PI-DLinear integrates derived thermal ODEs into DLinear to forecast AI data center power more accurately than SOTA models while respecting physical constraints under throttling and transients.
arXiv preprint arXiv:2409.11416 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
baseline 1
method 1
citation-polarity summary
verdicts
UNVERDICTED 6representative citing papers
EasyRider uses passive components plus actively controlled energy storage at the rack level, paired with lifetime-maximizing software, to keep AI training power transients inside grid safety limits without code changes or energy waste.
AI data centers raise surrounding land surface temperatures by 2°C on average, potentially affecting over 340 million people via local climate changes.
Singular perturbation analysis derives physically implementable droop control for inverters from reduced-system stability requirements to reject bounded-rate AI-induced power disturbances, providing explicit gain bounds, modulation conditions, and feasibility limits on load ramp rates.
AI data center temporal and spatial flexibility reduces grid investment and operational costs by 3-21% in some locations and load conditions but does not consistently lower required generation capacity and shows diminishing returns beyond certain deferral times.
AI datacenter workloads produce sustained power fluctuations that act as forcing inputs capable of amplifying local and inter-area oscillation modes in simulated grids.
citing papers explorer
-
A Physics-Aware Framework for Short-Term GPU Power Forecasting of AI Data Centers
PI-DLinear integrates derived thermal ODEs into DLinear to forecast AI data center power more accurately than SOTA models while respecting physical constraints under throttling and transients.
-
EasyRider: Mitigating Power Transients in Datacenter-Scale Training Workloads
EasyRider uses passive components plus actively controlled energy storage at the rack level, paired with lifetime-maximizing software, to keep AI training power transients inside grid safety limits without code changes or energy waste.
-
The data heat island effect: quantifying the impact of AI data centers in a warming world
AI data centers raise surrounding land surface temperatures by 2°C on average, potentially affecting over 340 million people via local climate changes.
-
Composite Control of Grid-Following Inverters for Stabilizing AI-Induced Fast Power Disturbances
Singular perturbation analysis derives physically implementable droop control for inverters from reduced-system stability requirements to reject bounded-rate AI-induced power disturbances, providing explicit gain bounds, modulation conditions, and feasibility limits on load ramp rates.
-
To Defer or To Shift? The Role of AI Data Center Flexibility on Grid Interconnection
AI data center temporal and spatial flexibility reduces grid investment and operational costs by 3-21% in some locations and load conditions but does not consistently lower required generation capacity and shows diminishing returns beyond certain deferral times.
-
Wide-Area Power System Oscillations from Large-Scale AI Workloads
AI datacenter workloads produce sustained power fluctuations that act as forcing inputs capable of amplifying local and inter-area oscillation modes in simulated grids.