Nilm Papers With Code Save

Reproducibility of scientific contributions is an important aspect of scholarship that has received way to little attention! This repository aims to collect information on peer-reviewed NILM (alias energy disaggregation) papers that have been published with source code or extensive supplemental material. We group NILM papers based on a number of categories: algorithms, toolkits, datasets, and misc. Feel free to contribute to this repository! Please consider our "style guide":

• This is a title. (year). [pdf] [code]
  • Main Author et al. Optional: Acronym of conference or journal i.e. Where was it published?

Algorithms

Graph Signal Processing

• On a Training-Less Solution for Non-Intrusive Appliance Load Monitoring Using Graph Signal Processing (2016). [pdf] [code]
  • B. Zhao et al. IEEE Access.

Hidden Markov Models

• Exploiting HMM Sparsity to Perform Online Real-Time Nonintrusive Load Monitoring (NILM). (2015). [pdf] [code]
  • S. Makonin et al. IEEE TSG.

Mathematical Optimization

• Mixed-Integer Nonlinear Programming for State-based Non-Intrusive Load Monitoring. (2022). [link] [code]
  • M. Balletti et al. IEEE TSG.*

Neural Nets

• Improving Non-Intrusive Load Disaggregation through an Attention-Based Deep Neural Network. (2021). [pdf] [code]

  • V. Piccialli et al. Energies

• Pruning Algorithms for Seq2Point Energy Disaggregation. (2020). [pdf] [code]

  • J. Barber et al. .

• Transfer Learning for Non-Intrusive Load Monitoring. (2019). [pdf] [code]

  • D. Michele et al. IEEE TSG.

• Neural NILM: Deep neural networks applied to energy disaggregation (2015) [pdf] [code]

  • J. Kelly et al. BuildSys'15

• Sliding Window Approach for Online Energy Disaggregation Using Artificial Neural Networks. (2018). [pdf] [code]

  • O. Krystalakos et al. Venue.

• Sequence-to-point learning with neural networks for non-intrusive load monitoring (2018) [pdf] [code]

  • C. Zhang et al. AAAI'18

• WaveNILM: A causal neural network for power disaggregation from the complex power signal (2019) [pdf] [code]

  • Alon Harell et al. ICASSP'19

Toolkits

• Towards reproducible state-of-the-art energy disaggregation. (2019) [pdf] [code]

  • N. Batra et al. BuildSys'19.

• NILM-Eval [pdf] [code]

• NILMTK [pdf] [code]

Metrics & Performance Evaluation

• Nonintrusive load monitoring (NILM) performance evaluation. (2015). [pdf] [code]

  • S. Makonin et al. Springer Energy Efficiency.

• Towards Comparability in Non-Intrusive Load Monitoring: On Data and Performance Evaluation [pdf] [code]

  • C. Klemenjak et al. 2020 IEEE ISGT.

Misc

• Device-Free User Activity Detection using Non-Intrusive Load Monitoring: A Case Study. (2020). [pdf] [code]

  • A. Reinhardt et al. DFHS Workshop.

• Machine learning approaches for non-intrusive load monitoring: from qualitative to quantitative comparation, Artificial Intelligence Review (2018). [pdf] [code]

  • C. Nalmpantis et al. Artificial Intelligence Review.

• Metadata for Energy Disaggregation. (2014) [pdf] [code]

  • J. Kelly et al. CDS'14.

• On time series representations for multi-label NILM. (2020) [pdf] [code]

  • C. Nalmpantis et al. Springer Neural Computing and Applications.

Datasets

Real-World Datasets

• REDD [link]
• UK-DALE [link]
• BLUED [link]
• GREEND [link]
• AMPds [link]
• ECO [link]
• HES [link]
• Tracebase [link]
• PLAID [link]
• ENERTALK [link]

Synthetic Datasets and Generators

• SmartSim: A Device-Accurate Smart Home Simulator for Energy Analytics. (2016). [pdf] [code]

  • D. Chen et al. SmartGridComm'16.

• How does Load Disaggregation Performance Depend on Data Characteristics? Insights from a Benchmarking Study. (2020). [pdf] [code]

  • A. Reinhardt et al. ACM e-energy.

• A synthetic energy dataset for non-intrusive load monitoring in households. (2020). [pdf] [code]

  • C. Klemenjak et al. Scientific Data.

Licence

To the extent possible under law, Christoph Klemenjak has waived all copyright and related or neighbouring rights to this work.