Page 154 - Kỷ yếu hội thảo quốc tế: Ứng dụng công nghệ mới trong công trình xanh - lần thứ 9 (ATiGB 2024)

th
HỘI THẢO QUỐC TẾ ATiGB LẦN THỨ CHÍN - The 9 ATiGB 2024 145

strict latency-sensitive applications which require [9]. D. Marutho, S. Hendra Handaka, E. Wijaya, Muljono, “The
real-time, Quality-of-Experience-based optimization. Determination of Cluster Number at k-Mean Using Elbow
It is obvious that more capacity, less latency Method and Purity Evaluation on Headline News”, in: Proc.
Int’l Seminar on Application for Technology of Information
synchronization and stronger resilience MBH is and Communication, ISEMANTIC, 2018, pp. 533-538.
essential to realize ultra-reliable low latency [10].F. Liu, Y. Deng, “Determine the Number of Unknown Targets
communication [12]. Consequently, timely in Open World Based on Elbow Method”, IEEE Trans. on
identification and localization of BSs’ KPI-degraded Fuzzy Systems. 29 (5) (2021) 986-995.
backhaul for correcting is very important. [11].K. P. Sinaga, M. Yang, “Unsupervised K-Means Clustering
Algorithm”, IEEE Access. 8 (2020) 80716-80727.
5. CONCLUSION
[12].Berke Tezergil, Ertan Onur, “Wireless Backhaul in 5G and
This paper proposes an approach utilizing Beyond: Issues, Challenges and Opportunities”, IEEE
unsupervised learning, specifically Elbow method Communications Surveys & Tutorials. 24(4) (2022). 2579 -
combined with the k-means clustering algorithm to 2632.
uncover hidden performance patterns of the MBH
from a real dataset. With the obtained results, MNOs
can optimally classify groups of BSs that have
kindred backhaul transmission attributes in respect of
PL and TWAMP setup success rate in order to
readjust properly and reasonably BSs having bad
transmission quality. According to the results of
clustering MBH data through the proposed method,
the group of BSs that belong to the cluster with poor
transmission quality will be preferentially troubleshot
in order to leverage quality of services and network
capabilities. We can apply the suggested method into
other clustering problems and reflect other behaviors
arising in the mobile network to have a complete
overview of the network’s performance for devising
fair-minded technical solutions.
REFERENCES
[1]. Amir Ashtari Gargari, Matteo Pagin, Michele Polese, Michele
Zorzi, “6G Integrated Access and Backhaul Networks with
Sub-Terahertz Links”, 2023 18th Wireless On-Demand
Network Systems and Services Conference (WONS). (2023)
13-19.
[2]. Ahmed Abdelmoaty, Diala Naboulsi, Ghassan Dahman,
François Gagnon, “When Resiliency Matters: An Overview of
5G and Beyond Wireless Backhaul Network Design”. IEEE
Communications Magazine. 61(12) (2023) 206 - 212.
[3]. Kenneth Y. Ho, Esa Metsälä, “Key 5G Transport
Requirements”. Wiley Telecom, (2023) 65 - 103.
[4]. Ibrahim Alhassan Gedel, Nnamdi I. Nwulu, “Low Latency 5G
IP Transmission Backhaul Network Architecture: A Techno-
Economic Analysis”, Wireless Communications and Mobile
Computing, 2024.
[5] T. –C. Chuang, M. Liu, Y. -Z. Haung, C. –W. Yang, “An
Integrated Monitoring System for 5G Crosshaul Network”, in:
Proc. 21st Asia-Pacific Network Operations and Management
Symposium, APNOMS, 2020, pp. 338–340.
[6]. Y. Türk, E. Zeydan, “A TWAMP Coordinated Data
Compression System for 5G Backhaul”, in: Proc. IEEE Conf.
on Network Softwarization, NetSoft, 2019, pp. 245-247.
[7]. C. Pham-Quoc, T. Tang-Anh, “Predicting mobile networks’
behaviors using Linear Neural Networks”, in: Proc. IEEE
Eighth Int’l Conf. on Communications and Electronics, IEEE
ICCE, 2021, pp. 75-79.
[8]. Paolo Di Prisco; Antti Pietiläinen; Juha Salmelin, "Wireless
Backhaul and Fronthaul," in 5G Backhaul and Fronthaul ,
Wiley, 2023, pp.165-189.

ISBN: 978-604-80-9779-0