Ask for Any Appliance: A Prompt-Programmable Foundation Model for Non-Intrusive Load Monitoring

Xudong Wang; Jiacheng Cui; Junyu Xue; Tongxin Li; Guoming Tang

cs.LGSep 19, 2026

Ask for Any Appliance: A Prompt-Programmable Foundation Model for Non-Intrusive Load Monitoring

Authors: Xudong Wang, Jiacheng Cui, Junyu Xue, Tongxin Li, Guoming Tang

Organizations: The Chinese University of Hong Kong, Shenzhen · The Hong Kong University of Science and Technology (Guangzhou) · Southern University of Science and Technology

Abstract

Non-intrusive load monitoring (NILM) estimates appliance-level consumption from a whole-home meter, but appliance-specific models and fixed output inventories make coverage costly to extend. We present FM4NILM (Foundation Model for NILM), a single prompt-programmable model that estimates a requested appliance's power trajectory from aggregate measurements, a natural-language description, and optional activation exemplars. A lightweight cadence-aware transformer is pretrained by masked reconstruction on 645k sequences from seven public corpora spanning 1-60 s sampling intervals, then aligned with appliance requests using observation-masked losses for partially labeled households. A Bernoulli-lognormal decoder separates activity detection from conditional power estimation. On held-out households and time periods from REDD, UK-DALE, and REFIT, one frozen text-prompted model serves twelve appliance-corpus requests, achieving 0.556 event F1, 0.625 AUPRC, and the lowest active-window MAE (251.8 W) among seven appliance-specific baselines. Streaming score aggregation raises event F1 to 0.582 with a 60 s aggregation delay. In a separate category-held-out evaluation, adding ten activation exemplars raises microwave AUPRC from 0.132 to 0.214 without parameter updates. Input-intervention ablations probe the model's dependence on appliance requests and aggregate measurements. These results demonstrate competitive disaggregation with one shared model and support extending appliance coverage through prompts and examples rather than additional specialist networks.

Figures & tables

Figure 1. FM4NILM : one foundation model for different appliance requests. (a) Text and optional cross-home exemplars form query $q_{a}$ through a multilayer perceptron (MLP), modality masking, mode and count embeddings, and layer normalization (LN); the snowflake marks frozen parameters. (b) Six-channel inputs become patch tokens with physical-time encodings; the inset repeats LN, attention (Attn), and a feed-forward network (FFN) with residual connections six times. The dashed link denotes shared encoder weights; tokens $H$ feed query-to-signal attention, and a convolution (conv) upsamples features $U$ . (c) Activation probability multiplies conditional mean on-power to produce expected power. Gray aggregates and teal predictions show two requests answered by fixed weights. Waveforms are schematic; window scoring and streaming are described in § 4.3 . Text and exemplar waveforms form a query. Aggregate waveforms become patch tokens, receive physical-time encoding, and pass through six shared attention and feed-forward layers with residual connections. Cross-attention and additive fusion condition two output heads. Activation probability times conditional mean power yields the requested trajectory, illustrated for dishwasher and microwave on the same aggregate.

Corpus	Aggregate	Lab. (%)	Agg. (W)	Res. (W)	Exc. (%)
REDD	site meter	30.6	309	205	0.08
UK-DALE	site meter	19.7	362	243	0.17
REFIT	site meter	6.2	543	459	0.74
ECO	site meter	30.1	417	305	0.47
IDEAL	site meter	25.3	485	346	2.23
GREEND	synth. (all meters)	34.6	257	142	0.00

Table 1. Aggregate provenance and label coverage. In the header, Lab., Agg., Res., and Exc. denote labeled share, aggregate power, residual power, and exceeds, respectively. Labeled share is the mean ratio of observed submeter power to aggregate power. Residual is the remaining consumption, and exceeds is the fraction of samples where the labeled sum is larger than the independently measured aggregate.

