# Convolutional Sequence to Sequence Non-intrusive Load Monitoring

arXiv: https://arxiv.org/abs/1806.02078 · HTML: https://mlsanity.com/paper/1806.02078/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jun 2018.

## Built on by (most cited first, 7 of 7)

- [Towards trustworthy Energy Disaggregation: A review of challenges, methods and perspectives for Non-Intrusive Load Monitoring](https://mlsanity.com/paper/2207.02009/) (2022)
- [Fed-NILM: A Federated Learning-based Non-Intrusive Load Monitoring Method for Privacy-Protection](https://mlsanity.com/paper/2105.11085/) (2021)
- [Domain Knowledge Aids in Signal Disaggregation; the Example of the Cumulative Water Heater](https://mlsanity.com/paper/2203.11268/) (2022)
- [Adversarial Energy Disaggregation for Non-intrusive Load Monitoring](https://mlsanity.com/paper/2108.01998/) (2021)
- [A Deep Learning Technique using Low Sampling rate for residential Non Intrusive Load Monitoring](https://mlsanity.com/paper/2111.05120/) (2021)
- [Conv-NILM-Net, a causal and multi-appliance model for energy source separation](https://mlsanity.com/paper/2208.02173/) (2022)
- [Learning Defensive Policies against Diverse Inference Attacks for Smart Meter Privacy](https://mlsanity.com/paper/2609.25484/) (2026)

## Abstract (arXiv)

A convolutional sequence to sequence non-intrusive load monitoring model is proposed in this paper. Gated linear unit convolutional layers are used to extract information from the sequences of aggregate electricity consumption. Residual blocks are also introduced to refine the output of the neural network. The partially overlapped output sequences of the network are averaged to produce the final output of the model. We apply the proposed model to the REDD dataset and compare it with the convolutional sequence to point model in the literature. Results show that the proposed model is able to give satisfactory disaggregation performance for appliances with varied characteristics.