Practical Nonintrusive Load Monitoring Approaches with Meaningful Performance Evaluation
A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Electronic Sensors".
Deadline for manuscript submissions: closed (30 June 2023) | Viewed by 30785
Special Issue Editors
Interests: signal and information processing; NILM; responsible AI
Special Issues, Collections and Topics in MDPI journals
Interests: sensing and data acquisition; smart metering; smart grids; data analytics; computational sustainability; NILM; performance evaluation; data sets and data formats; value proposition
Special Issues, Collections and Topics in MDPI journals
Special Issue Information
Dear Colleagues,
Nonintrusive load monitoring (NILM) or load disaggregation has seen significant breakthroughs since its conception in the early 1980s, with a range of signal processing and machine learning methods proposed. Over the past 20 years, there has been a rapid emergence of smart buildings and active large-scale roll-out of smart metering within smart grids, as well as the growing availability of public datasets. This has shifted the focus of NILM research toward a more practical user-centered approach whereby the meter readings from the majority of the residential sector and small buildings are available at resolutions of one second to one hour, and those of smart buildings at a higher rate. Recent years have seen the emergence of supervised and unsupervised approaches for solving both classification and regression problems in detecting individual appliance usage and their energy consumption. However, performance is still poor for a number of commonly used appliances (e.g., washing machines), resulting in unreliable energy feedback; additionally, the algorithms are not always trustworthy in that they are not reproducible on the same dataset and parameters or replicable to other datasets, and their outcomes are not interpretable. Additionally, the performance metrics—especially in relation to deep learning approaches—are not amenable to comparison with others in the literature or indeed explainable to the end user. In summary, this Special Issue focuses on addressing the following topics:
- Reliable supervised NILM methods that are transferable to ‘unseen’ datasets or reliable unsupervised NILM methods that can operate on any dataset;
- Reliable NILM methods that focus on accurate disaggregation of challenging loads;
- User-centered NILM algorithms for residential and nonresidential buildings;
- Interpretable and explainable algorithms for NILM;
- Fair and explainable metrics for the evaluation of different NILM algorithms;
- Practical NILM deployments or large-scale trials;
- Practical applications of NILM disaggregated data (e.g., flexibility estimation, life cycle analysis);
- Novel datasets, data models, and toolkits for NILM research.
Dr. Lina Stankovic
Dr. Lucas Pereira
Guest Editors
Manuscript Submission Information
Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.
Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.
Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.
Keywords
- nonintrusive load monitoring
- load disaggregation
- interpretable ML
- energy efficiency
- smart meters
- energy utilization
- machine learning
- explainable AI (XAI)
- performance evaluation
- user-centered
Benefits of Publishing in a Special Issue
- Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
- Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
- Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
- External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
- e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.
Further information on MDPI's Special Issue polices can be found here.