SavedAdd your journal

Journals / Zeki Sistemler Teori ve Uygulamaları Dergisi / 2026 / Cilt: 9 Sayı: 2026

Unveiling 5G Core Research Trends: Thematic Clustering and LLM-Enhanced Insights into Architecture, Security, and Artificial Intelligence

5G Çekirdek Araştırma Trendlerinin Açıklanması: Tematik Kümeleme ve Mimari, Güvenlik ve Yapay Zeka Konularında LLM ile Güçlendirilmiş İçgörüler

Hüseyin Parmaksız(BILECIK SEYH EDEBALI UNIVERSITY)0000-0001-8455-5625
Harun Şeker(BILECIK SEYH EDEBALI UNIVERSITY)0000-0002-9205-4035
Pages
1–14
Publication Date
2026-03-30
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

This methodology, which combines quantitative clustering with qualitative LLM analysis, highlights the strategic role of 5G Core in both communication and as the architecture, security, and AI infrastructure of digital transformation, in a multidimensional way.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:5G Core is the backbone of digital transformation with ultra-low latency, network slicing, and dense IoT integration.
📊
Key Findings & Data:In the study, 635 academic studies indexed in Web of Science were clustered using Leiden, Louvain, HDBSCAN, and K-Means, and five main themes were identified: service-based architecture, security (post-quantum, blockchain), artificial intelligence/machine learning Network Data Analytics Functionality (NWDAF), deep reinforcement learning), cloud/edge computing, and network resource management.
💡
Conclusion & Impact:This methodology, which combines quantitative clustering with qualitative LLM analysis, highlights the strategic role of 5G Core in both communication and as the architecture, security, and AI infrastructure of digital transformation, in a multidimensional way.
🔬Design:Review & Systematic Survey
📍Scope:Comprehensive Sample
⚙️Variables:5G çekirdek ağı · Büyük dil modelleri · Yapay zeka

Abstract

5G Core is the backbone of digital transformation with ultra-low latency, network slicing, and dense IoT integration. In the study, 635 academic studies indexed in Web of Science were clustered using Leiden, Louvain, HDBSCAN, and K-Means, and five main themes were identified: service-based architecture, security (post-quantum, blockchain), artificial intelligence/machine learning Network Data Analytics Functionality (NWDAF), deep reinforcement learning), cloud/edge computing, and network resource management. The clustering methods were evaluated using the Silhouette, Davies-Bouldin, and Calinski-Harabasz quality metrics. Although K-means appears to be at the top in terms of quality metrics, Leiden and Louvain outperform K-means in terms of interpretability. A hybrid Large Language Models (LLMs) approach was used for theme interpretation. General themes were identified using Qwen3-Max-Preview, and then the previously identified themes were supported using cloud-based free Nemotron, gpt-oss-20b, and Sonoma SkyAlpha models via OpenRouter. Qwen3 stands out in terms of semantic depth and summarization accuracy. This methodology, which combines quantitative clustering with qualitative LLM analysis, highlights the strategic role of 5G Core in both communication and as the architecture, security, and AI infrastructure of digital transformation, in a multidimensional way.

Özet

5G Core, ultra düşük gecikme süresi, ağ dilimleme ve yoğun IoT entegrasyonu ile dijital dönüşümün temel bileşenlerindendir. Bu çalışmada Web of Science veritabanında “5G Core” ifadesi aranmış ve bulunan 635 akademik yayın Leiden, Louvain, HDBSCAN ve K-Means kümeleme algoritmaları kullanılarak analiz edilmiştir. Analiz sonucunda; hizmet tabanlı mimari, güvenlik (kuantum sonrası, blok zinciri), yapay zeka/makine öğrenimi (NWDAF, derin pekiştirme öğrenimi), bulut/kenar bilişim ve ağ kaynak yönetimi olmak üzere beş ana tema belirlenmiştir. Kümeleme performansı Silhouette katsayısı, Davies–Bouldin indeksi ve Calinski–Harabasz skoru gibi içsel kalite metrikleri kullanılarak değerlendirilmiştir. Nicel metrikler açısından K-Means algoritması en yüksek performansı göstermiş olsa da, Leiden ve Louvain yöntemlerinin ortaya çıkardığı kümelerin tematik tutarlılığı ve yorumlanabilirliği daha yüksek bulunmuştur. Bu nedenle, nicel kalite ölçütlerinin ötesinde, kümelerin anlamsal anlamlandırılabilirliği de değerlendirmeye dâhil edilmiştir. Tematik yorumlama aşamasında hibrit bir Büyük Dil Modelleri (LLMs) yaklaşımı benimsenmiştir. İlk olarak Qwen3- Max-Preview modeli kullanılarak genel tematik yapı çıkarılmış, ardından OpenRouter platformu üzerinden erişilen Nemotron, gptoss- 20b ve Sonoma SkyAlpha modelleri ile bu temalar doğrulanmış ve zenginleştirilmiştir. Karşılaştırmalı analizler, Qwen3 modelinin anlamsal derinlik, kavramsal tutarlılık ve özetleme doğruluğu bakımından daha üstün performans sergilediğini göstermiştir. Nicel kümeleme ile nitel LLM analizini birleştiren bu metodoloji, 5G Core'un sadece iletişimde değil, aynı zamanda çok boyutlu bir şekilde dijital dönüşümün mimarisi, güvenliği ve yapay zeka altyapısı olarak da stratejik rolünü ortaya koymaktadır.