Appliance-specific, source-local (12 models)
Model	Deployed	Event F1 (%)	AUPRC (%)	MAE-on (W)
FHMM ( Kolter and Jaakkola, 2012 )	12 $\cdot$ tiny	34.9 $\pm$ 5.9	18.5 $\pm$ 2.5	661.3 $\pm$ 53.7
XGBoost ( Chen and Guestrin, 2016 )	12 $\cdot$ trees	51.6 $\pm$ 0.6	59.3 $\pm$ 1.1	420.9 $\pm$ 13.3
Seq2Point ( Zhang et al., 2018 )	222 M	47.3 $\pm$ 1.3	44.4 $\pm$ 0.7	878.0 $\pm$ 3.5
Seq2Seq ( Zhang et al., 2018 )	226 M	53.5 $\pm$ 0.8	59.5 $\pm$ 1.5	563.8 $\pm$ 15.1
BiLSTM ( Kelly and Knottenbelt, 2015a )	6.9 M	54.9 $\pm$ 1.6	61.5 $\pm$ 2.5	325.2 $\pm$ 18.8

Table 2. Held-out test results over 18,912 windows from unseen houses and periods using five seeds. Specialist baselines use one model per appliance and corpus, totaling twelve models. The closed-vocabulary control replaces the text prompt with a learned appliance identity. FM4NILM uses one shared, text-addressed network. “Deployed” gives the total parameter count for all twelve appliance–corpus requests. Best values are bold.

Variant	Event F1 (%)	AUPRC (%)	MAE-on (W)
FM4NILM (full)	55.6 $\pm$ 0.4	62.5 $\pm$ 2.2	251.8 $\pm$ 6.3
$-$ masked pretraining	54.3 $\pm$ 0.9	60.3 $\pm$ 1.8	269.1 $\pm$ 8.5
$-$ text (learned ID)	49.6 $\pm$ 5.3	49.4 $\pm$ 18.6	431.0 $\pm$ 172.8
$-$ exemplar episodes	53.3 $\pm$ 1.2	59.8 $\pm$ 2.6	369.6 $\pm$ 24.4
$+$ amplitude roles	54.1 $\pm$ 1.6	63.6 $\pm$ 1.1	297.8 $\pm$ 16.3
three corpora	53.1 $\pm$ 1.3	63.5 $\pm$ 1.1	287.2 $\pm$ 11.7

Table 3. Five-seed ablations (text-only prompts).

\Delta

AUPRC is the paired per-seed mean against the full FM4NILM model with a bootstrap 95% confidence interval (CI); an interval excluding zero is significant.

Figure 2. Model and pretraining scale. Points show five-seed means; bands show

\pm 1

standard deviation. (a) Detection scores across model sizes, spaced categorically; the shaded column marks the selected 3.7M model. (b) Event F1 improves overall as the pretraining pool grows from 10% to 100%, while AUPRC peaks at 25%. Two line charts show event F1 and AUPRC against model parameter count and pretraining-data fraction. The selected model has 3.7 million parameters.

Figure 3. Exemplar benefit and activation duration. Each point is the paired AUPRC gain from ten exemplars over text alone, averaged across five seeds; bars show

\pm 1

standard error. Duration is the median from submeter activations, shown on a log scale. Kettle and microwave show the largest gains. A scatter plot relates exemplar AUPRC gain to median appliance activation duration; short microwave and kettle events show larger gains than long multi-phase loads.

Category	Prompt	Event F1 (%)	AUPRC (%)	MAE-on (W)
Microwave	text only	31.1 $\pm$ 9.3	13.2 $\pm$ 8.9	968.4 $\pm$ 140.5
	text + 1 ex.	24.5 $\pm$ 2.2	11.2 $\pm$ 1.1	1113.6 $\pm$ 35.6
	text + 5 ex.	28.1 $\pm$ 4.1	16.5 $\pm$ 3.2	1021.8 $\pm$ 45.2
	text + 10 ex.	36.5 $\pm$ 4.7	21.4 $\pm$ 3.7	924.1 $\pm$ 52.1
	5 ex. only	27.5 $\pm$ 2.8	17.1 $\pm$ 2.3	1026.0 $\pm$ 33.2
Dishwasher	text only	12.8 $\pm$ 0.7	6.0 $\pm$ 1.1	1013.3 $\pm$ 48.3

Table 4. Zero-/few-shot transfer to categories excluded from all supervision and from pretraining submeter channels. Dense held-out test windows; five seeds

\times

five exemplar draws. The held-out category is absent from supervision, checkpoint selection, and the pretraining submeter pool.

