P042 Grid-side evasion and analog methods

What detection rate can grid-side methods (harmonic analysis, appliance-level load monitoring, theft detectors, time-series machine learning) keep against a load using smoothing and harmonic filters?

Grid-side evasion and analog disaggregation methods.

Terms: NILM (non-intrusive load monitoring): inferring individual loads from a single meter's total. harmonic state estimation: using the distortions a load imposes on AC power to identify it.

Status

Started Measured: a production training trace on DGX-H100 racks shows a large power swing recurring about once a second or slower. Built: GPU power smoothing in NVIDIA GB200 (ramp limits and a power floor), tested on hardware with a synthetic benchmark and simulated on the production trace (10.5% extra energy at a floor of 90% of rated power); rack batteries are modelled. These features exist for grid safety, and they also remove the rhythm a meter would look for; no detector has been tested against them. Dong et al. (2013) show that any meter-based classifier falls to chance once the hidden load's average trace matches the cover load's. A simulation study (Kimpson, Baker & Graham, October 2026) tracks the training rhythm through eight concealment strategies, but battery smoothing defeats it unless a second meter sits between the battery and the chips. The measured results so far point against meter-level detection; nothing shows every method fails.

This paper proposes a multi-faceted approach to mitigate these risks, grounded in real-world production telemetry.
Choukse et al. (2025), Power Stabilization for AI Training Datacenters (Microsoft, OpenAI, NVIDIA; arXiv 2508.14318v2) (2025-08), L70

Posed by

Sub-questions

IDSub-questionWhat the sources report
P042.1What detection rate do harmonic-state-estimation methods keep against loads using smoothing plus harmonic filters (as crypto miners deploy)?implied by a source, not stated as open
P042.2Has NILM been applied to disaggregate an AI-compute load from mixed feeder data, with reported accuracy?implied by a source, not stated as open
P042.3Does a non-technical-loss (electricity-theft) detector flag a synthetic AI-training load in utility meter data at a stated recall (a target to be agreed)?open

Possibly relevant work found by automated search

Found by AI agents searching for this problem's sub-questions, mostly by keyword and citation in the OpenAlex scholarly database and on the web; a second AI pass reviewed each one, and we spot-checked some by hand. They seemed reasonably related, as far as one can tell from outside each paper's field. Some come from neighbouring fields, such as arms control and financial audit, and bear on the problem by analogy. Not reviewed against the status above; a paper listed here does not change that status. 928 of 1052 quotes checked word for word against the paper's text.

For P042.3: Does a non-technical-loss (electricity-theft) detector flag a synthetic AI-training load in utility meter data at a stated recall (a target to be agreed)?

Data