Application of Self-Organizing Map and K-Means to Cluster Bandwidth Usage Patterns in Campus Environment

Yusup Miftahuddin; Abdur Rafi Syach Ridwan

doi:10.15575/join.v10i1.1438

Authors

Yusup Miftahuddin Department of Informatics, Faculty of Industrial Technology, Institut Teknologi Nasional Bandung, Indonesia
Abdur Rafi Syach Ridwan Department of Informatics, Faculty of Industrial Technology, Institut Teknologi Nasional Bandung, Indonesia

DOI:

https://doi.org/10.15575/join.v10i1.1438

Keywords:

Bandwidth, Clustering, Davies Bouldin Index, Self-Organizing Map, Silhouette Coefficient

Abstract

Unequal bandwidth distribution in campus environments often stems from a lack of understanding of WiFi usage patterns, as seen at Itenas Bandung. Here, bandwidth is allocated equally across all buildings, ignoring differences in demand, leading to inefficiencies in high-usage areas and poor money management due to unnecessary allocation of resources to low-demand buildings. This study aims to optimize bandwidth allocation by analyzing usage patterns using a combination of Self-Organizing Map (SOM) and K-Means clustering methods. SOM is used to group buildings into low, medium, and high bandwidth usage categories, while K-Means refines these clusters to enhance accuracy. The proposed approach demonstrated significant improvements in clustering quality, with the Silhouette Index increasing from 0.321 to 0.773 and the Davies-Bouldin Index dropping from 0.896 to 0.623 in the first test. Similar enhancements were observed in subsequent tests, highlighting the effectiveness of this method in addressing unequal bandwidth distribution. This research offers a practical solution for more efficient network and financial management in educational institutions.

References

[1] Irwansyah, H. Yudiastuti, and F. Panjaitan, “Analisis dan Monitoring WIFI pada Universitas Islam Negeri Palembang,” Journal of Information Technology Ampera, vol. 3, no. 2, pp. 277–290, 2022, [Online]. Available: https://journal-computing.org/index.php/journal-ita/index

[2] M. Saski, I. Iskandar, Novriyanto, and Pizaini, “Optimasi Kualitas Jaringan WIFI Fakultas Melalui Redesain Topologi Dengan Menggunakan Network Simulator 2,” KLIK: Kajian Ilmiah Informatika dan Komputer, vol. 4, no. 2, pp. 1032–1041, 2023, doi: 10.30865/klik.v4i2.1272.

[3] M. G. Nasrullah, N. Heryana, and A. Solehudin, “Manajemen Bandwith Menggunakan Metode Hirarchical Token Bucket Pada Pembatasan Kecepatan Internet (Studi Kasus : Kantor Kelurahan Ciparage Jaya),” JATI (Jurnal Mahasiswa Teknik Informatika), vol. 8, no. 2, pp. 2291–2296, 2024.

[4] T. I. Hermanto and Y. Muhyidin, “Analisis Data Sebaran Bandwidth Menggunakan Algoritma Dbscan Untuk Menentukan Tingkat Kebutuhan Bandwidth Di Kabupaten Purwakarta,” Rabit : Jurnal Teknologi dan Sistem Informasi Univrab, vol. 5, no. 2, pp. 130–137, Jul. 2020, doi: 10.36341/rabit.v5i2.1388.

[5] S. A. Arnomo and Y. Yulia, “Clustering the potential bandwidth upgrade of FTTH broadband subscribers,” ILKOM Jurnal Ilmiah, vol. 13, no. 1, pp. 51–57, Apr. 2021, doi: 10.33096/ilkom.v13i1.805.51-57.

[6] R. N. Zulfahmi, M. Kristiana Daul, M. Al Ayyubi, I. Wayan, Pradnyana, and R. Dwi Bekti, “Pemetaan Kerentanan Tingkat Kriminalitas Menggunakan Metode Self Organizing Map,” Media Cetak, vol. 2, no. 5, pp. 872–881, 2023, doi: 10.55123/insologi.v2i5.2566.