Figure 4. Transfer through exemplar requests. Curves show five-seed mean AUPRC with

\pm 1

standard deviation;

K{=}0

denotes text alone. (a) Microwave improves from one to ten exemplars, while dishwasher stays near its mismatched-exemplar control. Dashed references use five mismatched exemplars with text omitted. (b) REFIT transfer under strict exclusion and with unlabeled target pretraining. The dash-dot line is the supervised REFIT reference. AUPRC versus exemplar count for excluded microwave and dishwasher categories and for the excluded REFIT corpus. Each appliance has its own mismatched-exemplar reference. REFIT curves compare strict exclusion with unlabeled target pretraining.

Training	Prompt	Event F1 (%)	AUPRC (%)
REFIT trained (reference)	text	32.2 $\pm$ 2.2	47.5 $\pm$ 6.3
Strict	text	23.4 $\pm$ 2.0	28.9 $\pm$ 2.5
	+ 1 enroll.	20.6 $\pm$ 2.6	24.1 $\pm$ 1.9
	+ 5 enroll.	21.2 $\pm$ 3.3	27.1 $\pm$ 3.1
	+ 5 cross-src.	23.8 $\pm$ 2.5	30.1 $\pm$ 2.3
+ unlab. target	text	29.4 $\pm$ 2.1	34.2 $\pm$ 1.1

Table 5. Dataset exclusion (REFIT test houses 13/20). Strict exclusion removes REFIT from supervision and pretraining; the unlabeled-target variant admits only its unlabeled aggregates to pretraining. Enrollment draws exemplars from REFIT non-test houses at inference. MAE-on is in the released per-run JavaScript Object Notation (JSON) files.

Figure 5. Input interventions. Bars show five-seed mean AUPRC with

\pm 1

standard deviation. (a) Text requests across all evaluated appliance–corpus pairs. (b) Five exemplars without text for the excluded microwave. Altering the request or removing the aggregate signal reduces accuracy; panels use different AUPRC scales. Bar charts compare canonical prompts with altered text, missing aggregate input, and wrong-category exemplars; each intervention reduces AUPRC.

Setting	False power (W)	Energy ratio
FM4NILM (held-out households)	31.5 $\pm$ 2.5	2.54 $\pm$ 0.08
Closed vocab. (ID)	37.5 $\pm$ 22.8	4.35 $\pm$ 3.08
FM4NILM , unseen (strict)	20.7 $\pm$ 4.1	1.29 $\pm$ 0.23
FM4NILM , unseen (+unlab.)	24.1 $\pm$ 5.8	1.54 $\pm$ 0.35

Table 6. Scale containment. False power is the mean predicted wattage while the requested appliance is off; energy ratio is predicted energy divided by true energy. Their ideal values are zero and one, respectively.

Metric	All seven corpora	REFIT held out
Actual MAE-on (W)	202 $\pm$ 3	249 $\pm$ 16
Rescaled MAE-on (W)	163 $\pm$ 7	188 $\pm$ 9
Scale share	19%	25%
Median factor: seen	1.08	1.08
Median factor: REFIT	1.25	2.11
Under-predicted groups	93%	100%

Table 7. Power-error decomposition using a diagnostic multiplier fitted per household–appliance group. Values are macro-averaged over 14 groups, a different weighting from the equal-corpus main result. Factors above one indicate under-prediction.

Appendix figures & tables12 assets

Supplementary material from the paper’s appendix.

Appendix

Arm	seeds	$\Delta$ event F1 (pts)	$\Delta$ AUPRC (pts)	$\Delta$ MAE-on (W)
calendar time	5	$+2.71$ [ $+1.01$ , $+4.34$ ]	$+2.39$ [ $+0.79$ , $+4.72$ ]	$-3.2$ [ $-30.0$ , $+17.2$ ]
control: timestamps shuffled	5	$-0.36$ [ $-1.80$ , $+0.70$ ]	$+1.15$ [ $-0.52$ , $+2.82$ ]	$-13.7$ [ $-50.1$ , $+12.6$ ]
window-relative normalization	5	$-0.96$ [ $-2.21$ , $+0.13$ ]	$+4.67$ [ $+3.76$ , $+5.26$ ]	$-3.7$ [ $-34.1$ , $+19.3$ ]
local dynamics	3	$+0.05$ [ $-2.03$ , $+2.89$ ]	$+1.27$ [ $+0.08$ , $+3.02$ ]	$+5.5$ [ $-12.9$ , $+23.7$ ]
all channels	5	$+1.49$ [ $-0.31$ , $+3.02$ ]	$+3.52$ [ $+1.64$ , $+5.16$ ]	$+6.4$ [ $-29.0$ , $+28.6$ ]
static physical covariates	3	$+0.21$ [ $-3.83$ , $+2.81$ ]	$-2.47$ [ $-12.98$ , $+3.26$ ]	$+49.6$ [ $-3.5$ , $+132.8$ ]