🔖

Cite This Article

Parmaksız, H., Şeker, H. (2026). Unveiling 5G Core Research Trends: Thematic Clustering and LLM-Enhanced Insights into Architecture, Security, and Artificial Intelligence. Zeki Sistemler Teori ve Uygulamaları Dergisi, Cilt: 9 Sayı: 2026, 1–14. https://doi.org/10.38016/jista.1788856

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (38)

  1. Agarwal, S., Ahmad, L., Ai, J., Altman, S., Applebaum, A., Arbus, E.,. & Zhao, S., 2025. gpt-oss-120b & gpt-oss-20b model card. arXiv preprint arXiv:2508.10925.
  2. Akarsu, O., & Parmaksız, H., 2025. Anatomy of Digital Leadership Studies: An Analysis with Topic Modeling Approaches. Business and Economics Research Journal, 16(2), 179-205.
  3. Akashi, K., Watanabe, H., Yamamoto, S., Ishihara, T., Iimura, T., & Sekiya, Y., 2025. P-Cloud5GC: Innovative 5G Core Architecture on Public Cloud with Scalability and Fault Tolerance. 2025 IEEE 11th International Conference on Network Softwarization (NetSoft), June 2025, pp. 518-522.
  4. Anuar, S. H. H., Abas, Z. A., Yunos, N. M., Zaki, N. H. M., Hashim, N. A., Mokhtar, M. F.,. & Nizam, A. F., 2021. Comparison between Louvain and Leiden algorithm for network structure: A review. Journal of Physics: Conference Series 2129(1), 012028.
  5. Basant, A., Khairnar, A., Paithankar, A., Khattar, A., Renduchintala, A., Renduchintala, A.,. & Shahbazyan, R., 2025. NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba- Transformer Reasoning Model. arXiv preprint arXiv:2508.14444.
  6. Blondel, V. D., Guillaume, J. L., Lambiotte, R., & Lefebvre, E., 2008. Fast unfolding of communities in large networks. Journal of Statistical Mechanics: Theory and Experiment, 2008(10), P10008.
  7. Candal-Ventureira, D., Fondo-Ferreiro, P., Gil- Castiñeira, F., & González-Castaño, F. J., 2020. Quarantining malicious IoT devices in intelligent sliced mobile networks. Sensors, 20(18), 5054.
  8. Çakmak, M., 2024. The Impact of Denial-of-Service Attacks and Queue Management Algorithms on Cellular Networks. Journal of Intelligent Systems: Theory and Applications, 7(1), 1-13.
  9. Chakir, Y., & Lahsen-Cherif, I., 2025. ForensicsData: A Digital Forensics Dataset for Large Language Models. arXiv preprint arXiv:2509.05331.
  10. Coronado, E., Behravesh, R., Subramanya, T., Fernandez-Fernandez, A., Siddiqui, M. S., Costa- Pérez, X., & Riggio, R., 2022. Zero touch management: A survey of network automation solutions for 5G and 6G networks. IEEE Communications Surveys & Tutorials, 24(4), 2535- 2578.
  11. Corsi, A., Gür, S., Brighente, A., & Conti, M., 2025. Evaluation of Post-Quantum Key Encapsulation Methods in 5G Core Network. In 2025 IEEE Wireless Communications and Networking Conference (WCNC), March 2025, pp. 1-6.
  12. Davies, D. L., & Bouldin, D. W., 2009. A cluster separation measure. IEEE Transactions on Pattern Analysis and Machine Intelligence, (2), 224-227.
  13. Hussain, S. A., Kohli, R., Zahoor, S., & Sofi, S. A., 2025. Transforming the GUI Landscape: Harnessing the Power of MPNet base v2 Sentence Transformers. Procedia Computer Science, 259, 1809-1816.
  14. Joe Dhanith, P. R., & Surendiran, B., 2022. An ontology learning based approach for focused web crawling using combined normalized pointwise mutual information and Resnik algorithm. International Journal of Computers and Applications, 44(12), 1123-1129.
  15. Leyva-Pupo, I., Santoyo-González, A., & Cervelló- Pastor, C., 2019. A framework for the joint placement of edge service infrastructure and user plane functions for 5G. Sensors, 19(18), 3975.
  16. Ma, L., Wen, X., Wang, L., Lu, Z., & Knopp, R., 2018. An SDN/NFV based framework for management and deployment of service based 5G core network. China Communications, 15(10), 86-98.
  17. Manias, D. M., Chouman, A., & Shami, A., 2022. An NWDAF approach to 5G core network signaling traffic: Analysis and characterization. In GLOBECOM IEEE Global Communications Conference, December 2022, pp. 6001-6006.
