar: sun'iy intellekt, telekommunikatsiya tarmoqlari, mashinaviy o'qitish, LSTM, Random Forest, XGBoost, anomaliyalarni aniqlash, QoS, 5G, tarmoq monitoringi.
References
1. International Telecommunication Union (ITU). Measuring digital development: Facts and Figures 2023. ITU Publications, Geneva, 2023. [Online]. Available: https://www.itu.int/en/ITU-D/Statistics/
2. Springer AI Review. Artificial intelligence advances in anomaly detection for telecom networks. Artificial Intelligence Review. Springer Nature. Jan. 2025. DOI: 10.1007/s10462-025-11108-x
3. Machine learning-based network anomaly detection: Design, implementation, and evaluation. AI, vol. 5, no. 4, pp. 2967-2983, Dec. 2024. MDPI. DOI: 10.3390/ai5040143
4. Ren H., Wang R., Dong W., Li J., Tang Y. Dynamic resampling based boosting random forest for network anomaly traffic detection. Proc. IEA/AIE 2023. Lecture Notes in Artificial Intelligence, vol. 14179. Springer. 2023. pp. 329-340. DOI: 10.1007/978-3-031-36822-6_29
5. Otajonov, S., Khalilov, M., Juraev, N., Djalilov, B., Jo‘raeva, G., & Xusanova, S. (2024). Effects of the interaction of chlorine with PbTe surface and their effect kinetic parameters of strain-sensitive films. In E3S Web of Conferences (Vol. 587, p. 01001). EDP Sciences.
6. Xayitov, A., Sobirov, M., Juraev, N., Asraev, M., Sadikova, M., & Abdurasulova, D. (2024). Creating algorithms to optimize power output in weather station solar panels. In E3S Web of Conferences (Vol. 538, p. 01003). EDP Sciences.
7. 7.Uktam Salomov., Sultonali Abduraxmonov., Omadjon Urishev., Nurmakhamad Juraev. Calculation of the water flow rate of Micro HPP depending on the water fall angle in ideal cases. BIO Web of Conferences 05028 (2024) AQUACULTURE 2023., The Authors, published by EDP Sciences. This is an open access article distributed under the terms of the Creative Commons Attribution License 4.0 (https://creativecommons.org/licenses/by/4.0/)
8. Bikkasani D.C., Yerabolu M.R. AI-driven 5G network optimization: A comprehensive review of resource allocation, traffic management, and dynamic network slicing. American Journal of Artificial Intelligence, vol. 8, no. 2, pp. 55-62. 2024. DOI: 10.11648/j.ajai.20240802.14
9. Gudepu V. et al. Generative-AI for AI/ML model adaptive retraining in beyond 5G networks. arXiv preprint. arXiv:2408.14827. Aug. 2024. Available: https://arxiv.org/abs/2408.14827
10. Goodfellow I., Bengio Y., Courville A. Deep Learning. MIT Press. 2016. 800 p.