Appendix

Table 8. Covariates and watt-head parameterizations on the frozen test set, reported as paired differences from the deployed operator. Shuffling timestamps preserves their marginal distribution while removing their association with each window. Calendar channels improve both detection metrics; static physical covariates and the tested watt heads provide no consistent MAE-on gain.

Table 14

Span (s)	Token (s)	ts-AUPRC (%)	ts-AUPRC, multi-phase (%)	MAE-on (W)	seeds
480	4	74.57	84.16	219	reference
1920	16	$+2.49$ [ $+0.62$ , $+6.12$ ]	$+9.23$ [ $+7.81$ , $+10.74$ ]	$+20$ [ $-64$ , $+126$ ]	3
1920	4	$+1.53$ [ $-0.77$ , $+5.51$ ]	$+2.76$ [ $-3.75$ , $+8.63$ ]	$+27$ [ $+5$ , $+42$ ]	3
7200	16	$-6.07$ [ $-8.66$ , $-0.95$ ]	$-6.24$ [ $-17.83$ , $+3.58$ ]	$+158$ [ $+42$ , $+234$ ]	3
7200	60	$-5.39$ [ $-8.49$ , $-0.84$ ]	$+2.37$ [ $-3.02$ , $+5.42$ ]	$+161$ [ $+82$ , $+260$ ]	3

Appendix

Table 11. Request geometry scored per instant on the reconstructed timeline. Physical span and token span vary independently on the same recordings. The reference row gives absolute values and the remaining rows give paired differences. A 1920 s span gives the largest gain for multi-phase categories; extending to two hours reduces the number of independent training windows and reverses the overall gain. MAE-on remains stable across the 480–1920 s settings.

Channel	Context / rule	Delay	$\Delta$ event F1 (pts)				Pooled $\Delta$
			REDD	UK-DALE	REFIT	pooled	AUPRC (pts) / MAE-on
State	past 120 s	0 s	+2.78	+1.49	+0.00	+1.42	$-0.41$ / $+0.0$ W
State	past 120 s + future 60 s	60 s	+4.48	+3.08	+0.00	+2.52	$-0.14$ / $+0.0$ W
State	past 120 s + future 120 s	120 s	+4.48	+3.09	+0.00	+2.52	$-0.12$ / $+0.0$ W
Power	uniform average	n/a	+0.00	+0.00	+0.00	+0.00	$+70.8$ W
Power	Hann average	n/a	+0.00	+0.00	+0.00	+0.00	$+36.5$ W

Appendix

Table 12. Streaming inference with the final FM4NILM model over five seeds. State rows use the fixed 0.5 threshold and report paired changes from single-window inference. REDD and UK-DALE have 7.98-fold realized coverage; the selected REFIT windows have no neighbor within 120 s. Power rows modify power trajectories while preserving event scores.

		MAE-on (W)			amplitude ratio			ts-AUPRC (pts)
Scope	Corpus	base	revised	$\Delta$	base	revised	$\Delta$	$\Delta$
attributable	REDD	730	709	$-20$ [ $-91$ , $+41$ ]	0.543	0.670	$+0.127$ [ $+0.086$ , $+0.175$ ]	$+0.00$
attributable	UK-DALE	753	470	$-283$ [ $-338$ , $-217$ ]	0.440	0.840	$+0.400$ [ $+0.358$ , $+0.426$ ]	$+0.00$
attributable	REFIT	824	703	$-121$ [ $-140$ , $-107$ ]	0.558	0.721	$+0.163$ [ $+0.154$ , $+0.171$ ]	$+0.00$
all requested	REDD	282	275	$-7$ [ $-30$ , $+14$ ]	0.755	0.798	$+0.042$ [ $+0.029$ , $+0.058$ ]	$+0.00$
all requested	UK-DALE	473	303	$-170$ [ $-203$ , $-130$ ]	0.612	0.852	$+0.240$ [ $+0.215$ , $+0.255$ ]	$+0.00$

