Predicting Dual-WAN Failover Using a Variant of the RNN Algorithm for High-Availability Internet Networks
Downloads
The availability of the Internet network is very necessary for daily activities and in the business world. The need for the internet has been very massively used both with cell phones, personal computers and network computers using network hardware. One of the network hardware used in this study is a microtia router as load balancing. Failover prediction analysis with dual WAN to obtain Internet network availability using the RNN variant algorithm method to support stability performance in using the internet. Internet Service Provider (ISP) is an internet provider service used in this study, ISP Indihome 20 Mbps and ISP Telkomsel Modem Orbit GSM model HKM0130 use 4G prepaid cards as internet service providers. The purpose of this study is to predict the redirection of the internet from dual WAN to support the availability of the Internet network. With the stability method using algorithm support, this research provides convenience and algorithms in network reliability configuration. The results show that load balancing with PCC and ECMP methods combined with failover mechanisms significantly improves network performance. For 100 users, throughput increased from 90 Mbps to 180 Mbps, response time decreased from 150 ms to 70 ms, and packet loss dropped from 5% to 2%. The failover mechanism successfully maintains connectivity when one ISP line fails. In conclusion, the dual-WAN failover system with RNN-based prediction effectively ensures high-availability internet networks with proven reliability. The application of research results can be carried out by companies and education providers as well as for other needs.
Amalia, E. R., Nurheki, Saputra, R., Ramadhana, C., & Yossy, E. H. (2023). Computer network design and implementation using load balancing technique with per connection classifier (PCC) method based on MikroTik router. Procedia Computer Science, 216, 103-111. https://doi.org/10.1016/j.procs.2022.12.116
Chen, A., Law, J., & Aibin, M. (2021). A survey on traffic prediction techniques using artificial intelligence for communication networks. Telecom, 2(4), 518-535. https://doi.org/10.3390/telecom2040029
Deng, T., Wan, M., Shi, K., Zheng, Z., & Zhang, T. (2021). Short term prediction of wireless traffic based on tensor decomposition and recurrent neural network. Discover Applied Sciences, 3(8). https://doi.org/10.1007/s42452-021-04761-8
Deo, K., Chaudhary, K., & Assaf, M. (2024). Adaptive quality of service for packet loss reduction using OpenFlow meters. PeerJ Computer Science, 10, e1848. https://doi.org/10.7717/peerj-cs.1848
Haq, I., Ghorashi, S., Karim, F. K., & Mostafa, S. M. (2023). Quality of Service (QoS) performance analysis in a traffic engineering model for next-generation wireless sensor networks. Symmetry, 15(2), 513. https://doi.org/10.3390/sym15020513
Jayadi, A., & Sadamaputra, F. (2023). Implementation of failover on Mikrotik router using check gateway and distance parameters. Journal of Secure Computing, Information, Embedded Network, and Intelligent Systems, 1(2), 36-43. https://doi.org/10.61220/scientist.v1i2.20231
Khaerudin, M., Setiadi, D., Hendharsetiawan, A. A., Sinaga, D., & Susilo, D. D. (2025). Implementation of internet client with three ISP lines using the failover recursive gateway method. Jurnal Ilmiah METADATA, 7(2), 38-49. https://doi.org/10.47652/metadata.v7i2.611
Manurung, E. B. P., & Ula, M. (2023). Comparison analysis of bandwidth speed using MikroTik routerboard 750. Jurnal Techno Nusa Mandiri, 20(1), 48-53. https://doi.org/10.33480/techno.v20i1.4129
Pakiding, R., Iswahyudi, C., & Ariyana, R. Y. (2021). Simulasi perbandingan load balancing dengan metode PCC, ECMP, dan NTH menggunakan GNS3. Jurnal Jarkom, 9(1), 30-39.
Park, J., Yi, D., & Ji, S. (2020). Analysis of recurrent neural network and predictions. Symmetry, 12(4), 615. https://doi.org/10.3390/sym12040615
Pratama, M. B., Mirza, A. H., Suryayusra, & Mukti, A. R. (2024). Implementation of load balancing using PCC (Per-Connection Classifier) method with failover based on MikroTik router (Case Study at RSUD Siti Fatimah). ARRUS Journal of Engineering and Technology, 4(2), 151-164. https://doi.org/10.35877/jetech3112
Ramakrishnan, N., & Soni, T. (2018). Network traffic prediction using recurrent neural networks. In 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA) (pp. 1-6). IEEE. https://ieeexplore.ieee.org/document/8614060/
Saharuna, Z., Nur, R., & Sandi, A. (2020). Analisis Quality of Service jaringan load balancing menggunakan metode PCC dan NTH. CESS (Journal of Computer Engineering, System and Science), 5(1), 131. https://doi.org/10.24114/cess.v5i1.14629
Shafiq, D. A., Jhanjhi, N. Z., & Abdullah, A. (2022). Load balancing techniques in cloud computing environment: A review. Journal of King Saud University - Computer and Information Sciences, 34(7), 3910-3933. https://doi.org/10.1016/j.jksuci.2021.02.014
Tantoni, A., Zaen, M. T. A., & Mutawalli, L. (2022). Komparasi QoS load balancing pada 4 line internet dengan metode PCC, ECMP, dan NTH. Jurnal Media Informatika Budidarma, 6(1), 110. https://doi.org/10.30865/mib.v6i1.3436
Wahid, A., Zain, S. G., & Parenreng, J. M. (2024). Implementation of load balancing using the PCC (Per Connection Classifier) method on computer networks to improve responsiveness. IoTA, 4(4). https://doi.org/10.31763/iota.v4i4.810
Copyright (c) 2026 Tumbuh Tumbuh
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
