A measurement system for creating datasets of on/off-controlled electrical loads

Abstract

The change in the power grid configuration, where a consumer with renewable energy resources can become an energy source, has given rise to a need for a better monitoring of the energy flow. This can be achieved by having access to a more detailed information about the energy consumption. The Non-Intrusive Load Monitoring (NILM) is one of the approaches that can be used to get such detailed energy consumption information. Most of the proposed NILM techniques are based on the use of low sampling frequency (LSF) data (1 Hz or less). Even though NILM techniques based on high sampling frequency (HSF) data are expected to be able to improve the accuracy of the LSF NILM techniques, the lack of suitable datasets for the training and the test of such techniques delayed their development. In this paper, we address this issue and we propose a measurement system that can allow the building of a suitable dataset for the training and the test of HSF NILM techniques. The proposed measurement system has three main features that are: the high sampling frequency measurement capability (kHz), the control over the turn-on and off time instants in synchronization with the grid voltage sinusoid and the measurement with aggregation scenarios of up to six appliances.