DataCenterGym: A Physics-Grounded Simulator for Multi-Objective Data Center Scheduling
Provides a reusable testbed for researchers to develop and evaluate scheduling algorithms that account for coupled compute-thermal-energy dynamics in geo-distributed data centers.
DataCenterGym is a physics-grounded simulator for multi-objective data center scheduling that integrates compute, thermal, and power dynamics. The authors develop a Hierarchical Model Predictive Control (H-MPC) algorithm that outperforms baseline schedulers in nominal and sensitivity experiments.
Modern datacenters schedule heterogeneous workloads across geo-distributed sites with diverse compute capacities, electricity prices, and thermal conditions. Compute utilization, heat generation, cooling demand, and energy consumption are tightly coupled, yet most existing schedulers abstract these effects and treat them independently. We present \textit{DataCenterGym}, a physics-grounded simulation environment for job scheduling in geo-distributed data centers, designed as a reusable testbed for future research. The simulator integrates compute queueing, building thermal dynamics, localized HVAC behavior, and temperature-dependent service degradation within a Gymnasium-compatible interface. We also develop a Hierarchical Model Predictive Control (H-MPC) scheduling algorithm that performs distributed job placement while explicitly accounting for thermal and power dynamics. Through experiments on nominal operation and workload sensitivity, we demonstrate how H-MPC improves scheduling performance relative to baseline schedulers.