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

TL;DR

NILMFormer is a Transformer-based model that effectively addresses non-stationarity in household power consumption data, significantly improving appliance-level load disaggregation accuracy in real-world scenarios.

Contribution

The paper introduces NILMFormer, a novel Transformer architecture with a subsequence de-stationarization scheme and timestamp-based positional encoding for improved NILM performance.

Findings

Outperforms state-of-the-art NILM methods on four real-world datasets.

Successfully deployed in EDF's consumer energy monitoring service.

Effectively mitigates distribution drift caused by non-stationary data.

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 (Electricit\'e De France) consumption monitoring service, delivering detailed insights to millions of customers about their individual appliances' power consumption. This paper appeared in KDD 2025.