Synergies between AI Computing and Power Systems: Metrics, Scheduling, and Resilience

TL;DR

This paper develops a shared quantitative framework linking AI computing efficiency and transparency to power system impacts, enabling improved scheduling, planning, and resilience strategies.

Contribution

It introduces standardized carbon metrics and integrates them into AI-power system coordination architectures for enhanced operational and resilience capabilities.

Findings

Standardized carbon metrics bridge AI and power system impacts.

Integrated scheduling frameworks improve real-time and long-term planning.

Resilience is enhanced by shifting signals from emissions to stability during stress.

Abstract

In this paper, we first clarify the concepts of green AI versus frugal AI, positioning frugality as efficiency by design and green AI as transparency and accountability. We then argue that these approaches, while complementary, are insufficient without a shared quantitative foundation that links AI computing to power system contexts. This motivates the development of standardized carbon metrics as a bridge between algorithmic decisions and their physical consequences. We next embed these signals into scheduling and planning frameworks, presenting two architectures: (i) an iterative signal-response loop for real-time operations, and (ii) an integrated optimization that learns and encodes flexible-load behavior for long-term planning. Finally, we show how the same coordination stack supports resilience, enabling signals to shift from emissions-first to stability-first during stress events, providing targeted relief and faster restoration.