Applying Singular Value Decomposition to Network Throughput Forecasting

• Maria C. M. M. Ferreira UECE http://orcid.org/0000-0001-7749-6559
• Maria L. Linhares UECE https://orcid.org/0000-0001-5602-0885
• Thelmo P. Araújo UECE
• Rafael L. Gomes UECE https://orcid.org/0000-0001-7922-0695

DOI: https://doi.org/10.5753/sbrc.2025.6334

Abstract

Several companies and Internet Service Providers (ISPs) perform network monitoring services to understand network behavior and obtain relevant data for strategic planning. However, failures may occur during these measurements, particularly in throughput measurements, hindering the implementation of network performance prediction solutions. In this context, this article proposes an approach that combines data imputation with prediction to enhance the quality of throughput analysis. The solution is based on the Singular Value Decomposition (SVD) technique for univariate data imputation, leveraging the seasonal aspects of time series that influence network throughput performance. After imputation, the series are used in recurrent neural networks for highly efficient predictions. Experiments conducted with real data from the Ipê Network Monitoring Service (Monipê) validated the proposed model’s effectiveness, demonstrating superior efficiency compared to existing solutions.

Keywords: Temporal Data Imputation, Network Throughput Prediction, Singular Value Decomposition (SVD), Recurrent Neural Networks

References

Ahn, H., Sun, K., and Kim, K. (2021). Comparison of missing data imputation methods in time series forecasting. Computers, Materials and Continua, 70, 767–779.

Anil Jadhav, D. P. and Ramanathan, K. (2019). Comparison of performance of data imputation methods for numeric dataset. Applied Artificial Intelligence, 33(10), 913–933.

Cho, B., Dayrit, T., Gao, Y., Wang, Z., Hong, T., Sim, A., and Wu, K. (2020). Effective missing value imputation methods for building monitoring data. In 2020 IEEE International Conference on Big Data (Big Data), 2866–2875.

Ding, Z., Mei, G., Cuomo, S., Li, Y., and Xu, N. (2020). Comparison of estimating missing values in IoT time series data using different interpolation algorithms. International Journal of Parallel Programming, 48(3), 534–548.

Ferreira, M. C., Ribeiro, S. E., Nobre, F. V., Linhares, M. L., Araujo, T. P., and Gomes, R. L. (2024). Mitigating measurement failures in throughput performance forecasting. In 2024 20th International Conference on Network and Service Management (CNSM), 1–7.

García-Peña, M., Arciniegas Alarcón, S., Krzanowski, W., and Duarte Vogel, D. (2021). Missing-value imputation using the robust singular-value decomposition: Proposals and numerical evaluation. Crop Science, 61.

Gomes, R. L., Bittencourt, L. F., and Madeira, E. R. M. (2014a). A similarity model for virtual networks negotiation. In Proceedings of the 29th Annual ACM Symposium on Applied Computing, SAC ’14, 489–494. New York, NY, USA: Association for Computing Machinery.

Gomes, R. L., Bittencourt, L. F., Madeira, E. R. M., Cerqueira, E., and Gerla, M. (2014b). An architecture for dynamic resource adjustment in VSDNs based on traffic demand. In 2014 IEEE Global Communications Conference, 2005–2010.

Li, H. (2021). Time works well: Dynamic time warping based on time weighting for time series data mining. Information Sciences, 547, 592–608.

Naf, J., Spohn, M.-L., Michel, L., and Meinshausen, N. (2022). Imputation scores.

Park, J., Muller, J., Arora, B., Faybishenko, B., Pastorello, G., Varadharajan, C., Sahu, R., and Agarwal, D. (2023). Long-term missing value imputation for time series data using deep neural networks. Neural Computing and Applications, 35(12), 9071–9091.

Phan, T.-T.-H. (2020). Machine learning for univariate time series imputation. In 2020 International Conference on Multimedia Analysis and Pattern Recognition (MAPR), 1–6.

Pinheiro, B., Nascimento, V., Gomes, R., Cerqueira, E., and Abelem, A. (2011). A multimedia-based fuzzy queue-aware routing approach for wireless mesh networks. In 2011 Proceedings of 20th International Conference on Computer Communications and Networks (ICCCN), 1–7.

Portela, A., Linhares, M. M., Nobre, F. V. J., Menezes, R., Mesquita, M., and Gomes, R. L. (2024a). The role of TCP congestion control in the throughput forecasting. In Proceedings of the 13th Latin-American Symposium on Dependable and Secure Computing, LADC ’24, 196–199. New York, NY, USA: Association for Computing Machinery.

Portela, A. L., Menezes, R. A., Costa, W. L., Silveira, M. M., Bittecnourt, L. F., and Gomes, R. L. (2023). Detection of IoT devices and network anomalies based on anonymized network traffic. In NOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium, 1–6.

Portela, A. L. C., Ribeiro, S. E. S. B., Menezes, R. A., de Araujo, T., and Gomes, R. L. (2024b). T-for: An adaptable forecasting model for throughput performance. IEEE Transactions on Network and Service Management, 1–1.

Sandra Taylor, Matthew Ponzini, M. W. and Kim, K. (2022). Comparison of imputation and imputation-free methods for statistical analysis of mass spectrometry data with missing data. Briefings in Bioinformatics, 23(1), 913–933.

Silva, M., Ribeiro, S., Carvalho, V., Cardoso, F., and Gomes, R. L. (2023). Scalable detection of SQL injection in cyber-physical systems. In Proceedings of the 12th Latin-American Symposium on Dependable and Secure Computing, LADC ’23, 220–225. New York, NY, USA: Association for Computing Machinery.

Silva, M. V., Mosca, E. E., and Gomes, R. L. (2022). Green industrial Internet of Things through data compression. International Journal of Embedded Systems, 15(6), 457–466.

Silveira, M. M., Portela, A. L., Menezes, R. A., Souza, M. S., Silva, D. S., Mesquita, M. C., and Gomes, R. L. (2023a). Data protection based on searchable encryption and anonymization techniques. In NOMS 2023-2023 IEEE/IFIP Network Operations and Management Symposium, 1–5.

Silveira, M. M., Silva, D. S., Rodriguez, S. J. R., and Gomes, R. L. (2023b). Searchable symmetric encryption for private data protection in cloud environments. In Proceedings of the 11th Latin-American Symposium on Dependable Computing, LADC ’22, 95–98. New York, NY, USA: Association for Computing Machinery.

Spiliotis, E., Assimakopoulos, V., and Makridakis, S. (2020). Generalizing the theta method for automatic forecasting. European Journal of Operational Research, 284(2), 550–558.

Vasileva, P., McKee, S., Penev, A., and Vukotic, I. (2021). PS-DASH – analysis, monitoring and visualization of network measurements. In 2021 International Conference Automatics and Informatics (ICAI), 93–96.

Yamak, P. T., Yujian, L., and Gadosey, P. K. (2020). A comparison between ARIMA, LSTM, and GRU for time series forecasting. In Proceedings of the 2019 2nd International Conference on Algorithms, Computing and Artificial Intelligence, ACAI ’19, 49–55. New York, NY, USA: Association for Computing Machinery.