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

• URL: http://arxiv.org/abs/2506.05880v1
• Date: Fri, 06 Jun 2025 08:46:58 GMT
• Title: NILMFormer: Non-Intrusive Load Monitoring that Accounts for Non-Stationarity
• Authors: Adrien Petralia, Philippe Charpentier, Youssef Kadhi, Themis Palpanas,
• Abstract summary: Non-Intrusive Load Monitoring is the problem of disaggregating a household's collected total power consumption to retrieve the consumed power for individual appliances.<n>Current state-of-the-art solutions for NILM are based on deep-learning (DL) and operate on subsequences of an entire household consumption reading.<n>This paper introduces NILMFormer, a Transformer-based architecture that incorporates a new subsequence stationarization/de-stationarization scheme to mitigate the distribution drift.
• Score: 8.687178298010972
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Few Labels are all you need: A Weakly Supervised Framework for Appliance Localization in Smart-Meter Series [10.862097756793574]
  CamAL is a weakly supervised approach for appliance pattern localization that only requires information on the presence of an appliance in a household to be trained.<n>Our experimental evaluation, conducted on 4 real-world datasets, demonstrates that CamAL significantly outperforms existing weakly supervised baselines.
  arXiv  Detail & Related papers  (2025-06-06T09:08:34Z)
• Preventing Non-intrusive Load Monitoring Privacy Invasion: A Precise Adversarial Attack Scheme for Networked Smart Meters [99.90150979732641]
  We propose an innovative scheme based on adversarial attack in this paper.<n>The scheme effectively prevents NILM models from violating appliance-level privacy, while also ensuring accurate billing calculation for users.<n>Our solutions exhibit transferability, making the generated perturbation signal from one target model applicable to other diverse NILM models.
  arXiv  Detail & Related papers  (2024-12-22T07:06:46Z)
• Benchmarking Active Learning for NILM [2.896640219222859]
  Non-intrusive load monitoring (NILM) focuses on disaggregating total household power consumption into appliance-specific usage. Many advanced NILM methods are based on neural networks that typically require substantial amounts of labeled appliance data. We propose an active learning approach to selectively install appliance monitors in a limited number of houses.
  arXiv  Detail & Related papers  (2024-11-24T12:22:59Z)
• MATNilm: Multi-appliance-task Non-intrusive Load Monitoring with Limited Labeled Data [4.460954839118025]
  Existing approaches mainly focus on developing an individual model for each appliance. In this paper, we propose a multi-appliance-task framework with a training-efficient sample augmentation scheme. The relative errors can be reduced by more than 50% on average.
  arXiv  Detail & Related papers  (2023-07-27T11:14:11Z)
• Non-Intrusive Load Monitoring (NILM) using Deep Neural Networks: A Review [0.0]
  Non-intrusive load monitoring (NILM) is a method for decomposing the total energy consumption profile into individual appliance load profiles. Various methods, including machine learning and deep learning, have been used to implement and improve NILM algorithms. This paper reviews some recent NILM methods based on deep learning and introduces the most accurate methods for residential loads.
  arXiv  Detail & Related papers  (2023-06-08T08:11:21Z)
• Privacy Adhering Machine Un-learning in NLP [66.17039929803933]
  In real world industry use Machine Learning to build models on user data. Such mandates require effort both in terms of data as well as model retraining. continuous removal of data and model retraining steps do not scale. We propose textitMachine Unlearning to tackle this challenge.
  arXiv  Detail & Related papers  (2022-12-19T16:06:45Z)
• Domain Knowledge Aids in Signal Disaggregation; the Example of the Cumulative Water Heater [68.8204255655161]
  We present an unsupervised low-frequency method aimed at detecting and disaggregating the power used by Cumulative Water Heaters (CWH) in residential homes. Our model circumvents the inherent difficulty of unsupervised signal disaggregation by using both the shape of a power spike and its time of occurrence. Our model, despite its simplicity, offers promising applications: detection of mis-configured CWHs on off-peak contracts and slow performance degradation.
  arXiv  Detail & Related papers  (2022-03-22T10:39:19Z)
• Automated Machine Learning: A Case Study on Non-Intrusive Appliance Load Monitoring [81.06807079998117]
  We propose a novel approach to enable Automated Machine Learning (AutoML) for Non-Intrusive Appliance Load Monitoring (NIALM)<n>NIALM offers a cost-effective alternative to smart meters for measuring the energy consumption of electric devices and appliances.
  arXiv  Detail & Related papers  (2022-03-06T10:12:56Z)
• Adversarial Energy Disaggregation for Non-intrusive Load Monitoring [78.47901044638525]
  Energy disaggregation, also known as non-intrusive load monitoring (NILM), challenges the problem of separating the whole-home electricity usage into appliance-specific individual consumptions. Recent advances reveal that deep neural networks (DNNs) can get favorable performance for NILM. We introduce the idea of adversarial learning into NILM, which is new for the energy disaggregation task.
  arXiv  Detail & Related papers  (2021-08-02T03:56:35Z)
• Reinforcement Learning for Minimizing Age of Information in Real-time Internet of Things Systems with Realistic Physical Dynamics [158.67956699843168]
  This paper studies the problem of minimizing the weighted sum of age of information (AoI) and total energy consumption of Internet of Things (IoT) devices. A distributed reinforcement learning approach is proposed to optimize the sampling policy. Simulations with real data of PM 2.5 pollution show that the proposed algorithm can reduce the sum of AoI by up to 17.8% and 33.9%.
  arXiv  Detail & Related papers  (2021-04-04T03:17:26Z)
• Energy Disaggregation using Variational Autoencoders [11.940343835617046]
  Non-intrusive load monitoring (NILM) is a technique that uses a single sensor to measure the total power consumption of a building. Recent disaggregation algorithms have significantly improved the performance of NILM systems. We propose an energy disaggregation approach based on the variational autoencoders (VAE) framework.
  arXiv  Detail & Related papers  (2021-03-22T20:53:36Z)
• Multi-Agent Meta-Reinforcement Learning for Self-Powered and Sustainable Edge Computing Systems [87.4519172058185]
  An effective energy dispatch mechanism for self-powered wireless networks with edge computing capabilities is studied. A novel multi-agent meta-reinforcement learning (MAMRL) framework is proposed to solve the formulated problem. Experimental results show that the proposed MAMRL model can reduce up to 11% non-renewable energy usage and by 22.4% the energy cost.
  arXiv  Detail & Related papers  (2020-02-20T04:58:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.