DSUALM10

In this repository (10_APLICATIVOS_SIN_ARMONICOS) we analyse the impact of NOT taking harmonics up to order 50 of the voltage, current and power offered by OZM v2 (i.e. the new version of oVm v2 which is the three-phase version of oZM). Note that in the attached Jupyter Notebook, not only is the Python code but also the results of running on the DSUALM10H dataset where the harmonics have been disregarded. Also, to run this code we need to have the NILMTK toolkit installed (also available on Github), as well as the new dataset that no longer includes the harmonics.

**DUE TO ITS SIZE, DUE TO ITS EXTENSION, THE DATA FILES IN FROMATO CSV ARE NOT AVAILABLE IN THIS PARTICULAR REPOSITORY AS WELL AS THE DATASET, BUT THE COMPLETE DATASET WITH ALL THE HARMONICS IS AVAILABLE IN THE DSUALM10H REPOSITORY. ** Our aim is to provide NILM researchers with new data repositories to extend the existing range. As these new datasets may contain more than 150 electrical variables recorded at high frequency in different everyday applications, by offering this wide range of data, we hope to boost and improve research in the NILM field.

In this repository we use 3 OZM v2 units that allow us to record real time electrical measurements of 10 devices plus the aggregate, but in this case we will only NOT use the harmonics. The main conclusions of taking only the odd harmonics, disregarding all the harmonics or taking all of them (even and odd) are presented in a generic way below.