Non-intrusive load monitoring is an important en-ergy disaggregation technology, which can provide appliance-levelconsumption estimation given a series of total consumption overtime, aiding users green awareness and living as well as devicefault detection. Despite of the claimed performance, an insightfulanalysis on practical perspectives is still lacking. In this paperwe therefore propose a unified pipeline to conduct comparativeexperiments on four representative state-of-the-art algorithms.We further provide an in-depth look at two crucial factorsaffecting algorithms’ feasibility in practice, namely sampling rateand transferability, as well as the algorithms’ performance onenergy disaggregation.
|Conference|| 2021 IEEE International Conference on Consumer Electronics (ICCE)|
|Period||10/01/2021 → 12/01/2021|
|Series||IEEE International Conference on Consumer Electronics, (ICCE) |
- deep learning
- energy disaggregation