| dc.creator |
Faustine, Anthony |
|
| dc.creator |
Pereira, Lucas |
|
| dc.creator |
Klemenjak, Christoph |
|
| dc.date |
2021-05-04T12:55:19Z |
|
| dc.date |
2021-05-04T12:55:19Z |
|
| dc.date |
2021 |
|
| dc.date.accessioned |
2022-10-20T13:47:43Z |
|
| dc.date.available |
2022-10-20T13:47:43Z |
|
| dc.identifier |
Faustine, A., Pereira, L., & Klemenjak, C. (2021). Adaptive weighted recurrence graphs for appliance recognition in non-intrusive load monitoring. IEEE Transactions on Smart Grid, 12(1), 398-406. |
|
| dc.identifier |
DOI: https://doi.org/10.1109/TSG.2020.3010621 |
|
| dc.identifier |
http://hdl.handle.net/20.500.12661/2925 |
|
| dc.identifier.uri |
http://hdl.handle.net/20.500.12661/2925 |
|
| dc.description |
Abstract. Full Text Article Available at: https://doi.org/10.1109/TSG.2020.3010621 |
|
| dc.description |
To this day, hyperparameter tuning remains a cumbersome task in Non-Intrusive Load Monitoring (NILM) research, as researchers and practitioners are forced to invest a considerable amount of time in this task. This paper proposes adaptive weighted recurrence graph blocks (AWRG) for appliance feature representation in event-based NILM. An AWRG block can be combined with traditional deep neural network architectures such as Convolutional Neural Networks for appliance recognition. Our approach transforms one cycle per activation current into an weighted recurrence graph and treats the associated hyper-parameters as learn-able parameters. We evaluate our technique on two energy datasets, the industrial dataset LILACD and the residential PLAID dataset. The outcome of our experiments shows that transforming current waveforms into weighted recurrence graphs provides a better feature representation and thus, improved classification results. It is concluded that our approach can guarantee uniqueness of appliance features, leading to enhanced generalisation abilities when compared to the widely researched V-I image features. Furthermore, we show that the initialisation parameters of the AWRG's have a significant impact on the performance and training convergence. |
|
| dc.language |
en |
|
| dc.publisher |
IEEE |
|
| dc.subject |
Non-Intrusive Load Monitoring |
|
| dc.subject |
NILM |
|
| dc.subject |
Neural network |
|
| dc.subject |
Hyperparameter |
|
| dc.subject |
Load monitoring |
|
| dc.subject |
Training convergence |
|
| dc.title |
Adaptive weighted recurrence graphs for appliance recognition in non-intrusive load monitoring |
|
| dc.type |
Article |
|