  18. Ming, L., Leau, Y. B., & Xie, Y. (2024). Distributed denial of service attack in HTTP/2: Review on security issues and future challenges. IEEE Access, 12, 33296-33308.
  19. Nadar, A., & Härri, J., 2024. Enhancing network data analytics functions: Integrating AIaaS with ML model provisioning. 2024 22nd Mediterranean Communication and Computer Networking Conference (MedComNet), June 2024, pp. 1-4.
  20. Pawar, A., & Deshmukh, S., 2025. Novel Clustering Approach for Anomaly Detection in 5G Signals. 2025 6th International Conference for Emerging Technology (INCET), May 2025, pp. 1-5.
  21. Popovski, P., Trillingsgaard, K. F., Simeone, O., & Durisi, G., 2018. 5G wireless network slicing for eMBB, URLLC, and mMTC: A communication- theoretic view. IEEE Access, 6, 55765-55779.
  22. Qazzaz, M. M., Kułacz, Ł., Kliks, A., Zaidi, S. A., Dryjanski, M., & McLernon, D., 2024. Machine learning-based xApp for dynamic resource allocation in O-RAN networks. 2024 IEEE International Conference on Machine Learning for Communication and Networking (ICMLCN), May 2024, pp. 492-497.
  23. Quan, B. L. Y., Wahab, N. H. A., Al-Dhaqm, A., Alshammari, A., Aqarni, A., Abd Razak, S., & Wei, K. T., 2024. Recent advances in sharding techniques for scalable blockchain networks: A review. IEEE Access.
  24. Ros, F., Riad, R., & Guillaume, S., 2023. PDBI: A partitioning Davies-Bouldin index for clustering evaluation. Neurocomputing, 528, 178-199.
  25. Sharaf, H., Ahmad, I., & Dimitriou, T., 2022. Extended berkeley packet filter: An application perspective. IEEE Access, 10, 126370-126393.
  26. Şeker, H., & Parmaksız, H., 2025. 5G çekirdek ağında yapay sinir ağı modeli ile saldırı tespiti. 5th Artificial Intelligence and Data Science Congress (ICADA 2025)
  27. Singgalen, Y. A., 2024. Analyzing Social Networks and Topic Clustering in Backpacker Tourism Content Reviews using K-means, Fast HDBScan, and Gaussian Mixture with Communalytic.
  28. Singh, S. K., Rothenberg, C. E., Langlet, J., Kassler, A., Vörös, P., Laki, S., & Pongrácz, G., 2022. Hybrid P4 programmable pipelines for 5G gNodeB and user plane functions. IEEE Transactions on Mobile Computing, 22(12), 6921-6937.
  29. Traag, V. A., Waltman, L., & Van Eck, N. J., 2019. From Louvain to Leiden: Guaranteeing well- connected communities. Scientific reports, 9(1), 1-12.
  30. Tsai, Y. H., & Chen, S. J., 2025. Strengthening SUPI security in 5G Core networks for non-public applications. IEEE Communications Standards Magazine.
  31. Ullah, I., Lim, H. K., Seok, Y. J., & Han, Y. H., 2023. Optimizing task offloading and resource allocation in edge-cloud networks: a DRL approach. Journal of Cloud Computing, 12(1), 112.
  32. Wang, X., & Xu, Y., 2019. An improved index for clustering validation based on Silhouette index and Calinski-Harabasz index. IOP Conference Series: Materials Science and Engineering 569(5), 052024. Wang, X., Sun, T.,
  33. Duan, X., Wang, D., Li, Y., Zhao, M., & Tian, Z., 2022. Holistic service-based architecture for space-air-ground integrated network for 5G-advanced and beyond. China Communications, 19(1), 14-28.
  34. Zhang, D., & Li, S., 2011. Topic detection based on K- means. 2011 International Conference on Electronics, Communications and Control (ICECC), September 2011, pp. 2983-2985.
  35. Zhou, H. B., & Gao, J. T., 2014. Automatic method for determining cluster number based on silhouette coefficient. Advanced Materials Research, 951, 227-230.
  36. Agarwal, S., Ahmad, L., Ai, J., Altman, S., Applebaum, A., Arbus, E.,. & Zhao, S., 2025. gpt-oss-120b & gpt-oss-20b model card. arXiv preprint arXiv:2508.10925.
  37. Anuar, S. H. H., Abas, Z. A., Yunos, N. M., Zaki, N. H. M., Hashim, N. A., Mokhtar, M. F.,. & Nizam, A. F., 2021. Comparison between Louvain and Leiden algorithm for network structure: A review. Journal of Physics: Conference Series 2129(1), 012028.
  38. Basant, A., Khairnar, A., Paithankar, A., Khattar, A., Renduchintala, A., Renduchintala, A.,. & Shahbazyan, R., 2025. NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba- Transformer Reasoning Model. arXiv preprint arXiv:2508.14444.