Super-Resolution Reconstruction of Interval Energy Data
This addresses the need for high-resolution data in energy applications, but it is incremental as it applies an existing deep learning method to a specific domain.
The paper tackles the problem of upsampling low-resolution hourly interval energy data from Advanced Metering Infrastructure into higher-resolution 15-minute data using a Super-Resolution Reconstruction approach with deep learning, achieving much improved performance compared to a baseline model.
High-resolution data are desired in many data-driven applications; however, in many cases only data whose resolution is lower than expected are available due to various reasons. It is then a challenge how to obtain as much useful information as possible from the low-resolution data. In this paper, we target interval energy data collected by Advanced Metering Infrastructure (AMI), and propose a Super-Resolution Reconstruction (SRR) approach to upsample low-resolution (hourly) interval data into higher-resolution (15-minute) data using deep learning. Our preliminary results show that the proposed SRR approaches can achieve much improved performance compared to the baseline model.