PENERAPAN METODE LSTM, ARIMA DAN SARIMA UNTUK MEMPREDIKSI JAM SIBUK PADA TRAFIK INTERNET
DOI:
https://doi.org/10.22441/incomtech.v16i1.27716Keywords:
Trafik, TCBH, LSTM, SARIMA, ARIMAAbstract
Jam sibuk terjadi karena antrian padat jaringan di jam-jam tertentu menyebabkan kemacetan jaringan dan penurunan kinerja. Penelitian ini melakukan peramalan jam sibuk trafik internet dari PT. Comtelindo Balikpapan menggunakan metode LSTM, ARIMA dan SARIMA. Hasil peramalan dihitung menggunakan metode TCBH untuk menentukan nilai jam sibuk. Metode ARIMA, SARIMA dan LSTM diterapkan untuk meramalkan trafik jam sibuk selama periode 28 hari, 56 hari dan 84 hari. Analisis nilai RMSE dan MAPE menunjukkan variasi akurasi prediksi. ARIMA dan SARIMA mengalami peningkatan nilai RMSE dan MAPE seiring dengan panjang periode peramalan, menunjukkan ketidakpastian lebih tinggi. Namun, pada peramalan 56 hari terdapat penurunan signifikan dalam RMSE dan MAPE dengan ARIMA mencatat RMSE sebesar 5013.23, MAPE sebesar 7.73% dan SARIMA mencatat RMSE sebesar 5127.80, MAPE sebesar 8.07%. Ini menunjukkan akurasi sangat baik di bawah 10%. LSTM menunjukkan kesalahan rendah untuk periode pendek (28 hari) dengan RMSE sebesar 1057.18 dan MAPE sebesar 3.34%, tetapi performanya menurun untuk periode lebih panjang. Pengujian dilakukan pada ketiga metode dengan membagi data menjadi empat bagian untuk melihat bagaimana metode merespons data yang ada. Metode ARIMA mendapatkan nilai parameter terbaik untuk data yang sangat kompleks, walaupun nilai parameter MAPE termasuk kategori peramalan yang cukup. Metode SARIMA mendapatkan nilai parameter terbaik untuk data yang cukup kompleks. Metode LSTM mendapatkan nilai parameter terbaik untuk data yang tidak kompleks. Semua model bermanfaat untuk prediksi trafik internet, namun pengembangan lebih lanjut dalam pengolahan data pelatihan diperlukan untuk meningkatkan akurasi peramalan, terutama untuk LSTM.
Downloads
References
F. Hutomo and Y. Astuti, “Analysis of Internet Traffic Using Average Daily Peak Hour (ADPH),” Conference SENATIK STT Adisutjipto Yogyakarta, vol. 4, Nov. 2018, doi: 10.28989/senatik.v4i0.164.
D. A. Lubis, M. B. Johra, and G. Darmawan, “Peramalan Indeks Harga Konsumen dengan Metode Singular Spectral Analysis (SSA) dan Seasonal Autoregressive Integrated Moving Average (SARIMA),” Jurnal Matematika “MANTIK,” vol. 3, no. 2, pp. 74–82, Oct. 2017, doi: 10.15642/mantik.2017.3.2.74-82.
P. Utomo and A. Fanani, “Peramalan Jumlah Penumpang Kereta Api di Indonesia Menggunakan Metode Seasonal Autoregressive Integrated Moving Average (SARIMA),” 2020.
A. D. Milniadi and N. O. Adiwijaya, “ANALISIS PERBANDINGAN MODEL ARIMA DAN LSTM DALAM PERAMALAN HARGA PENUTUPAN SAHAM (STUDI KASUS : 6 KRITERIA KATEGORI SAHAM MENURUT PETER LYNCH),” SIBATIK JOURNAL: Jurnal Ilmiah Bidang Sosial, Ekonomi, Budaya, Teknologi dan Pendidikan, vol. 2, no. 6, pp. 1683 1692, May 2023, doi: 10.54443/sibatik.v2i6.798.