Appendix

Table 13. Retroactive edge anchoring over five seeds. A switch-off paired with an earlier switch-on defines an interval whose watts are set from the measured step height. “Attributable” covers categories described by a separable, uninterrupted power plateau. Other categories retain their original outputs, diluting the effect in the “all requested” rows. The rule updates the watt channel, so detection remains unchanged up to numerical noise.

AUPRC (%)	Fridge	Microwave	Dishwasher	Kettle	Toaster	Washing machine
Canonical	79.5	50.0	72.9	75.6	20.4	41.1
User mean	72.9	17.4	32.3	27.0	10.9	34.5
User worst	66.7	9.1	13.3	4.3	4.5	28.4
Retention	92%	35%	44%	36%	54%	84%

Appendix

Table 14. Prompt-phrasing robustness over five seeds. “Canonical” is the structured appliance card; “user phrasings” are held-out colloquial requests for the same appliance. Retention is mean user-phrasing AUPRC divided by canonical AUPRC. Categories with distinctive electrical signatures retain the most accuracy.

Modality	Intervention	AUPRC (%)
Text	canonical card	62.5 $\pm$ 2.2
	matched confuser	27.4 $\pm$ 0.7
	deranged permutation	13.8 $\pm$ 1.9
	zero signal	7.8 $\pm$ 0.0
Exemplar	correct category ( $K{=}5$ )	17.1 $\pm$ 2.3
Exemplar	wrong category ( $K{=}5$ )	1.3 $\pm$ 0.3

Appendix

Table 15. Causal controls at inference (five seeds). Text controls apply to the full model over all requests; exemplar controls apply to the held-out microwave under the unseen-appliance protocol, in exemplar-only mode. These are the values plotted in Fig. 5 .

Corpus	Cad.	Win	Train	Val	Test	Houses (tr/va/te)
REDD	1 s	480	25,844	3,577	7,332	1/2;1/2;1/2
UKDALE	1 s	480	23,147	3,203	6,580	1/2;1/2;1/2
REFIT	8 s	120	10,000	5,000	5,000	3/5/6/9;2/11;13/20
ECO	8 s	120	6,822	3,565	0	1/3/4/6;2/5;–
IDEAL	8 s	120	33,532	3,993	0	25 houses;105/175/311/328;–
GREEND	8 s	120	5,388	3,589	0	1/4/5;2/6;–

Appendix

Table 16. Per-corpus splits and window counts under the fixed splits. Houses are disjoint across splits for REFIT; REDD and UK-DALE use strict chronological within-house splits with purge gaps; the four auxiliary corpora supply supervision and pretraining but carry no frozen test split. All windows are non-overlapping at the listed stride.

Corpus	Appliance	Thr. (W)	Events	Pos. (%)	Peak (W)
REDD	fridge	50	582	34.9	188
REDD	microwave	200	246	0.9	1575
REDD	dishwasher	50	180	2.4	1107
UKDALE	kettle	200	128	0.9	2979
UKDALE	microwave	200	169	0.5	1339
UKDALE	fridge	50	708	39.5	95

Appendix

Table 17. Per-appliance statistics under the fixed splits: on/off threshold, number of complete activation events, positive-window rate (fraction of observed windows in which the appliance is active), and median on-state peak power. Only appliances that are actually submetered in a corpus are listed.

Table 22

		FM4NILM (shared)			BERT4NILM (per-appliance)
Corpus	Appliance	F1 (%)	AUPRC (%)	MAE (W)	F1 (%)	AUPRC (%)	MAE (W)
REDD	fridge	78.7	90.4	29	80.9	89.6	69
REDD	microwave	84.4	56.0	418	85.6	60.4	345
REDD	dishwasher	53.8	77.4	60	62.6	74.4	92
UKDALE	kettle	94.6	86.7	357	95.6	92.7	154
UKDALE	microwave	79.4	62.4	402	90.1	74.5	196

Appendix

Table 20. Per-corpus, per-appliance results (five-seed means): one shared FM4NILM with a text prompt versus BERT4NILM, the strongest per-appliance specialist with a dedicated model for each row. Detection is mixed across categories; FM4NILM has lower MAE-on for most appliances while using one network.

