ATRO: A Fast Solver-Free Algorithm for Topology and Routing Optimization of Reconfigurable Datacenter Networks
By: Yingming Mao , Qiaozhu Zhai , Zhen Yao and more
Potential Business Impact:
Makes computer networks faster and smarter.
The growing scale and complexity of reconfigurable data center networks (DCNs) demand more scalable and efficient algorithms for computing logical topologies and routing. Reconfigurable DCNs typically operate in two modes: one-hop configurations that require frequent topology optimization (TO), and multi-hop scenarios that involve joint topology and routing optimization (TRO). In both cases, the combinatorial nature of topology decisions makes it difficult for existing methods to balance solution quality and runtime efficiency. To address this, we introduce Alternating Topology and Routing Optimization (ATRO), a solver-free framework that alternates between TO and routing optimization (RO). This decomposition exploits two key insights: first, each alternating update step monotonically reduces maximum link utilization (MLU), ensuring consistent performance improvement across iterations; second, the TO subproblem, equivalent to one-hop optimization, exhibits a monotonic structure that enables optimal solutions via an efficient Accelerated Binary Search Method (ABSM). To preserve the solver-free design, RO is solved using existing Traffic Engineering accelerators. ATRO attains the global optimum in one-hop scenarios and significantly outperforms baselines in multi-hop settings in terms of both runtime and solution quality. Evaluations confirm its scalability and robustness across diverse DCNs.
Similar Papers
ATRO: A Fast Algorithm for Topology Engineering of Reconfigurable Datacenter Networks
Networking and Internet Architecture
Makes computer networks faster by changing connections.
RoTO: Robust Topology Obfuscation Against Tomography Inference Attacks
Networking and Internet Architecture
Hides computer network maps from spies.
Toward Self-Healing Networks-on-Chip: RL-Driven Routing in 2D Torus Architectures
Distributed, Parallel, and Cluster Computing
Makes computer chips work better when parts break.