The SmartNIALMeter Electrical Appliance Disaggregation Dataset

Intro

Electrical disaggregation, also known as non-intrusive load monitoring (NILM) or non-intrusive appliance load monitoring (NIALM), attempts to recognize the energy consumption of single electrical appliances from the aggregated signal. This capability unlocks several applications, such as giving feedback to users regarding their energy consumption patterns or helping distribution system operators (DSOs) to recognize loads which could be shifted to stabilize the electrical grid. The project SmartNIALMeter brought together universities, companies and DSOs and involved the collection of a large data corpus comprising 20 buildings with a total of 100 electrical appliances for a period of up to two years at a sampling interval of five seconds. The variability of the loads, including heat pumps and a charging station for electric vehicles, and the presence of single-phase and three-phase devices make this dataset suitable for several investigations. The total consumption was collected through smart meters and each appliance’s consumption was measured with a dedicated sensor, providing sub-metering for all loads. The dataset can be used to tackle several open research questions, for example to investigate new NILM algorithms able to learn with a limited amount of sub-metered data.

Data Description

For the residential data we chose the Hierarchical Data Format (HDF5), which has been developed for big datasets and fast access. We publish two versions of the SNM dataset - a raw version with minimal curation steps and a version with more extensive preprocessing applied. Both versions of the dataset are organized along the same structure: Each appliance is saved individually as HDF5 and grouped by the building they are measured in. Measurements from individual phases are denoted by the ending L1, L2 or L3 in the file header (e.g. active power L1). This leads to the following file structure: <type>/building_<x>/<appliance>.h5, where:
•  <type> denotes the type of the dataset, i.e. raw or preprocessed.
•  <x> is a unique integer assigned to the building.
•  <appliance> is the name of the measured appliance. The naming follows the NILM metadata convention.

A detailed description of the dataset, corresponding metadata and the measurement setup can be found in M. Vogel, M. Friedli, M. Camenzind, G. Kniesel, Ch. Klemenjak, G. Gugolz, P. Huber, A. Calatroni, L. Kaufmann, A. Rumsch, A. Paice, "The SmartNIALMeter Electrical Appliance Disaggregation Dataset".
2024-05-02, Data-In-Brief (under review)

Code
The code to generate the preprocessed version of the dataset can be downloaded alongside the dataset. Check on GitHub if an updated versions is available.