NILMFormer: Non-Intrusive Load Monitoring that Accounts for Non-Stationarity

Abstract

Millions of smart meters have been deployed worldwide, collecting the total power consumed by individual households. Based on these data, electricity suppliers offer their clients energy monitoring solutions to provide feedback on the consumption of their individual appliances. Historically, such estimates have relied on statistical methods that use coarse-grained total monthly consumption and static customer data, such as appliance ownership. Non-Intrusive Load Monitoring (NILM) is the problem of disaggregating a household's collected total power consumption to retrieve the consumed power for individual appliances. Current state-of-the-art (SotA) solutions for NILM are based on deep-learning (DL) and operate on subsequences of an entire household consumption reading. However, the non-stationary nature of real-world smart meter data leads to a drift in the data distribution within each segmented window, which significantly affects model performance. This paper introduces NILMFormer, a Transformer-based architecture that incorporates a new subsequence stationarization/de-stationarization scheme to mitigate the distribution drift and that uses a novel positional encoding that relies only on the subsequence's timestamp information. Experiments with 4 real-world datasets show that NILMFormer significantly outperforms the SotA approaches. Our solution has been deployed as the backbone algorithm for EDF's (Electricité De France) consumption monitoring service, delivering detailed insights to millions of customers about their individual appliances' power consumption. This paper appeared in KDD 2025.

12 pages, 8 figures. This paper appeared in ACM SIGKDD 2025

References in corpus (10)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• The UK-DALE dataset, domestic appliance-level electricity demand and whole-house demand from five UK homes
• Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
• Improving Position Encoding of Transformers for Multivariate Time Series Classification
• Should we really use post-hoc tests based on mean-ranks?
• Appliance Detection Using Very Low-Frequency Smart Meter Time Series
• NILM as a regression versus classification problem: the importance of thresholding
• ADF & TransApp: A Transformer-Based Framework for Appliance Detection Using Smart Meter Consumption Series
• DeviceScope: An Interactive App to Detect and Localize Appliance Patterns in Electricity Consumption Time Series
• Few Labels are all you need: A Weakly Supervised Framework for Appliance Localization in Smart-Meter Series