Artificial Neural Networks to Assess Fault Tolerance of Optical Networks
Abstract
Network resilience is a task that requires huge computationally costly mainly because the most popular and reliable approach is by network simulation. On the other hand, machine learning techniques have been used as good surrogate models for some network performance indicators. This paper proposes the use of Artificial Neural Networks (ANN) to predict fault tolerance indicators in optical transport networks. This study focuses on failures in fiber links and uses topological metrics and other network information as ANN input. We have produced a database for training ANNs for real world deployed backbones and compared our results with the ones provided by a discrete event simulator. According to the obtained results, it is possible to obtain a network failure assessment method based on ANN which is 51, 050 times faster than network simulators with a mean square error around 3 · 10-3.
Keywords:
Artificial neural networks, optical networks, regression, surrogate models
References
Araújo, D. R. B., Bastos-Filho, C. J. A., & Martins-Filho, J. F. (2015, July). Artificial neural networks to estimate blocking probability of transparent optical networks: A robustness study for different networks. In 2015 17th international conference on transparent optical networks (icton) (p. 1-4). doi: 10.1109/ICTON.2015.7193693
Araújo, D. R. B., de Barros, G. H. P. S., Bastos-Filho, C. J. A., & Martins-Filho, J. F. (2017, Nov). Surrogate models assisted by neural networks to assess the resilience of networks. In 2017 ieee latin american conference on computational intelligence (la-cci) (p. 1-6). doi: 10.1109/LA-CCI.2017.8285704
Chaves, D., Pereira, H., Bastos-Filho, C., & Martins Filho, J. (2010, 04). Simton: A simulator for transparent optical networks. Journal of Communication and Information Systems, 25, 1-10. doi: 10.14209/jcis.2010.1
de Araujo, D. R. B., Bastos-filho, C. J. A., & Martins-filho, J. F. (2015, May). Methodology to obtain a fast and accurate estimator for blocking probability of optical networks. IEEE/OSA Journal of Optical Communications and Networking, 7(5), 380-391. doi: 10.1364/JOCN.7.000380
de Andrade Barboza, E., Bastos Filho, C. J., & Martins Filho, J. F. (2019). Adaptive control of optical amplifier operating point using voa and multi-objective optimization. Journal of Lightwave Technology.
De Araújo, D. R., Bastos-Filho, C. J., & Martins-Filho, J. F. (2015). An evolutionary approach with surrogate models and network science concepts to design optical networks. Engineering Applications of Artificial Intelligence, 43, 67–80.
Derrible, S., & Kennedy, C. (2010, 09). The complexity and robustness of metro networks. Physica A: Statistical Mechanics and its Applications, 3678-3691. doi: 10.1016/j.physa.2010.04.008
Figueirôa, E., Lima, E., Bastos-Filho, C. J., da Silva, J., Xavier, A. V., & Araújo, D. R. (2017). A routing algorithm based on fuzzy logics for elastic optical networks. In 2017 ieee 18th international conference on high performance switching and routing (hpsr) (pp. 1–6).
Glorot, X., Bordes, A., & Bengio, Y. (2011). Deep sparse rectifier neural networks. In Proceedings of the fourteenth international conference on artificial intelligence and statistics (pp. 315–323).
Hahnloser, R. H., Sarpeshkar, R., Mahowald, M. A., Douglas, R. J., & Seung, H. S. (2000). Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature, 405(6789), 947.
Hastie, T., Tibshirani, R., & Friedman, J. (2008). The elements of statistical learning. Springer.
Haykin, S. (2010). Neural networks and learning machines (3rd ed.). PHI Learning Private Limited.
Ian J. Goodfellow, A. C., Yoshua Bengio. (2016). Deep learning. Cambridge, MA, USA: MIT Press.
Internet growth statistics. (2019). Retrieved from https://www.internetworldstats.com/emarketing.htm. (Acessado em 27/08/2019).
Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. Retrieved from http://arxiv.org/abs/1412.6980
Knight, S., Nguyen, H. X., Falkner, N., Bowden, R., & Roughan, M. (2011). The internet topology zoo. IEEE Journal on Selected Areas in Communications, 29(9), 1765– 1775.
Lewis, T. G. (2009). Network science - theory and applications. John Wiley & Sons.
Mieghem, P. v. (2010). Graph spectra for complex networks. Cambridge University Press. doi: 10.1017/CBO9780511921681
Ramaswami, R., Sivarajan, K., & Sasaki, G. (2009). Optical networks: a practical perspective. Morgan Kaufmann.
