Designing a Novel Dataset for Non-intrusive Load Monitoring

Non-intrusive Load Monitoring (NILM) is a technology that allows the identification of individual electrical loads from a single aggregated measurement of voltage/current, hence, useful for diagnostic of the consumption of electrical energy. This is performed by means of load detection and disaggregation techniques, as there are several different power signatures from the active loads. In order to develop more precise and efficient strategies and algorithms for load detection and disaggregation, several efforts have been made to build datasets that represent different scenarios of combined power loads and the events that cause changes in their states, such as power on and power off. The research presented here shows the conception of a new dataset for NILM research, from the analysis of the limitations of existing datasets, as well as the development and evaluation of a data collecting jig that is being used to collect this dataset. As a result, the infrastructure has been set up to build the LIT dataset, which is expected to provide the NILM field of study with more precise data for power signature analysis.