Name
Title | ||
|---|---|---|
A learning approach for identification of refrigerator load from aggregate load signal |
Abstract | ||
|---|---|---|
Estimation of appliance-specific power consumption from aggregate power signal is an important and challenging problem. The problem is also known as electrical load disaggregation. This paper addresses the problem of identification of refrigerator load, since refrigerators contribute to significant power consumption in domestic scenario. The key idea is to detect events corresponding to refrigerator, which are embedded in the aggregate power signal. Firstly, features based on amplitude and duration of events are identified by observation of refrigerator-specific power signal. Secondly, these features are extracted from the aggregate power signal. Thirdly, the extracted features are utilized in both supervised and unsupervised learning schemes to identify regions of activity of refrigerator. Performance of event detection demonstrates the potential of relevant features in both supervised and unsupervised learning frameworks. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/ICACCI.2014.6968516 | Advances in Computing, Communications and Informatics |
Keywords | DocType | Citations |
demand side management,learning (artificial intelligence),power engineering computing,refrigerators,active demand- side energy management,aggregate load signal,appliance-specific power consumption estimation,electrical load disaggregation,feature extraction,learning approach,refrigerator load identification,supervised learning,unsupervised learning,Load disaggregation,events,features,learning,refrigerator,supervised,unsupervised | Conference | 1 |
PageRank | References | Authors |
0.38 | 3 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Guruprasad, S. | 1 | 1 | 0.38 |
| M. Girish Chandra | 2 | 112 | 24.49 |
| Balamuralidhar P | 3 | 10 | 5.25 |