Wu, J., Barahona, M., Yue-Jin, T., & Deng, H.-Z. (2010, 07). Natural connectivity of complex networks. Chinese Physics Letters, 27, 078902. doi: 10.1088/0256307X/27/7/078902
Zhao, Z., Feng, X., Wei, F., Wang, S., Cao, M., & Hou, Z. (2013). Optimized neural network ensemble by combination of particle swarm optimization and differential evolution. Advances in Neural Networks, 7951, 367-374. Retrieved from http://dx.doi.org/10.1007/978-3-642-39065-44 5 doi: 10.1007/978-3-642-39065-44 5
Araújo, D. R. B., de Barros, G. H. P. S., Bastos-Filho, C. J. A., & Martins-Filho, J. F. (2017, Nov). Surrogate models assisted by neural networks to assess the resilience of networks. In 2017 ieee latin american conference on computational intelligence (la-cci) (p. 1-6). doi: 10.1109/LA-CCI.2017.8285704
Chaves, D., Pereira, H., Bastos-Filho, C., & Martins Filho, J. (2010, 04). Simton: A simulator for transparent optical networks. Journal of Communication and Information Systems, 25, 1-10. doi: 10.14209/jcis.2010.1
de Araujo, D. R. B., Bastos-filho, C. J. A., & Martins-filho, J. F. (2015, May). Methodology to obtain a fast and accurate estimator for blocking probability of optical networks. IEEE/OSA Journal of Optical Communications and Networking, 7(5), 380-391. doi: 10.1364/JOCN.7.000380
de Andrade Barboza, E., Bastos Filho, C. J., & Martins Filho, J. F. (2019). Adaptive control of optical amplifier operating point using voa and multi-objective optimization. Journal of Lightwave Technology.
De Araújo, D. R., Bastos-Filho, C. J., & Martins-Filho, J. F. (2015). An evolutionary approach with surrogate models and network science concepts to design optical networks. Engineering Applications of Artificial Intelligence, 43, 67–80.
Derrible, S., & Kennedy, C. (2010, 09). The complexity and robustness of metro networks. Physica A: Statistical Mechanics and its Applications, 3678-3691. doi: 10.1016/j.physa.2010.04.008
Figueirôa, E., Lima, E., Bastos-Filho, C. J., da Silva, J., Xavier, A. V., & Araújo, D. R. (2017). A routing algorithm based on fuzzy logics for elastic optical networks. In 2017 ieee 18th international conference on high performance switching and routing (hpsr) (pp. 1–6).
Glorot, X., Bordes, A., & Bengio, Y. (2011). Deep sparse rectifier neural networks. In Proceedings of the fourteenth international conference on artificial intelligence and statistics (pp. 315–323).
Hahnloser, R. H., Sarpeshkar, R., Mahowald, M. A., Douglas, R. J., & Seung, H. S. (2000). Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature, 405(6789), 947.
Hastie, T., Tibshirani, R., & Friedman, J. (2008). The elements of statistical learning. Springer.
Haykin, S. (2010). Neural networks and learning machines (3rd ed.). PHI Learning Private Limited.
Ian J. Goodfellow, A. C., Yoshua Bengio. (2016). Deep learning. Cambridge, MA, USA: MIT Press.
Internet growth statistics. (2019). Retrieved from https://www.internetworldstats.com/emarketing.htm. (Acessado em 27/08/2019).
Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization. Retrieved from http://arxiv.org/abs/1412.6980
Knight, S., Nguyen, H. X., Falkner, N., Bowden, R., & Roughan, M. (2011). The internet topology zoo. IEEE Journal on Selected Areas in Communications, 29(9), 1765– 1775.
Lewis, T. G. (2009). Network science - theory and applications. John Wiley & Sons.
Mieghem, P. v. (2010). Graph spectra for complex networks. Cambridge University Press. doi: 10.1017/CBO9780511921681
Ramaswami, R., Sivarajan, K., & Sasaki, G. (2009). Optical networks: a practical perspective. Morgan Kaufmann.
Wu, J., Barahona, M., Yue-Jin, T., & Deng, H.-Z. (2010, 07). Natural connectivity of complex networks. Chinese Physics Letters, 27, 078902. doi: 10.1088/0256307X/27/7/078902
Zhao, Z., Feng, X., Wei, F., Wang, S., Cao, M., & Hou, Z. (2013). Optimized neural network ensemble by combination of particle swarm optimization and differential evolution. Advances in Neural Networks, 7951, 367-374. Retrieved from http://dx.doi.org/10.1007/978-3-642-39065-44 5 doi: 10.1007/978-3-642-39065-44 5
Published
2019-10-15
How to Cite
LIRA, Christian; BARROS, Jonas; ARAÚJO, Pedro; ARAÚJO, Danilo de.
Artificial Neural Networks to Assess Fault Tolerance of Optical Networks. In: NATIONAL MEETING ON ARTIFICIAL AND COMPUTATIONAL INTELLIGENCE (ENIAC), 16. , 2019, Salvador.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2019
.
p. 377-388.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2019.9299.