[7] S. Aziz and Mustakim, “Implementasi Algoritma Self Organizing Map untuk Identifikasi Pola Pengelompokan Tingkat Kesejahteraan Keluarga Kabupaten Siak,” IJIRSE: Indonesian Journal of Informatic Research and Software Engineering, vol. 2, no. 2, pp. 82–92, 2022.

[8] R. Shwartz-Ziv and A. Armon, “Tabular data: Deep learning is not all you need,” Information Fusion, vol. 81, pp. 84–90, May 2022, doi: 10.1016/j.inffus.2021.11.011.

[9] A. Ambarwari, Q. J. Adrian, and Y. Herdiyeni, “Analisis Pengaruh Data Scaling Terhadap Performa Algoritme Machine Learning untuk Identifikasi Tanaman,” JURNAL RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 4, no. 1, pp. 117–122, 2020.

[10] A. Kharunnisa and B. Harianja, “Klasifikasi Kompetensi Tenaga Kerja Program Magang Ke Luar Negeri Dengan Metode Self Organizing Maps (SOM),” Journal of Machine Learning and Data Analytics (MALDA), vol. 01, no. 01, 2022.

[11] A. U. Khasanah, “A Comparison Study: Clustering using Self-Organizing Map and K-means Algorithm,” Jurnal Universitas Sebelas Maret, vol. 15, no. 1, pp. 51–58, 2016.

[12] Y. Miftahuddin, S. Umaroh, and F. R. Karim, “Perbandingan Metode Perhitungan Jarak Euclidean, Haversine, Dan Manhattan Dalam Penentuan Posisi Karyawan,” Jurnal Tekno Insentif, vol. 14, no. 2, pp. 69–77, Aug. 2020, doi: 10.36787/jti.v14i2.270.

[13] I. Ahmad Zaki and I. A. Sembe, “Penerapan K-Means Clustering dalam Pengelompokan Data (Studi Kasus Profil Mahasiswa Matematika FMIPA UNM),” Journal of Mathematics, Computations, and Statistics, vol. 5, no. 2, pp. 163–176, 2022, [Online]. Available: http://www.ojs.unm.ac.id/jmathcos

[14] Zubair, M., Iqbal, M. A., Shil, A., Chowdhury, M. J. M., Moni, M. A., & Sarker, I. H. (2024). An improved K-means clustering algorithm towards an efficient data-driven modeling. Annals of Data Science, 11(5), 1525-1544.

[15] N. Ulinnuha, “Provincial Clustering in Indonesia Based on Plantation Production Using Fuzzy C-Means,” ITSMART: Jurnal Ilmiah Teknologi dan Informasi, vol. 9, no. 1, pp. 8–12, 2020.

[16] Juanita, S., & Cahyono, R. D. (2024). K-means clustering with comparison of Elbow and silhouette methods for medicines clustering based on user reviews. Jurnal Teknik Informatika (JUTIF), 5(1), 283-289.

[17] Jatmiko, A. R., Hendrawan, N. D., Arief, R. M., Putra, F. A. I. A., & Karyudi, M. D. P. (2023). Signifikansi pengaruh akses teknologi informasi terhadap indeks pembangunan manusia di Indonesia. JITEKH: Jurnal Ilmiah Teknologi Harapan, 11(2), 83-94.

[18] Dinata, R. K., & Retno, S. (2024). Optimizing the Evaluation of K-means Clustering Using the Weight Product. Revue d'Intelligence Artificielle, 38(4).

[19] Muningsih, E., Kesuma, C., Sunanto, S., Suripah, S., & Widayanto, A. (2023, May). Combination of K-Means method with Davies Bouldin index and decision tree method with parameter optimization for best performance. In AIP Conference Proceedings (Vol. 2714, No. 1). AIP Publishing.

[20] I. T. Umagapi, B. Umaternate, S. Komputer, P. Pasca Sarjana Universitas Handayani, B. Kepegawaian Daerah Kabupaten Pulau Morotai, and B. Riset dan Inovasi, “Uji Kinerja K-Means Clustering Menggunakan Davies-Bouldin Index Pada Pengelompokan Data Prestasi Siswa,” Seminar Nasional Sistem Informasi dan Teknologi (SISFOTEK), vol. 7, no. 1, pp. 303–308, 2023.