S. Suparyuti, “ANALISIS PERFORMANSI QUALITY OF SERVICE DROP CALL PADA JARINGAN TELEKOMUNIKASI BERBASIS TEKNOLOGI GSM (Global System for Mobile),” 2017.
B. A. Forouzan and S. C. Fegan, “Data Communications and Networking – Forouzan.fourth edition,” 2007.
A. Pankratz, “Forecasting With Dynamic Regression Models,” 1991.
M. Yusuf Fajar Z, “Implementasi Model SARIMA dan Algoritma Genetika pada Prediksi Produksi Minyak Bumi,” 2020.
F. Nur Iman and D. Wulandari, “PREDIKSI HARGA SAHAM MENGGUNAKAN METODE LONG SHORT TERM MEMORY,” 2023 [Online].
D. Sanjaya and S. Budi, “Prediksi Pencapaian Target Kerja Menggunakan Metode Deep Learning dan Data Envelopment Analysis,” Jurnal Teknik Informatika dan Sistem Informasi, vol. 6, no. 2, Aug. 2020, doi: 10.28932/jutisi.v6i2.2678.
S. R. Putra, “IMPLEMENTASI CONVOLUTIONAL NEURAL NETWORK UNTUK KLASIFIKASI OBYEK PADA CITRA,” 2015.
M. Q. Hendikawati and P. Walid, “Time Series Modelling of Stock Price By Modwt-Arima Method Semarang,” UNNES Journal of Mathematics, vol. 8, no. 2, pp. 79–89, 2019.
R. Adhikari and R. K. Agrawal, “An Introductory Study on Time Series Modeling and Forecasting,” 2013.
N. Darina, Widiarti, S. Laelatul Chasanah, and E. Setiawan, “PENERAPAN METODE DOUBLE MOVING AVERAGE DAN DOUBLE EXPONENTIAL SMOOTHING PADA PERAMALAN NILAI IMPOR BARANG KONSUMSI TAHUN 2017-2022,” 2024.
S. Haryadi, TELECOMMUNICATIONS TRAFFIC: TECHNICAL AND BUSINESS CONSIDERATIONS Lantip Safari Media-2013-1st Edition. 2012. [Online].
Downloads
Published
How to Cite
Issue
Section
License
The copyright to this article is transferred to Universitas Mercu Buana (UMB) if and when the article is accepted for publication. The undersigned hereby transfers any and all rights in and to the paper including without limitation all copyrights to UMB. The undersigned hereby represents and warrants that the paper is original and that he/she is the author of the paper, except for material that is clearly identified as to its original source, with permission notices from the copyright owners where required. The undersigned represents that he/she has the power and authority to make and execute this assignment.
We declare that:
1. This paper has not been published in the same form elsewhere.
2. It will not be submitted anywhere else for publication prior to acceptance/rejection by this Journal.
3. A copyright permission is obtained for materials published elsewhere and which require this permission for reproduction.
Furthermore, I/We hereby transfer the unlimited rights of publication of the above mentioned paper in whole to UMB. The copyright transfer covers the exclusive right to reproduce and distribute the article, including reprints, translations, photographic reproductions, microform, electronic form (offline, online) or any other reproductions of similar nature.
The corresponding author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors. This agreement is to be signed by at least one of the authors who have obtained the assent of the co-author(s) where applicable. After submission of this agreement signed by the corresponding author, changes of authorship or in the order of the authors listed will not be accepted.
Retained Rights/Terms and Conditions
1. Authors retain all proprietary rights in any process, procedure, or article of manufacture described in the Work.
2. Authors may reproduce or authorize others to reproduce the Work or derivative works for the authors personal use or for company use, provided that the source and the UMB copyright notice are indicated, the copies are not used in any way that implies UMB endorsement of a product or service of any employer, and the copies themselves are not offered for sale.
3. Although authors are permitted to re-use all or portions of the Work in other works, this does not include granting third-party requests for reprinting, republishing, or other types of re-use.
