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

๐Ÿ“… 2026-09-16
๐Ÿ“ˆ Citations: 0
โœจ Influential: 0
๐Ÿ“„ PDF
๐Ÿค– AI Summary
ๆœฌๆ–‡ๆๅ‡บไบ†ไธ€็ง้€š่ฟ‡ไฟ็•™ๆ ‡็ญพ็š„่šๅˆ้‡็ป„ๅ’Œ้ข„ๆต‹ไธ€่‡ดๆ€งๆ–นๆณ•ๆฅๆ้ซ˜่ทจๅฎถๅบญ็”ตๅ™จ้žไพตๅ…ฅๅผ่ดŸ่ท็›‘ๆต‹ๅ‡†็กฎๆ€ง็š„้—ฎ้ข˜ใ€‚
๐Ÿ“ Abstract
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.
Problem

Research questions and friction points this paper is trying to address.

Non-intrusive load monitoring
Aggregate power
Prediction accuracy
Residual background
Unseen households
Innovation

Methods, ideas, or system contributions that make the work stand out.

label-preserving aggregate recomposition
prediction consistency
multi-appliance architecture
๐Ÿ”Ž Similar Papers
No similar papers found.
J
Jiangfeng Liu
School of Electrical Engineering, Xinjiang University, Urumqi, Xinjiang 830047, China
Y
Yanfang Fan
School of Electrical Engineering, Xinjiang University, Urumqi, Xinjiang 830047, China