Figure 6. Examples of requested disaggregation. Gray lines show aggregate power, blue traces and shading show the target, and dashed teal lines show predicted power, all in kW. (a) A UK-DALE kettle requested by text. (b) A REFIT microwave with a low event score and underestimated amplitude. (c) A microwave excluded from supervision and pretraining submeter channels, requested with text and ten exemplars. Each panel reports its saved window event score. Table 4 summarizes category transfer across test windows. Three time-series panels compare aggregate, target, predicted power, and window event score for a supervised kettle, a REFIT microwave, and a held-out microwave prompted with ten exemplars.

Non-Intrusive Load Monitoring

Non-intrusive load monitoring estimates individual appliance use from a household’s combined electricity measurements.

See all 12 papers

Multi-Appliance Non-Intrusive Load Monitoring via Label-Preserving Aggregate Recomposition and Prediction Consistency
Sep 16, 2026Jiangfeng Liu, Yanfang FanNon-Intrusive Load Monitoring Data Augmentation
School of Electrical Engineering, Xinjiang University, Urumqi, Xinjiang 830047, China
Lightweight and Scalable Transfer Learning Framework for Load Disaggregation
Mar 5, 2026L. E. Garcia-Marrero, G. Petrone, E. MonmassonNon-Intrusive Load Monitoring Transfer Learning
Systèmes et Applications des Technologies de l’Information et de l’Energie laboratory, Cergy-Pontoise · Dipartimento di Ingegneria dell’Informazione ed Elettrica e Matematica Applicata/DIEM, University of Salerno, 84084 Fisciano
A Real-Time Tsetlin Machine-based Non-intrusive Load Monitoring System on MCUs
Aug 19, 2026Han Wu, Tianhang Tan, Shengyu Duan +3Non-Intrusive Load Monitoring On-Device Inference
School of Engineering, Newcastle University, Newcastle upon Tyne, United Kingdom

Sep 16, 2026J/K move · Enter open · S save

Multi-Appliance Non-Intrusive Load Monitoring via Label-Preserving Aggregate Recomposition and Prediction Consistency

Jiangfeng Liu, Yanfang Fan

School of Electrical Engineering, Xinjiang University, Urumqi, Xinjiang 830047, China

Non-Intrusive Load Monitoring Data Augmentation Domain Generalization Consistency Regularization

Open paper AskPDF arXiv

Non-intrusive load monitoring (NILM) estimates appliance power sequences from aggregate power, but models trained on source households commonly lose accuracy in unseen households. Aggregate power also contains loads from other appliances and measurement error, so predictions may depend on the residual background that co-occurs with source-household targets. Time-aligned submetered measurements and the additive decomposition of aggregate power expose a relation unused by window-wise supervision: an aggregate window can be recomposed by replacing only its residual background while preserving all modeled target-appliance power sequences pointwise. We combine label-preserving aggregate recomposition with prediction consistency. Both windows receive complete power and operating-state supervision. For each appliance, disagreement between the two power predictions is penalized only when both satisfy a fixed reliability criterion and only to the extent that it exceeds a fixed margin. The proposed method is implemented using a multi-appliance architecture with two-stage shared-to-specific mixture-of-experts routing. On REDD, UK-DALE, and REFIT, the proposed method lowers appliance-averaged mean absolute error relative to single-window training from 14.75 to 13.14 W, from 8.88 to 8.51 W, and from 15.83 to 14.55 W. Label-preserving aggregate recomposition and prediction consistency are used only during training, and add no inference-time module or parameter.

Abstract

Non-Intrusive Load Monitoring

Explore similar work

Multi-Appliance Non-Intrusive Load Monitoring via Label-Preserving Aggregate Recomposition and Prediction Consistency

Lightweight and Scalable Transfer Learning Framework for Load Disaggregation

A Real-Time Tsetlin Machine-based Non-intrusive Load Monitoring System on MCUs