We propose a machine learning-based approach using a random forest for the fast computation of optimized transport network routing configurations. An evaluation in a 7-node network shows that our approach achieves competitive results in terms of solution quality and computation time compared to an exact ILP solution.
Year
2019
Reference entry
Enderle, T. Finding Transport Network Configurations Using Supervised Machine Learning
Proceedings of the 45th European Conference on Optical Communication (ECOC 2019), Dublin, September 2019, pp. 1-4