Calibrating Microgrid Simulations for Energy-Aware Computing Systems

TL;DR

This paper introduces a self-calibrating, energy-aware microgrid simulation testbed that integrates real computing nodes with renewable energy simulators, enhancing power consumption accuracy for energy-efficient computing systems.

Contribution

It presents a novel self-calibrating testbed combining Vessim and real hardware to improve energy-aware computing simulations with real-time power measurements.

Findings

Kepler framework accurately estimates node power with R^2 of 0.95.

Calibration improves GPU workload power accuracy by ~50%.

Idle power approximation has an average error of ~5.23 W.

Abstract

The surge for computing resource demand is increasing global electricity consumption in data centers which is expected to exceed 1000 TWh by 2026, mainly attributable to adoption of new AI technologies. Carbon-aware computing strategies can mitigate their environmental impact by aligning power consumption with the production of low-carbon renewable energy, but they face challenges due to the scarcity of development environments. Existing solutions either rely on costly and complex physical system architectures that are difficult to integrate and maintain or on full simulations that, while more economical, often lack realism by ignoring system overheads, and real-time node power consumption and resource fluctuations. This thesis remediates these issues by proposing a self-calibrating energy-aware software testbed that uses the Software-in-the-Loop co-simulation framework Vessim to integrate renewable energy production simulators, while including real computing nodes. The application-level power consumption of these are first approximated by the Kepler framework and then calibrated within Vessim's microgrid simulation using an external socket power meter as a definitive measurement source on the system-level. The evaluation of the testbed with GPU and CPU intensive workloads reveal fairly accurate power approximation of the whole computing node by the Kepler framework, with an average regression coefficient of 1.01 and R^2 values of 0.95, though certain machine learning workloads showed higher deviation. The average static y-intercept of the regression line of ~5.23 W indicate inaccuracies in the idle power approximation. Calibration of dynamic per-process power consumption improved accuracy for GPU workloads by ~50%, while CPU workloads saw a modest improvement of ~3.5%.