GATE: GPU-Accelerated Traffic Engineering for the WAN

2026-05-03

AI Summary

This work addresses the high computational cost of traditional traffic engineering methods in large-scale wide-area networks, which either incur prohibitive overhead when computing optimal paths or sacrifice resource efficiency through approximation. The authors propose a GPU-compatible, highly parallelized decomposition framework that scales more effectively with network size, supports diverse fairness objectives, and offers theoretical convergence guarantees alongside near-optimal solutions within bounded time. By integrating parallel optimization algorithms, scalable decomposition strategies, and an iterative convergence mechanism, the approach achieves 5–10× faster solution times than state-of-the-art methods on two real-world cloud WAN datasets while maintaining performance close to the optimum.

Abstract

Traffic engineering (TE) has become a crucial tool for enforcing routing policy and maintaining operational efficiency in large networks. Existing TE solutions pick an objective function to optimize, aiming to balance (i) allocating traffic optimally with (ii) reacting quickly to demand changes and disruption events. However, as the scale of networks grows, the runtime of the existing optimal solution becomes infeasibly large. The alternative - approximate solvers - result in costly inefficiencies. We present GPU-Accelerated Traffic Engineering (GATE), which achieves the best of both worlds: enabling fast TE runtimes through a highly-parallelizable GPU-compatible decomposition, while iteratively converging to the provably optimal solution. GATE unlocks a unique set of desirable properties: it becomes increasingly parallelizable with network size, supports a wide spectrum of fairness objectives, and offers theoretically guaranteed convergence to the optimal solution and near-optimal convergence within a bounded time. We evaluate GATE on production traces from two large cloud WANs, and show that GATE achieves near-optimal solutions 5-10x faster than state-of-the-art.

Problem

• Traffic Engineering
• GPU Acceleration
• WAN Optimization
• Scalability
• Optimal Routing

Innovation

• GPU acceleration
• traffic engineering
• parallel optimization
• convergence guarantee
• WAN