Permutation-Equivariant Graph Reinforcement Learning for Thermal-Aware Microservice Scheduling in Co-Packaged Optics Data Centers

Abstract

As data-center interconnects move to co-packaged optics (CPO), high-power application-specific integrated circuits (ASICs) and heat-sensitive optical engines share a single interposer, and the resulting intra-module thermal coupling overwhelms conventional schedulers. Thermal-aware microservice directed acyclic graph (DAG) scheduling on CPO modules is recast here as a question of symmetry. Whereas a homogeneous-graph policy assumes the full node-permutation symmetry, that symmetry is broken twice: by the distinct task and processor node types, and by the asymmetric ASIC–engine coupling. We therefore propose a heterogeneous-graph Proximal Policy Optimization (PPO) scheduler in which the placement head is permutation-equivariant, the delay head is permutation-invariant, and the parameterization stays invariant to the processor count N. Because these symmetries hold by construction, the policy transfers zero-shot across module sizes. Heterogeneous edge typing and the resistor–capacitor (RC) coupling edge attribute are isolated by a six-test ablation chain. Evaluated on the Alibaba 2021 microservice trace across all module sizes and ambient regimes under the standard auto-cool budget, the proposed scheduler cuts the thermal-violation rate from roughly 98% under the Heterogeneous Earliest-Finish-Time (HEFT) heuristic to about 0.3%; at the hot operating point it lowers peak temperature by about 25% and raises DAG completion from about 26% to 100%, with the rare residual violations most frequent in the extreme-ambient band. With the env auto-cool budget disabled, a controlled single-axis comparison shows that removing the RC-coupling edge attribute raises the violation rate by over an order of magnitude, isolating its contribution. A single parameter set serves every N without retraining.