An ML-Accelerated Framework for Large-Scale Constrained Traffic Engineering

Traffic engineering (TE) mechanisms are crucial for achieving optimal levels of network performance over wide-area networks across geographically distributed datacenters. Existing work on traffic engineering formulated the challenges at hand as combinatorial optimization problems, which could take hours to compute on modern wide-area network topologies at the scale of thousands of nodes. To improve the performance of TE mechanisms, we introduce DeepTE, a new TE framework based on machine learning (ML) that is designed for the best possible scalability and performance, capable of completing the computation within milliseconds with networks involving thousands of nodes, and of generating near-optimal TE policies while guaranteeing that all constraints are satisfied. DeepTE is also designed with a distributed ML model architecture, which can be horizontally scaled up to multiple GPUs for even better performance. With real-world traffic matrices, our extensive array of performance evaluations of DeepTE on various network topologies and TE problems show that DeepTE is capable of producing policies within 5% of the optimal results while offering up to 100x performance improvements over state-of-the-art traffic engineering mechanisms.