On Metrics to Assess the Transferability of Machine Learning Models in Non-Intrusive Load Monitoring

1 code implementation • 12 Dec 2019 • Christoph Klemenjak, Anthony Faustine, Stephen Makonin, Wilfried Elmenreich

To assess the performance of load disaggregation algorithms it is common practise to train a candidate algorithm on data from one or multiple households and subsequently apply cross-validation by evaluating the classification and energy estimation performance on unseen portions of the dataset derived from the same households.

BIG-bench Machine Learning Non-Intrusive Load Monitoring