Analyzing Energy and Performance Trade-offs for Network Anomaly Detection based on Deep Learning

• Tiago Torres Schmidt UFRGS http://orcid.org/0009-0007-3469-7212
• Lisandro Z. Granville UFRGS https://orcid.org/0000-0001-8956-8660
• Alberto Schaeffer-Filho UFRGS

DOI: https://doi.org/10.5753/sbrc.2025.5887

Resumo

A detecção de anomalias em redes baseada em aprendizado profundo já atingiu resultados impressionantes. No entanto, a performance obtida por modelos de aprendizado profundo é parcialmente explicada pela grande escala de tais modelos basilares. Este artigo estuda as compensações entre energia e performance para modelos de aprendizado profundo e suas configurações de hiperparâmetros, quando aplicados em detecção de anomalias em redes. O artigo propõe um mecanismo de perfilação de energia e performance para observar os resultados obtidos de cada configuração diferente de um determinado modelo, usando uma combinação de perfilação estatística e instrumentada.

Palavras-chave: Anomaly Detection, Energy Cost, Performance, Deep Learning

Referências

Arafa, Y., ElWazir, A., ElKanishy, A., Aly, Y., Elsayed, A., Badawy, A.-H., Chennupati, G., Eidenbenz, S., and Santhi, N. (2020). Verified instruction-level energy consumption measurement for NVIDIA GPUs. In Proceedings of the 17th ACM International Conference on Computing Frontiers, CF ’20, 60–70. New York, NY, USA: ACM.

Bengio, Y., Simard, P., and Frasconi, P. (1994). Learning long-term dependencies with gradient descent is difficult. IEEE Transactions on Neural Networks, 5(2), 157–166.

Bianco, S., Buzzelli, M., Ciocca, G., and Schettini, R. (2020). Neural architecture search for image saliency fusion. Information Fusion, 57, 89–101.

Boutaba, R., Salahuddin, M. A., Limam, N., Ayoubi, S., Shahriar, N., Estrada-Solano, F., and Caicedo, O. M. (2018). A comprehensive survey on machine learning for networking: Evolution, applications and research opportunities. Journal of Internet Services and Applications, 9(1), 1–99.

Candelieri, A., Perego, R., and Archetti, F. (2021). Green machine learning via augmented Gaussian processes and multi-information source optimization. Soft Computing, 25(19), 12591–12603.

Demme, J. and Sethumadhavan, S. (2011). Rapid identification of architectural bottlenecks via precise event counting. SIGARCH Computer Architecture News, 39(3), 353–364.

Dhanabal, L. and Shantharajah, S. (2015). A study on NSL-KDD dataset for intrusion detection system based on classification algorithms. International Journal of Advanced Research in Computer and Communication Engineering, 4(6), 446–452.

Ene, C. (2023). Council post: 10.5 trillion reasons why we need a united response to cyber risk.

Faustini, P. H. A., Silva, A. S., Granville, L. Z., and Schaeffer-Filho, A. E. (2017). Employing NFV and reinforcement learning to detect and mitigate anomalies in software-defined networks. In Anais do XXXV Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos, Porto Alegre, RS, Brasil. SBC.

Goel, B., McKee, S., and Själander, M. (2012). Techniques to measure, model, and manage power. Volume 87, 7–54.

Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780.

Hsu, C., Chang, S., Juan, D., Pan, J., Chen, Y., Wei, W., and Chang, S. (2018). MONAS: Multi-objective neural architecture search using reinforcement learning. CoRR, abs/1806.10332.

Kim, J., Kim, J., Thi Thu, H. L., and Kim, H. (2016). Long short-term memory recurrent neural network classifier for intrusion detection. In 2016 International Conference on Platform Technology and Service (PlatCon), 1–5.

Kostas, K. (2018). Anomaly detection in networks using machine learning. Research Proposal, 23, 343.

LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. Nature, 521(7553), 436–444.

Marnerides, A., Schaeffer-Filho, A., and Mauthe, A. (2014). Traffic anomaly diagnosis in internet backbone networks: A survey. Computer Networks, 73, 224–243.

Naseer, S., Saleem, Y., Khalid, S., Bashir, M. K., Han, J., Iqbal, M. M., and Han, K. (2018). Enhanced network anomaly detection based on deep neural networks. IEEE Access, 6, 48231–48246.

Preuveneers, D., Tsingenopoulos, I., and Joosen, W. (2020). Resource usage and performance trade-offs for machine learning models in smart environments. Sensors, 20(4).

Rodrigues, C. F., Riley, G., and Luján, M. (2018). Synergy: An energy measurement and prediction framework for convolutional neural networks on Jetson TX1. In Proceedings of the International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA), 375–382.

Saeed, M. M., Saeed, R. A., Azim, M. A., Ali, E. S., Mokhtar, R. A., and Khalifa, O. (2022). Green machine learning approach for QoS improvement in cellular communications. In 2022 IEEE 2nd International Maghreb Meeting of the Conference on Sciences and Techniques of Automatic Control and Computer Engineering (MI-STA), 523–528.

Santos da Silva, A., Wickboldt, J. A., Granville, L. Z., and Schaeffer-Filho, A. (2016). Atlantic: A framework for anomaly traffic detection, classification, and mitigation in SDN. In NOMS 2016 - 2016 IEEE/IFIP Network Operations and Management Symposium, 27–35.

Sedjelmaci, H., Senouci, S. M., and Al-Bahri, M. (2016). A lightweight anomaly detection technique for low-resource IoT devices: A game-theoretic methodology. In 2016 IEEE International Conference on Communications (ICC), 1–6.

Tavallaee, M., Bagheri, E., Lu, W., and Ghorbani, A. A. (2009). A detailed analysis of the KDD Cup 99 data set. In 2009 IEEE Symposium on Computational Intelligence for Security and Defense Applications, 1–6.

Teoh, T. T., Chiew, G., Franco, E. J., Ng, P. C., Benjamin, M., and Goh, Y. J. (2018). Anomaly detection in cyber security attacks on networks using MLP deep learning. In 2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE), 1–5.

Tripp, C. E., Perr-Sauer, J., Gafur, J., Nag, A., Purkayastha, A., Zisman, S., and Bensen, E. A. (2024). Measuring the energy consumption and efficiency of deep neural networks: An empirical analysis and design recommendations.

Vikram, A. and Mohana (2020). Anomaly detection in network traffic using unsupervised machine learning approach. In 2020 5th International Conference on Communication and Electronics Systems (ICCES), 476–479.

Wang, S., Balarezo, J. F., Kandeepan, S., Al-Hourani, A., Chavez, K. G., and Rubinstein, B. (2021). Machine learning in network anomaly detection: A survey. IEEE Access, 9, 152379–152396.

Weaver, V. M., Johnson, M., Kasichayanula, K., Ralph, J., Luszczek, P., Terpstra, D., and Moore, S. (2012). Measuring energy and power with PAPI. In 2012 41st International Conference on Parallel Processing Workshops, 262–268.

Yang, X., Hua, S., Shi, Y., Wang, H., Zhang, J., and Letaief, K. B. (2020). Sparse optimization for green edge AI inference. Journal of Communications and Information Networks, 5(1), 1–15.