**5. Conclusions**

In summary, this work offers three main contributions to the community of smart meter data analytics:


The high sampling rates, the achieved clock synchronization, and the marked events allow for using datasets that have been recorded using our framework (like FIRED) to evaluate event-based and event-less NILM algorithms. Additional data like detailed textual labels and additional sensor readings allow for developing disaggregation algorithms that utilize multi-modal information. Offering simultaneous, high frequency aggregated and individual appliance recordings will allow researchers to develop hybrid load monitoring systems which use individual appliance recordings in a semi-supervised fashion to aid the laborious training process of supervised NILM systems.

Besides the mentioned advantages, the framework is currently optimized for use in the residential domain as, e.g., plug level meters and WiFi are being used. While it should be possible to move the overall concepts to the commercial or industrial domain, such specialized environments may require additional adaption. Besides temperature and humidity readings, other environmental information such as occupancy or light sensors may be of interest and are theoretically supported by the framework but have not been installed while generating the FIRED dataset. Further increasing the sampling rate of the meters or the sheer number of meters is theoretically possible; however, in our findings, it reduced the reliability of our framework mainly due to bandwidth problems. One suggestion to overcome such a limitation in the future is to compress the data before it is sent over the bandwidth limited WiFi channel.

We provide electricity datasets and the software and hardware to record these so that researchers can set their focus on improving load monitoring and eco-feedback techniques. These have shown tremendous potential in saving our earth's energy resources.

**Author Contributions:** Conceptualization, B.V.; Writing—review and editing, M.P.; Writing—review and editing, P.M.S.; Supervision, B.B. All authors have read and agreed to the published version of the manuscript.

**Funding:** This research received no external funding.

**Institutional Review Board Statement:** Not applicable.

**Informed Consent Statement:** Not applicable.

**Data Availability Statement:** Data available in a publicly accessible repository that does not issue DOIs.

**Conflicts of Interest:** The authors declare no conflict of interest.
