The rapid growth of large-scale data centers has made accurate dynamic data center load modeling increasingly important for power system analysis. Such loads are characterized by fast workload-driven variability and protection-driven disconnection and reconnection behavior that are not captured by conventional load models. Existing approaches to data center load modeling include physics-based methods, which provide interpretable structure for grid simulation, and data-driven approaches, which capture empirical workload variability from data. However, physics-based models are typically uncalibrated to facility-level operation, while trajectory alignment in data-driven methods often leads to overfitting and unrealistic dynamic behavior. To resolve these limitations, we design the framework to leverage both physics-based structure and data-driven adaptability. We further show that trajectory-level alignment is limited for inherently stochastic data center loads. Therefore, we design the calibration to align temporal and statistical patterns using temporal contrastive learning (TCL). This calibration is performed locally at the facility, and only calibrated parameters are shared with utilities, reducing the need to share full-resolution operational time-series traces with utilities. The proposed load model is calibrated by real-world operational load data from the MIT Supercloud, ASU Sol, Blue Waters, and ASHRAE datasets. Then it is integrated into the ANDES platform and evaluated on the IEEE 39-bus, NPCC 140-bus, and WECC 179-bus systems. We simulate the collective dynamic responses of multiple heterogeneous data centers under system-level disturbances. We find that interactions among data centers can fundamentally alter post-disturbance recovery behavior, producing compound disconnection-reconnection dynamics and delayed stabilization that are not captured by uncalibrated load models.
翻译:暂无翻译